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 48	99.69 2	99.57 22	99.02 21	99.62 16	99.36 27	98.53 11	99.52 227	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	99.11 105	97.89 16	99.47 3	99.32 41	99.08 16	97.87 224	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	98.97 134	89.65 357	99.43 4	99.81 2	99.30 9	98.36 146	99.86 2	93.15 270	99.88 22	98.50 45	99.84 51	99.99 1

TDRefinement		98.90 8	98.86 11	99.02 9	99.54 28	98.06 8	99.34 5	99.44 34	98.85 27	99.00 63	99.20 41	97.42 52	99.59 202	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 78	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 77	99.17 7	99.05 110	98.05 61	99.61 17	99.52 13	93.72 255	99.88 22	98.72 39	99.88 28	99.65 41

DVP-MVS++		97.96 68	97.90 90	98.12 96	97.75 346	95.40 132	99.03 8	98.89 162	96.62 131	98.62 110	98.30 179	96.97 86	99.75 85	95.70 182	99.25 283	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	95.92 103	98.97 10	99.53 28	99.67 3	99.79 2	99.71 3	98.33 14	99.78 58	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 93	98.91 11	99.55 26	99.67 3	99.78 3	99.69 4	98.63 10	99.77 69	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 86	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 74	98.87 12	99.30 43	99.01 22	99.63 15	99.66 6	99.27 2	99.68 151	97.75 74	99.89 26	99.62 45

Anonymous20231211		98.55 24	98.76 16	97.94 113	98.79 170	94.37 191	98.84 14	99.15 76	99.37 6	99.67 11	99.43 21	95.61 178	99.72 111	98.12 52	99.86 35	99.73 28

mmtdpeth		98.33 36	98.53 31	97.71 128	99.07 111	93.44 230	98.80 15	99.78 4	99.10 15	96.61 326	99.63 10	95.42 188	99.73 101	98.53 44	99.86 35	99.95 2

MIMVSNet1		98.51 28	98.45 36	98.67 43	99.72 8	96.71 57	98.76 16	98.89 162	98.49 40	99.38 32	99.14 53	95.44 187	99.84 33	96.47 134	99.80 64	99.47 107

EPP-MVSNet		96.84 198	96.58 220	97.65 136	99.18 91	93.78 216	98.68 17	96.34 416	97.91 64	97.30 262	98.06 225	88.46 373	99.85 30	93.85 314	99.40 237	99.32 161

v7n		98.73 14	98.99 8	97.95 112	99.64 14	94.20 200	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	96.36 242	95.49 345	97.68 356	87.81 421	98.67 18	99.02 123	96.50 142	94.48 431	96.15 406	86.90 403	99.92 5	98.73 37	99.13 301	98.74 308

test_djsdf		98.73 14	98.74 19	98.69 42	99.63 15	96.30 82	98.67 18	99.02 123	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 76	98.66 21	95.66 430	98.31 47	97.09 286	95.45 444	97.17 69	98.50 459	98.67 40	97.45 457	96.48 481

anonymousdsp		98.72 17	98.63 23	98.99 13	99.62 16	97.29 41	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 35	98.57 23	99.05 110	95.43 224	97.41 258	97.50 296	97.98 23	99.79 53	95.58 196	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	96.68 211	97.70 130	99.25 71	94.00 207	98.57 23	96.74 408	98.36 45	98.14 185	97.98 237	88.23 380	99.71 127	93.10 345	99.72 91	99.38 144

WR-MVS_H		98.65 18	98.62 25	98.75 34	99.51 32	96.61 64	98.55 25	99.17 68	99.05 19	99.17 47	98.79 92	95.47 185	99.89 20	97.95 63	99.91 19	99.75 24

FE-MVS		92.95 415	92.22 421	95.11 365	97.21 403	88.33 401	98.54 26	93.66 473	89.91 435	96.21 357	98.14 206	70.33 515	99.50 233	87.79 455	98.24 407	97.51 441

test2506		89.86 472	89.16 477	91.97 496	98.95 135	76.83 538	98.54 26	61.07 558	96.20 160	97.07 287	99.16 50	55.19 545	99.69 144	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 69	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	98.45 240	96.69 59	98.52 29	99.69 8	98.07 59	96.07 365	97.19 326	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 83	98.51 30	99.10 90	98.76 29	96.79 309	99.34 30	96.61 117	98.82 419	96.38 141	99.50 198	96.98 459
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	95.47 130	98.49 31	99.13 81	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	97.74 349	93.65 223	98.49 31	98.88 169	96.86 122	97.11 280	98.55 134	95.82 165	99.73 101	95.94 169	99.42 231	99.13 215

DTE-MVSNet		98.79 11	98.86 11	98.59 49	99.55 24	96.12 91	98.48 33	99.10 90	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 69	98.45 34	99.12 82	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	95.67 114	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	96.24 440	97.58 27	98.45 34	98.85 181	98.58 36	97.51 247	97.94 241	95.74 172	99.63 184	95.19 230	98.97 320	98.51 340

balanced_ft_v1		96.29 242	96.60 218	95.38 354	96.77 420	88.73 389	98.44 37	98.44 275	94.97 247	95.91 373	98.77 96	91.03 323	99.75 85	96.16 156	98.91 333	97.65 432

SPE-MVS-test		97.91 84	97.84 98	98.14 94	98.52 223	96.03 100	98.38 38	99.67 9	98.11 57	95.50 400	96.92 355	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	93.10 242	98.35 39	99.21 58	98.43 42	98.89 76	98.83 91	94.30 237	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 28	97.48 34	98.35 39	99.03 119	95.88 193	97.88 221	98.22 197	98.15 20	99.74 95	96.50 133	99.62 124	99.42 128

ab-mvs		96.59 220	96.59 219	96.60 240	98.64 197	92.21 272	98.35 39	97.67 357	94.45 276	96.99 294	98.79 92	94.96 212	99.49 239	90.39 415	99.07 312	98.08 392

EGC-MVSNET		83.08 510	77.93 515	98.53 54	99.57 20	97.55 29	98.33 42	98.57 256	4.71 556	10.38 559	98.90 86	95.60 179	99.50 233	95.69 184	99.61 135	98.55 333

test1111		94.53 354	94.81 328	93.72 440	99.06 113	81.94 508	98.31 43	83.87 547	96.37 149	98.49 127	99.17 49	81.49 455	99.73 101	96.64 123	99.86 35	99.49 97

ECVR-MVS		94.37 361	94.48 347	94.05 429	98.95 135	83.10 498	98.31 43	82.48 549	96.20 160	98.23 172	99.16 50	81.18 459	99.66 169	95.95 168	99.83 56	99.38 144

EC-MVSNet		97.90 86	97.94 89	97.79 121	98.66 196	95.14 158	98.31 43	99.66 12	97.57 79	95.95 371	97.01 347	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	94.58 180	98.28 46	99.00 135	97.57 79	99.27 40	99.22 40	98.32 15	99.50 233	97.09 104	99.75 83	99.50 89

SixPastTwentyTwo		97.49 141	97.57 138	97.26 181	99.56 22	92.33 265	98.28 46	96.97 398	98.30 49	99.45 25	99.35 29	88.43 374	99.89 20	98.01 60	99.76 73	99.54 74

FA-MVS(test-final)		94.91 329	94.89 319	94.99 375	97.51 379	88.11 412	98.27 48	95.20 446	92.40 364	96.68 318	98.60 127	83.44 442	99.28 342	93.34 335	98.53 385	97.59 438

CP-MVSNet		98.42 33	98.46 33	98.30 75	99.46 40	95.22 152	98.27 48	98.84 185	99.05 19	99.01 61	98.65 120	95.37 190	99.90 17	97.57 82	99.91 19	99.77 15

GG-mvs-BLEND				90.60 509	91.00 542	84.21 491	98.23 50	72.63 557		82.76 544	84.11 544	56.14 538	96.79 507	72.20 544	92.09 534	90.78 539

GBi-Net		96.99 182	96.80 204	97.56 142	97.96 303	93.67 219	98.23 50	98.66 240	95.59 211	97.99 204	99.19 42	89.51 355	99.73 101	94.60 280	99.44 218	99.30 167

test1		96.99 182	96.80 204	97.56 142	97.96 303	93.67 219	98.23 50	98.66 240	95.59 211	97.99 204	99.19 42	89.51 355	99.73 101	94.60 280	99.44 218	99.30 167

FMVSNet1		97.95 72	98.08 68	97.56 142	99.14 103	93.67 219	98.23 50	98.66 240	97.41 93	99.00 63	99.19 42	95.47 185	99.73 101	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	93.54 225	98.23 50	99.05 110	97.40 94	99.37 33	99.08 61	98.79 6	99.47 248	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	93.39 234	98.20 55	98.87 171	98.23 53	99.48 22	99.27 35	98.47 13	99.55 218	96.52 132	99.53 177	99.60 47

gg-mvs-nofinetune		88.28 494	86.96 499	92.23 493	92.84 536	84.44 486	98.19 56	74.60 554	99.08 16	87.01 539	99.47 17	56.93 535	98.23 478	78.91 530	95.61 513	94.01 517

QAPM		95.88 268	95.57 289	96.80 225	97.90 311	91.84 290	98.18 57	98.73 222	88.41 458	96.42 340	98.13 208	94.73 214	99.75 85	88.72 442	98.94 326	98.81 291

NR-MVSNet		97.96 68	97.86 97	98.26 79	98.73 181	95.54 122	98.14 58	98.73 222	97.79 66	99.42 29	97.83 255	94.40 232	99.78 58	95.91 172	99.76 73	99.46 109

MIMVSNet		93.42 396	92.86 402	95.10 367	98.17 280	88.19 404	98.13 59	93.69 470	92.07 370	95.04 415	98.21 198	80.95 462	99.03 396	81.42 521	98.06 415	98.07 394

