High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 40	99.71 10	96.99 49	99.69 2	99.57 22	99.02 21	99.62 16	99.36 27	98.53 11	99.52 228	98.58 43	99.95 5	99.66 38
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UA-Net		98.88 10	98.76 16	99.22 2	99.11 106	97.89 16	99.47 3	99.32 41	99.08 16	97.87 225	99.67 5	96.47 128	99.92 5	97.88 65	99.98 2	99.85 6

mvs5depth		98.06 60	98.58 29	96.51 252	98.97 135	89.65 358	99.43 4	99.81 2	99.30 9	98.36 146	99.86 2	93.15 271	99.88 22	98.50 45	99.84 51	99.99 1

TDRefinement		98.90 8	98.86 11	99.02 9	99.54 27	98.06 8	99.34 5	99.44 34	98.85 27	99.00 63	99.20 41	97.42 52	99.59 203	97.21 97	99.76 73	99.40 135

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 45	99.77 5	96.34 79	99.18 6	99.20 60	99.67 3	99.73 7	99.65 8	99.15 3	99.86 27	97.22 96	99.92 15	99.77 15

OurMVSNet-221017-0		98.61 19	98.61 27	98.63 47	99.77 5	96.35 78	99.17 7	99.05 111	98.05 61	99.61 17	99.52 13	93.72 256	99.88 22	98.72 39	99.88 28	99.65 41

DVP-MVS++		97.96 68	97.90 90	98.12 96	97.75 348	95.40 133	99.03 8	98.89 163	96.62 131	98.62 110	98.30 179	96.97 86	99.75 86	95.70 182	99.25 284	99.21 195

FOURS1					99.59 18	98.20 7	99.03 8	99.25 51	98.96 24	98.87 80

tt0320		99.07 6	99.29 4	98.43 62	99.55 24	95.92 104	98.97 10	99.53 28	99.67 3	99.79 2	99.71 3	98.33 14	99.78 59	98.11 53	99.92 15	99.57 60

tt0320-xc		99.10 4	99.31 3	98.49 57	99.57 20	96.09 94	98.91 11	99.55 26	99.67 3	99.78 3	99.69 4	98.63 10	99.77 70	98.02 59	99.93 11	99.60 47

sc_t1		99.09 5	99.28 5	98.53 54	99.72 8	96.21 87	98.87 12	99.19 63	99.71 2	99.76 4	99.65 8	98.64 9	99.79 53	98.07 57	99.90 25	99.58 52

pmmvs6		99.07 6	99.24 7	98.56 51	99.81 2	96.38 75	98.87 12	99.30 43	99.01 22	99.63 15	99.66 6	99.27 2	99.68 152	97.75 74	99.89 26	99.62 45

Anonymous20231211		98.55 24	98.76 16	97.94 113	98.79 171	94.37 192	98.84 14	99.15 76	99.37 6	99.67 11	99.43 21	95.61 179	99.72 112	98.12 52	99.86 35	99.73 28

mmtdpeth		98.33 36	98.53 31	97.71 128	99.07 112	93.44 231	98.80 15	99.78 4	99.10 15	96.61 327	99.63 10	95.42 189	99.73 102	98.53 44	99.86 35	99.95 2

MIMVSNet1		98.51 28	98.45 36	98.67 43	99.72 8	96.71 58	98.76 16	98.89 163	98.49 40	99.38 32	99.14 53	95.44 188	99.84 33	96.47 134	99.80 64	99.47 107

EPP-MVSNet		96.84 198	96.58 221	97.65 136	99.18 92	93.78 217	98.68 17	96.34 417	97.91 64	97.30 263	98.06 226	88.46 374	99.85 30	93.85 315	99.40 238	99.32 161

v7n		98.73 14	98.99 8	97.95 112	99.64 14	94.20 201	98.67 18	99.14 79	99.08 16	99.42 29	99.23 39	96.53 123	99.91 13	99.27 10	99.93 11	99.73 28

MVSFormer		96.14 253	96.36 243	95.49 345	97.68 358	87.81 423	98.67 18	99.02 124	96.50 142	94.48 433	96.15 408	86.90 404	99.92 5	98.73 37	99.13 302	98.74 308

test_djsdf		98.73 14	98.74 19	98.69 42	99.63 15	96.30 83	98.67 18	99.02 124	96.50 142	99.32 37	99.44 20	97.43 51	99.92 5	98.73 37	99.95 5	99.86 5

tt0805		97.44 147	97.56 139	97.11 192	99.55 24	96.36 77	98.66 21	95.66 431	98.31 47	97.09 287	95.45 446	97.17 69	98.50 461	98.67 40	97.45 459	96.48 482

anonymousdsp		98.72 17	98.63 23	98.99 13	99.62 16	97.29 42	98.65 22	99.19 63	95.62 209	99.35 36	99.37 25	97.38 54	99.90 17	98.59 42	99.91 19	99.77 15

HPM-MVS		98.11 55	97.83 101	98.92 24	99.42 45	97.46 36	98.57 23	99.05 111	95.43 224	97.41 259	97.50 297	97.98 23	99.79 53	95.58 197	99.57 155	99.50 89
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IS-MVSNet		96.93 189	96.68 212	97.70 130	99.25 72	94.00 208	98.57 23	96.74 409	98.36 45	98.14 186	97.98 238	88.23 381	99.71 128	93.10 346	99.72 91	99.38 144

WR-MVS_H		98.65 18	98.62 25	98.75 34	99.51 32	96.61 65	98.55 25	99.17 68	99.05 19	99.17 47	98.79 92	95.47 186	99.89 20	97.95 63	99.91 19	99.75 24

FE-MVS		92.95 416	92.22 423	95.11 366	97.21 405	88.33 402	98.54 26	93.66 474	89.91 437	96.21 358	98.14 206	70.33 517	99.50 234	87.79 457	98.24 409	97.51 442

test2506		89.86 473	89.16 479	91.97 497	98.95 136	76.83 540	98.54 26	61.07 560	96.20 160	97.07 288	99.16 50	55.19 547	99.69 145	96.43 139	99.83 56	99.38 144

mvs_tets		98.90 8	98.94 9	98.75 34	99.69 11	96.48 70	98.54 26	99.22 57	96.23 158	99.71 8	99.48 16	98.77 7	99.93 3	98.89 31	99.95 5	99.84 8

CS-MVS		98.09 56	98.01 77	98.32 72	98.45 242	96.69 60	98.52 29	99.69 8	98.07 59	96.07 366	97.19 327	96.88 99	99.86 27	97.50 85	99.73 86	98.41 351

Gipuma		98.07 59	98.31 49	97.36 172	99.76 7	96.28 84	98.51 30	99.10 91	98.76 29	96.79 310	99.34 30	96.61 117	98.82 421	96.38 141	99.50 199	96.98 460
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PS-CasMVS		98.73 14	98.85 13	98.39 66	99.55 24	95.47 131	98.49 31	99.13 82	99.22 12	99.22 44	98.96 75	97.35 56	99.92 5	97.79 71	99.93 11	99.79 13

3Dnovator	96.53 2	97.61 125	97.64 127	97.50 154	97.74 351	93.65 224	98.49 31	98.88 170	96.86 122	97.11 281	98.55 134	95.82 166	99.73 102	95.94 169	99.42 232	99.13 215

DTE-MVSNet		98.79 11	98.86 11	98.59 49	99.54 27	96.12 92	98.48 33	99.10 91	99.36 7	99.29 39	99.06 62	97.27 60	99.93 3	97.71 76	99.91 19	99.70 33

jajsoiax		98.77 12	98.79 15	98.74 37	99.66 13	96.48 70	98.45 34	99.12 83	95.83 198	99.67 11	99.37 25	98.25 17	99.92 5	98.77 34	99.94 8	99.82 9

PEN-MVS		98.75 13	98.85 13	98.44 61	99.58 19	95.67 115	98.45 34	99.15 76	99.33 8	99.30 38	99.00 69	97.27 60	99.92 5	97.64 80	99.92 15	99.75 24

LS3D		97.77 104	97.50 149	98.57 50	96.24 442	97.58 28	98.45 34	98.85 182	98.58 36	97.51 248	97.94 242	95.74 173	99.63 185	95.19 231	98.97 321	98.51 340

balanced_ft_v1		96.29 242	96.60 219	95.38 354	96.77 422	88.73 390	98.44 37	98.44 276	94.97 248	95.91 374	98.77 96	91.03 324	99.75 86	96.16 156	98.91 334	97.65 433

SPE-MVS-test		97.91 84	97.84 98	98.14 94	98.52 224	96.03 101	98.38 38	99.67 9	98.11 57	95.50 401	96.92 356	96.81 105	99.87 25	96.87 116	99.76 73	98.51 340

FC-MVSNet-test		98.16 49	98.37 40	97.56 142	99.49 36	93.10 243	98.35 39	99.21 58	98.43 42	98.89 76	98.83 91	94.30 238	99.81 43	97.87 66	99.91 19	99.77 15

HPM-MVS_fast		98.32 38	98.13 60	98.88 26	99.54 27	97.48 35	98.35 39	99.03 120	95.88 193	97.88 222	98.22 197	98.15 20	99.74 96	96.50 133	99.62 124	99.42 128

ab-mvs		96.59 220	96.59 220	96.60 240	98.64 198	92.21 273	98.35 39	97.67 358	94.45 277	96.99 295	98.79 92	94.96 213	99.49 240	90.39 417	99.07 313	98.08 393

EGC-MVSNET		83.08 511	77.93 517	98.53 54	99.57 20	97.55 30	98.33 42	98.57 257	4.71 558	10.38 561	98.90 86	95.60 180	99.50 234	95.69 184	99.61 135	98.55 333

test1111		94.53 354	94.81 329	93.72 441	99.06 114	81.94 510	98.31 43	83.87 549	96.37 149	98.49 127	99.17 49	81.49 456	99.73 102	96.64 123	99.86 35	99.49 97

ECVR-MVS		94.37 361	94.48 348	94.05 430	98.95 136	83.10 500	98.31 43	82.48 551	96.20 160	98.23 173	99.16 50	81.18 460	99.66 170	95.95 168	99.83 56	99.38 144

EC-MVSNet		97.90 86	97.94 89	97.79 121	98.66 197	95.14 159	98.31 43	99.66 12	97.57 79	95.95 372	97.01 348	96.99 84	99.82 38	97.66 79	99.64 118	98.39 354

pm-mvs1		98.47 31	98.67 21	97.86 117	99.52 31	94.58 181	98.28 46	99.00 136	97.57 79	99.27 40	99.22 40	98.32 15	99.50 234	97.09 104	99.75 83	99.50 89

SixPastTwentyTwo		97.49 141	97.57 138	97.26 181	99.56 22	92.33 266	98.28 46	96.97 399	98.30 49	99.45 25	99.35 29	88.43 375	99.89 20	98.01 60	99.76 73	99.54 74

FA-MVS(test-final)		94.91 329	94.89 320	94.99 376	97.51 381	88.11 414	98.27 48	95.20 447	92.40 365	96.68 319	98.60 127	83.44 443	99.28 343	93.34 336	98.53 387	97.59 439

CP-MVSNet		98.42 33	98.46 33	98.30 75	99.46 40	95.22 153	98.27 48	98.84 186	99.05 19	99.01 61	98.65 120	95.37 191	99.90 17	97.57 82	99.91 19	99.77 15

GG-mvs-BLEND				90.60 510	91.00 544	84.21 493	98.23 50	72.63 559		82.76 546	84.11 546	56.14 540	96.79 509	72.20 546	92.09 536	90.78 540

GBi-Net		96.99 182	96.80 205	97.56 142	97.96 305	93.67 220	98.23 50	98.66 241	95.59 211	97.99 205	99.19 42	89.51 356	99.73 102	94.60 281	99.44 219	99.30 167

test1		96.99 182	96.80 205	97.56 142	97.96 305	93.67 220	98.23 50	98.66 241	95.59 211	97.99 205	99.19 42	89.51 356	99.73 102	94.60 281	99.44 219	99.30 167

FMVSNet1		97.95 72	98.08 68	97.56 142	99.14 104	93.67 220	98.23 50	98.66 241	97.41 93	99.00 63	99.19 42	95.47 186	99.73 102	95.83 179	99.76 73	99.30 167

ACMH	93.61 9	98.44 32	98.76 16	97.51 148	99.43 43	93.54 226	98.23 50	99.05 111	97.40 94	99.37 33	99.08 61	98.79 6	99.47 249	97.74 75	99.71 94	99.50 89
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TransMVSNet (Re)		98.38 35	98.67 21	97.51 148	99.51 32	93.39 235	98.20 55	98.87 172	98.23 53	99.48 22	99.27 35	98.47 13	99.55 219	96.52 132	99.53 177	99.60 47

gg-mvs-nofinetune		88.28 495	86.96 501	92.23 494	92.84 538	84.44 488	98.19 56	74.60 556	99.08 16	87.01 541	99.47 17	56.93 537	98.23 480	78.91 532	95.61 515	94.01 518

QAPM		95.88 268	95.57 290	96.80 225	97.90 313	91.84 291	98.18 57	98.73 223	88.41 460	96.42 341	98.13 209	94.73 215	99.75 86	88.72 444	98.94 327	98.81 291

NR-MVSNet		97.96 68	97.86 97	98.26 79	98.73 182	95.54 123	98.14 58	98.73 223	97.79 66	99.42 29	97.83 256	94.40 233	99.78 59	95.91 172	99.76 73	99.46 109

MIMVSNet		93.42 397	92.86 404	95.10 368	98.17 282	88.19 405	98.13 59	93.69 471	92.07 372	95.04 416	98.21 198	80.95 463	99.03 397	81.42 523	98.06 417	98.07 395

PS-MVSNAJss		98.53 27	98.63 23	98.21 87	99.68 12	94.82 170	98.10 60	99.21 58	96.91 120	99.75 5	99.45 19	95.82 166	99.92 5	98.80 33	99.96 4	99.89 4

ACMMP		98.05 61	97.75 114	98.93 21	99.23 76	97.60 26	98.09 61	98.96 148	95.75 203	97.91 219	98.06 226	96.89 97	99.76 78	95.32 223	99.57 155	99.43 126
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
lecture		98.59 20	98.60 28	98.55 52	99.48 37	96.38 75	98.08 62	99.09 96	98.46 41	98.68 106	98.73 102	97.88 27	99.80 50	97.43 88	99.59 145	99.48 103

APDe-MVS		98.14 50	98.03 74	98.47 60	98.72 185	96.04 97	98.07 63	99.10 91	95.96 185	98.59 115	98.69 113	96.94 88	99.81 43	96.64 123	99.58 151	99.57 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
Vis-MVSNet		98.27 42	98.34 45	98.07 99	99.33 61	95.21 155	98.04 64	99.46 32	97.32 100	97.82 229	99.11 55	96.75 108	99.86 27	97.84 68	99.36 251	99.15 207
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	96.13 3	97.73 108	97.59 136	98.15 93	98.11 292	95.60 118	98.04 64	98.70 232	98.13 56	96.93 301	98.45 148	95.30 196	99.62 190	95.64 190	98.96 324	99.24 189

MVSMamba_PlusPlus		97.43 149	97.98 80	95.78 317	98.88 152	89.70 355	98.03 66	98.85 182	99.18 13	96.84 309	99.12 54	93.04 277	99.91 13	98.38 48	99.55 167	97.73 428

FIs		97.93 79	98.07 69	97.48 159	99.38 52	92.95 247	98.03 66	99.11 86	98.04 62	98.62 110	98.66 116	93.75 255	99.78 59	97.23 95	99.84 51	99.73 28

sd_testset		97.97 66	98.12 61	97.51 148	99.41 46	93.44 231	97.96 68	98.25 301	98.58 36	98.78 90	99.39 22	98.21 18	99.56 214	92.65 353	99.86 35	99.52 82

COLMAP_ROB	94.48 6	98.25 44	98.11 63	98.64 46	99.21 86	97.35 40	97.96 68	99.16 70	98.34 46	98.78 90	98.52 137	97.32 57	99.45 264	94.08 301	99.67 109	99.13 215
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
BridgeMVS		96.88 194	97.29 164	95.63 331	97.66 363	89.47 363	97.95 70	98.89 163	95.94 188	97.77 233	98.55 134	92.23 303	99.68 152	97.05 109	99.61 135	97.73 428

usedtu_dtu_shiyan2		97.54 136	97.26 167	98.37 67	99.54 27	96.04 97	97.94 71	98.06 334	97.36 98	98.62 110	98.20 199	95.52 183	99.73 102	90.90 395	99.18 294	99.33 159

VDDNet		96.98 185	96.84 201	97.41 168	99.40 49	93.26 239	97.94 71	95.31 444	99.26 11	98.39 142	99.18 46	87.85 388	99.62 190	95.13 241	99.09 310	99.35 158