PS-MVSNAJss		98.53 27	98.63 23	98.21 87	99.68 12	94.82 169	98.10 60	99.21 58	96.91 120	99.75 5	99.45 19	95.82 165	99.92 5	98.80 33	99.96 4	99.89 4

ACMMP		98.05 61	97.75 114	98.93 21	99.23 75	97.60 25	98.09 61	98.96 147	95.75 203	97.91 218	98.06 225	96.89 97	99.76 77	95.32 222	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 74	98.08 62	99.09 95	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	98.72 184	96.04 96	98.07 63	99.10 90	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 60	95.21 154	98.04 64	99.46 32	97.32 100	97.82 228	99.11 55	96.75 108	99.86 27	97.84 68	99.36 250	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	98.11 290	95.60 117	98.04 64	98.70 231	98.13 56	96.93 300	98.45 148	95.30 195	99.62 189	95.64 189	98.96 323	99.24 189

MVSMamba_PlusPlus		97.43 149	97.98 80	95.78 317	98.88 151	89.70 354	98.03 66	98.85 181	99.18 13	96.84 308	99.12 54	93.04 276	99.91 13	98.38 48	99.55 167	97.73 427

FIs		97.93 79	98.07 69	97.48 159	99.38 52	92.95 246	98.03 66	99.11 85	98.04 62	98.62 110	98.66 116	93.75 254	99.78 58	97.23 95	99.84 51	99.73 28

sd_testset		97.97 66	98.12 61	97.51 148	99.41 46	93.44 230	97.96 68	98.25 300	98.58 36	98.78 90	99.39 22	98.21 18	99.56 213	92.65 352	99.86 35	99.52 82

COLMAP_ROB	94.48 6	98.25 44	98.11 63	98.64 46	99.21 85	97.35 39	97.96 68	99.16 70	98.34 46	98.78 90	98.52 137	97.32 57	99.45 263	94.08 300	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	97.29 163	95.63 331	97.66 361	89.47 362	97.95 70	98.89 162	95.94 188	97.77 232	98.55 134	92.23 302	99.68 151	97.05 109	99.61 135	97.73 427

usedtu_dtu_shiyan2		97.54 136	97.26 166	98.37 67	99.54 28	96.04 96	97.94 71	98.06 333	97.36 98	98.62 110	98.20 199	95.52 182	99.73 101	90.90 394	99.18 293	99.33 159

VDDNet		96.98 185	96.84 200	97.41 168	99.40 49	93.26 238	97.94 71	95.31 443	99.26 11	98.39 142	99.18 46	87.85 387	99.62 189	95.13 240	99.09 309	99.35 158

CP-MVS		97.92 80	97.56 139	98.99 13	98.99 130	97.82 18	97.93 73	98.96 147	96.11 170	96.89 304	97.45 300	96.85 102	99.78 58	95.19 230	99.63 121	99.38 144

mvsmamba		94.91 329	94.41 352	96.40 272	97.65 363	91.30 303	97.92 74	95.32 442	91.50 393	95.54 397	98.38 161	83.06 446	99.68 151	92.46 358	97.84 430	98.23 379

ANet_high		98.31 39	98.94 9	96.41 269	99.33 60	89.64 358	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 78	95.66 115	97.90 76	99.08 99	98.31 47	99.02 60	98.74 101	97.68 35	99.61 197	97.77 73	99.85 48	99.70 33

ambc				96.56 247	98.23 270	91.68 294	97.88 77	98.13 323		98.42 137	98.56 133	94.22 239	99.04 393	94.05 303	99.35 256	98.95 264

Anonymous20240529		97.96 68	98.04 73	97.71 128	98.69 193	94.28 198	97.86 78	98.31 297	98.79 28	99.23 43	98.86 90	95.76 171	99.61 197	95.49 199	99.36 250	99.23 191

sasdasda		97.23 166	97.21 171	97.30 176	97.65 363	94.39 188	97.84 79	99.05 110	97.42 89	96.68 318	93.85 477	97.63 41	99.33 319	96.29 148	98.47 393	98.18 386

canonicalmvs		97.23 166	97.21 171	97.30 176	97.65 363	94.39 188	97.84 79	99.05 110	97.42 89	96.68 318	93.85 477	97.63 41	99.33 319	96.29 148	98.47 393	98.18 386

tfpnnormal		97.72 111	97.97 81	96.94 210	99.26 68	92.23 271	97.83 81	98.45 271	98.25 52	99.13 51	98.66 116	96.65 114	99.69 144	93.92 311	99.62 124	98.91 275

MGCFI-Net		97.20 168	97.23 169	97.08 197	97.68 356	93.71 218	97.79 82	99.09 95	97.40 94	96.59 327	93.96 474	97.67 36	99.35 314	96.43 139	98.50 390	98.17 388

Anonymous20240521		97.07 178	97.51 147	95.76 318	99.35 58	88.18 407	97.78 83	98.40 283	97.11 108	98.34 150	99.04 64	89.58 350	99.79 53	98.09 55	99.93 11	99.30 167

XVS		97.96 68	97.63 129	98.94 18	99.15 96	97.66 22	97.77 84	98.83 192	97.42 89	96.32 345	97.64 282	96.49 126	99.72 111	95.66 187	99.37 245	99.45 113

X-MVStestdata		92.86 416	90.83 455	98.94 18	99.15 96	97.66 22	97.77 84	98.83 192	97.42 89	96.32 345	36.50 554	96.49 126	99.72 111	95.66 187	99.37 245	99.45 113

VPA-MVSNet		98.27 42	98.46 33	97.70 130	99.06 113	93.80 214	97.76 86	99.00 135	98.40 44	99.07 57	98.98 72	96.89 97	99.75 85	97.19 100	99.79 66	99.55 72

aaatest				98.17 88	99.36 54	95.35 137	97.75 87	99.30 43	94.02 295	98.88 78	97.54 290		99.73 101	95.36 217	99.53 177	99.44 123

MED-MVS		98.14 50	98.09 67	98.27 78	99.36 54	95.35 137	97.75 87	99.30 43	97.28 103	98.88 78	98.41 155	96.99 84	99.73 101	95.36 217	99.51 190	99.74 26

TestfortrainingZip a		98.22 46	98.18 57	98.33 71	99.36 54	95.49 128	97.75 87	98.86 175	97.28 103	98.87 80	98.41 155	96.31 138	99.77 69	97.40 89	99.38 243	99.74 26

TestfortrainingZip				97.39 170	97.24 402	94.58 180	97.75 87	97.64 365	96.08 174	96.48 336	96.31 395	92.56 291	99.27 345		96.62 484	98.31 367

dcpmvs_2		97.12 175	97.99 79	94.51 407	99.11 105	84.00 492	97.75 87	99.65 13	97.38 96	99.14 50	98.42 152	95.16 202	99.96 2	95.52 198	99.78 70	99.58 52

UGNet		96.81 203	96.56 223	97.58 141	96.64 423	93.84 213	97.75 87	97.12 386	96.47 146	93.62 460	98.88 88	93.22 268	99.53 224	95.61 193	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 78	97.87 17	97.74 93	98.78 210	96.04 179	97.10 281	97.73 273	96.53 123	99.78 58	95.16 235	99.50 198	99.46 109

OpenMVS	94.22 8	95.48 296	95.20 298	96.32 278	97.16 405	91.96 286	97.74 93	98.84 185	87.26 472	94.36 433	98.01 233	93.95 247	99.67 161	90.70 406	98.75 363	97.35 448

RRT-MVS		95.78 273	96.25 248	94.35 417	96.68 422	84.47 485	97.72 95	99.11 85	97.23 105	97.27 264	98.72 103	86.39 412	99.79 53	95.49 199	97.67 444	98.80 292

testf1		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 36	97.69 75	98.92 73	98.77 96	97.80 30	99.25 350	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 96	99.42 36	97.69 75	98.92 73	98.77 96	97.80 30	99.25 350	96.27 150	99.69 100	98.76 306

MonoMVSNet		93.30 404	93.96 371	91.33 504	94.14 522	81.33 514	97.68 98	96.69 410	95.38 226	96.32 345	98.42 152	84.12 436	96.76 509	90.78 399	92.12 533	95.89 493

MSP-MVS		97.45 145	96.92 194	99.03 8	99.26 68	97.70 21	97.66 99	98.89 162	95.65 207	98.51 124	96.46 384	92.15 304	99.81 43	95.14 238	98.58 383	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	94.88 321	96.62 236	98.03 293	91.47 298	97.65 100	90.72 519	99.11 14	97.89 220	98.31 173	79.20 471	99.48 242	93.91 312	99.12 304	98.93 271

K. test v3		96.44 233	96.28 247	96.95 209	99.41 46	91.53 295	97.65 100	90.31 525	98.89 26	98.93 72	99.36 27	84.57 432	99.92 5	97.81 69	99.56 160	99.39 142

TSAR-MVS + MP.		97.42 151	97.23 169	98.00 108	99.38 52	95.00 162	97.63 102	98.20 307	93.00 342	98.16 181	98.06 225	95.89 160	99.72 111	95.67 186	99.10 308	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	98.63 206	92.81 250	97.60 103	99.61 19	90.87 413	98.76 96	99.66 6	94.03 243	97.90 489	99.24 11	99.68 105	99.81 10

region2R		97.92 80	97.59 136	98.92 24	99.22 78	97.55 29	97.60 103	98.84 185	96.00 182	97.22 268	97.62 284	96.87 101	99.76 77	95.48 203	99.43 228	99.46 109

HFP-MVS		97.94 76	97.64 127	98.83 28	99.15 96	97.50 33	97.59 105	98.84 185	96.05 177	97.49 249	97.54 290	97.07 75	99.70 136	95.61 193	99.46 212	99.30 167

ACMMPR		97.95 72	97.62 131	98.94 18	99.20 87	97.56 28	97.59 105	98.83 192	96.05 177	97.46 255	97.63 283	96.77 107	99.76 77	95.61 193	99.46 212	99.49 97

RPSCF		97.87 91	97.51 147	98.95 17	99.15 96	98.43 6	97.56 107	99.06 104	96.19 164	98.48 129	98.70 112	94.72 215	99.24 354	94.37 289	99.33 266	99.17 203

KD-MVS_self_test		97.86 93	98.07 69	97.25 182	99.22 78	92.81 250	97.55 108	98.94 152	97.10 109	98.85 82	98.88 88	95.03 207	99.67 161	97.39 91	99.65 114	99.26 181

SR-MVS-dyc-post		98.14 50	97.84 98	99.02 9	98.81 164	98.05 9	97.55 108	98.86 175	97.77 67	98.20 174	98.07 219	96.60 119	99.76 77	95.49 199	99.20 288	99.26 181

RE-MVS-def			97.88 95		98.81 164	98.05 9	97.55 108	98.86 175	97.77 67	98.20 174	98.07 219	96.94 88		95.49 199	99.20 288	99.26 181

APD-MVS_3200maxsize		98.13 54	97.90 90	98.79 32	98.79 170	97.31 40	97.55 108	98.92 156	97.72 72	98.25 169	98.13 208	97.10 71	99.75 85	95.44 208	99.24 286	99.32 161

ACMH+	93.58 10	98.23 45	98.31 49	97.98 110	99.39 50	95.22 152	97.55 108	99.20 60	98.21 54	99.25 42	98.51 140	98.21 18	99.40 286	94.79 269	99.72 91	99.32 161

Vis-MVSNet (Re-imp)		95.11 320	94.85 324	95.87 314	99.12 104	89.17 368	97.54 113	94.92 451	96.50 142	96.58 328	97.27 320	83.64 441	99.48 242	88.42 448	99.67 109	98.97 260

MP-MVS		97.64 121	97.18 175	99.00 12	99.32 62	97.77 20	97.49 114	98.73 222	96.27 153	95.59 394	97.75 268	96.30 141	99.78 58	93.70 325	99.48 206	99.45 113
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SD_0403		93.73 384	93.43 385	94.64 396	97.85 314	86.35 451	97.47 115	97.94 337	93.50 314	93.71 456	96.73 368	93.77 253	98.84 417	73.48 542	96.39 490	98.72 311

ZNCC-MVS		97.92 80	97.62 131	98.83 28	99.32 62	97.24 43	97.45 116	98.84 185	95.76 201	96.93 300	97.43 302	97.26 64	99.79 53	96.06 158	99.53 177	99.45 113

tttt0517		93.31 402	92.56 414	95.57 335	98.71 188	87.86 417	97.44 117	87.17 541	95.79 200	97.47 254	96.84 359	64.12 523	99.81 43	96.20 153	99.32 268	99.02 248

v10		97.55 135	97.97 81	96.31 279	98.60 210	89.64 358	97.44 117	99.02 123	96.60 133	98.72 101	99.16 50	93.48 261	99.72 111	98.76 35	99.92 15	99.58 52

v8		97.60 126	98.06 72	96.23 284	98.71 188	89.44 363	97.43 119	98.82 200	97.29 102	98.74 98	99.10 57	93.86 249	99.68 151	98.61 41	99.94 8	99.56 68

PMVS	89.60 17	96.71 214	96.97 188	95.95 307	99.51 32	97.81 19	97.42 120	97.49 371	97.93 63	95.95 371	98.58 129	96.88 99	96.91 505	89.59 429	99.36 250	93.12 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
usedtu_blend_shiyan5		93.74 382	93.08 394	95.71 326	94.99 501	89.17 368	97.38 121	98.93 154	96.40 147	94.75 421	87.24 537	80.36 465	99.40 286	91.84 370	95.85 502	98.55 333

SR-MVS		98.00 64	97.66 123	99.01 11	98.77 177	97.93 14	97.38 121	98.83 192	97.32 100	98.06 195	97.85 252	96.65 114	99.77 69	95.00 250	99.11 305	99.32 161

Elysia		98.19 47	98.37 40	97.66 134	99.28 64	93.52 226	97.35 123	98.90 158	98.63 32	99.45 25	98.32 171	94.31 235	99.91 13	99.19 14	99.88 28	99.54 74

StellarMVS		98.19 47	98.37 40	97.66 134	99.28 64	93.52 226	97.35 123	98.90 158	98.63 32	99.45 25	98.32 171	94.31 235	99.91 13	99.19 14	99.88 28	99.54 74

FMVSNet5		93.39 397	92.35 418	96.50 253	95.83 468	90.81 320	97.31 125	98.27 298	92.74 353	96.27 352	98.28 185	62.23 525	99.67 161	90.86 395	99.36 250	99.03 245

HY-MVS	91.43 15	92.58 424	91.81 431	94.90 382	96.49 429	88.87 382	97.31 125	94.62 456	85.92 488	90.50 511	96.84 359	85.05 426	99.40 286	83.77 511	95.78 510	96.43 484

CSCG		97.40 152	97.30 162	97.69 132	98.95 135	94.83 168	97.28 127	98.99 140	96.35 152	98.13 186	95.95 422	95.99 155	99.66 169	94.36 291	99.73 86	98.59 328

MTAPA		98.14 50	97.84 98	99.06 6	99.44 42	97.90 15	97.25 128	98.73 222	97.69 75	97.90 219	97.96 238	95.81 169	99.82 38	96.13 157	99.61 135	99.45 113

CPTT-MVS		96.69 215	96.08 257	98.49 57	98.89 150	96.64 62	97.25 128	98.77 212	92.89 349	96.01 369	97.13 334	92.23 302	99.67 161	92.24 361	99.34 261	99.17 203

EU-MVSNet		94.25 363	94.47 348	93.60 444	98.14 286	82.60 503	97.24 130	92.72 489	85.08 498	98.48 129	98.94 78	82.59 450	98.76 427	97.47 87	99.53 177	99.44 123

XXY-MVS		97.54 136	97.70 116	97.07 198	99.46 40	92.21 272	97.22 131	99.00 135	94.93 250	98.58 116	98.92 82	97.31 58	99.41 284	94.44 284	99.43 228	99.59 51

APD_test1		97.95 72	97.68 120	98.75 34	99.60 17	98.60 5	97.21 132	99.08 99	96.57 140	98.07 194	98.38 161	96.22 146	99.14 373	94.71 277	99.31 271	98.52 339

GST-MVS		97.82 98	97.49 151	98.81 30	99.23 75	97.25 42	97.16 133	98.79 206	95.96 185	97.53 245	97.40 304	96.93 90	99.77 69	95.04 244	99.35 256	99.42 128

SteuartSystems-ACMMP		98.02 63	97.76 112	98.79 32	99.43 43	97.21 45	97.15 134	98.90 158	96.58 137	98.08 192	97.87 251	97.02 82	99.76 77	95.25 225	99.59 145	99.40 135
Skip Steuart: Steuart Systems R&D Blog.
FMVSNet2		96.72 212	96.67 212	96.87 218	97.96 303	91.88 288	97.15 134	98.06 333	95.59 211	98.50 126	98.62 122	89.51 355	99.65 173	94.99 256	99.60 142	99.07 236

AllTest		97.20 168	96.92 194	98.06 101	99.08 109	96.16 88	97.14 136	99.16 70	94.35 280	97.78 230	98.07 219	95.84 162	99.12 378	91.41 380	99.42 231	98.91 275

DP-MVS		97.87 91	97.89 93	97.81 120	98.62 208	94.82 169	97.13 137	98.79 206	98.98 23	98.74 98	98.49 141	95.80 170	99.49 239	95.04 244	99.44 218	99.11 226

GeoE		97.75 106	97.70 116	97.89 115	98.88 151	94.53 183	97.10 138	98.98 143	95.75 203	97.62 239	97.59 286	97.61 43	99.77 69	96.34 144	99.44 218	99.36 154

PGM-MVS		97.88 89	97.52 145	98.96 16	99.20 87	97.62 24	97.09 139	99.06 104	95.45 219	97.55 244	97.94 241	97.11 70	99.78 58	94.77 272	99.46 212	99.48 103

LPG-MVS_test		97.94 76	97.67 121	98.74 37	99.15 96	97.02 46	97.09 139	99.02 123	95.15 235	98.34 150	98.23 194	97.91 25	99.70 136	94.41 286	99.73 86	99.50 89

SF-MVS		97.60 126	97.39 154	98.22 84	98.93 142	95.69 112	97.05 141	99.10 90	95.32 228	97.83 227	97.88 248	96.44 131	99.72 111	94.59 283	99.39 241	99.25 188

FE-MVSNET2		97.69 113	97.97 81	96.85 219	99.19 89	91.46 299	97.04 142	99.11 85	95.85 196	98.73 100	99.02 67	96.66 111	99.68 151	96.31 146	99.86 35	99.40 135

reproduce_model		98.54 25	98.33 47	99.15 3	99.06 113	98.04 11	97.04 142	99.09 95	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	97.25 167	97.74 126	98.69 193	94.50 186	97.04 142	95.61 434	98.59 35	98.51 124	98.72 103	92.54 295	99.58 205	96.02 163	99.49 201	99.12 221

wuyk23d		93.25 406	95.20 298	87.40 527	96.07 456	95.38 134	97.04 142	94.97 449	95.33 227	99.70 10	98.11 213	98.14 21	91.94 544	77.76 535	99.68 105	74.89 548

LCM-MVSNet-Re		97.33 159	97.33 160	97.32 175	98.13 289	93.79 215	96.99 146	99.65 13	96.74 128	99.47 24	98.93 79	96.91 94	99.84 33	90.11 419	99.06 315	98.32 365