CP-MVS		97.92 80	97.56 139	98.99 13	98.99 131	97.82 18	97.93 73	98.96 148	96.11 170	96.89 305	97.45 301	96.85 102	99.78 59	95.19 231	99.63 121	99.38 144

mvsmamba		94.91 329	94.41 353	96.40 272	97.65 365	91.30 304	97.92 74	95.32 443	91.50 395	95.54 398	98.38 161	83.06 447	99.68 152	92.46 359	97.84 432	98.23 380

ANet_high		98.31 39	98.94 9	96.41 269	99.33 61	89.64 359	97.92 74	99.56 24	99.27 10	99.66 13	99.50 15	97.67 36	99.83 35	97.55 83	99.98 2	99.77 15

nrg030		98.54 25	98.62 25	98.32 72	99.22 79	95.66 116	97.90 76	99.08 100	98.31 47	99.02 60	98.74 101	97.68 35	99.61 198	97.77 73	99.85 48	99.70 33

ambc				96.56 247	98.23 272	91.68 295	97.88 77	98.13 324		98.42 137	98.56 133	94.22 240	99.04 394	94.05 304	99.35 257	98.95 264

Anonymous20240529		97.96 68	98.04 73	97.71 128	98.69 194	94.28 199	97.86 78	98.31 298	98.79 28	99.23 43	98.86 90	95.76 172	99.61 198	95.49 200	99.36 251	99.23 191

sasdasda		97.23 166	97.21 172	97.30 176	97.65 365	94.39 189	97.84 79	99.05 111	97.42 89	96.68 319	93.85 479	97.63 41	99.33 320	96.29 148	98.47 395	98.18 387

canonicalmvs		97.23 166	97.21 172	97.30 176	97.65 365	94.39 189	97.84 79	99.05 111	97.42 89	96.68 319	93.85 479	97.63 41	99.33 320	96.29 148	98.47 395	98.18 387

tfpnnormal		97.72 111	97.97 81	96.94 210	99.26 69	92.23 272	97.83 81	98.45 272	98.25 52	99.13 51	98.66 116	96.65 114	99.69 145	93.92 312	99.62 124	98.91 275

RA-MVS			97.39 154		99.35 58	97.72 21	97.79 82	99.14 79	92.39 366	98.33 153	98.14 206	96.16 150	99.79 53	95.68 186	99.51 190

MGCFI-Net		97.20 168	97.23 170	97.08 197	97.68 358	93.71 219	97.79 82	99.09 96	97.40 94	96.59 328	93.96 476	97.67 36	99.35 315	96.43 139	98.50 392	98.17 389

Anonymous20240521		97.07 178	97.51 147	95.76 318	99.35 58	88.18 408	97.78 84	98.40 284	97.11 108	98.34 150	99.04 64	89.58 351	99.79 53	98.09 55	99.93 11	99.30 167

XVS		97.96 68	97.63 129	98.94 18	99.15 97	97.66 23	97.77 85	98.83 193	97.42 89	96.32 346	97.64 283	96.49 126	99.72 112	95.66 188	99.37 246	99.45 113

X-MVStestdata		92.86 417	90.83 457	98.94 18	99.15 97	97.66 23	97.77 85	98.83 193	97.42 89	96.32 346	36.50 556	96.49 126	99.72 112	95.66 188	99.37 246	99.45 113

VPA-MVSNet		98.27 42	98.46 33	97.70 130	99.06 114	93.80 215	97.76 87	99.00 136	98.40 44	99.07 57	98.98 72	96.89 97	99.75 86	97.19 100	99.79 66	99.55 72

aaatest				98.17 88	99.36 54	95.35 138	97.75 88	99.30 43	94.02 296	98.88 78	97.54 291		99.73 102	95.36 218	99.53 177	99.44 123

MED-MVS		98.14 50	98.09 67	98.27 78	99.36 54	95.35 138	97.75 88	99.30 43	97.28 103	98.88 78	98.41 155	96.99 84	99.73 102	95.36 218	99.51 190	99.74 26

TestfortrainingZip a		98.22 46	98.18 57	98.33 71	99.36 54	95.49 129	97.75 88	98.86 176	97.28 103	98.87 80	98.41 155	96.31 138	99.77 70	97.40 89	99.38 244	99.74 26

TestfortrainingZip				97.39 170	97.24 404	94.58 181	97.75 88	97.64 366	96.08 174	96.48 337	96.31 397	92.56 292	99.27 346		96.62 486	98.31 367

dcpmvs_2		97.12 175	97.99 79	94.51 408	99.11 106	84.00 494	97.75 88	99.65 13	97.38 96	99.14 50	98.42 152	95.16 203	99.96 2	95.52 199	99.78 70	99.58 52

UGNet		96.81 203	96.56 224	97.58 141	96.64 425	93.84 214	97.75 88	97.12 387	96.47 146	93.62 462	98.88 88	93.22 269	99.53 225	95.61 194	99.69 100	99.36 154
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
mPP-MVS		97.91 84	97.53 144	99.04 7	99.22 79	97.87 17	97.74 94	98.78 211	96.04 179	97.10 282	97.73 274	96.53 123	99.78 59	95.16 236	99.50 199	99.46 109

OpenMVS	94.22 8	95.48 296	95.20 299	96.32 278	97.16 407	91.96 287	97.74 94	98.84 186	87.26 474	94.36 435	98.01 234	93.95 248	99.67 162	90.70 408	98.75 364	97.35 449

RRT-MVS		95.78 273	96.25 249	94.35 418	96.68 424	84.47 487	97.72 96	99.11 86	97.23 105	97.27 265	98.72 103	86.39 413	99.79 53	95.49 200	97.67 446	98.80 292

testf1		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 97	99.42 36	97.69 75	98.92 73	98.77 96	97.80 30	99.25 351	96.27 150	99.69 100	98.76 306

APD_test2		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 97	99.42 36	97.69 75	98.92 73	98.77 96	97.80 30	99.25 351	96.27 150	99.69 100	98.76 306

MonoMVSNet		93.30 405	93.96 372	91.33 505	94.14 524	81.33 516	97.68 99	96.69 411	95.38 226	96.32 346	98.42 152	84.12 437	96.76 511	90.78 401	92.12 535	95.89 494

MSP-MVS		97.45 145	96.92 195	99.03 8	99.26 69	97.70 22	97.66 100	98.89 163	95.65 207	98.51 124	96.46 385	92.15 305	99.81 43	95.14 239	98.58 385	99.58 52
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
LFMVS		95.32 309	94.88 322	96.62 236	98.03 295	91.47 299	97.65 101	90.72 521	99.11 14	97.89 221	98.31 173	79.20 472	99.48 243	93.91 313	99.12 305	98.93 271

K. test v3		96.44 233	96.28 248	96.95 209	99.41 46	91.53 296	97.65 101	90.31 527	98.89 26	98.93 72	99.36 27	84.57 433	99.92 5	97.81 69	99.56 160	99.39 142

TSAR-MVS + MP.		97.42 151	97.23 170	98.00 108	99.38 52	95.00 163	97.63 103	98.20 308	93.00 343	98.16 182	98.06 226	95.89 161	99.72 112	95.67 187	99.10 309	99.28 175
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs3		97.38 154	97.56 139	96.84 222	98.63 207	92.81 251	97.60 104	99.61 19	90.87 415	98.76 96	99.66 6	94.03 244	97.90 491	99.24 11	99.68 105	99.80 12

region2R		97.92 80	97.59 136	98.92 24	99.22 79	97.55 30	97.60 104	98.84 186	96.00 182	97.22 269	97.62 285	96.87 101	99.76 78	95.48 204	99.43 229	99.46 109

HFP-MVS		97.94 76	97.64 127	98.83 28	99.15 97	97.50 34	97.59 106	98.84 186	96.05 177	97.49 250	97.54 291	97.07 75	99.70 137	95.61 194	99.46 213	99.30 167

ACMMPR		97.95 72	97.62 131	98.94 18	99.20 88	97.56 29	97.59 106	98.83 193	96.05 177	97.46 256	97.63 284	96.77 107	99.76 78	95.61 194	99.46 213	99.49 97

RPSCF		97.87 91	97.51 147	98.95 17	99.15 97	98.43 6	97.56 108	99.06 105	96.19 164	98.48 129	98.70 112	94.72 216	99.24 355	94.37 290	99.33 267	99.17 203

KD-MVS_self_test		97.86 93	98.07 69	97.25 182	99.22 79	92.81 251	97.55 109	98.94 153	97.10 109	98.85 82	98.88 88	95.03 208	99.67 162	97.39 91	99.65 114	99.26 181

SR-MVS-dyc-post		98.14 50	97.84 98	99.02 9	98.81 165	98.05 9	97.55 109	98.86 176	97.77 67	98.20 175	98.07 220	96.60 119	99.76 78	95.49 200	99.20 289	99.26 181

RE-MVS-def			97.88 95		98.81 165	98.05 9	97.55 109	98.86 176	97.77 67	98.20 175	98.07 220	96.94 88		95.49 200	99.20 289	99.26 181

APD-MVS_3200maxsize		98.13 54	97.90 90	98.79 32	98.79 171	97.31 41	97.55 109	98.92 157	97.72 72	98.25 170	98.13 209	97.10 71	99.75 86	95.44 209	99.24 287	99.32 161

ACMH+	93.58 10	98.23 45	98.31 49	97.98 110	99.39 50	95.22 153	97.55 109	99.20 60	98.21 54	99.25 42	98.51 140	98.21 18	99.40 287	94.79 270	99.72 91	99.32 161

Vis-MVSNet (Re-imp)		95.11 320	94.85 325	95.87 314	99.12 105	89.17 369	97.54 114	94.92 452	96.50 142	96.58 329	97.27 321	83.64 442	99.48 243	88.42 450	99.67 109	98.97 260

MP-MVS		97.64 121	97.18 176	99.00 12	99.32 63	97.77 20	97.49 115	98.73 223	96.27 153	95.59 395	97.75 269	96.30 141	99.78 59	93.70 326	99.48 207	99.45 113
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SD_0403		93.73 385	93.43 387	94.64 397	97.85 316	86.35 453	97.47 116	97.94 338	93.50 315	93.71 458	96.73 369	93.77 254	98.84 419	73.48 544	96.39 492	98.72 311

ZNCC-MVS		97.92 80	97.62 131	98.83 28	99.32 63	97.24 44	97.45 117	98.84 186	95.76 201	96.93 301	97.43 303	97.26 64	99.79 53	96.06 158	99.53 177	99.45 113

tttt0517		93.31 403	92.56 416	95.57 335	98.71 189	87.86 419	97.44 118	87.17 543	95.79 200	97.47 255	96.84 360	64.12 525	99.81 43	96.20 153	99.32 269	99.02 248

v10		97.55 135	97.97 81	96.31 279	98.60 211	89.64 359	97.44 118	99.02 124	96.60 133	98.72 101	99.16 50	93.48 262	99.72 112	98.76 35	99.92 15	99.58 52

v8		97.60 126	98.06 72	96.23 284	98.71 189	89.44 364	97.43 120	98.82 201	97.29 102	98.74 98	99.10 57	93.86 250	99.68 152	98.61 41	99.94 8	99.56 68

PMVS	89.60 17	96.71 214	96.97 189	95.95 307	99.51 32	97.81 19	97.42 121	97.49 372	97.93 63	95.95 372	98.58 129	96.88 99	96.91 507	89.59 431	99.36 251	93.12 524
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
usedtu_blend_shiyan5		93.74 383	93.08 396	95.71 326	94.99 503	89.17 369	97.38 122	98.93 155	96.40 147	94.75 423	87.24 539	80.36 466	99.40 287	91.84 371	95.85 504	98.55 333

SR-MVS		98.00 64	97.66 123	99.01 11	98.77 178	97.93 14	97.38 122	98.83 193	97.32 100	98.06 196	97.85 253	96.65 114	99.77 70	95.00 251	99.11 306	99.32 161

Elysia		98.19 47	98.37 40	97.66 134	99.28 65	93.52 227	97.35 124	98.90 159	98.63 32	99.45 25	98.32 171	94.31 236	99.91 13	99.19 14	99.88 28	99.54 74

StellarMVS		98.19 47	98.37 40	97.66 134	99.28 65	93.52 227	97.35 124	98.90 159	98.63 32	99.45 25	98.32 171	94.31 236	99.91 13	99.19 14	99.88 28	99.54 74

FMVSNet5		93.39 398	92.35 420	96.50 253	95.83 470	90.81 321	97.31 126	98.27 299	92.74 354	96.27 353	98.28 185	62.23 527	99.67 162	90.86 397	99.36 251	99.03 245

HY-MVS	91.43 15	92.58 425	91.81 433	94.90 383	96.49 431	88.87 383	97.31 126	94.62 457	85.92 490	90.50 513	96.84 360	85.05 427	99.40 287	83.77 513	95.78 512	96.43 485

CSCG		97.40 152	97.30 163	97.69 132	98.95 136	94.83 169	97.28 128	98.99 141	96.35 152	98.13 187	95.95 424	95.99 156	99.66 170	94.36 292	99.73 86	98.59 328

MTAPA		98.14 50	97.84 98	99.06 6	99.44 42	97.90 15	97.25 129	98.73 223	97.69 75	97.90 220	97.96 239	95.81 170	99.82 38	96.13 157	99.61 135	99.45 113

CPTT-MVS		96.69 215	96.08 258	98.49 57	98.89 151	96.64 63	97.25 129	98.77 213	92.89 350	96.01 370	97.13 335	92.23 303	99.67 162	92.24 362	99.34 262	99.17 203

EU-MVSNet		94.25 363	94.47 349	93.60 445	98.14 288	82.60 505	97.24 131	92.72 491	85.08 500	98.48 129	98.94 78	82.59 451	98.76 429	97.47 87	99.53 177	99.44 123

XXY-MVS		97.54 136	97.70 116	97.07 198	99.46 40	92.21 273	97.22 132	99.00 136	94.93 251	98.58 116	98.92 82	97.31 58	99.41 285	94.44 285	99.43 229	99.59 51

APD_test1		97.95 72	97.68 120	98.75 34	99.60 17	98.60 5	97.21 133	99.08 100	96.57 140	98.07 195	98.38 161	96.22 146	99.13 377	94.71 278	99.31 272	98.52 339

GST-MVS		97.82 98	97.49 151	98.81 30	99.23 76	97.25 43	97.16 134	98.79 207	95.96 185	97.53 246	97.40 305	96.93 90	99.77 70	95.04 245	99.35 257	99.42 128

SteuartSystems-ACMMP		98.02 63	97.76 112	98.79 32	99.43 43	97.21 46	97.15 135	98.90 159	96.58 137	98.08 193	97.87 252	97.02 82	99.76 78	95.25 226	99.59 145	99.40 135
Skip Steuart: Steuart Systems R&D Blog.
FMVSNet2		96.72 212	96.67 213	96.87 218	97.96 305	91.88 289	97.15 135	98.06 334	95.59 211	98.50 126	98.62 122	89.51 356	99.65 174	94.99 257	99.60 142	99.07 236

AllTest		97.20 168	96.92 195	98.06 101	99.08 110	96.16 89	97.14 137	99.16 70	94.35 281	97.78 231	98.07 220	95.84 163	99.12 379	91.41 381	99.42 232	98.91 275

DP-MVS		97.87 91	97.89 93	97.81 120	98.62 209	94.82 170	97.13 138	98.79 207	98.98 23	98.74 98	98.49 141	95.80 171	99.49 240	95.04 245	99.44 219	99.11 226

GeoE		97.75 106	97.70 116	97.89 115	98.88 152	94.53 184	97.10 139	98.98 144	95.75 203	97.62 240	97.59 287	97.61 43	99.77 70	96.34 144	99.44 219	99.36 154

PGM-MVS		97.88 89	97.52 145	98.96 16	99.20 88	97.62 25	97.09 140	99.06 105	95.45 219	97.55 245	97.94 242	97.11 70	99.78 59	94.77 273	99.46 213	99.48 103

LPG-MVS_test		97.94 76	97.67 121	98.74 37	99.15 97	97.02 47	97.09 140	99.02 124	95.15 235	98.34 150	98.23 194	97.91 25	99.70 137	94.41 287	99.73 86	99.50 89

SF-MVS		97.60 126	97.39 154	98.22 84	98.93 143	95.69 113	97.05 142	99.10 91	95.32 228	97.83 228	97.88 249	96.44 131	99.72 112	94.59 284	99.39 242	99.25 188

FE-MVSNET2		97.69 113	97.97 81	96.85 219	99.19 90	91.46 300	97.04 143	99.11 86	95.85 196	98.73 100	99.02 67	96.66 111	99.68 152	96.30 147	99.86 35	99.40 135

reproduce_model		98.54 25	98.33 47	99.15 3	99.06 114	98.04 11	97.04 143	99.09 96	98.42 43	99.03 58	98.71 110	96.93 90	99.83 35	97.09 104	99.63 121	99.56 68