MAR-MVS		94.21 366	93.03 396	97.76 125	96.94 415	97.44 37	96.97 147	97.15 384	87.89 468	92.00 497	92.73 496	92.14 305	99.12 378	83.92 507	97.51 453	96.73 473
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	95.89 273	95.03 371	98.18 277	89.89 349	96.94 148	99.28 47	88.25 462	98.20 174	98.92 82	86.69 407	97.19 499	97.70 78	98.82 348	98.00 406

KinetiMVS		97.82 98	98.02 75	97.24 184	99.24 72	92.32 267	96.92 149	98.38 286	98.56 39	99.03 58	98.33 168	93.22 268	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	92.21 272	96.92 149	98.60 248	98.58 36	98.78 90	99.39 22	97.80 30	99.62 189	94.98 258	99.86 35	99.52 82

h-mvs33		96.29 242	95.63 287	98.26 79	98.50 231	96.11 92	96.90 151	97.09 390	96.58 137	97.21 270	98.19 200	84.14 434	99.78 58	95.89 173	96.17 497	98.89 279

test0726					99.24 72	95.51 124	96.89 152	98.89 162	95.92 190	98.64 108	98.31 173	97.06 76

NormalMVS		96.87 195	96.39 239	98.30 75	99.48 37	95.57 119	96.87 153	98.90 158	96.94 118	96.85 306	97.88 248	85.36 423	99.76 77	95.63 190	99.59 145	99.57 60

SymmetryMVS		96.43 235	95.85 276	98.17 88	98.58 214	95.57 119	96.87 153	95.29 444	96.94 118	96.85 306	97.88 248	85.36 423	99.76 77	95.63 190	99.27 279	99.19 199

baseline		97.44 147	97.78 110	96.43 264	98.52 223	90.75 321	96.84 155	99.03 119	96.51 141	97.86 225	98.02 231	96.67 110	99.36 310	97.09 104	99.47 209	99.19 199

API-MVS		95.09 323	95.01 310	95.31 356	96.61 424	94.02 206	96.83 156	97.18 383	95.60 210	95.79 384	94.33 470	94.54 227	98.37 471	85.70 485	98.52 386	93.52 519

test_vis3_rt		97.04 179	96.98 187	97.23 185	98.44 241	95.88 104	96.82 157	99.67 9	90.30 426	99.27 40	99.33 32	94.04 242	96.03 515	97.14 102	97.83 431	99.78 14

reproduce-ours		98.48 29	98.27 53	99.12 4	98.99 130	98.02 12	96.81 158	99.02 123	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	98.99 130	98.02 12	96.81 158	99.02 123	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	95.28 296	94.99 375	98.15 284	89.13 374	96.81 158	99.43 35	86.97 479	97.21 270	98.92 82	83.00 447	97.13 500	98.09 55	98.94 326	98.72 311

test_fmvs2		96.38 239	96.45 235	96.16 293	97.85 314	91.30 303	96.81 158	99.45 33	89.24 445	98.49 127	99.38 24	88.68 371	97.62 494	98.83 32	99.32 268	99.57 60

SED-MVS		97.94 76	97.90 90	98.07 99	99.22 78	95.35 137	96.79 162	98.83 192	96.11 170	99.08 55	98.24 192	97.87 28	99.72 111	95.44 208	99.51 190	99.14 213

OPU-MVS				97.64 137	98.01 297	95.27 147	96.79 162				97.35 314	96.97 86	98.51 458	91.21 386	99.25 283	99.14 213

BP-MVS1		95.36 304	94.86 322	96.89 216	98.35 253	91.72 292	96.76 164	95.21 445	96.48 145	96.23 355	97.19 326	75.97 491	99.80 50	97.91 64	99.60 142	99.15 207

PHI-MVS		96.96 188	96.53 230	98.25 82	97.48 382	96.50 67	96.76 164	98.85 181	93.52 313	96.19 359	96.85 358	95.94 157	99.42 274	93.79 318	99.43 228	98.83 289

DVP-MVS		97.78 103	97.65 124	98.16 90	99.24 72	95.51 124	96.74 166	98.23 303	95.92 190	98.40 140	98.28 185	97.06 76	99.71 127	95.48 203	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 75	95.49 128	96.74 166	98.89 162					99.75 85	95.48 203	99.52 184	99.53 79

Anonymous202405211		96.34 241	95.98 265	97.43 165	98.25 267	93.85 212	96.74 166	94.41 460	97.72 72	98.37 143	98.03 229	87.15 399	99.53 224	94.06 301	99.07 312	98.92 274

SMA-MVS		97.48 142	97.11 177	98.60 48	98.83 161	96.67 60	96.74 166	98.73 222	91.61 384	98.48 129	98.36 163	96.53 123	99.68 151	95.17 233	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	99.07 111	95.87 105	96.73 170	99.05 110	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	98.85 158	92.74 255	96.71 171	99.23 52	98.07 59	98.55 119	98.47 146	97.38 54	99.44 266	96.95 113	99.62 124	99.38 144

test_0402		97.84 94	97.97 81	97.47 161	99.19 89	94.07 203	96.71 171	98.73 222	98.66 31	98.56 118	98.41 155	96.84 103	99.69 144	94.82 266	99.81 60	98.64 320

test_fmvsmconf0.01_n		98.57 21	98.74 19	98.06 101	99.39 50	94.63 177	96.70 173	99.82 1	95.44 222	99.64 14	99.52 13	98.96 4	99.74 95	99.38 7	99.86 35	99.81 10

SSC-MVS		95.92 266	97.03 185	92.58 484	99.28 64	78.39 527	96.68 174	95.12 447	98.90 25	99.11 52	98.66 116	91.36 319	99.68 151	95.00 250	99.16 297	99.67 36

ACMM	93.33 11	98.05 61	97.79 106	98.85 27	99.15 96	97.55 29	96.68 174	98.83 192	95.21 231	98.36 146	98.13 208	98.13 22	99.62 189	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		93.14 409	92.64 412	94.62 399	97.34 395	87.20 435	96.67 176	93.02 483	94.71 260	96.51 335	95.83 428	81.64 454	98.60 449	90.00 422	88.06 541	98.07 394

SSM_0404		97.47 143	97.75 114	96.64 235	98.81 164	91.26 305	96.57 177	99.16 70	96.95 116	98.44 135	98.09 215	97.05 78	99.72 111	95.21 228	99.44 218	98.95 264

fmvsm_s_conf0.1_n_a		97.80 101	98.01 77	97.18 186	99.17 92	92.51 260	96.57 177	99.15 76	93.68 308	98.89 76	99.30 33	96.42 133	99.37 306	99.03 25	99.83 56	99.66 38

ALIKED-LG		94.42 357	93.57 380	96.97 207	96.80 419	97.51 32	96.56 179	98.87 171	90.23 430	96.16 361	96.93 352	83.76 440	97.07 501	84.00 506	98.80 351	96.33 485

casdiffseed414692147		97.67 118	97.88 95	97.03 203	98.82 163	92.32 267	96.55 180	99.17 68	96.99 111	98.01 202	98.67 115	97.64 39	99.38 299	95.45 207	99.66 112	99.40 135

MTMP							96.55 180	74.60 554

SD-MVS		97.37 156	97.70 116	96.35 274	98.14 286	95.13 159	96.54 182	98.92 156	95.94 188	99.19 46	98.08 217	97.74 33	95.06 523	95.24 226	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	99.01 125	90.45 332	96.50 183	99.23 52	96.19 164	98.27 161	98.72 103	97.49 46	99.47 248	96.64 123	99.62 124	99.42 128

E6new		97.59 129	97.97 81	96.45 258	99.01 125	90.45 332	96.50 183	99.23 52	96.20 160	98.27 161	98.72 103	97.49 46	99.47 248	96.64 123	99.62 124	99.42 128

E6		97.59 129	97.97 81	96.45 258	99.01 125	90.45 332	96.50 183	99.23 52	96.20 160	98.27 161	98.72 103	97.49 46	99.47 248	96.64 123	99.62 124	99.42 128

E5		97.59 129	97.96 87	96.45 258	99.01 125	90.45 332	96.50 183	99.23 52	96.19 164	98.27 161	98.72 103	97.49 46	99.47 248	96.64 123	99.62 124	99.42 128

HQP_MVS		96.66 217	96.33 244	97.68 133	98.70 190	94.29 195	96.50 183	98.75 218	96.36 150	96.16 361	96.77 365	91.91 314	99.46 255	92.59 354	99.20 288	99.28 175

plane_prior2							96.50 183		96.36 150

RoMa-HiRes		97.28 162	97.05 184	97.98 110	98.78 174	96.22 85	96.48 189	98.47 268	93.69 306	98.97 67	97.73 273	93.48 261	98.47 462	96.31 146	99.51 190	99.26 181

GDP-MVS		95.39 302	94.89 319	96.90 215	98.26 266	91.91 287	96.48 189	99.28 47	95.06 240	96.54 334	97.12 336	74.83 495	99.82 38	97.19 100	99.27 279	98.96 261

hybridcas		97.73 108	98.10 66	96.62 236	98.84 160	91.10 308	96.46 191	99.20 60	97.53 83	98.65 107	98.42 152	97.41 53	99.38 299	96.79 119	99.59 145	99.37 153

Effi-MVS+-dtu		96.81 203	96.09 256	98.99 13	96.90 417	98.69 4	96.42 192	98.09 326	95.86 195	95.15 409	95.54 439	94.26 238	99.81 43	94.06 301	98.51 389	98.47 346

SSM_0407		97.39 153	97.67 121	96.54 250	98.51 225	90.96 313	96.40 193	99.16 70	96.95 116	98.27 161	98.09 215	97.05 78	99.67 161	95.21 228	99.40 237	98.98 256

guyue		96.21 249	96.29 246	95.98 304	98.80 167	89.14 373	96.40 193	94.34 462	95.99 184	98.58 116	98.13 208	87.42 395	99.64 179	97.39 91	99.55 167	99.16 206

MM		96.87 195	96.62 214	97.62 138	97.72 351	93.30 235	96.39 195	92.61 492	97.90 65	96.76 314	98.64 121	90.46 334	99.81 43	99.16 18	99.94 8	99.76 21

thres100view900		91.76 447	91.26 447	93.26 456	98.21 271	84.50 484	96.39 195	90.39 522	96.87 121	96.33 344	93.08 485	73.44 506	99.42 274	78.85 531	97.74 437	95.85 495

XVG-ACMP-BASELINE		97.58 134	97.28 165	98.49 57	99.16 93	96.90 51	96.39 195	98.98 143	95.05 241	98.06 195	98.02 231	95.86 161	99.56 213	94.37 289	99.64 118	99.00 249

Patchmtry		95.03 326	94.59 341	96.33 275	94.83 509	90.82 318	96.38 198	97.20 381	96.59 136	97.49 249	98.57 131	77.67 478	99.38 299	92.95 348	99.62 124	98.80 292

fmvsm_s_conf0.1_n		97.73 108	98.02 75	96.85 219	99.09 108	91.43 302	96.37 199	99.11 85	94.19 286	99.01 61	99.25 36	96.30 141	99.38 299	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 52	96.36 200	98.79 206	95.07 239	97.88 221	98.35 165	97.24 66	99.72 111	96.05 160	99.58 151	99.45 113

VNet		96.84 198	96.83 201	96.88 217	98.06 292	92.02 284	96.35 201	97.57 370	97.70 74	97.88 221	97.80 261	92.40 300	99.54 221	94.73 275	98.96 323	99.08 233

V42		97.04 179	97.16 176	96.68 234	98.59 212	91.05 309	96.33 202	98.36 289	94.60 264	97.99 204	98.30 179	93.32 265	99.62 189	97.40 89	99.53 177	99.38 144

test_fmvsmvis_n_1920		98.08 57	98.47 32	96.93 211	99.03 122	93.29 236	96.32 203	99.65 13	95.59 211	99.71 8	99.01 68	97.66 38	99.60 200	99.44 5	99.83 56	97.90 412

APD-MVS		97.00 181	96.53 230	98.41 64	98.55 219	96.31 80	96.32 203	98.77 212	92.96 347	97.44 257	97.58 288	95.84 162	99.74 95	91.96 365	99.35 256	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	98.75 179	90.50 330	96.28 205	99.56 24	97.05 110	99.15 49	99.11 55	96.31 138	99.69 144	98.97 29	99.84 51	99.62 45

AstraMVS		96.41 237	96.48 234	96.20 287	98.91 147	89.69 355	96.28 205	93.29 479	96.11 170	98.70 103	98.36 163	89.41 359	99.66 169	97.60 81	99.63 121	99.26 181

VPNet		97.26 164	97.49 151	96.59 242	99.47 39	90.58 323	96.27 207	98.53 259	97.77 67	98.46 132	98.41 155	94.59 223	99.68 151	94.61 279	99.29 276	99.52 82

thres600view7		92.03 442	91.43 440	93.82 435	98.19 274	84.61 483	96.27 207	90.39 522	96.81 124	96.37 343	93.11 481	73.44 506	99.49 239	80.32 525	97.95 422	97.36 446

EPNet		93.72 385	92.62 413	97.03 203	87.61 553	92.25 270	96.27 207	91.28 510	96.74 128	87.65 536	97.39 309	85.00 427	99.64 179	92.14 363	99.48 206	99.20 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DSMNet-mixed		92.19 436	91.83 430	93.25 457	96.18 447	83.68 496	96.27 207	93.68 472	76.97 543	92.54 493	99.18 46	89.20 364	98.55 453	83.88 508	98.60 382	97.51 441

IMVS_0407		96.35 240	96.88 199	94.74 393	97.83 324	86.11 455	96.25 211	98.82 200	94.48 271	97.57 242	97.14 330	96.08 152	99.33 319	95.00 250	98.78 354	98.78 295

fmvsm_s_conf0.5_n_a		97.65 120	97.83 101	97.13 191	98.80 167	92.51 260	96.25 211	99.06 104	93.67 309	98.64 108	99.00 69	96.23 145	99.36 310	98.99 27	99.80 64	99.53 79

ACMP	92.54 13	97.47 143	97.10 178	98.55 52	99.04 121	96.70 58	96.24 213	98.89 162	93.71 304	97.97 211	97.75 268	97.44 50	99.63 184	93.22 341	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	98.78 174	95.72 110	96.23 214	99.02 123	93.92 300	98.62 110	98.99 71	97.69 34	99.62 189	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	97.10 178	98.14 94	98.91 147	96.77 54	96.20 215	98.63 246	93.82 301	98.54 120	98.33 168	93.98 245	99.05 390	95.99 166	99.45 215	98.61 327

test_fmvsmconf0.1_n		98.41 34	98.54 30	98.03 106	99.16 93	94.61 178	96.18 216	99.73 5	95.05 241	99.60 18	99.34 30	98.68 8	99.72 111	99.21 12	99.85 48	99.76 21

MVS_Test		96.27 244	96.79 206	94.73 394	96.94 415	86.63 446	96.18 216	98.33 293	94.94 248	96.07 365	98.28 185	95.25 197	99.26 347	97.21 97	97.90 427	98.30 370

CR-MVSNet		93.29 405	92.79 405	94.78 390	95.44 486	88.15 408	96.18 216	97.20 381	84.94 503	94.10 442	98.57 131	77.67 478	99.39 295	95.17 233	95.81 506	96.81 470

RPMNet		94.68 343	94.60 339	94.90 382	95.44 486	88.15 408	96.18 216	98.86 175	97.43 88	94.10 442	98.49 141	79.40 470	99.76 77	95.69 184	95.81 506	96.81 470

LuminaMVS		96.76 207	96.58 220	97.30 176	98.94 138	92.96 245	96.17 220	96.15 418	95.54 215	98.96 70	98.18 203	87.73 389	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	98.88 151	93.95 209	96.17 220	99.57 22	95.66 206	99.52 21	98.71 110	97.04 80	99.64 179	99.21 12	99.87 33	98.69 316

fmvsm_s_conf0.5_n		97.62 124	97.89 93	96.80 225	98.79 170	91.44 301	96.14 222	99.06 104	94.19 286	98.82 87	98.98 72	96.22 146	99.38 299	98.98 28	99.86 35	99.58 52

WB-MVS		95.50 293	96.62 214	92.11 495	99.21 85	77.26 537	96.12 223	95.40 441	98.62 34	98.84 84	98.26 190	91.08 322	99.50 233	93.37 333	98.70 370	99.58 52

EIA-MVS		96.04 258	95.77 281	96.85 219	97.80 334	92.98 244	96.12 223	99.16 70	94.65 262	93.77 453	91.69 509	95.68 174	99.67 161	94.18 296	98.85 342	97.91 411

Effi-MVS+		96.19 251	96.01 261	96.71 231	97.43 388	92.19 276	96.12 223	99.10 90	95.45 219	93.33 472	94.71 462	97.23 67	99.56 213	93.21 342	97.54 451	98.37 357

FE-MVSNET		96.59 220	96.65 213	96.41 269	98.94 138	90.51 329	96.07 226	99.05 110	92.94 348	98.03 199	98.00 235	93.08 274	99.42 274	94.04 304	99.74 85	99.30 167

alignmvs		96.01 261	95.52 291	97.50 154	97.77 343	94.71 171	96.07 226	96.84 402	97.48 86	96.78 313	94.28 471	85.50 422	99.40 286	96.22 152	98.73 367	98.40 352

fmvsm_l_conf0.5_n_3		98.29 41	98.46 33	97.79 121	98.90 149	94.05 205	96.06 228	99.63 17	96.07 175	99.37 33	98.93 79	98.29 16	99.68 151	99.11 22	99.79 66	99.65 41

VortexMVS		96.04 258	96.56 223	94.49 409	97.60 370	84.36 487	96.05 229	98.67 237	94.74 255	98.95 71	98.78 95	87.13 400	99.50 233	97.37 93	99.76 73	99.60 47

PatchT		93.75 381	93.57 380	94.29 421	95.05 499	87.32 433	96.05 229	92.98 484	97.54 82	94.25 434	98.72 103	75.79 492	99.24 354	95.92 171	95.81 506	96.32 486

aaEdge-Enhanced		97.53 139	97.32 161	98.16 90	98.70 190	95.35 137	96.04 231	98.60 248	96.16 169	97.99 204	97.54 290	95.94 157	99.70 136	95.36 217	99.53 177	99.44 123

Patchmatch-test		93.60 392	93.25 389	94.63 398	96.14 452	87.47 427	96.04 231	94.50 458	93.57 310	96.47 338	96.97 349	76.50 486	98.61 447	90.67 408	98.41 399	97.81 420

thisisatest0530		92.71 420	91.76 435	95.56 340	98.42 246	88.23 403	96.03 233	87.35 540	94.04 294	96.56 331	95.47 443	64.03 524	99.77 69	94.78 271	99.11 305	98.68 319

9.14			96.69 210		98.53 222		96.02 234	98.98 143	93.23 325	97.18 274	97.46 299	96.47 128	99.62 189	92.99 346	99.32 268