VDD-MVS		97.37 156	97.25 168	97.74 126	98.69 194	94.50 187	97.04 143	95.61 435	98.59 35	98.51 124	98.72 103	92.54 296	99.58 206	96.02 163	99.49 202	99.12 221

wuyk23d		93.25 407	95.20 299	87.40 528	96.07 458	95.38 135	97.04 143	94.97 450	95.33 227	99.70 10	98.11 214	98.14 21	91.94 546	77.76 537	99.68 105	74.89 549

LCM-MVSNet-Re		97.33 159	97.33 161	97.32 175	98.13 291	93.79 216	96.99 147	99.65 13	96.74 128	99.47 24	98.93 79	96.91 94	99.84 33	90.11 421	99.06 316	98.32 365

MAR-MVS		94.21 366	93.03 398	97.76 125	96.94 417	97.44 38	96.97 148	97.15 385	87.89 470	92.00 499	92.73 498	92.14 306	99.12 379	83.92 509	97.51 455	96.73 474
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
test_vis1_n		95.67 284	95.89 274	95.03 372	98.18 279	89.89 350	96.94 149	99.28 47	88.25 464	98.20 175	98.92 82	86.69 408	97.19 501	97.70 78	98.82 349	98.00 407

KinetiMVS		97.82 98	98.02 75	97.24 184	99.24 73	92.32 268	96.92 150	98.38 287	98.56 39	99.03 58	98.33 168	93.22 269	99.83 35	98.74 36	99.71 94	99.57 60

SDMVSNet		97.97 66	98.26 55	97.11 192	99.41 46	92.21 273	96.92 150	98.60 249	98.58 36	98.78 90	99.39 22	97.80 30	99.62 190	94.98 259	99.86 35	99.52 82

h-mvs33		96.29 242	95.63 288	98.26 79	98.50 232	96.11 93	96.90 152	97.09 391	96.58 137	97.21 271	98.19 200	84.14 435	99.78 59	95.89 173	96.17 499	98.89 279

test0726					99.24 73	95.51 125	96.89 153	98.89 163	95.92 190	98.64 108	98.31 173	97.06 76

NormalMVS		96.87 195	96.39 240	98.30 75	99.48 37	95.57 120	96.87 154	98.90 159	96.94 118	96.85 307	97.88 249	85.36 424	99.76 78	95.63 191	99.59 145	99.57 60

SymmetryMVS		96.43 235	95.85 277	98.17 88	98.58 215	95.57 120	96.87 154	95.29 445	96.94 118	96.85 307	97.88 249	85.36 424	99.76 78	95.63 191	99.27 280	99.19 199

baseline		97.44 147	97.78 110	96.43 264	98.52 224	90.75 322	96.84 156	99.03 120	96.51 141	97.86 226	98.02 232	96.67 110	99.36 311	97.09 104	99.47 210	99.19 199

API-MVS		95.09 323	95.01 311	95.31 356	96.61 426	94.02 207	96.83 157	97.18 384	95.60 210	95.79 385	94.33 472	94.54 228	98.37 473	85.70 487	98.52 388	93.52 520

test_vis3_rt		97.04 179	96.98 188	97.23 185	98.44 243	95.88 105	96.82 158	99.67 9	90.30 428	99.27 40	99.33 32	94.04 243	96.03 517	97.14 102	97.83 433	99.78 14

reproduce-ours		98.48 29	98.27 53	99.12 4	98.99 131	98.02 12	96.81 159	99.02 124	98.29 50	98.97 67	98.61 123	97.27 60	99.82 38	96.86 117	99.61 135	99.51 86

our_new_method		98.48 29	98.27 53	99.12 4	98.99 131	98.02 12	96.81 159	99.02 124	98.29 50	98.97 67	98.61 123	97.27 60	99.82 38	96.86 117	99.61 135	99.51 86

test_fmvs1_n		95.21 313	95.28 297	94.99 376	98.15 286	89.13 374	96.81 159	99.43 35	86.97 481	97.21 271	98.92 82	83.00 448	97.13 502	98.09 55	98.94 327	98.72 311

test_fmvs2		96.38 239	96.45 236	96.16 293	97.85 316	91.30 304	96.81 159	99.45 33	89.24 447	98.49 127	99.38 24	88.68 372	97.62 496	98.83 32	99.32 269	99.57 60

SED-MVS		97.94 76	97.90 90	98.07 99	99.22 79	95.35 138	96.79 163	98.83 193	96.11 170	99.08 55	98.24 192	97.87 28	99.72 112	95.44 209	99.51 190	99.14 213

OPU-MVS				97.64 137	98.01 299	95.27 148	96.79 163				97.35 315	96.97 86	98.51 460	91.21 387	99.25 284	99.14 213

BP-MVS1		95.36 304	94.86 323	96.89 216	98.35 255	91.72 293	96.76 165	95.21 446	96.48 145	96.23 356	97.19 327	75.97 493	99.80 50	97.91 64	99.60 142	99.15 207

PHI-MVS		96.96 188	96.53 231	98.25 82	97.48 384	96.50 68	96.76 165	98.85 182	93.52 314	96.19 360	96.85 359	95.94 158	99.42 275	93.79 319	99.43 229	98.83 289

DVP-MVS		97.78 103	97.65 124	98.16 90	99.24 73	95.51 125	96.74 167	98.23 304	95.92 190	98.40 140	98.28 185	97.06 76	99.71 128	95.48 204	99.52 184	99.26 181
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.25 82	99.23 76	95.49 129	96.74 167	98.89 163					99.75 86	95.48 204	99.52 184	99.53 79

Anonymous202405211		96.34 241	95.98 266	97.43 165	98.25 269	93.85 213	96.74 167	94.41 461	97.72 72	98.37 143	98.03 230	87.15 400	99.53 225	94.06 302	99.07 313	98.92 274

SMA-MVS		97.48 142	97.11 178	98.60 48	98.83 162	96.67 61	96.74 167	98.73 223	91.61 386	98.48 129	98.36 163	96.53 123	99.68 152	95.17 234	99.54 173	99.45 113
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
TranMVSNet+NR-MVSNet		98.33 36	98.30 51	98.43 62	99.07 112	95.87 106	96.73 171	99.05 111	98.67 30	98.84 84	98.45 148	97.58 44	99.88 22	96.45 137	99.86 35	99.54 74

Casviewmamba		97.95 72	98.20 56	97.18 186	98.85 159	92.74 256	96.71 172	99.23 52	98.07 59	98.55 119	98.47 146	97.38 54	99.44 267	96.95 113	99.62 124	99.38 144

test_0402		97.84 94	97.97 81	97.47 161	99.19 90	94.07 204	96.71 172	98.73 223	98.66 31	98.56 118	98.41 155	96.84 103	99.69 145	94.82 267	99.81 60	98.64 320

testing915		94.01 376	93.64 381	95.13 365	98.48 236	88.13 411	96.70 174	93.57 477	95.09 238	95.00 417	96.39 392	77.97 477	99.01 398	90.87 396	98.69 372	98.26 377

test_fmvsmconf0.01_n		98.57 21	98.74 19	98.06 101	99.39 50	94.63 178	96.70 174	99.82 1	95.44 222	99.64 14	99.52 13	98.96 4	99.74 96	99.38 7	99.86 35	99.81 10

SSC-MVS		95.92 266	97.03 186	92.58 485	99.28 65	78.39 529	96.68 176	95.12 448	98.90 25	99.11 52	98.66 116	91.36 320	99.68 152	95.00 251	99.16 298	99.67 36

ACMM	93.33 11	98.05 61	97.79 106	98.85 27	99.15 97	97.55 30	96.68 176	98.83 193	95.21 231	98.36 146	98.13 209	98.13 22	99.62 190	96.04 161	99.54 173	99.39 142
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		93.14 410	92.64 414	94.62 400	97.34 397	87.20 437	96.67 178	93.02 485	94.71 261	96.51 336	95.83 430	81.64 455	98.60 451	90.00 424	88.06 543	98.07 395

SSM_0404		97.47 143	97.75 114	96.64 235	98.81 165	91.26 306	96.57 179	99.16 70	96.95 116	98.44 135	98.09 216	97.05 78	99.72 112	95.21 229	99.44 219	98.95 264

fmvsm_s_conf0.1_n_a		97.80 101	98.01 77	97.18 186	99.17 93	92.51 261	96.57 179	99.15 76	93.68 309	98.89 76	99.30 33	96.42 133	99.37 307	99.03 25	99.83 56	99.66 38

ALIKED-LG		94.42 357	93.57 382	96.97 207	96.80 421	97.51 33	96.56 181	98.87 172	90.23 432	96.16 362	96.93 353	83.76 441	97.07 503	84.00 508	98.80 352	96.33 486

casdiffseed414692147		97.67 118	97.88 95	97.03 203	98.82 164	92.32 268	96.55 182	99.17 68	96.99 111	98.01 203	98.67 115	97.64 39	99.38 300	95.45 208	99.66 112	99.40 135

MTMP							96.55 182	74.60 556

SD-MVS		97.37 156	97.70 116	96.35 274	98.14 288	95.13 160	96.54 184	98.92 157	95.94 188	99.19 46	98.08 218	97.74 33	95.06 525	95.24 227	99.54 173	98.87 285
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
E5new		97.59 129	97.96 87	96.45 258	99.01 126	90.45 333	96.50 185	99.23 52	96.19 164	98.27 162	98.72 103	97.49 46	99.47 249	96.64 123	99.62 124	99.42 128

E6new		97.59 129	97.97 81	96.45 258	99.01 126	90.45 333	96.50 185	99.23 52	96.20 160	98.27 162	98.72 103	97.49 46	99.47 249	96.64 123	99.62 124	99.42 128

E6		97.59 129	97.97 81	96.45 258	99.01 126	90.45 333	96.50 185	99.23 52	96.20 160	98.27 162	98.72 103	97.49 46	99.47 249	96.64 123	99.62 124	99.42 128

E5		97.59 129	97.96 87	96.45 258	99.01 126	90.45 333	96.50 185	99.23 52	96.19 164	98.27 162	98.72 103	97.49 46	99.47 249	96.64 123	99.62 124	99.42 128

HQP_MVS		96.66 217	96.33 245	97.68 133	98.70 191	94.29 196	96.50 185	98.75 219	96.36 150	96.16 362	96.77 366	91.91 315	99.46 256	92.59 355	99.20 289	99.28 175

plane_prior2							96.50 185		96.36 150

RoMa-HiRes		97.28 162	97.05 185	97.98 110	98.78 175	96.22 86	96.48 191	98.47 269	93.69 307	98.97 67	97.73 274	93.48 262	98.47 464	96.31 146	99.51 190	99.26 181

GDP-MVS		95.39 302	94.89 320	96.90 215	98.26 268	91.91 288	96.48 191	99.28 47	95.06 241	96.54 335	97.12 337	74.83 497	99.82 38	97.19 100	99.27 280	98.96 261

hybridcas		97.73 108	98.10 66	96.62 236	98.84 161	91.10 309	96.46 193	99.20 60	97.53 83	98.65 107	98.42 152	97.41 53	99.38 300	96.79 119	99.59 145	99.37 153

Effi-MVS+-dtu		96.81 203	96.09 257	98.99 13	96.90 419	98.69 4	96.42 194	98.09 327	95.86 195	95.15 410	95.54 441	94.26 239	99.81 43	94.06 302	98.51 391	98.47 346

SSM_0407		97.39 153	97.67 121	96.54 250	98.51 226	90.96 314	96.40 195	99.16 70	96.95 116	98.27 162	98.09 216	97.05 78	99.67 162	95.21 229	99.40 238	98.98 256

guyue		96.21 249	96.29 247	95.98 304	98.80 168	89.13 374	96.40 195	94.34 463	95.99 184	98.58 116	98.13 209	87.42 396	99.64 180	97.39 91	99.55 167	99.16 206

MM		96.87 195	96.62 215	97.62 138	97.72 353	93.30 236	96.39 197	92.61 494	97.90 65	96.76 315	98.64 121	90.46 335	99.81 43	99.16 18	99.94 8	99.76 21

thres100view900		91.76 448	91.26 449	93.26 457	98.21 273	84.50 486	96.39 197	90.39 524	96.87 121	96.33 345	93.08 487	73.44 508	99.42 275	78.85 533	97.74 439	95.85 496

XVG-ACMP-BASELINE		97.58 134	97.28 166	98.49 57	99.16 94	96.90 52	96.39 197	98.98 144	95.05 242	98.06 196	98.02 232	95.86 162	99.56 214	94.37 290	99.64 118	99.00 249

Patchmtry		95.03 326	94.59 342	96.33 275	94.83 511	90.82 319	96.38 200	97.20 382	96.59 136	97.49 250	98.57 131	77.67 480	99.38 300	92.95 349	99.62 124	98.80 292

fmvsm_s_conf0.1_n		97.73 108	98.02 75	96.85 219	99.09 109	91.43 303	96.37 201	99.11 86	94.19 287	99.01 61	99.25 36	96.30 141	99.38 300	99.00 26	99.88 28	99.73 28

ACMMP_NAP		97.89 88	97.63 129	98.67 43	99.35 58	96.84 53	96.36 202	98.79 207	95.07 240	97.88 222	98.35 165	97.24 66	99.72 112	96.05 160	99.58 151	99.45 113

VNet		96.84 198	96.83 202	96.88 217	98.06 294	92.02 285	96.35 203	97.57 371	97.70 74	97.88 222	97.80 262	92.40 301	99.54 222	94.73 276	98.96 324	99.08 233

V42		97.04 179	97.16 177	96.68 234	98.59 213	91.05 310	96.33 204	98.36 290	94.60 265	97.99 205	98.30 179	93.32 266	99.62 190	97.40 89	99.53 177	99.38 144

test_fmvsmvis_n_1920		98.08 57	98.47 32	96.93 211	99.03 123	93.29 237	96.32 205	99.65 13	95.59 211	99.71 8	99.01 68	97.66 38	99.60 201	99.44 5	99.83 56	97.90 413

APD-MVS		97.00 181	96.53 231	98.41 64	98.55 220	96.31 81	96.32 205	98.77 213	92.96 348	97.44 258	97.58 289	95.84 163	99.74 96	91.96 366	99.35 257	99.19 199
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n_11		97.90 86	98.34 45	96.60 240	98.75 180	90.50 331	96.28 207	99.56 24	97.05 110	99.15 49	99.11 55	96.31 138	99.69 145	98.97 29	99.84 51	99.62 45

AstraMVS		96.41 237	96.48 235	96.20 287	98.91 148	89.69 356	96.28 207	93.29 481	96.11 170	98.70 103	98.36 163	89.41 360	99.66 170	97.60 81	99.63 121	99.26 181

VPNet		97.26 164	97.49 151	96.59 242	99.47 39	90.58 324	96.27 209	98.53 260	97.77 67	98.46 132	98.41 155	94.59 224	99.68 152	94.61 280	99.29 277	99.52 82

thres600view7		92.03 443	91.43 442	93.82 436	98.19 276	84.61 485	96.27 209	90.39 524	96.81 124	96.37 344	93.11 483	73.44 508	99.49 240	80.32 527	97.95 424	97.36 447

EPNet		93.72 386	92.62 415	97.03 203	87.61 555	92.25 271	96.27 209	91.28 512	96.74 128	87.65 538	97.39 310	85.00 428	99.64 180	92.14 364	99.48 207	99.20 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DSMNet-mixed		92.19 437	91.83 432	93.25 458	96.18 449	83.68 498	96.27 209	93.68 473	76.97 545	92.54 495	99.18 46	89.20 365	98.55 455	83.88 510	98.60 384	97.51 442

IMVS_0407		96.35 240	96.88 200	94.74 394	97.83 326	86.11 457	96.25 213	98.82 201	94.48 272	97.57 243	97.14 331	96.08 153	99.33 320	95.00 251	98.78 355	98.78 295

fmvsm_s_conf0.5_n_a		97.65 120	97.83 101	97.13 191	98.80 168	92.51 261	96.25 213	99.06 105	93.67 310	98.64 108	99.00 69	96.23 145	99.36 311	98.99 27	99.80 64	99.53 79

ACMP	92.54 13	97.47 143	97.10 179	98.55 52	99.04 122	96.70 59	96.24 215	98.89 163	93.71 305	97.97 212	97.75 269	97.44 50	99.63 185	93.22 342	99.70 98	99.32 161
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS	95.41 4	97.82 98	97.70 116	98.16 90	98.78 175	95.72 111	96.23 216	99.02 124	93.92 301	98.62 110	98.99 71	97.69 34	99.62 190	96.18 155	99.87 33	99.15 207
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PM-MVS		97.36 158	97.10 179	98.14 94	98.91 148	96.77 55	96.20 217	98.63 247	93.82 302	98.54 120	98.33 168	93.98 246	99.05 391	95.99 166	99.45 216	98.61 327

test_fmvsmconf0.1_n		98.41 34	98.54 30	98.03 106	99.16 94	94.61 179	96.18 218	99.73 5	95.05 242	99.60 18	99.34 30	98.68 8	99.72 112	99.21 12	99.85 48	99.76 21