DeepC-MVS_fast	94.34 7	96.74 208	96.51 232	97.44 164	97.69 355	94.15 201	96.02 234	98.43 276	93.17 335	97.30 262	97.38 311	95.48 184	99.28 342	93.74 320	99.34 261	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	96.77 207	94.76 391	97.83 324	86.11 455	96.00 236	98.82 200	94.48 271	97.49 249	97.14 330	95.38 189	99.40 286	95.00 250	98.78 354	98.78 295

ttmdpeth		94.05 373	94.15 364	93.75 439	95.81 470	85.32 467	96.00 236	94.93 450	92.07 370	94.19 437	99.09 59	85.73 418	96.41 512	90.98 390	98.52 386	99.53 79

test_fmvsmconf_n		98.30 40	98.41 39	97.99 109	98.94 138	94.60 179	96.00 236	99.64 16	94.99 246	99.43 28	99.18 46	98.51 12	99.71 127	99.13 20	99.84 51	99.67 36

fmvsm_s_conf0.5_n_10		97.74 107	98.11 63	96.62 236	98.72 184	90.95 316	95.99 239	99.50 30	96.22 159	99.20 45	98.93 79	95.13 204	99.77 69	99.49 3	99.76 73	99.15 207

114514_t		93.96 376	93.22 390	96.19 289	99.06 113	90.97 312	95.99 239	98.94 152	73.88 546	93.43 469	96.93 352	92.38 301	99.37 306	89.09 436	99.28 277	98.25 377

FMVSNet3		95.26 312	94.94 314	96.22 286	96.53 427	90.06 343	95.99 239	97.66 359	94.11 290	97.99 204	97.91 246	80.22 469	99.63 184	94.60 280	99.44 218	98.96 261

HPM-MVS++		96.99 182	96.38 241	98.81 30	98.64 197	97.59 26	95.97 242	98.20 307	95.51 216	95.06 412	96.53 380	94.10 241	99.70 136	94.29 292	99.15 298	99.13 215

casdiffmvs_mvg		97.83 95	98.11 63	97.00 206	98.57 216	92.10 280	95.97 242	99.18 65	97.67 78	99.00 63	98.48 145	97.64 39	99.50 233	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	96.50 233	94.80 388	99.26 68	87.69 424	95.96 244	98.58 254	95.08 238	98.02 201	96.25 400	97.92 24	97.60 495	88.68 444	98.74 364	99.11 226

EG-PatchMatch MVS		97.69 113	97.79 106	97.40 169	99.06 113	93.52 226	95.96 244	98.97 146	94.55 268	98.82 87	98.76 100	97.31 58	99.29 337	97.20 99	99.44 218	99.38 144

fmvsm_s_conf0.5_n_3		97.88 89	98.37 40	96.41 269	98.73 181	89.82 351	95.94 246	99.49 31	96.81 124	99.09 54	99.03 66	97.09 73	99.65 173	99.37 8	99.76 73	99.76 21

PAPM_NR		94.61 348	94.17 363	95.96 305	98.36 252	91.23 306	95.93 247	97.95 336	92.98 343	93.42 470	94.43 469	90.53 332	98.38 469	87.60 460	96.29 494	98.27 374

UniMVSNet (Re)		97.83 95	97.65 124	98.35 70	98.80 167	95.86 106	95.92 248	99.04 118	97.51 84	98.22 173	97.81 260	94.68 219	99.78 58	97.14 102	99.75 83	99.41 134

test_vis1_n_1920		95.77 274	96.41 238	93.85 434	98.55 219	84.86 479	95.91 249	99.71 7	92.72 355	97.67 236	98.90 86	87.44 394	98.73 429	97.96 62	98.85 342	97.96 408

RoMa-SfM		96.87 195	96.56 223	97.79 121	98.50 231	96.46 71	95.89 250	98.45 271	91.48 395	98.84 84	97.40 304	93.93 248	97.96 486	94.99 256	99.58 151	98.96 261

fmvsm_l_conf0.5_n		97.68 116	97.81 104	97.27 179	98.92 144	92.71 257	95.89 250	99.41 39	93.36 319	99.00 63	98.44 150	96.46 130	99.65 173	99.09 23	99.76 73	99.45 113

fmvsm_s_conf0.5_n_9		97.98 65	98.32 48	96.96 208	98.92 144	91.45 300	95.87 252	99.53 28	97.44 87	99.56 19	99.05 63	95.34 191	99.67 161	99.52 2	99.70 98	99.77 15

PRO-TEST		95.35 306	95.48 292	94.95 379	96.49 429	87.11 438	95.86 253	98.74 220	93.21 328	95.07 410	95.57 438	93.10 273	99.51 231	92.89 351	98.37 400	98.24 378

1314		92.38 429	92.30 419	92.64 483	95.42 488	85.15 472	95.86 253	96.97 398	85.40 496	90.62 508	93.06 486	91.12 321	97.80 492	86.74 472	95.49 515	94.97 508

MVS		90.02 467	89.20 474	92.47 487	94.71 510	86.90 442	95.86 253	96.74 408	64.72 548	90.62 508	92.77 494	92.54 295	98.39 468	79.30 528	95.56 514	92.12 524

fmvsm_l_conf0.5_n_a		97.60 126	97.76 112	97.11 192	98.92 144	92.28 269	95.83 256	99.32 41	93.22 326	98.91 75	98.49 141	96.31 138	99.64 179	99.07 24	99.76 73	99.40 135

casdiffmvs		97.50 140	97.81 104	96.56 247	98.51 225	91.04 310	95.83 256	99.09 95	97.23 105	98.33 153	98.30 179	97.03 81	99.37 306	96.58 131	99.38 243	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		91.89 444	91.45 439	93.21 461	89.01 547	84.87 478	95.82 258	95.05 448	91.50 393	98.75 97	99.19 42	57.56 531	95.11 521	97.78 72	98.37 400	99.64 44

tpmvs		90.79 461	90.87 453	90.57 510	92.75 537	76.30 539	95.79 259	93.64 474	91.04 409	91.91 498	96.26 398	77.19 484	98.86 416	89.38 433	89.85 538	96.56 478

fmvsm_s_conf0.5_n_6		97.45 145	97.79 106	96.44 262	98.58 214	90.31 338	95.77 260	99.33 40	94.52 269	98.85 82	98.44 150	95.68 174	99.62 189	99.15 19	99.81 60	99.38 144

fmvsm_s_conf0.5_n_8		97.66 119	98.12 61	96.27 281	98.79 170	89.43 364	95.76 261	99.42 36	97.49 85	99.16 48	99.04 64	94.56 226	99.69 144	99.18 16	99.73 86	99.70 33

mvsany_test3		96.21 249	95.93 270	97.05 199	97.40 390	94.33 193	95.76 261	94.20 464	89.10 446	99.36 35	99.60 11	93.97 246	97.85 490	95.40 215	98.63 378	98.99 253

MSLP-MVS++		96.42 236	96.71 209	95.57 335	97.82 328	90.56 325	95.71 263	98.84 185	94.72 259	96.71 317	97.39 309	94.91 213	98.10 483	95.28 223	99.02 317	98.05 401

tfpn200view9		91.55 449	91.00 449	93.21 461	98.02 295	84.35 488	95.70 264	90.79 516	96.26 154	95.90 377	92.13 504	73.62 503	99.42 274	78.85 531	97.74 437	95.85 495

Anonymous20231206		95.27 311	95.06 308	95.88 313	98.72 184	89.37 365	95.70 264	97.85 345	88.00 466	96.98 297	97.62 284	91.95 311	99.34 317	89.21 434	99.53 177	98.94 267

thres400		91.68 448	91.00 449	93.71 441	98.02 295	84.35 488	95.70 264	90.79 516	96.26 154	95.90 377	92.13 504	73.62 503	99.42 274	78.85 531	97.74 437	97.36 446

reproduce_monomvs		92.05 441	92.26 420	91.43 501	95.42 488	75.72 542	95.68 267	97.05 393	94.47 275	97.95 214	98.35 165	55.58 542	99.05 390	96.36 142	99.44 218	99.51 86

test20.03		96.58 223	96.61 216	96.48 256	98.49 233	91.72 292	95.68 267	97.69 356	96.81 124	98.27 161	97.92 244	94.18 240	98.71 434	90.78 399	99.66 112	99.00 249

hse-mvs2		95.77 274	95.09 305	97.79 121	97.84 321	95.51 124	95.66 269	95.43 440	96.58 137	97.21 270	96.16 405	84.14 434	99.54 221	95.89 173	96.92 468	98.32 365

UniMVSNet_NR-MVSNet		97.83 95	97.65 124	98.37 67	98.72 184	95.78 108	95.66 269	99.02 123	98.11 57	98.31 156	97.69 277	94.65 221	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	98.48 235	89.89 349	95.65 271	99.26 49	94.73 258	98.72 101	98.58 129	95.58 180	99.57 211	99.28 9	99.67 109	99.73 28

dmvs_re		92.08 440	91.27 445	94.51 407	97.16 405	92.79 253	95.65 271	92.64 491	94.11 290	92.74 486	90.98 517	83.41 444	94.44 532	80.72 524	94.07 526	96.29 487

DU-MVS		97.79 102	97.60 135	98.36 69	98.73 181	95.78 108	95.65 271	98.87 171	97.57 79	98.31 156	97.83 255	94.69 217	99.85 30	97.02 110	99.71 94	99.46 109

EPMVS		89.26 481	88.55 481	91.39 503	92.36 539	79.11 525	95.65 271	79.86 550	88.60 456	93.12 475	96.53 380	70.73 514	98.10 483	90.75 401	89.32 539	96.98 459

MVP-Stereo		95.69 281	95.28 296	96.92 212	98.15 284	93.03 243	95.64 275	98.20 307	90.39 423	96.63 325	97.73 273	91.63 316	99.10 385	91.84 370	97.31 462	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	98.77 177	92.33 265	95.63 276	99.58 20	93.53 312	99.10 53	98.66 116	96.44 131	99.65 173	99.12 21	99.68 105	99.12 221

test_cas_vis1_n_1920		95.34 307	95.67 284	94.35 417	98.21 271	86.83 444	95.61 277	99.26 49	90.45 420	98.17 180	98.96 75	84.43 433	98.31 474	96.74 120	99.17 296	97.90 412

test_f		95.82 272	95.88 274	95.66 330	97.61 368	93.21 241	95.61 277	98.17 314	86.98 478	98.42 137	99.47 17	90.46 334	94.74 527	97.71 76	98.45 395	99.03 245

F-COLMAP		95.30 310	94.38 353	98.05 105	98.64 197	96.04 96	95.61 277	98.66 240	89.00 449	93.22 473	96.40 389	92.90 281	99.35 314	87.45 466	97.53 452	98.77 304

AUN-MVS		93.95 378	92.69 410	97.74 126	97.80 334	95.38 134	95.57 280	95.46 439	91.26 403	92.64 490	96.10 412	74.67 496	99.55 218	93.72 324	96.97 467	98.30 370

ALIKED-MNN		93.09 412	92.12 425	96.00 301	96.50 428	96.72 56	95.52 281	98.20 307	82.37 518	90.90 506	96.15 406	87.02 402	96.30 513	83.03 515	99.42 231	94.99 507

fmvsm_s_conf0.1_n_2		97.68 116	98.18 57	96.20 287	99.06 113	89.08 376	95.51 282	99.72 6	96.06 176	99.48 22	99.24 37	95.18 200	99.60 200	99.45 4	99.88 28	99.94 3

v144192		96.69 215	96.90 197	96.03 300	98.25 267	88.92 380	95.49 283	98.77 212	93.05 340	98.09 190	98.29 183	92.51 298	99.70 136	98.11 53	99.56 160	99.47 107

Fast-Effi-MVS+-dtu		96.44 233	96.12 254	97.39 170	97.18 404	94.39 188	95.46 284	98.73 222	96.03 181	94.72 424	94.92 458	96.28 144	99.69 144	93.81 317	97.98 419	98.09 391

viewmacassd2359aftdt		97.25 165	97.52 145	96.43 264	98.83 161	90.49 331	95.45 285	99.18 65	95.44 222	97.98 209	98.47 146	96.90 96	99.37 306	95.93 170	99.55 167	99.43 126

Baseline_NR-MVSNet		97.72 111	97.79 106	97.50 154	99.56 22	93.29 236	95.44 286	98.86 175	98.20 55	98.37 143	99.24 37	94.69 217	99.55 218	95.98 167	99.79 66	99.65 41

LF4IMVS		96.07 255	95.63 287	97.36 172	98.19 274	95.55 121	95.44 286	98.82 200	92.29 365	95.70 390	96.55 378	92.63 289	98.69 437	91.75 376	99.33 266	97.85 416

v1921920		96.72 212	96.96 190	95.99 302	98.21 271	88.79 386	95.42 288	98.79 206	93.22 326	98.19 178	98.26 190	92.68 286	99.70 136	98.34 50	99.55 167	99.49 97

plane_prior						94.29 195	95.42 288		94.31 282						98.93 331

v1144		96.84 198	97.08 180	96.13 295	98.42 246	89.28 367	95.41 290	98.67 237	94.21 284	97.97 211	98.31 173	93.06 275	99.65 173	98.06 58	99.62 124	99.45 113

ETV-MVS		96.13 254	95.90 272	96.82 223	97.76 344	93.89 210	95.40 291	98.95 149	95.87 194	95.58 395	91.00 516	96.36 137	99.72 111	93.36 334	98.83 346	96.85 466

fmvsm_l_conf0.5_n_9		97.92 80	98.37 40	96.57 245	98.94 138	90.54 326	95.39 292	99.58 20	96.82 123	99.56 19	98.77 96	97.23 67	99.61 197	99.17 17	99.86 35	99.57 60

v1240		96.74 208	97.02 186	95.91 310	98.18 277	88.52 392	95.39 292	98.88 169	93.15 337	98.46 132	98.40 160	92.80 283	99.71 127	98.45 46	99.49 201	99.49 97

MP-MVS-pluss		97.69 113	97.36 158	98.70 41	99.50 35	96.84 52	95.38 294	98.99 140	92.45 360	98.11 187	98.31 173	97.25 65	99.77 69	96.60 129	99.62 124	99.48 103
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MGCNet		95.71 280	95.18 300	97.33 174	94.85 507	92.82 248	95.36 295	90.89 515	95.51 216	95.61 393	97.82 258	88.39 375	99.78 58	98.23 51	99.91 19	99.40 135

v1192		96.83 201	97.06 182	96.15 294	98.28 261	89.29 366	95.36 295	98.77 212	93.73 303	98.11 187	98.34 167	93.02 280	99.67 161	98.35 49	99.58 151	99.50 89

v2v482		96.78 205	97.06 182	95.95 307	98.57 216	88.77 387	95.36 295	98.26 299	95.18 234	97.85 226	98.23 194	92.58 290	99.63 184	97.80 70	99.69 100	99.45 113

test_fmvs1		94.51 355	94.60 339	94.26 422	95.91 462	87.92 414	95.35 298	99.02 123	86.56 483	96.79 309	98.52 137	82.64 449	97.00 504	97.87 66	98.71 368	97.88 414

EI-MVSNet-Vis-set		97.32 160	97.39 154	97.11 192	97.36 392	92.08 281	95.34 299	97.65 361	97.74 70	98.29 159	98.11 213	95.05 205	99.68 151	97.50 85	99.50 198	99.56 68

fmvsm_s_conf0.5_n_2		97.59 129	98.07 69	96.17 291	98.78 174	89.10 375	95.33 300	99.55 26	95.96 185	99.41 31	99.10 57	95.18 200	99.59 202	99.43 6	99.86 35	99.81 10

EI-MVSNet-UG-set		97.32 160	97.40 153	97.09 196	97.34 395	92.01 285	95.33 300	97.65 361	97.74 70	98.30 158	98.14 206	95.04 206	99.69 144	97.55 83	99.52 184	99.58 52

CostFormer		89.75 474	89.25 470	91.26 505	94.69 511	78.00 531	95.32 302	91.98 501	81.50 523	90.55 510	96.96 351	71.06 512	98.89 410	88.59 445	92.63 531	96.87 464

viewdifsd2359ckpt13		96.47 230	96.42 237	96.61 239	98.35 253	91.50 297	95.31 303	98.84 185	93.21 328	96.73 315	97.58 288	95.28 196	99.26 347	94.02 306	98.45 395	99.07 236

PVSNet_Blended_VisFu		95.95 264	95.80 279	96.42 266	99.28 64	90.62 322	95.31 303	99.08 99	88.40 459	96.97 298	98.17 205	92.11 306	99.78 58	93.64 326	99.21 287	98.86 286

UnsupCasMVSNet_eth		95.91 267	95.73 282	96.44 262	98.48 235	91.52 296	95.31 303	98.45 271	95.76 201	97.48 252	97.54 290	89.53 354	98.69 437	94.43 285	94.61 522	99.13 215

EI-MVSNet		96.63 218	96.93 192	95.74 320	97.26 400	88.13 410	95.29 306	97.65 361	96.99 111	97.94 216	98.19 200	92.55 293	99.58 205	96.91 114	99.56 160	99.50 89

CVMVSNet		92.33 431	92.79 405	90.95 506	97.26 400	75.84 541	95.29 306	92.33 496	81.86 520	96.27 352	98.19 200	81.44 457	98.46 464	94.23 295	98.29 405	98.55 333

E4		97.28 162	97.55 142	96.46 257	98.86 156	90.53 328	95.28 308	99.18 65	95.82 199	98.01 202	98.59 128	96.78 106	99.46 255	95.86 177	99.56 160	99.38 144

viewdifsd2359ckpt09		96.23 248	96.04 259	96.82 223	98.29 258	92.06 283	95.25 309	99.03 119	91.51 392	96.19 359	97.01 347	94.41 230	99.40 286	93.76 319	98.90 334	99.00 249

OPM-MVS		97.54 136	97.25 167	98.41 64	99.11 105	96.61 64	95.24 310	98.46 270	94.58 267	98.10 189	98.07 219	97.09 73	99.39 295	95.16 235	99.44 218	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	94.23 358	97.04 201	98.18 277	94.51 184	95.22 311	98.73 222	81.22 525	96.25 354	95.95 422	93.80 252	98.98 401	89.89 424	98.87 339	97.62 435
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPE-MVS		97.64 121	97.35 159	98.50 56	98.85 158	96.18 87	95.21 312	98.99 140	95.84 197	98.78 90	98.08 217	96.84 103	99.81 43	93.98 308	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	97.38 156	96.55 249	98.51 225	90.96 313	95.19 313	99.06 104	96.60 133	98.27 161	97.78 263	96.58 120	99.72 111	95.04 244	99.40 237	98.98 256

SSM_04072		97.14 171	97.38 156	96.42 266	98.51 225	90.96 313	95.19 313	99.06 104	96.60 133	98.27 161	97.78 263	96.58 120	99.31 329	95.04 244	99.40 237	98.98 256

MVSTER		94.21 366	93.93 372	95.05 370	95.83 468	86.46 447	95.18 315	97.65 361	92.41 363	97.94 216	98.00 235	72.39 508	99.58 205	96.36 142	99.56 160	99.12 221

testing3-2		90.09 466	90.38 463	89.24 517	98.07 291	69.88 554	95.12 316	90.71 520	96.65 130	93.60 463	94.03 473	55.81 541	99.33 319	90.69 407	98.71 368	98.51 340