MVS_Test		96.27 244	96.79 207	94.73 395	96.94 417	86.63 448	96.18 218	98.33 294	94.94 249	96.07 366	98.28 185	95.25 198	99.26 348	97.21 97	97.90 429	98.30 370

CR-MVSNet		93.29 406	92.79 407	94.78 391	95.44 488	88.15 409	96.18 218	97.20 382	84.94 505	94.10 444	98.57 131	77.67 480	99.39 296	95.17 234	95.81 508	96.81 471

RPMNet		94.68 343	94.60 340	94.90 383	95.44 488	88.15 409	96.18 218	98.86 176	97.43 88	94.10 444	98.49 141	79.40 471	99.76 78	95.69 184	95.81 508	96.81 471

LuminaMVS		96.76 207	96.58 221	97.30 176	98.94 139	92.96 246	96.17 222	96.15 419	95.54 215	98.96 70	98.18 203	87.73 390	99.80 50	97.98 61	99.61 135	99.15 207

test_fmvsm_n_1920		98.08 57	98.29 52	97.43 165	98.88 152	93.95 210	96.17 222	99.57 22	95.66 206	99.52 21	98.71 110	97.04 80	99.64 180	99.21 12	99.87 33	98.69 316

fmvsm_s_conf0.5_n		97.62 124	97.89 93	96.80 225	98.79 171	91.44 302	96.14 224	99.06 105	94.19 287	98.82 87	98.98 72	96.22 146	99.38 300	98.98 28	99.86 35	99.58 52

WB-MVS		95.50 293	96.62 215	92.11 496	99.21 86	77.26 539	96.12 225	95.40 442	98.62 34	98.84 84	98.26 190	91.08 323	99.50 234	93.37 334	98.70 371	99.58 52

EIA-MVS		96.04 258	95.77 282	96.85 219	97.80 336	92.98 245	96.12 225	99.16 70	94.65 263	93.77 455	91.69 511	95.68 175	99.67 162	94.18 297	98.85 343	97.91 412

Effi-MVS+		96.19 251	96.01 262	96.71 231	97.43 390	92.19 277	96.12 225	99.10 91	95.45 219	93.33 474	94.71 464	97.23 67	99.56 214	93.21 343	97.54 453	98.37 357

FE-MVSNET		96.59 220	96.65 214	96.41 269	98.94 139	90.51 330	96.07 228	99.05 111	92.94 349	98.03 200	98.00 236	93.08 275	99.42 275	94.04 305	99.74 85	99.30 167

alignmvs		96.01 261	95.52 292	97.50 154	97.77 345	94.71 172	96.07 228	96.84 403	97.48 86	96.78 314	94.28 473	85.50 423	99.40 287	96.22 152	98.73 368	98.40 352

fmvsm_l_conf0.5_n_3		98.29 41	98.46 33	97.79 121	98.90 150	94.05 206	96.06 230	99.63 17	96.07 175	99.37 33	98.93 79	98.29 16	99.68 152	99.11 22	99.79 66	99.65 41

VortexMVS		96.04 258	96.56 224	94.49 410	97.60 372	84.36 489	96.05 231	98.67 238	94.74 256	98.95 71	98.78 95	87.13 401	99.50 234	97.37 93	99.76 73	99.60 47

PatchT		93.75 382	93.57 382	94.29 422	95.05 501	87.32 435	96.05 231	92.98 486	97.54 82	94.25 436	98.72 103	75.79 494	99.24 355	95.92 171	95.81 508	96.32 487

aaEdge-Enhanced		97.53 139	97.32 162	98.16 90	98.70 191	95.35 138	96.04 233	98.60 249	96.16 169	97.99 205	97.54 291	95.94 158	99.70 137	95.36 218	99.53 177	99.44 123

Patchmatch-test		93.60 393	93.25 391	94.63 399	96.14 454	87.47 429	96.04 233	94.50 459	93.57 311	96.47 339	96.97 350	76.50 488	98.61 449	90.67 410	98.41 401	97.81 421

thisisatest0530		92.71 421	91.76 437	95.56 340	98.42 248	88.23 404	96.03 235	87.35 542	94.04 295	96.56 332	95.47 445	64.03 526	99.77 70	94.78 272	99.11 306	98.68 319

9.14			96.69 211		98.53 223		96.02 236	98.98 144	93.23 326	97.18 275	97.46 300	96.47 128	99.62 190	92.99 347	99.32 269

DeepC-MVS_fast	94.34 7	96.74 208	96.51 233	97.44 164	97.69 357	94.15 202	96.02 236	98.43 277	93.17 336	97.30 263	97.38 312	95.48 185	99.28 343	93.74 321	99.34 262	98.88 283
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
IMVS_0403		96.27 244	96.77 208	94.76 392	97.83 326	86.11 457	96.00 238	98.82 201	94.48 272	97.49 250	97.14 331	95.38 190	99.40 287	95.00 251	98.78 355	98.78 295

ttmdpeth		94.05 373	94.15 365	93.75 440	95.81 472	85.32 469	96.00 238	94.93 451	92.07 372	94.19 439	99.09 59	85.73 419	96.41 514	90.98 391	98.52 388	99.53 79

test_fmvsmconf_n		98.30 40	98.41 39	97.99 109	98.94 139	94.60 180	96.00 238	99.64 16	94.99 247	99.43 28	99.18 46	98.51 12	99.71 128	99.13 20	99.84 51	99.67 36

fmvsm_s_conf0.5_n_10		97.74 107	98.11 63	96.62 236	98.72 185	90.95 317	95.99 241	99.50 30	96.22 159	99.20 45	98.93 79	95.13 205	99.77 70	99.49 3	99.76 73	99.15 207

114514_t		93.96 377	93.22 392	96.19 289	99.06 114	90.97 313	95.99 241	98.94 153	73.88 548	93.43 471	96.93 353	92.38 302	99.37 307	89.09 438	99.28 278	98.25 378

FMVSNet3		95.26 312	94.94 315	96.22 286	96.53 429	90.06 344	95.99 241	97.66 360	94.11 291	97.99 205	97.91 247	80.22 470	99.63 185	94.60 281	99.44 219	98.96 261

HPM-MVS++		96.99 182	96.38 242	98.81 30	98.64 198	97.59 27	95.97 244	98.20 308	95.51 216	95.06 413	96.53 381	94.10 242	99.70 137	94.29 293	99.15 299	99.13 215

casdiffmvs_mvg		97.83 95	98.11 63	97.00 206	98.57 217	92.10 281	95.97 244	99.18 65	97.67 78	99.00 63	98.48 145	97.64 39	99.50 234	96.96 112	99.54 173	99.40 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testgi		96.07 255	96.50 234	94.80 389	99.26 69	87.69 426	95.96 246	98.58 255	95.08 239	98.02 202	96.25 402	97.92 24	97.60 497	88.68 446	98.74 365	99.11 226

EG-PatchMatch MVS		97.69 113	97.79 106	97.40 169	99.06 114	93.52 227	95.96 246	98.97 147	94.55 269	98.82 87	98.76 100	97.31 58	99.29 338	97.20 99	99.44 219	99.38 144

fmvsm_s_conf0.5_n_3		97.88 89	98.37 40	96.41 269	98.73 182	89.82 352	95.94 248	99.49 31	96.81 124	99.09 54	99.03 66	97.09 73	99.65 174	99.37 8	99.76 73	99.76 21

PAPM_NR		94.61 348	94.17 364	95.96 305	98.36 254	91.23 307	95.93 249	97.95 337	92.98 344	93.42 472	94.43 471	90.53 333	98.38 471	87.60 462	96.29 496	98.27 374

UniMVSNet (Re)		97.83 95	97.65 124	98.35 70	98.80 168	95.86 107	95.92 250	99.04 119	97.51 84	98.22 174	97.81 261	94.68 220	99.78 59	97.14 102	99.75 83	99.41 134

test_vis1_n_1920		95.77 274	96.41 239	93.85 435	98.55 220	84.86 481	95.91 251	99.71 7	92.72 356	97.67 237	98.90 86	87.44 395	98.73 431	97.96 62	98.85 343	97.96 409

RoMa-SfM		96.87 195	96.56 224	97.79 121	98.50 232	96.46 72	95.89 252	98.45 272	91.48 397	98.84 84	97.40 305	93.93 249	97.96 488	94.99 257	99.58 151	98.96 261

fmvsm_l_conf0.5_n		97.68 116	97.81 104	97.27 179	98.92 145	92.71 258	95.89 252	99.41 39	93.36 320	99.00 63	98.44 150	96.46 130	99.65 174	99.09 23	99.76 73	99.45 113

fmvsm_s_conf0.5_n_9		97.98 65	98.32 48	96.96 208	98.92 145	91.45 301	95.87 254	99.53 28	97.44 87	99.56 19	99.05 63	95.34 192	99.67 162	99.52 2	99.70 98	99.77 15

PRO-TEST		95.35 306	95.48 293	94.95 380	96.49 431	87.11 440	95.86 255	98.74 221	93.21 329	95.07 411	95.57 440	93.10 274	99.51 232	92.89 352	98.37 402	98.24 379

1314		92.38 430	92.30 421	92.64 484	95.42 490	85.15 474	95.86 255	96.97 399	85.40 498	90.62 510	93.06 488	91.12 322	97.80 494	86.74 474	95.49 517	94.97 509

MVS		90.02 468	89.20 476	92.47 488	94.71 512	86.90 444	95.86 255	96.74 409	64.72 550	90.62 510	92.77 496	92.54 296	98.39 470	79.30 530	95.56 516	92.12 525

fmvsm_l_conf0.5_n_a		97.60 126	97.76 112	97.11 192	98.92 145	92.28 270	95.83 258	99.32 41	93.22 327	98.91 75	98.49 141	96.31 138	99.64 180	99.07 24	99.76 73	99.40 135

casdiffmvs		97.50 140	97.81 104	96.56 247	98.51 226	91.04 311	95.83 258	99.09 96	97.23 105	98.33 153	98.30 179	97.03 81	99.37 307	96.58 131	99.38 244	99.28 175
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVStest1		91.89 445	91.45 441	93.21 462	89.01 549	84.87 480	95.82 260	95.05 449	91.50 395	98.75 97	99.19 42	57.56 533	95.11 523	97.78 72	98.37 402	99.64 44

tpmvs		90.79 462	90.87 455	90.57 511	92.75 539	76.30 541	95.79 261	93.64 475	91.04 411	91.91 500	96.26 400	77.19 486	98.86 418	89.38 435	89.85 540	96.56 479

fmvsm_s_conf0.5_n_6		97.45 145	97.79 106	96.44 262	98.58 215	90.31 339	95.77 262	99.33 40	94.52 270	98.85 82	98.44 150	95.68 175	99.62 190	99.15 19	99.81 60	99.38 144

fmvsm_s_conf0.5_n_8		97.66 119	98.12 61	96.27 281	98.79 171	89.43 365	95.76 263	99.42 36	97.49 85	99.16 48	99.04 64	94.56 227	99.69 145	99.18 16	99.73 86	99.70 33

mvsany_test3		96.21 249	95.93 271	97.05 199	97.40 392	94.33 194	95.76 263	94.20 465	89.10 448	99.36 35	99.60 11	93.97 247	97.85 492	95.40 216	98.63 380	98.99 253

MSLP-MVS++		96.42 236	96.71 210	95.57 335	97.82 330	90.56 326	95.71 265	98.84 186	94.72 260	96.71 318	97.39 310	94.91 214	98.10 485	95.28 224	99.02 318	98.05 402

tfpn200view9		91.55 450	91.00 451	93.21 462	98.02 297	84.35 490	95.70 266	90.79 518	96.26 154	95.90 378	92.13 506	73.62 505	99.42 275	78.85 533	97.74 439	95.85 496

Anonymous20231206		95.27 311	95.06 309	95.88 313	98.72 185	89.37 366	95.70 266	97.85 346	88.00 468	96.98 298	97.62 285	91.95 312	99.34 318	89.21 436	99.53 177	98.94 267

thres400		91.68 449	91.00 451	93.71 442	98.02 297	84.35 490	95.70 266	90.79 518	96.26 154	95.90 378	92.13 506	73.62 505	99.42 275	78.85 533	97.74 439	97.36 447

reproduce_monomvs		92.05 442	92.26 422	91.43 502	95.42 490	75.72 544	95.68 269	97.05 394	94.47 276	97.95 215	98.35 165	55.58 544	99.05 391	96.36 142	99.44 219	99.51 86

test20.03		96.58 223	96.61 217	96.48 256	98.49 234	91.72 293	95.68 269	97.69 357	96.81 124	98.27 162	97.92 245	94.18 241	98.71 436	90.78 401	99.66 112	99.00 249

hse-mvs2		95.77 274	95.09 306	97.79 121	97.84 323	95.51 125	95.66 271	95.43 441	96.58 137	97.21 271	96.16 407	84.14 435	99.54 222	95.89 173	96.92 470	98.32 365

UniMVSNet_NR-MVSNet		97.83 95	97.65 124	98.37 67	98.72 185	95.78 109	95.66 271	99.02 124	98.11 57	98.31 157	97.69 278	94.65 222	99.85 30	97.02 110	99.71 94	99.48 103

fmvsm_s_conf0.5_n_4		97.43 149	97.77 111	96.39 273	98.48 236	89.89 350	95.65 273	99.26 49	94.73 259	98.72 101	98.58 129	95.58 181	99.57 212	99.28 9	99.67 109	99.73 28

dmvs_re		92.08 441	91.27 447	94.51 408	97.16 407	92.79 254	95.65 273	92.64 493	94.11 291	92.74 488	90.98 519	83.41 445	94.44 534	80.72 526	94.07 528	96.29 488

DU-MVS		97.79 102	97.60 135	98.36 69	98.73 182	95.78 109	95.65 273	98.87 172	97.57 79	98.31 157	97.83 256	94.69 218	99.85 30	97.02 110	99.71 94	99.46 109

EPMVS		89.26 482	88.55 483	91.39 504	92.36 541	79.11 527	95.65 273	79.86 552	88.60 458	93.12 477	96.53 381	70.73 516	98.10 485	90.75 403	89.32 541	96.98 460

MVP-Stereo		95.69 281	95.28 297	96.92 212	98.15 286	93.03 244	95.64 277	98.20 308	90.39 425	96.63 326	97.73 274	91.63 317	99.10 386	91.84 371	97.31 464	98.63 322
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
fmvsm_s_conf0.5_n_5		97.63 123	97.83 101	97.04 201	98.77 178	92.33 266	95.63 278	99.58 20	93.53 313	99.10 53	98.66 116	96.44 131	99.65 174	99.12 21	99.68 105	99.12 221

test_cas_vis1_n_1920		95.34 307	95.67 285	94.35 418	98.21 273	86.83 446	95.61 279	99.26 49	90.45 422	98.17 181	98.96 75	84.43 434	98.31 476	96.74 120	99.17 297	97.90 413

test_f		95.82 272	95.88 275	95.66 330	97.61 370	93.21 242	95.61 279	98.17 315	86.98 480	98.42 137	99.47 17	90.46 335	94.74 529	97.71 76	98.45 397	99.03 245

F-COLMAP		95.30 310	94.38 354	98.05 105	98.64 198	96.04 97	95.61 279	98.66 241	89.00 451	93.22 475	96.40 390	92.90 282	99.35 315	87.45 468	97.53 454	98.77 304

AUN-MVS		93.95 379	92.69 412	97.74 126	97.80 336	95.38 135	95.57 282	95.46 440	91.26 405	92.64 492	96.10 414	74.67 498	99.55 219	93.72 325	96.97 469	98.30 370

ALIKED-MNN		93.09 413	92.12 427	96.00 301	96.50 430	96.72 57	95.52 283	98.20 308	82.37 520	90.90 508	96.15 408	87.02 403	96.30 515	83.03 517	99.42 232	94.99 508

fmvsm_s_conf0.1_n_2		97.68 116	98.18 57	96.20 287	99.06 114	89.08 377	95.51 284	99.72 6	96.06 176	99.48 22	99.24 37	95.18 201	99.60 201	99.45 4	99.88 28	99.94 3

v144192		96.69 215	96.90 198	96.03 300	98.25 269	88.92 381	95.49 285	98.77 213	93.05 341	98.09 191	98.29 183	92.51 299	99.70 137	98.11 53	99.56 160	99.47 107

Fast-Effi-MVS+-dtu		96.44 233	96.12 255	97.39 170	97.18 406	94.39 189	95.46 286	98.73 223	96.03 181	94.72 426	94.92 460	96.28 144	99.69 145	93.81 318	97.98 421	98.09 392

viewmacassd2359aftdt		97.25 165	97.52 145	96.43 264	98.83 162	90.49 332	95.45 287	99.18 65	95.44 222	97.98 210	98.47 146	96.90 96	99.37 307	95.93 170	99.55 167	99.43 126

Baseline_NR-MVSNet		97.72 111	97.79 106	97.50 154	99.56 22	93.29 237	95.44 288	98.86 176	98.20 55	98.37 143	99.24 37	94.69 218	99.55 219	95.98 167	99.79 66	99.65 41

LF4IMVS		96.07 255	95.63 288	97.36 172	98.19 276	95.55 122	95.44 288	98.82 201	92.29 367	95.70 391	96.55 379	92.63 290	98.69 439	91.75 377	99.33 267	97.85 417

v1921920		96.72 212	96.96 191	95.99 302	98.21 273	88.79 387	95.42 290	98.79 207	93.22 327	98.19 179	98.26 190	92.68 287	99.70 137	98.34 50	99.55 167	99.49 97

plane_prior						94.29 196	95.42 290		94.31 283						98.93 332

v1144		96.84 198	97.08 181	96.13 295	98.42 248	89.28 368	95.41 292	98.67 238	94.21 285	97.97 212	98.31 173	93.06 276	99.65 174	98.06 58	99.62 124	99.45 113

ETV-MVS		96.13 254	95.90 273	96.82 223	97.76 346	93.89 211	95.40 293	98.95 150	95.87 194	95.58 396	91.00 518	96.36 137	99.72 112	93.36 335	98.83 347	96.85 467

fmvsm_l_conf0.5_n_9		97.92 80	98.37 40	96.57 245	98.94 139	90.54 327	95.39 294	99.58 20	96.82 123	99.56 19	98.77 96	97.23 67	99.61 198	99.17 17	99.86 35	99.57 60

v1240		96.74 208	97.02 187	95.91 310	98.18 279	88.52 393	95.39 294	98.88 170	93.15 338	98.46 132	98.40 160	92.80 284	99.71 128	98.45 46	99.49 202	99.49 97

MP-MVS-pluss		97.69 113	97.36 159	98.70 41	99.50 35	96.84 53	95.38 296	98.99 141	92.45 361	98.11 188	98.31 173	97.25 65	99.77 70	96.60 129	99.62 124	99.48 103
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MGCNet		95.71 280	95.18 301	97.33 174	94.85 509	92.82 249	95.36 297	90.89 517	95.51 216	95.61 394	97.82 259	88.39 376	99.78 59	98.23 51	99.91 19	99.40 135

v1192		96.83 201	97.06 183	96.15 294	98.28 263	89.29 367	95.36 297	98.77 213	93.73 304	98.11 188	98.34 167	93.02 281	99.67 162	98.35 49	99.58 151	99.50 89

v2v482		96.78 205	97.06 183	95.95 307	98.57 217	88.77 388	95.36 297	98.26 300	95.18 234	97.85 227	98.23 194	92.58 291	99.63 185	97.80 70	99.69 100	99.45 113

test_fmvs1		94.51 355	94.60 340	94.26 423	95.91 464	87.92 416	95.35 300	99.02 124	86.56 485	96.79 310	98.52 137	82.64 450	97.00 506	97.87 66	98.71 369	97.88 415

EI-MVSNet-Vis-set		97.32 160	97.39 154	97.11 192	97.36 394	92.08 282	95.34 301	97.65 362	97.74 70	98.29 160	98.11 214	95.05 206	99.68 152	97.50 85	99.50 199	99.56 68

fmvsm_s_conf0.5_n_2		97.59 129	98.07 69	96.17 291	98.78 175	89.10 376	95.33 302	99.55 26	95.96 185	99.41 31	99.10 57	95.18 201	99.59 203	99.43 6	99.86 35	99.81 10

EI-MVSNet-UG-set		97.32 160	97.40 153	97.09 196	97.34 397	92.01 286	95.33 302	97.65 362	97.74 70	98.30 159	98.14 206	95.04 207	99.69 145	97.55 83	99.52 184	99.58 52

CostFormer		89.75 475	89.25 472	91.26 506	94.69 513	78.00 533	95.32 304	91.98 503	81.50 525	90.55 512	96.96 352	71.06 514	98.89 412	88.59 447	92.63 533	96.87 465

viewdifsd2359ckpt13		96.47 230	96.42 238	96.61 239	98.35 255	91.50 298	95.31 305	98.84 186	93.21 329	96.73 316	97.58 289	95.28 197	99.26 348	94.02 307	98.45 397	99.07 236

PVSNet_Blended_VisFu		95.95 264	95.80 280	96.42 266	99.28 65	90.62 323	95.31 305	99.08 100	88.40 461	96.97 299	98.17 205	92.11 307	99.78 59	93.64 327	99.21 288	98.86 286

UnsupCasMVSNet_eth		95.91 267	95.73 283	96.44 262	98.48 236	91.52 297	95.31 305	98.45 272	95.76 201	97.48 253	97.54 291	89.53 355	98.69 439	94.43 286	94.61 524	99.13 215

EI-MVSNet		96.63 218	96.93 193	95.74 320	97.26 402	88.13 411	95.29 308	97.65 362	96.99 111	97.94 217	98.19 200	92.55 294	99.58 206	96.91 114	99.56 160	99.50 89

CVMVSNet		92.33 432	92.79 407	90.95 507	97.26 402	75.84 543	95.29 308	92.33 498	81.86 522	96.27 353	98.19 200	81.44 458	98.46 466	94.23 296	98.29 407	98.55 333

E4		97.28 162	97.55 142	96.46 257	98.86 157	90.53 329	95.28 310	99.18 65	95.82 199	98.01 203	98.59 128	96.78 106	99.46 256	95.86 177	99.56 160	99.38 144

viewdifsd2359ckpt09		96.23 248	96.04 260	96.82 223	98.29 260	92.06 284	95.25 311	99.03 120	91.51 394	96.19 360	97.01 348	94.41 231	99.40 287	93.76 320	98.90 335	99.00 249

OPM-MVS		97.54 136	97.25 168	98.41 64	99.11 106	96.61 65	95.24 312	98.46 271	94.58 268	98.10 190	98.07 220	97.09 73	99.39 296	95.16 236	99.44 219	99.21 195
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TAPA-MVS	93.32 12	94.93 328	94.23 359	97.04 201	98.18 279	94.51 185	95.22 313	98.73 223	81.22 527	96.25 355	95.95 424	93.80 253	98.98 403	89.89 426	98.87 340	97.62 436
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPE-MVS		97.64 121	97.35 160	98.50 56	98.85 159	96.18 88	95.21 314	98.99 141	95.84 197	98.78 90	98.08 218	96.84 103	99.81 43	93.98 309	99.57 155	99.52 82
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mamba_0408		97.17 170	97.38 157	96.55 249	98.51 226	90.96 314	95.19 315	99.06 105	96.60 133	98.27 162	97.78 264	96.58 120	99.72 112	95.04 245	99.40 238	98.98 256

SSM_04072		97.14 171	97.38 157	96.42 266	98.51 226	90.96 314	95.19 315	99.06 105	96.60 133	98.27 162	97.78 264	96.58 120	99.31 330	95.04 245	99.40 238	98.98 256

MVSTER		94.21 366	93.93 373	95.05 371	95.83 470	86.46 449	95.18 317	97.65 362	92.41 364	97.94 217	98.00 236	72.39 510	99.58 206	96.36 142	99.56 160	99.12 221

testing3-2		90.09 467	90.38 465	89.24 518	98.07 293	69.88 556	95.12 318	90.71 522	96.65 130	93.60 465	94.03 475	55.81 543	99.33 320	90.69 409	98.71 369	98.51 340

PatchmatchNet		91.98 444	91.87 431	92.30 492	94.60 515	79.71 524	95.12 318	93.59 476	89.52 441	93.61 463	97.02 344	77.94 478	99.18 366	90.84 398	94.57 526	98.01 406
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmanbaseed2359cas		96.77 206	96.94 192	96.27 281	98.41 250	90.24 340	95.11 320	99.03 120	94.28 284	97.45 257	97.85 253	95.92 160	99.32 328	95.18 233	99.19 293	99.24 189

IterMVS-LS		96.92 190	97.29 164	95.79 316	98.51 226	88.13 411	95.10 321	98.66 241	96.99 111	98.46 132	98.68 114	92.55 294	99.74 96	96.91 114	99.79 66	99.50 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		96.58 223	96.97 189	95.42 348	98.63 207	87.57 427	95.09 322	97.90 342	95.91 192	98.24 171	97.96 239	93.42 264	99.39 296	96.04 161	99.52 184	99.29 174

tpm2		88.47 491	87.69 495	90.79 509	94.98 506	77.34 537	95.09 322	91.83 504	77.51 544	89.40 527	96.41 388	67.83 522	98.73 431	83.58 515	92.60 534	96.29 488

OpenMVS_ROB	91.80 14	93.64 392	93.05 397	95.42 348	97.30 401	91.21 308	95.08 324	96.68 412	81.56 524	96.88 306	96.41 388	90.44 337	99.25 351	85.39 493	97.67 446	95.80 498

E2		96.97 186	97.19 174	96.33 275	98.64 198	90.34 337	95.07 325	99.12 83	95.00 245	97.66 238	98.31 173	96.19 148	99.43 271	95.35 221	99.35 257	99.23 191

E3		96.97 186	97.19 174	96.33 275	98.64 198	90.34 337	95.07 325	99.12 83	95.00 245	97.66 238	98.31 173	96.19 148	99.43 271	95.35 221	99.35 257	99.23 191

TAMVS		95.49 294	94.94 315	97.16 188	98.31 258	93.41 234	95.07 325	96.82 405	91.09 409	97.51 248	97.82 259	89.96 346	99.42 275	88.42 450	99.44 219	98.64 320

tpmrst		90.31 465	90.61 462	89.41 517	94.06 525	72.37 553	95.06 328	93.69 471	88.01 467	92.32 497	96.86 358	77.45 482	98.82 421	91.04 389	87.01 544	97.04 459

ADS-MVSNet2		91.47 452	90.51 463	94.36 415	95.51 486	85.63 463	95.05 329	95.70 430	83.46 514	92.69 489	96.84 360	79.15 473	99.41 285	85.66 489	90.52 537	98.04 403

ADS-MVSNet		90.95 460	90.26 466	93.04 468	95.51 486	82.37 506	95.05 329	93.41 478	83.46 514	92.69 489	96.84 360	79.15 473	98.70 437	85.66 489	90.52 537	98.04 403

tpm		91.08 458	90.85 456	91.75 499	95.33 493	78.09 531	95.03 331	91.27 513	88.75 454	93.53 467	97.40 305	71.24 512	99.30 334	91.25 386	93.87 529	97.87 416

NCCC		96.52 225	95.99 264	98.10 97	97.81 332	95.68 114	94.99 332	98.20 308	95.39 225	95.40 405	96.36 393	93.81 252	99.45 264	93.55 331	98.42 400	99.17 203

test_post1							94.98 333				10.37 561	76.21 491	99.04 394	89.47 433

FBQ-MVS		89.51 480	87.89 491	94.36 415	96.47 434	87.19 438	94.96 334	92.96 487	91.01 414	90.38 515	88.46 533	57.42 535	98.55 455	83.35 516	96.03 502	97.35 449

viewcassd2359sk11		96.73 210	96.89 199	96.24 283	98.46 241	90.20 342	94.94 335	99.07 104	94.43 278	97.33 262	98.05 229	95.69 174	99.40 287	94.98 259	99.11 306	99.12 221

fmvsm_s_conf0.5_n_7		97.13 172	97.50 149	96.04 299	98.43 246	89.03 380	94.92 336	99.00 136	94.51 271	98.42 137	98.96 75	94.97 212	99.54 222	98.42 47	99.85 48	99.56 68

AdaColmap		95.11 320	94.62 339	96.58 243	97.33 399	94.45 188	94.92 336	98.08 329	93.15 338	93.98 451	95.53 443	94.34 235	99.10 386	85.69 488	98.61 382	96.20 490

MDTV_nov1_ep13_2view						57.28 560	94.89 338		80.59 529	94.02 449		78.66 475		85.50 491		97.82 419

CNVR-MVS		96.92 190	96.55 228	98.03 106	98.00 303	95.54 123	94.87 339	98.17 315	94.60 265	96.38 343	97.05 342	95.67 177	99.36 311	95.12 242	99.08 311	99.19 199

OMC-MVS		96.48 229	96.00 263	97.91 114	98.30 259	96.01 102	94.86 340	98.60 249	91.88 378	97.18 275	97.21 326	96.11 152	99.04 394	90.49 416	99.34 262	98.69 316

E3new		96.50 226	96.61 217	96.17 291	98.28 263	90.09 343	94.85 341	99.02 124	93.95 300	97.01 293	97.74 272	95.19 200	99.39 296	94.70 279	98.77 362	99.04 243

viewdifsd2359ckpt11		97.13 172	97.62 131	95.67 328	98.64 198	88.36 399	94.84 342	98.95 150	96.24 156	98.70 103	98.61 123	96.66 111	99.29 338	96.46 135	99.45 216	99.36 154

viewmsd2359difaftdt		97.13 172	97.62 131	95.67 328	98.64 198	88.36 399	94.84 342	98.95 150	96.24 156	98.70 103	98.61 123	96.66 111	99.29 338	96.46 135	99.45 216	99.36 154

testing3		89.72 476	88.26 487	94.10 427	97.66 363	84.30 492	94.80 344	88.25 537	94.66 262	95.07 411	92.51 501	41.15 558	99.43 271	91.81 374	98.44 399	98.55 333

EPNet_dtu		91.39 454	90.75 458	93.31 456	90.48 547	82.61 504	94.80 344	92.88 488	93.39 319	81.74 548	94.90 461	81.36 459	99.11 382	88.28 452	98.87 340	98.21 383
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			91.28 446		94.31 518	73.51 551	94.80 344	93.16 482	86.75 484	93.45 470	97.40 305	76.37 489	98.55 455	88.85 441	96.43 490

LoFTR		95.39 302	95.01 311	96.52 251	97.16 407	95.19 156	94.77 347	96.95 401	90.31 427	98.78 90	98.29 183	86.71 407	97.91 490	92.56 357	99.57 155	96.46 484

pmmvs-eth3d		96.49 228	96.18 254	97.42 167	98.25 269	94.29 196	94.77 347	98.07 333	89.81 438	97.97 212	98.33 168	93.11 273	99.08 388	95.46 207	99.84 51	98.89 279

test_yl		94.40 358	94.00 369	95.59 333	96.95 415	89.52 361	94.75 349	95.55 438	96.18 167	96.79 310	96.14 411	81.09 461	99.18 366	90.75 403	97.77 435	98.07 395

DCV-MVSNet		94.40 358	94.00 369	95.59 333	96.95 415	89.52 361	94.75 349	95.55 438	96.18 167	96.79 310	96.14 411	81.09 461	99.18 366	90.75 403	97.77 435	98.07 395

dmvs_testset		87.30 503	86.99 500	88.24 524	96.71 423	77.48 536	94.68 351	86.81 545	92.64 357	89.61 526	87.01 542	85.91 417	93.12 543	61.04 551	88.49 542	94.13 517

MCST-MVS		96.24 247	95.80 280	97.56 142	98.75 180	94.13 203	94.66 352	98.17 315	90.17 434	96.21 358	96.10 414	95.14 204	99.43 271	94.13 300	98.85 343	99.13 215

XVG-OURS-SEG-HR		97.38 154	97.07 182	98.30 75	99.01 126	97.41 39	94.66 352	99.02 124	95.20 232	98.15 184	97.52 295	98.83 5	98.43 467	94.87 263	96.41 491	99.07 236

mvs_anonymous		95.36 304	96.07 259	93.21 462	96.29 441	81.56 512	94.60 354	97.66 360	93.30 324	96.95 300	98.91 85	93.03 280	99.38 300	96.60 129	97.30 465	98.69 316

DP-MVS Recon		95.55 292	95.13 304	96.80 225	98.51 226	93.99 209	94.60 354	98.69 233	90.20 433	95.78 387	96.21 404	92.73 286	98.98 403	90.58 412	98.86 342	97.42 446

ELoFTR		95.12 319	94.86 323	95.90 311	98.39 251	93.23 241	94.57 356	97.21 381	87.26 474	98.53 123	98.52 137	86.67 410	97.37 498	93.24 341	99.36 251	97.12 455

viewdifsd2359ckpt07		97.10 177	97.55 142	95.76 318	98.64 198	88.58 392	94.54 357	99.11 86	96.96 115	98.54 120	98.18 203	96.91 94	99.44 267	95.58 197	99.49 202	99.26 181

save fliter					98.48 236	94.71 172	94.53 358	98.41 281	95.02 244

patch_mono-2		96.59 220	96.93 193	95.55 341	98.88 152	87.12 439	94.47 359	99.30 43	94.12 290	96.65 325	98.41 155	94.98 211	99.87 25	95.81 181	99.78 70	99.66 38

tpm cat1		88.01 497	87.33 497	90.05 516	94.48 516	76.28 542	94.47 359	94.35 462	73.84 549	89.26 528	95.61 439	73.64 504	98.30 477	84.13 506	86.20 545	95.57 503

DKM		96.39 238	95.99 264	97.59 140	98.44 243	96.42 73	94.42 361	98.51 263	92.81 352	98.15 184	97.47 299	89.37 362	97.26 500	95.02 250	99.68 105	99.09 232

DKM-HiRes		96.47 230	95.93 271	98.09 98	98.86 157	96.41 74	94.38 362	98.56 258	94.05 294	96.93 301	97.48 298	87.73 390	98.55 455	95.86 177	99.48 207	99.31 166

CANet		95.86 270	95.65 287	96.49 254	96.41 437	90.82 319	94.36 363	98.41 281	94.94 249	92.62 494	96.73 369	92.68 287	99.71 128	95.12 242	99.60 142	98.94 267

WR-MVS		96.90 192	96.81 203	97.16 188	98.56 219	92.20 276	94.33 364	98.12 325	97.34 99	98.20 175	97.33 317	92.81 283	99.75 86	94.79 270	99.81 60	99.54 74

SP-LightGlue		95.19 315	94.96 314	95.89 312	95.10 500	94.93 167	94.29 365	98.47 269	94.91 253	94.92 421	95.51 444	86.69 408	95.61 519	97.08 107	97.67 446	97.12 455

HQP-NCC					97.85 316		94.26 366		93.18 333	92.86 485

ACMP_Plane					97.85 316		94.26 366		93.18 333	92.86 485

HQP-MVS		95.17 318	94.58 343	96.92 212	97.85 316	92.47 263	94.26 366	98.43 277	93.18 333	92.86 485	95.08 454	90.33 338	99.23 357	90.51 414	98.74 365	99.05 241

viewmamba		96.62 219	96.92 195	95.74 320	97.85 316	88.83 385	94.25 369	99.00 136	95.69 205	97.18 275	97.90 248	95.34 192	99.29 338	96.20 153	98.85 343	99.11 226

PLC	91.02 16	94.05 373	92.90 403	97.51 148	98.00 303	95.12 161	94.25 369	98.25 301	86.17 487	91.48 505	95.25 452	91.01 325	99.19 363	85.02 500	96.69 484	98.22 382
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MatchFormer		93.37 400	93.14 394	94.07 428	96.06 459	92.91 248	94.24 371	94.92 452	85.51 494	98.29 160	97.79 263	85.70 420	96.13 516	86.23 480	99.51 190	93.18 523

1112_ss		94.12 369	93.42 388	96.23 284	98.59 213	90.85 318	94.24 371	98.85 182	85.49 495	92.97 480	94.94 458	86.01 416	99.64 180	91.78 375	97.92 425	98.20 384

MS-PatchMatch		94.83 333	94.91 319	94.57 404	96.81 420	87.10 441	94.23 373	97.34 377	88.74 455	97.14 278	97.11 338	91.94 313	98.23 480	92.99 347	97.92 425	98.37 357

Fast-Effi-MVS+		95.49 294	95.07 307	96.75 229	97.67 362	92.82 249	94.22 374	98.60 249	91.61 386	93.42 472	92.90 492	96.73 109	99.70 137	92.60 354	97.89 430	97.74 427

CMPMVS	73.10 23	92.74 420	91.39 443	96.77 228	93.57 531	94.67 175	94.21 375	97.67 358	80.36 531	93.61 463	96.60 377	82.85 449	97.35 499	84.86 502	98.78 355	98.29 373
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
DenseAffine		96.06 257	95.57 290	97.53 147	98.44 243	95.79 108	94.20 376	98.14 322	92.44 363	97.95 215	97.18 329	88.87 369	97.96 488	93.41 333	99.52 184	98.85 288

dp		88.08 496	88.05 489	88.16 526	92.85 537	68.81 558	94.17 377	92.88 488	85.47 496	91.38 506	96.14 411	68.87 521	98.81 423	86.88 473	83.80 547	96.87 465

JIA-IIPM		91.79 447	90.69 460	95.11 366	93.80 528	90.98 312	94.16 378	91.78 506	96.38 148	90.30 518	99.30 33	72.02 511	98.90 411	88.28 452	90.17 539	95.45 504

D2MVS		95.18 316	95.17 302	95.21 360	97.76 346	87.76 425	94.15 379	97.94 338	89.77 439	96.99 295	97.68 279	87.45 393	99.14 374	95.03 249	99.81 60	98.74 308

TSAR-MVS + GP.		96.47 230	96.12 255	97.49 157	97.74 351	95.23 150	94.15 379	96.90 402	93.26 325	98.04 199	96.70 371	94.41 231	98.89 412	94.77 273	99.14 300	98.37 357

PVSNet_BlendedMVS		95.02 327	94.93 317	95.27 357	97.79 341	87.40 433	94.14 381	98.68 235	88.94 452	94.51 431	98.01 234	93.04 277	99.30 334	89.77 428	99.49 202	99.11 226

TinyColmap		96.00 262	96.34 244	94.96 379	97.90 313	87.91 417	94.13 382	98.49 266	94.41 279	98.16 182	97.76 266	96.29 143	98.68 442	90.52 413	99.42 232	98.30 370

CNLPA		95.04 324	94.47 349	96.75 229	97.81 332	95.25 149	94.12 383	97.89 343	94.41 279	94.57 429	95.69 434	90.30 341	98.35 474	86.72 475	98.76 363	96.64 475

SP-SuperGlue		95.41 301	95.38 295	95.51 343	94.92 508	94.67 175	94.09 384	97.93 340	95.45 219	95.62 392	96.26 400	89.54 352	95.26 521	96.70 121	97.92 425	96.61 478

BH-untuned		94.69 341	94.75 332	94.52 407	97.95 309	87.53 428	94.07 385	97.01 397	93.99 297	97.10 282	95.65 436	92.65 289	98.95 408	87.60 462	96.74 480	97.09 457

fmvsm_l_mol_unc0.5_1		97.76 105	98.18 57	96.49 254	99.02 125	90.21 341	94.06 386	99.63 17	96.81 124	99.74 6	99.60 11	95.96 157	99.66 170	98.92 30	99.86 35	99.60 47

onestephybrid01		96.25 246	96.31 246	96.07 298	97.54 378	90.01 348	94.06 386	98.77 213	94.74 256	96.32 346	97.74 272	94.03 244	99.20 361	94.81 268	98.79 353	98.98 256

ArgMatch-SfM		95.74 278	95.15 303	97.49 157	97.82 330	95.16 158	94.03 388	98.41 281	89.33 443	97.58 242	96.65 374	90.07 345	98.89 412	93.17 344	99.30 276	98.44 350

pmmvs5		94.63 347	94.34 355	95.50 344	97.63 369	88.34 401	94.02 389	97.13 386	87.15 477	95.22 409	97.15 330	87.50 392	99.27 346	93.99 308	99.26 283	98.88 283

thres200		91.00 459	90.42 464	92.77 480	97.47 388	83.98 495	94.01 390	91.18 514	95.12 237	95.44 402	91.21 516	73.93 501	99.31 330	77.76 537	97.63 451	95.01 507

xiu_mvs_v1_base_debu		95.62 288	95.96 267	94.60 401	98.01 299	88.42 396	93.99 391	98.21 305	92.98 344	95.91 374	94.53 467	96.39 134	99.72 112	95.43 212	98.19 410	95.64 500

xiu_mvs_v1_base		95.62 288	95.96 267	94.60 401	98.01 299	88.42 396	93.99 391	98.21 305	92.98 344	95.91 374	94.53 467	96.39 134	99.72 112	95.43 212	98.19 410	95.64 500

xiu_mvs_v1_base_debi		95.62 288	95.96 267	94.60 401	98.01 299	88.42 396	93.99 391	98.21 305	92.98 344	95.91 374	94.53 467	96.39 134	99.72 112	95.43 212	98.19 410	95.64 500

test_vis1_rt		94.03 375	93.65 379	95.17 363	95.76 477	93.42 233	93.97 394	98.33 294	84.68 506	93.17 476	95.89 427	92.53 298	94.79 527	93.50 332	94.97 520	97.31 452

CDS-MVSNet		94.88 332	94.12 366	97.14 190	97.64 368	93.57 225	93.96 395	97.06 393	90.05 435	96.30 352	96.55 379	86.10 415	99.47 249	90.10 422	99.31 272	98.40 352
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SP-DiffGlue		94.64 346	94.54 346	94.97 378	93.53 532	94.33 194	93.94 396	97.84 348	93.35 321	96.58 329	95.54 441	88.87 369	94.71 530	93.73 323	97.44 460	95.87 495

CANet_DTU		94.65 345	94.21 362	95.96 305	95.90 465	89.68 357	93.92 397	97.83 351	93.19 332	90.12 521	95.64 437	88.52 373	99.57 212	93.27 340	99.47 210	98.62 323

WTY-MVS		93.55 394	93.00 400	95.19 361	97.81 332	87.86 419	93.89 398	96.00 423	89.02 450	94.07 446	95.44 447	86.27 414	99.33 320	87.69 460	96.82 476	98.39 354

sss		94.22 364	93.72 377	95.74 320	97.71 355	89.95 349	93.84 399	96.98 398	88.38 462	93.75 456	95.74 433	87.94 383	98.89 412	91.02 390	98.10 414	98.37 357

baseline2		89.65 478	88.44 485	93.25 458	95.62 483	82.71 502	93.82 400	85.94 546	88.89 453	87.35 540	92.54 500	71.23 513	99.33 320	86.01 483	94.60 525	97.72 430

XVG-OURS		97.12 175	96.74 209	98.26 79	98.99 131	97.45 37	93.82 400	99.05 111	95.19 233	98.32 155	97.70 277	95.22 199	98.41 468	94.27 294	98.13 413	98.93 271

MVS_111021_LR		96.82 202	96.55 228	97.62 138	98.27 266	95.34 144	93.81 402	98.33 294	94.59 267	96.56 332	96.63 376	96.61 117	98.73 431	94.80 269	99.34 262	98.78 295

BH-RMVSNet		94.56 352	94.44 352	94.91 381	97.57 373	87.44 430	93.78 403	96.26 418	93.69 307	96.41 342	96.50 384	92.10 308	99.00 399	85.96 485	97.71 442	98.31 367

dtuplus		95.73 279	95.86 276	95.33 355	97.72 353	87.82 422	93.74 404	98.60 249	92.12 370	97.27 265	97.92 245	94.35 234	99.13 377	92.24 362	98.83 347	99.05 241

SP-MNN		94.33 362	94.22 361	94.67 396	94.94 507	92.73 257	93.74 404	96.59 416	92.73 355	93.75 456	95.38 449	88.24 379	95.08 524	94.86 266	97.78 434	96.20 490

diffmvs_AUTHOR		96.50 226	96.81 203	95.57 335	98.03 295	88.26 403	93.73 406	99.14 79	94.92 252	97.24 268	97.84 255	94.62 223	99.33 320	96.44 138	99.37 246	99.13 215

CDPH-MVS		95.45 299	94.65 335	97.84 119	98.28 263	94.96 165	93.73 406	98.33 294	85.03 502	95.44 402	96.60 377	95.31 195	99.44 267	90.01 423	99.13 302	99.11 226

hybridnocas07		96.00 262	96.21 252	95.39 353	97.56 375	87.89 418	93.70 408	98.93 155	93.96 299	96.48 337	97.65 281	93.38 265	99.19 363	95.39 217	98.81 351	99.08 233

PatchMatch-RL		94.61 348	93.81 374	97.02 205	98.19 276	95.72 111	93.66 409	97.23 380	88.17 465	94.94 419	95.62 438	91.43 318	98.57 452	87.36 469	97.68 445	96.76 473

hybrid		95.77 274	95.95 270	95.23 359	97.54 378	87.44 430	93.65 410	98.86 176	93.16 337	96.06 368	97.65 281	93.14 272	99.20 361	94.94 261	98.57 386	99.04 243

UWE-MVS-28		83.78 509	82.36 513	88.03 527	90.72 546	71.58 554	93.64 411	77.87 553	87.62 472	85.91 544	92.89 493	59.94 529	95.99 518	56.06 553	96.56 489	96.52 480

TEST9					97.84 323	95.23 150	93.62 412	98.39 285	86.81 482	93.78 453	95.99 420	94.68 220	99.52 228

train_agg		95.46 298	94.66 334	97.88 116	97.84 323	95.23 150	93.62 412	98.39 285	87.04 478	93.78 453	95.99 420	94.58 225	99.52 228	91.76 376	98.90 335	98.89 279

viewmambaseed2359dif		95.68 283	95.85 277	95.17 363	97.51 381	87.41 432	93.61 414	98.58 255	91.06 410	96.68 319	97.66 280	94.71 217	99.11 382	93.93 311	98.94 327	98.99 253

test_prior4						95.38 135	93.61 414

ArgMatch-Sym		95.60 291	94.97 313	97.48 159	97.70 356	95.41 132	93.60 416	97.89 343	89.33 443	97.70 235	96.03 419	91.00 327	98.66 444	92.25 361	99.18 294	98.39 354

test_8					97.81 332	95.07 162	93.54 417	98.38 287	87.04 478	93.71 458	95.96 423	94.58 225	99.52 228

TR-MVS		92.54 426	92.20 424	93.57 446	96.49 431	86.66 447	93.51 418	94.73 455	89.96 436	94.95 418	93.87 478	90.24 343	98.61 449	81.18 525	94.88 521	95.45 504

PMatch-SfM		95.65 287	95.03 310	97.51 148	97.96 305	95.00 163	93.49 419	98.51 263	92.24 368	97.80 230	98.03 230	83.97 440	99.19 363	94.77 273	98.50 392	98.35 363

新几何2							93.43 420

diffmvs		96.04 258	96.23 250	95.46 347	97.35 395	88.03 415	93.42 421	99.08 100	94.09 293	96.66 323	96.93 353	93.85 251	99.29 338	96.01 165	98.67 375	99.06 239
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_HR		96.73 210	96.54 230	97.27 179	98.35 255	93.66 223	93.42 421	98.36 290	94.74 256	96.58 329	96.76 368	96.54 122	98.99 401	94.87 263	99.27 280	99.15 207

PMatch-Up-SfM		95.95 264	95.43 294	97.51 148	97.90 313	95.17 157	93.40 423	98.78 211	92.45 361	98.24 171	98.07 220	87.10 402	99.18 366	94.87 263	98.10 414	98.19 385

UnsupCasMVSNet_bld		94.72 340	94.26 358	96.08 297	98.62 209	90.54 327	93.38 424	98.05 336	90.30 428	97.02 291	96.80 365	89.54 352	99.16 372	88.44 449	96.18 498	98.56 330

旧先验2							93.35 425		77.95 542	95.77 389			98.67 443	90.74 406

test_prior2							93.33 426		94.21 285	94.02 449	96.25 402	93.64 258		91.90 368	98.96 324

WB-MVSnew		91.50 451	91.29 445	92.14 495	94.85 509	80.32 522	93.29 427	88.77 534	88.57 459	94.03 448	92.21 504	92.56 292	98.28 478	80.21 528	97.08 467	97.81 421

IMVS_0404		95.66 286	96.03 261	94.55 405	97.83 326	86.11 457	93.24 428	98.82 201	94.48 272	95.51 400	97.14 331	93.49 261	98.78 425	95.00 251	98.78 355	98.78 295

SCA		93.38 399	93.52 384	92.96 473	96.24 442	81.40 515	93.24 428	94.00 466	91.58 393	94.57 429	96.97 350	87.94 383	99.42 275	89.47 433	97.66 449	98.06 399

无先验							93.20 430	97.91 341	80.78 528				99.40 287	87.71 458		97.94 411

MG-MVS		94.08 372	94.00 369	94.32 420	97.09 411	85.89 462	93.19 431	95.96 425	92.52 358	94.93 420	97.51 296	89.54 352	98.77 427	87.52 466	97.71 442	98.31 367

ALIKED-NN		90.94 461	89.58 471	95.02 373	94.61 514	96.31 81	93.16 432	97.27 378	79.38 534	86.25 543	95.27 451	83.42 444	94.29 535	79.08 531	97.77 435	94.46 512

nomal-1		90.42 464	88.88 481	95.06 370	96.01 460	88.66 391	93.13 433	92.16 499	91.23 406	90.46 514	91.32 515	61.17 528	98.72 434	87.70 459	96.70 483	97.79 424

MVS-HIRNet		88.40 492	90.20 467	82.99 530	97.01 413	60.04 559	93.11 434	85.61 547	84.45 510	88.72 533	99.09 59	84.72 431	98.23 480	82.52 519	96.59 488	90.69 541

new-patchmatchnet		95.67 284	96.58 221	92.94 474	97.48 384	80.21 523	92.96 435	98.19 314	94.83 254	98.82 87	98.79 92	93.31 267	99.51 232	95.83 179	99.04 317	99.12 221

ETVMVS		87.62 500	85.75 508	93.22 461	96.15 453	83.26 499	92.94 436	90.37 526	91.39 402	90.37 516	88.45 534	51.93 553	98.64 446	73.76 542	96.38 493	97.75 426

MDA-MVSNet-bldmvs		95.69 281	95.67 285	95.74 320	98.48 236	88.76 389	92.84 437	97.25 379	96.00 182	97.59 241	97.95 241	91.38 319	99.46 256	93.16 345	96.35 494	98.99 253

原ACMM2							92.82 438

testdata1							92.77 439		93.78 303

Test_1112_low_res		93.53 395	92.86 404	95.54 342	98.60 211	88.86 384	92.75 440	98.69 233	82.66 518	92.65 491	96.92 356	84.75 430	99.56 214	90.94 393	97.76 438	98.19 385

USDC		94.56 352	94.57 345	94.55 405	97.78 344	86.43 451	92.75 440	98.65 246	85.96 489	96.91 304	97.93 244	90.82 329	98.74 430	90.71 407	99.59 145	98.47 346

test222					98.17 282	93.24 240	92.74 442	97.61 370	75.17 546	94.65 428	96.69 372	90.96 328			98.66 377	97.66 432

jason		94.39 360	94.04 368	95.41 350	98.29 260	87.85 421	92.74 442	96.75 408	85.38 499	95.29 407	96.15 408	88.21 382	99.65 174	94.24 295	99.34 262	98.74 308
jason: jason.
testing91		89.67 477	88.55 483	93.04 468	95.90 465	81.80 511	92.71 444	93.71 470	93.71 305	90.18 519	90.15 524	57.11 536	99.22 359	87.17 472	96.32 495	98.12 391

testing99		89.21 483	88.04 490	92.70 482	95.78 475	81.00 519	92.65 445	92.03 501	93.20 331	89.90 524	90.08 526	55.25 545	99.14 374	87.54 464	95.95 503	97.97 408

Patchmatch-RL test		94.66 344	94.49 347	95.19 361	98.54 222	88.91 382	92.57 446	98.74 221	91.46 400	98.32 155	97.75 269	77.31 485	98.81 423	96.06 158	99.61 135	97.85 417

DeepPCF-MVS	94.58 5	96.90 192	96.43 237	98.31 74	97.48 384	97.23 45	92.56 447	98.60 249	92.84 351	98.54 120	97.40 305	96.64 116	98.78 425	94.40 289	99.41 237	98.93 271

N_pmnet		95.18 316	94.23 359	98.06 101	97.85 316	96.55 67	92.49 448	91.63 507	89.34 442	98.09 191	97.41 304	90.33 338	99.06 390	91.58 379	99.31 272	98.56 330

testing11		88.93 485	87.63 496	92.80 479	95.87 467	81.49 513	92.48 449	91.54 508	91.62 385	88.27 536	90.24 522	55.12 548	99.11 382	87.30 470	96.28 497	97.81 421

Syy-MVS		92.09 440	91.80 434	92.93 475	95.19 497	82.65 503	92.46 450	91.35 510	90.67 419	91.76 502	87.61 536	85.64 422	98.50 461	94.73 276	96.84 474	97.65 433

myMVS_eth3d		87.16 505	85.61 509	91.82 498	95.19 497	79.32 525	92.46 450	91.35 510	90.67 419	91.76 502	87.61 536	41.96 557	98.50 461	82.66 518	96.84 474	97.65 433

BH-w/o		92.14 438	91.94 429	92.73 481	97.13 410	85.30 470	92.46 450	95.64 432	89.33 443	94.21 438	92.74 497	89.60 350	98.24 479	81.68 522	94.66 523	94.66 511

IterMVS-SCA-FT		95.86 270	96.19 253	94.85 386	97.68 358	85.53 465	92.42 453	97.63 369	96.99 111	98.36 146	98.54 136	87.94 383	99.75 86	97.07 108	99.08 311	99.27 179

IterMVS		95.42 300	95.83 279	94.20 424	97.52 380	83.78 497	92.41 454	97.47 374	95.49 218	98.06 196	98.49 141	87.94 383	99.58 206	96.02 163	99.02 318	99.23 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing222		87.35 502	85.50 510	92.93 475	95.79 474	82.83 501	92.40 455	90.10 530	92.80 353	88.87 532	89.02 529	48.34 556	98.70 437	75.40 541	96.74 480	97.27 453

DELS-MVS		96.17 252	96.23 250	95.99 302	97.55 377	90.04 346	92.38 456	98.52 261	94.13 289	96.55 334	97.06 341	94.99 210	99.58 206	95.62 193	99.28 278	98.37 357
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
blended_shiyan8		93.34 401	92.55 417	95.73 324	95.69 480	89.08 377	92.36 457	97.11 388	91.47 398	95.42 404	88.94 532	82.26 453	99.48 243	93.84 316	95.81 508	98.62 323

blended_shiyan6		93.34 401	92.54 418	95.73 324	95.68 481	89.08 377	92.35 458	97.10 389	91.47 398	95.37 406	88.96 531	82.26 453	99.48 243	93.83 317	95.85 504	98.62 323

new_pmnet		92.34 431	91.69 440	94.32 420	96.23 444	89.16 372	92.27 459	92.88 488	84.39 511	95.29 407	96.35 394	85.66 421	96.74 512	84.53 504	97.56 452	97.05 458

myMVS_eth3d28		88.32 493	87.73 494	90.11 515	96.42 435	74.96 548	92.21 460	92.37 497	93.56 312	90.14 520	89.61 527	56.13 541	98.05 487	81.84 520	97.26 466	97.33 451

CHOSEN 1792x2688		94.10 370	93.41 389	96.18 290	99.16 94	90.04 346	92.15 461	98.68 235	79.90 532	96.22 357	97.83 256	87.92 387	99.42 275	89.18 437	99.65 114	99.08 233

blend_shiyan4		88.73 489	86.43 505	95.61 332	95.31 494	89.17 369	92.13 462	97.10 389	91.59 392	94.15 443	87.38 538	52.97 552	99.40 287	91.84 371	75.42 552	98.27 374

xiu_mvs_v2_base		94.22 364	94.63 338	92.99 472	97.32 400	84.84 482	92.12 463	97.84 348	91.96 376	94.17 441	93.43 481	96.07 155	99.71 128	91.27 384	97.48 456	94.42 514

lupinMVS		93.77 381	93.28 390	95.24 358	97.68 358	87.81 423	92.12 463	96.05 421	84.52 508	94.48 433	95.06 456	86.90 404	99.63 185	93.62 330	99.13 302	98.27 374

pmmvs4		94.82 334	94.19 363	96.70 232	97.42 391	92.75 255	92.09 465	96.76 407	86.80 483	95.73 390	97.22 325	89.28 363	98.89 412	93.28 339	99.14 300	98.46 348

SP-NN		92.63 424	92.38 419	93.37 449	93.30 533	92.36 265	92.04 466	94.24 464	91.60 390	89.19 529	93.92 477	87.21 399	91.28 547	93.73 323	96.17 499	96.48 482

PAPR		92.22 436	91.27 447	95.07 369	95.73 479	88.81 386	91.97 467	97.87 345	85.80 492	90.91 507	92.73 498	91.16 321	98.33 475	79.48 529	95.76 513	98.08 393

UWE-MVS		87.57 501	86.72 503	90.13 514	95.21 496	73.56 550	91.94 468	83.78 550	88.73 456	93.00 479	92.87 494	55.22 546	99.25 351	81.74 521	97.96 423	97.59 439

gbinet_0.2-2-1-0.02		92.86 417	91.78 436	96.13 295	94.34 517	90.06 344	91.90 469	96.63 415	91.73 380	94.24 437	86.22 545	80.26 469	99.56 214	93.87 314	96.80 478	98.77 304

PS-MVSNAJ		94.10 370	94.47 349	93.00 471	97.35 395	84.88 479	91.86 470	97.84 348	91.96 376	94.17 441	92.50 502	95.82 166	99.71 128	91.27 384	97.48 456	94.40 515

c3_l		95.20 314	95.32 296	94.83 388	96.19 447	86.43 451	91.83 471	98.35 293	93.47 317	97.36 261	97.26 323	88.69 371	99.28 343	95.41 215	99.36 251	98.78 295

icg_test_0407_2		95.88 268	96.39 240	94.36 415	97.83 326	86.11 457	91.82 472	98.82 201	94.48 272	97.57 243	97.14 331	96.08 153	98.20 483	95.00 251	98.78 355	98.78 295

test0.0.03 1		90.11 466	89.21 475	92.83 478	93.89 527	86.87 445	91.74 473	88.74 535	92.02 374	94.71 427	91.14 517	73.92 502	94.48 533	83.75 514	92.94 531	97.16 454

UBG		88.29 494	87.17 498	91.63 500	96.08 456	78.21 530	91.61 474	91.50 509	89.67 440	89.71 525	88.97 530	59.01 531	98.91 409	81.28 524	96.72 482	97.77 425

SSC-MVS3.2		95.75 277	96.56 224	93.34 451	98.69 194	80.75 520	91.60 475	97.43 376	97.37 97	96.99 295	97.02 344	93.69 257	99.71 128	96.32 145	99.89 26	99.55 72

FPMVS		89.92 472	88.63 482	93.82 436	98.37 253	96.94 50	91.58 476	93.34 480	88.00 468	90.32 517	97.10 339	70.87 515	91.13 549	71.91 547	96.16 501	93.39 522

ET-MVSNet_ETH3D		91.12 455	89.67 470	95.47 346	96.41 437	89.15 373	91.54 477	90.23 528	89.07 449	86.78 542	92.84 495	69.39 519	99.44 267	94.16 298	96.61 487	97.82 419

WBMVS		91.11 456	90.72 459	92.26 493	95.99 461	77.98 534	91.47 478	95.90 427	91.63 384	95.90 378	96.45 386	59.60 530	99.46 256	89.97 425	99.59 145	99.33 159

PVSNet_Blended		93.96 377	93.65 379	94.91 381	97.79 341	87.40 433	91.43 479	98.68 235	84.50 509	94.51 431	94.48 470	93.04 277	99.30 334	89.77 428	98.61 382	98.02 405

CLD-MVS		95.47 297	95.07 307	96.69 233	98.27 266	92.53 260	91.36 480	98.67 238	91.22 407	95.78 387	94.12 474	95.65 178	98.98 403	90.81 399	99.72 91	98.57 329
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
eth_miper_zixun_eth		94.89 331	94.93 317	94.75 393	95.99 461	86.12 456	91.35 481	98.49 266	93.40 318	97.12 280	97.25 324	86.87 406	99.35 315	95.08 244	98.82 349	98.78 295

cl____		94.73 336	94.64 336	95.01 374	95.85 469	87.00 442	91.33 482	98.08 329	93.34 322	97.10 282	97.33 317	84.01 439	99.30 334	95.14 239	99.56 160	98.71 315

DIV-MVS_self_test		94.73 336	94.64 336	95.01 374	95.86 468	87.00 442	91.33 482	98.08 329	93.34 322	97.10 282	97.34 316	84.02 438	99.31 330	95.15 238	99.55 167	98.72 311

miper_ehance_all_eth		94.69 341	94.70 333	94.64 397	95.77 476	86.22 454	91.32 484	98.24 303	91.67 383	97.05 289	96.65 374	88.39 376	99.22 359	94.88 262	98.34 404	98.49 345

usedtu_dtu_shiyan1		94.61 348	94.29 356	95.57 335	97.93 310	88.45 394	91.30 485	97.64 366	91.61 386	95.85 383	95.79 431	86.65 411	99.48 243	92.92 350	98.97 321	98.78 295

FE-MVSNET3		94.61 348	94.29 356	95.57 335	97.93 310	88.45 394	91.30 485	97.64 366	91.61 386	95.85 383	95.79 431	86.65 411	99.48 243	92.92 350	98.97 321	98.78 295

pmmvs3		90.00 469	88.90 480	93.32 455	94.20 523	85.34 468	91.25 487	92.56 496	78.59 539	93.82 452	95.17 453	67.36 523	98.69 439	89.08 439	98.03 419	95.92 492

SIFT-NCM-Cal		93.81 380	93.73 375	94.05 430	96.55 427	96.75 56	91.23 488	93.80 468	91.44 401	95.86 382	96.27 399	90.82 329	93.76 537	88.26 454	99.37 246	91.63 531

SIFT-MNN		93.13 412	92.91 402	93.79 438	96.42 435	96.49 69	91.23 488	93.73 469	92.18 369	95.52 399	96.08 417	84.66 432	93.04 544	87.49 467	98.94 327	91.84 527

HyFIR lowres test		93.72 386	92.65 413	96.91 214	98.93 143	91.81 292	91.23 488	98.52 261	82.69 516	96.46 340	96.52 383	80.38 465	99.90 17	90.36 418	98.79 353	99.03 245

DPM-MVS		93.68 389	92.77 410	96.42 266	97.91 312	92.54 259	91.17 491	97.47 374	84.99 504	93.08 478	94.74 463	89.90 347	99.00 399	87.54 464	98.09 416	97.72 430

CL-MVSNet_self_test		95.04 324	94.79 331	95.82 315	97.51 381	89.79 353	91.14 492	96.82 405	93.05 341	96.72 317	96.40 390	90.82 329	99.16 372	91.95 367	98.66 377	98.50 343

miper_lstm_enhance		94.81 335	94.80 330	94.85 386	96.16 450	86.45 450	91.14 492	98.20 308	93.49 316	97.03 290	97.37 314	84.97 429	99.26 348	95.28 224	99.56 160	98.83 289

dtuonlycased		95.11 320	95.70 284	93.35 450	99.05 120	81.45 514	91.13 494	98.48 268	93.11 340	97.98 210	97.27 321	96.15 151	99.32 328	89.61 430	98.50 392	99.27 179

cl22		93.25 407	92.84 406	94.46 412	94.30 519	86.00 461	91.09 495	96.64 414	90.74 416	95.79 385	96.31 397	78.24 476	98.77 427	94.15 299	98.34 404	98.62 323

MSDG		95.33 308	95.13 304	95.94 309	97.40 392	91.85 290	91.02 496	98.37 289	95.30 229	96.31 351	95.99 420	94.51 229	98.38 471	89.59 431	97.65 450	97.60 438

wanda-best-256-512		92.66 422	91.75 438	95.40 351	94.99 503	88.19 405	90.89 497	97.05 394	91.02 412	94.75 423	87.24 539	80.36 466	99.46 256	93.63 328	95.85 504	98.55 333

FE-blended-shiyan7		92.66 422	91.75 438	95.40 351	94.99 503	88.19 405	90.89 497	97.05 394	91.02 412	94.75 423	87.24 539	80.36 466	99.46 256	93.63 328	95.85 504	98.55 333

IB-MVS	85.98 20	88.63 490	86.95 502	93.68 443	95.12 499	84.82 483	90.85 499	90.17 529	87.55 473	88.48 535	91.34 514	58.01 532	99.59 203	87.24 471	93.80 530	96.63 477
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
mvsany_test1		93.47 396	93.03 398	94.79 390	94.05 526	92.12 278	90.82 500	90.01 531	85.02 503	97.26 267	98.28 185	93.57 259	97.03 504	92.51 358	95.75 514	95.23 506

test123		12.59 524	15.49 528	3.87 541	6.07 566	2.55 568	90.75 501	2.59 569	2.52 559	5.20 563	13.02 559	4.96 565	1.85 563	5.20 561	9.09 561	7.23 557

SIFT-UMatch		93.66 390	93.67 378	93.63 444	96.30 440	96.15 91	90.62 502	94.47 460	92.12 370	97.39 260	96.18 405	87.74 389	93.63 539	88.59 447	99.64 118	91.12 535

ppachtmachnet_test		94.49 356	94.84 326	93.46 448	96.16 450	82.10 507	90.59 503	97.48 373	90.53 421	97.01 293	97.59 287	91.01 325	99.36 311	93.97 310	99.18 294	98.94 267

SIFT-ConvMatch		93.72 386	93.47 385	94.48 411	96.22 446	96.63 64	90.58 504	93.91 467	91.70 381	97.70 235	96.17 406	89.03 366	95.12 522	86.29 479	99.65 114	91.69 530

PMMVS		92.39 429	91.08 450	96.30 280	93.12 535	92.81 251	90.58 504	95.96 425	79.17 536	91.85 501	92.27 503	90.29 342	98.66 444	89.85 427	96.68 485	97.43 445

our_test_3		94.20 368	94.58 343	93.07 466	96.16 450	81.20 517	90.42 506	96.84 403	90.72 417	97.14 278	97.13 335	90.47 334	99.11 382	94.04 305	98.25 408	98.91 275

SIFT-NN-NCMNet		92.32 433	91.79 435	93.89 434	96.32 439	96.91 51	90.32 507	90.69 523	90.36 426	91.72 504	95.43 448	88.98 367	94.27 536	84.23 505	98.06 417	90.49 543

YYNet1		94.73 336	94.84 326	94.41 414	97.47 388	85.09 476	90.29 508	95.85 429	92.52 358	97.53 246	97.76 266	91.97 311	99.18 366	93.31 338	96.86 473	98.95 264

MDA-MVSNet_test_wron		94.73 336	94.83 328	94.42 413	97.48 384	85.15 474	90.28 509	95.87 428	92.52 358	97.48 253	97.76 266	91.92 314	99.17 371	93.32 337	96.80 478	98.94 267

SIFT-NN-PointCN		92.48 428	92.19 425	93.33 454	95.40 492	95.65 117	90.19 510	93.07 484	88.67 457	92.90 481	95.95 424	89.38 361	93.20 542	85.21 496	98.94 327	91.15 534

SIFT-NN-UMatch		92.28 435	91.93 430	93.34 451	96.13 455	96.04 97	90.05 511	92.08 500	90.41 423	92.88 483	95.29 450	87.36 398	93.63 539	85.33 494	97.87 431	90.34 544

GA-MVS		92.83 419	92.15 426	94.87 385	96.97 414	87.27 436	90.03 512	96.12 420	91.83 379	94.05 447	94.57 465	76.01 492	98.97 407	92.46 359	97.34 463	98.36 362

miper_enhance_ethall		93.14 410	92.78 409	94.20 424	93.65 529	85.29 471	89.97 513	97.85 346	85.05 501	96.15 365	94.56 466	85.74 418	99.14 374	93.74 321	98.34 404	98.17 389

test-LLR		89.97 471	89.90 468	90.16 512	94.24 521	74.98 545	89.89 514	89.06 532	92.02 374	89.97 522	90.77 520	73.92 502	98.57 452	91.88 369	97.36 461	96.92 462

TESTMET0.1,1		87.20 504	86.57 504	89.07 519	93.62 530	72.84 552	89.89 514	87.01 544	85.46 497	89.12 530	90.20 523	56.00 542	97.72 495	90.91 394	96.92 470	96.64 475

test-mter		87.92 498	87.17 498	90.16 512	94.24 521	74.98 545	89.89 514	89.06 532	86.44 486	89.97 522	90.77 520	54.96 549	98.57 452	91.88 369	97.36 461	96.92 462

PCF-MVS	89.43 18	92.12 439	90.64 461	96.57 245	97.80 336	93.48 230	89.88 517	98.45 272	74.46 547	96.04 369	95.68 435	90.71 332	99.31 330	73.73 543	99.01 320	96.91 464
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SIFT-CM-Cal		93.31 403	93.10 395	93.95 433	96.19 447	96.32 80	89.81 518	93.40 479	91.16 408	97.19 274	96.07 418	88.24 379	94.58 532	86.11 481	99.69 100	90.94 538

SIFT-UM-Cal		93.74 383	93.73 375	93.78 439	95.97 463	96.07 95	89.78 519	96.67 413	91.69 382	97.77 233	96.09 416	89.51 356	94.75 528	86.68 476	99.39 242	90.52 542

MASt3R-SfM		91.42 453	90.88 454	93.06 467	92.40 540	92.08 282	89.76 520	93.15 483	78.62 538	95.98 371	97.33 317	82.42 452	91.17 548	90.23 420	97.98 421	95.92 492

SIFT-PointCN		93.04 414	92.72 411	94.01 432	95.80 473	95.33 147	89.76 520	92.60 495	90.24 431	96.32 346	95.87 428	87.45 393	94.70 531	86.65 477	99.77 72	92.01 526

thisisatest0515		90.43 463	89.18 478	94.17 426	97.07 412	85.44 466	89.75 522	87.58 541	88.28 463	93.69 461	91.72 510	65.27 524	99.58 206	90.59 411	98.67 375	97.50 444

SIFT-PCN-Cal		93.02 415	92.95 401	93.23 460	95.63 482	94.57 183	89.68 523	94.71 456	90.40 424	97.02 291	95.84 429	88.33 378	93.66 538	85.26 495	99.65 114	91.45 533

PatchmatchNet2					0.00 568	78.83 528	89.63 524	94.76 454	87.65 471
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
KD-MVS_2432*1600		88.93 485	87.74 492	92.49 486	88.04 553	81.99 508	89.63 524	95.62 433	91.35 403	95.06 413	93.11 483	56.58 538	98.63 447	85.19 497	95.07 518	96.85 467

miper_refine_blended		88.93 485	87.74 492	92.49 486	88.04 553	81.99 508	89.63 524	95.62 433	91.35 403	95.06 413	93.11 483	56.58 538	98.63 447	85.19 497	95.07 518	96.85 467

SIFT-NN-CMatch		92.54 426	92.03 428	94.07 428	96.08 456	96.27 85	89.47 527	90.90 516	90.26 430	92.89 482	94.83 462	90.17 344	94.95 526	84.92 501	98.78 355	90.99 537

dtuonly		92.30 434	93.44 386	88.89 520	95.60 484	69.49 557	89.18 528	98.09 327	88.17 465	94.19 439	96.35 394	88.98 367	98.72 434	91.74 378	98.69 372	98.45 349

testmvs		12.33 525	15.23 529	3.64 542	5.77 567	2.23 569	88.99 529	3.62 567	2.30 560	5.29 562	13.09 558	4.52 566	1.95 562	5.16 562	8.32 562	6.75 558

SIFT-NN		89.78 474	89.23 473	91.41 503	95.04 502	94.89 168	88.98 530	90.76 520	89.26 446	89.11 531	92.97 490	81.45 457	88.25 550	78.47 536	97.06 468	91.08 536

cascas		91.89 445	91.35 444	93.51 447	94.27 520	85.60 464	88.86 531	98.61 248	79.32 535	92.16 498	91.44 513	89.22 364	98.12 484	90.80 400	97.47 458	96.82 470

PAPM		87.64 499	85.84 507	93.04 468	96.54 428	84.99 478	88.42 532	95.57 437	79.52 533	83.82 545	93.05 489	80.57 464	98.41 468	62.29 550	92.79 532	95.71 499

SIFT-NCMNet		93.23 409	93.19 393	93.34 451	95.31 494	95.59 119	88.29 533	95.60 436	91.60 390	98.43 136	96.34 396	89.80 349	93.57 541	83.82 512	99.57 155	90.85 539

PDCNetPlus		89.44 481	88.28 486	92.93 475	91.75 543	85.02 477	87.69 534	99.67 9	82.69 516	95.89 381	97.02 344	51.15 554	95.27 520	88.79 442	99.86 35	98.50 343

PVSNet	86.72 19	91.10 457	90.97 453	91.49 501	97.56 375	78.04 532	87.17 535	94.60 458	84.65 507	92.34 496	92.20 505	87.37 397	98.47 464	85.17 499	97.69 444	97.96 409

0.4-1-1-0.1		83.64 510	80.50 514	93.08 465	90.32 548	85.42 467	86.48 536	87.71 540	83.60 513	80.38 551	75.45 550	53.19 551	98.91 409	86.46 478	80.88 549	94.93 510

PMMVS2		93.66 390	94.07 367	92.45 489	97.57 373	80.67 521	86.46 537	96.00 423	93.99 297	97.10 282	97.38 312	89.90 347	97.82 493	88.76 443	99.47 210	98.86 286

CHOSEN 280x420		89.98 470	89.19 477	92.37 490	95.60 484	81.13 518	86.22 538	97.09 391	81.44 526	87.44 539	93.15 482	73.99 500	99.47 249	88.69 445	99.07 313	96.52 480

dongtai		63.43 516	63.37 520	63.60 534	83.91 557	53.17 561	85.14 539	43.40 564	77.91 543	80.96 549	79.17 549	36.36 559	77.10 555	37.88 556	45.63 557	60.54 550

kuosan		54.81 518	54.94 522	54.42 535	74.43 558	50.03 562	84.98 540	44.27 563	61.80 551	62.49 557	70.43 553	35.16 560	58.04 557	19.30 558	41.61 558	55.19 551

0.3-1-1-0.015		82.33 513	78.89 516	92.66 483	88.57 550	84.69 484	84.76 541	88.02 539	82.48 519	77.55 553	72.96 551	49.60 555	98.87 417	86.05 482	80.02 551	94.43 513

XFeat-MNN		88.85 488	88.16 488	90.91 508	88.38 551	89.73 354	84.46 542	91.81 505	83.72 512	95.56 397	92.95 491	74.60 499	92.68 545	84.01 507	97.99 420	90.32 545

tmp_tt		57.23 517	62.50 521	41.44 536	34.77 563	49.21 563	83.93 543	60.22 561	15.31 556	71.11 555	79.37 548	70.09 518	44.86 559	64.76 549	82.93 548	30.25 552

0.4-1-1-0.2		82.53 512	79.25 515	92.37 490	88.10 552	83.96 496	83.72 544	88.15 538	82.14 521	78.97 552	72.49 552	53.22 550	98.84 419	85.99 484	80.50 550	94.30 516

PVSNet_0	81.89 21	84.49 507	83.21 512	88.34 523	95.76 477	74.97 547	83.49 545	92.70 492	78.47 540	87.94 537	86.90 544	83.38 446	96.63 513	73.44 545	66.86 554	93.40 521

E-PMN		89.52 479	89.78 469	88.73 521	93.14 534	77.61 535	83.26 546	92.02 502	94.82 255	93.71 458	93.11 483	75.31 495	96.81 508	85.81 486	96.81 477	91.77 529

EMVS		89.06 484	89.22 474	88.61 522	93.00 536	77.34 537	82.91 547	90.92 515	94.64 264	92.63 493	91.81 509	76.30 490	97.02 505	83.83 511	96.90 472	91.48 532

MVE	73.61 22	86.48 506	85.92 506	88.18 525	96.23 444	85.28 472	81.78 548	75.79 555	86.01 488	82.53 547	91.88 508	92.74 285	87.47 552	71.42 548	94.86 522	91.78 528
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-NN		84.28 508	83.52 511	86.54 529	85.42 556	86.22 454	78.86 549	88.43 536	79.17 536	90.71 509	89.11 528	69.18 520	85.27 554	76.68 539	94.13 527	88.13 546

GLUNet-SfM		74.13 514	71.69 518	81.46 531	63.16 559	74.17 549	66.80 550	76.03 554	58.10 552	88.60 534	86.99 543	57.56 533	86.25 553	50.03 554	97.91 428	83.95 547

test_method		66.88 515	66.13 519	69.11 533	62.68 560	25.73 566	49.76 551	96.04 422	14.32 557	64.27 556	91.69 511	73.45 507	88.05 551	76.06 540	66.94 553	93.54 519

MVS_clip		42.92 519	47.56 523	28.98 538	56.50 561	40.01 564	44.33 552	12.68 565	16.97 555	74.98 554	81.47 547	34.48 561	17.21 560	43.66 555	63.00 555	29.72 553

VLMVS_CLIP		41.19 520	42.85 524	36.20 537	35.69 562	29.96 565	41.27 553	59.71 562	20.51 554	51.77 558	61.89 554	24.86 562	51.47 558	37.87 557	52.12 556	27.15 554

VLMVS		16.27 523	17.60 527	12.26 539	17.44 565	14.02 567	13.33 554	7.39 566	0.97 561	23.14 560	32.55 557	21.01 563	8.58 561	7.93 560	34.66 560	14.18 555

MVS_baseline		16.43 522	20.39 526	4.55 540	19.03 564	1.35 570	10.44 555	3.04 568	0.59 562	41.63 559	49.56 555	10.52 564	0.00 564	9.18 559	39.56 559	12.29 556

mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		24.22 521	32.30 525	0.00 543	0.00 568	0.00 571	0.00 556	98.10 326	0.00 563	0.00 564	95.06 456	97.54 45	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		7.98 526	10.65 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	95.82 166	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		7.91 527	10.55 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	94.94 458	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet1														91.55 380	99.31 272	98.56 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.05 391
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					98.88 152	95.35 138		98.76 218		98.18 180		95.58 181	99.73 102	96.66 122	99.51 190

WAC-MVS						79.32 525								85.41 492

MSC_two_6792asdad				98.22 84	97.75 348	95.34 144		98.16 319					99.75 86	95.87 175	99.51 190	99.57 60

PC_three_1452									87.24 476	98.37 143	97.44 302	97.00 83	96.78 510	92.01 365	99.25 284	99.21 195

No_MVS				98.22 84	97.75 348	95.34 144		98.16 319					99.75 86	95.87 175	99.51 190	99.57 60

test_one_0601					99.05 120	95.50 128		98.87 172	97.21 107	98.03 200	98.30 179	96.93 90

eth-test2					0.00 568

eth-test					0.00 568

ZD-MVS					98.43 246	95.94 103		98.56 258	90.72 417	96.66 323	97.07 340	95.02 209	99.74 96	91.08 388	98.93 332

IU-MVS					99.22 79	95.40 133		98.14 322	85.77 493	98.36 146				95.23 228	99.51 190	99.49 97

test_241102_TWO								98.83 193	96.11 170	98.62 110	98.24 192	96.92 93	99.72 112	95.44 209	99.49 202	99.49 97

test_241102_ONE					99.22 79	95.35 138		98.83 193	96.04 179	99.08 55	98.13 209	97.87 28	99.33 320

test_0728_THIRD									96.62 131	98.40 140	98.28 185	97.10 71	99.71 128	95.70 182	99.62 124	99.58 52

GSMVS																98.06 399

test_part2					99.03 123	96.07 95				98.08 193

sam_mvs1												77.80 479				98.06 399

sam_mvs												77.38 483

MTGPA								98.73 223

test_post											10.87 560	76.83 487	99.07 389

patchmatchnet-post											96.84 360	77.36 484	99.42 275

gm-plane-assit					91.79 542	71.40 555			81.67 523		90.11 525		98.99 401	84.86 502

test9_res														91.29 383	98.89 339	99.00 249

agg_prior2														90.34 419	98.90 335	99.10 231

agg_prior					97.80 336	94.96 165		98.36 290		93.49 468			99.53 225

TestCases				98.06 101	99.08 110	96.16 89		99.16 70	94.35 281	97.78 231	98.07 220	95.84 163	99.12 379	91.41 381	99.42 232	98.91 275

test_prior				97.46 162	97.79 341	94.26 200		98.42 280					99.34 318			98.79 294

新几何1				97.25 182	98.29 260	94.70 174		97.73 355	77.98 541	94.83 422	96.67 373	92.08 309	99.45 264	88.17 455	98.65 379	97.61 437

旧先验1					97.80 336	93.87 212		97.75 354			97.04 343	93.57 259			98.68 374	98.72 311

原ACMM1				96.58 243	98.16 284	92.12 278		98.15 321	85.90 491	93.49 468	96.43 387	92.47 300	99.38 300	87.66 461	98.62 381	98.23 380

testdata2													99.46 256	87.84 456

segment_acmp												95.34 192

testdata				95.70 327	98.16 284	90.58 324		97.72 356	80.38 530	95.62 392	97.02 344	92.06 310	98.98 403	89.06 440	98.52 388	97.54 441

test12				97.46 162	97.61 370	94.07 204		97.78 353		93.57 466		93.31 267	99.42 275		98.78 355	98.89 279

plane_prior7					98.70 191	94.67 175

plane_prior6					98.38 252	94.37 192						91.91 315

plane_prior5								98.75 219					99.46 256	92.59 355	99.20 289	99.28 175

plane_prior4											96.77 366

plane_prior3						94.51 185			95.29 230	96.16 362

plane_prior1					98.49 234

n2								0.00 570

nn								0.00 570

door-mid								98.17 315

lessismore_v0				97.05 199	99.36 54	92.12 278		84.07 548		98.77 95	98.98 72	85.36 424	99.74 96	97.34 94	99.37 246	99.30 167

LGP-MVS_train				98.74 37	99.15 97	97.02 47		99.02 124	95.15 235	98.34 150	98.23 194	97.91 25	99.70 137	94.41 287	99.73 86	99.50 89

test11								98.08 329

door								97.81 352

HQP5-MVS						92.47 263

BP-MVS														90.51 414

HQP4-MVS										92.87 484			99.23 357			99.06 239

HQP3-MVS								98.43 277							98.74 365

HQP2-MVS												90.33 338

NP-MVS					98.14 288	93.72 218					95.08 454

ACMMP++_ref															99.52 184

ACMMP++															99.55 167

Test By Simon												94.51 229

ITE_SJBPF				97.85 118	98.64 198	96.66 62		98.51 263	95.63 208	97.22 269	97.30 320	95.52 183	98.55 455	90.97 392	98.90 335	98.34 364

DeepMVS_CX				77.17 532	90.94 545	85.28 472		74.08 558	52.51 553	80.87 550	88.03 535	75.25 496	70.63 556	59.23 552	84.94 546	75.62 548

High-resolution multi-view benchmark