PatchmatchNet		91.98 443	91.87 429	92.30 491	94.60 513	79.71 522	95.12 316	93.59 475	89.52 439	93.61 461	97.02 343	77.94 476	99.18 365	90.84 396	94.57 524	98.01 405
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmanbaseed2359cas		96.77 206	96.94 191	96.27 281	98.41 248	90.24 339	95.11 318	99.03 119	94.28 283	97.45 256	97.85 252	95.92 159	99.32 327	95.18 232	99.19 292	99.24 189

IterMVS-LS		96.92 190	97.29 163	95.79 316	98.51 225	88.13 410	95.10 319	98.66 240	96.99 111	98.46 132	98.68 114	92.55 293	99.74 95	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	96.97 188	95.42 348	98.63 206	87.57 425	95.09 320	97.90 341	95.91 192	98.24 170	97.96 238	93.42 263	99.39 295	96.04 161	99.52 184	99.29 174

tpm2		88.47 490	87.69 493	90.79 508	94.98 504	77.34 535	95.09 320	91.83 502	77.51 542	89.40 525	96.41 387	67.83 520	98.73 429	83.58 513	92.60 532	96.29 487

OpenMVS_ROB	91.80 14	93.64 391	93.05 395	95.42 348	97.31 399	91.21 307	95.08 322	96.68 411	81.56 522	96.88 305	96.41 387	90.44 336	99.25 350	85.39 491	97.67 444	95.80 497

E2		96.97 186	97.19 173	96.33 275	98.64 197	90.34 336	95.07 323	99.12 82	95.00 244	97.66 237	98.31 173	96.19 148	99.43 270	95.35 220	99.35 256	99.23 191

E3		96.97 186	97.19 173	96.33 275	98.64 197	90.34 336	95.07 323	99.12 82	95.00 244	97.66 237	98.31 173	96.19 148	99.43 270	95.35 220	99.35 256	99.23 191

TAMVS		95.49 294	94.94 314	97.16 188	98.31 256	93.41 233	95.07 323	96.82 404	91.09 407	97.51 247	97.82 258	89.96 345	99.42 274	88.42 448	99.44 218	98.64 320

tpmrst		90.31 464	90.61 460	89.41 516	94.06 523	72.37 551	95.06 326	93.69 470	88.01 465	92.32 495	96.86 357	77.45 480	98.82 419	91.04 388	87.01 542	97.04 458

ADS-MVSNet2		91.47 451	90.51 461	94.36 414	95.51 484	85.63 461	95.05 327	95.70 429	83.46 512	92.69 487	96.84 359	79.15 472	99.41 284	85.66 487	90.52 535	98.04 402

ADS-MVSNet		90.95 459	90.26 464	93.04 467	95.51 484	82.37 504	95.05 327	93.41 476	83.46 512	92.69 487	96.84 359	79.15 472	98.70 435	85.66 487	90.52 535	98.04 402

tpm		91.08 457	90.85 454	91.75 498	95.33 491	78.09 529	95.03 329	91.27 511	88.75 452	93.53 465	97.40 304	71.24 510	99.30 333	91.25 385	93.87 527	97.87 415

NCCC		96.52 225	95.99 263	98.10 97	97.81 330	95.68 113	95.00 330	98.20 307	95.39 225	95.40 404	96.36 391	93.81 251	99.45 263	93.55 330	98.42 398	99.17 203

test_post1							94.98 331				10.37 559	76.21 489	99.04 393	89.47 431

FBQ-MVS		89.51 479	87.89 489	94.36 414	96.47 432	87.19 436	94.96 332	92.96 485	91.01 412	90.38 513	88.46 531	57.42 533	98.55 453	83.35 514	96.03 500	97.35 448

viewcassd2359sk11		96.73 210	96.89 198	96.24 283	98.46 239	90.20 341	94.94 333	99.07 103	94.43 277	97.33 261	98.05 228	95.69 173	99.40 286	94.98 258	99.11 305	99.12 221

fmvsm_s_conf0.5_n_7		97.13 172	97.50 149	96.04 299	98.43 244	89.03 379	94.92 334	99.00 135	94.51 270	98.42 137	98.96 75	94.97 211	99.54 221	98.42 47	99.85 48	99.56 68

AdaColmap		95.11 320	94.62 338	96.58 243	97.33 397	94.45 187	94.92 334	98.08 328	93.15 337	93.98 449	95.53 441	94.34 234	99.10 385	85.69 486	98.61 380	96.20 489

MDTV_nov1_ep13_2view						57.28 558	94.89 336		80.59 527	94.02 447		78.66 474		85.50 489		97.82 418

CNVR-MVS		96.92 190	96.55 227	98.03 106	98.00 301	95.54 122	94.87 337	98.17 314	94.60 264	96.38 342	97.05 341	95.67 176	99.36 310	95.12 241	99.08 310	99.19 199

OMC-MVS		96.48 229	96.00 262	97.91 114	98.30 257	96.01 101	94.86 338	98.60 248	91.88 376	97.18 274	97.21 325	96.11 151	99.04 393	90.49 414	99.34 261	98.69 316

E3new		96.50 226	96.61 216	96.17 291	98.28 261	90.09 342	94.85 339	99.02 123	93.95 299	97.01 292	97.74 271	95.19 199	99.39 295	94.70 278	98.77 361	99.04 243

viewdifsd2359ckpt11		97.13 172	97.62 131	95.67 328	98.64 197	88.36 398	94.84 340	98.95 149	96.24 156	98.70 103	98.61 123	96.66 111	99.29 337	96.46 135	99.45 215	99.36 154

viewmsd2359difaftdt		97.13 172	97.62 131	95.67 328	98.64 197	88.36 398	94.84 340	98.95 149	96.24 156	98.70 103	98.61 123	96.66 111	99.29 337	96.46 135	99.45 215	99.36 154

testing3		89.72 475	88.26 485	94.10 426	97.66 361	84.30 490	94.80 342	88.25 535	94.66 261	95.07 410	92.51 499	41.15 556	99.43 270	91.81 373	98.44 397	98.55 333

EPNet_dtu		91.39 453	90.75 456	93.31 455	90.48 545	82.61 502	94.80 342	92.88 486	93.39 318	81.74 546	94.90 459	81.36 458	99.11 381	88.28 450	98.87 339	98.21 382
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			91.28 444		94.31 516	73.51 549	94.80 342	93.16 480	86.75 482	93.45 468	97.40 304	76.37 487	98.55 453	88.85 439	96.43 488

LoFTR		95.39 302	95.01 310	96.52 251	97.16 405	95.19 155	94.77 345	96.95 400	90.31 425	98.78 90	98.29 183	86.71 406	97.91 488	92.56 356	99.57 155	96.46 483

pmmvs-eth3d		96.49 228	96.18 253	97.42 167	98.25 267	94.29 195	94.77 345	98.07 332	89.81 436	97.97 211	98.33 168	93.11 272	99.08 387	95.46 206	99.84 51	98.89 279

test_yl		94.40 358	94.00 368	95.59 333	96.95 413	89.52 360	94.75 347	95.55 437	96.18 167	96.79 309	96.14 409	81.09 460	99.18 365	90.75 401	97.77 433	98.07 394

DCV-MVSNet		94.40 358	94.00 368	95.59 333	96.95 413	89.52 360	94.75 347	95.55 437	96.18 167	96.79 309	96.14 409	81.09 460	99.18 365	90.75 401	97.77 433	98.07 394

dmvs_testset		87.30 502	86.99 498	88.24 523	96.71 421	77.48 534	94.68 349	86.81 543	92.64 356	89.61 524	87.01 540	85.91 416	93.12 541	61.04 549	88.49 540	94.13 516

MCST-MVS		96.24 247	95.80 279	97.56 142	98.75 179	94.13 202	94.66 350	98.17 314	90.17 432	96.21 357	96.10 412	95.14 203	99.43 270	94.13 299	98.85 342	99.13 215

XVG-OURS-SEG-HR		97.38 154	97.07 181	98.30 75	99.01 125	97.41 38	94.66 350	99.02 123	95.20 232	98.15 183	97.52 294	98.83 5	98.43 465	94.87 262	96.41 489	99.07 236

mvs_anonymous		95.36 304	96.07 258	93.21 461	96.29 439	81.56 510	94.60 352	97.66 359	93.30 323	96.95 299	98.91 85	93.03 279	99.38 299	96.60 129	97.30 463	98.69 316

DP-MVS Recon		95.55 292	95.13 303	96.80 225	98.51 225	93.99 208	94.60 352	98.69 232	90.20 431	95.78 386	96.21 402	92.73 285	98.98 401	90.58 410	98.86 341	97.42 445

ELoFTR		95.12 319	94.86 322	95.91 310	98.39 249	93.23 240	94.57 354	97.21 380	87.26 472	98.53 123	98.52 137	86.67 409	97.37 496	93.24 340	99.36 250	97.12 454

viewdifsd2359ckpt07		97.10 177	97.55 142	95.76 318	98.64 197	88.58 391	94.54 355	99.11 85	96.96 115	98.54 120	98.18 203	96.91 94	99.44 266	95.58 196	99.49 201	99.26 181

save fliter					98.48 235	94.71 171	94.53 356	98.41 280	95.02 243

patch_mono-2		96.59 220	96.93 192	95.55 341	98.88 151	87.12 437	94.47 357	99.30 43	94.12 289	96.65 324	98.41 155	94.98 210	99.87 25	95.81 181	99.78 70	99.66 38

tpm cat1		88.01 496	87.33 495	90.05 515	94.48 514	76.28 540	94.47 357	94.35 461	73.84 547	89.26 526	95.61 437	73.64 502	98.30 475	84.13 504	86.20 543	95.57 502

DKM		96.39 238	95.99 263	97.59 140	98.44 241	96.42 72	94.42 359	98.51 262	92.81 351	98.15 183	97.47 298	89.37 361	97.26 498	95.02 249	99.68 105	99.09 232

DKM-HiRes		96.47 230	95.93 270	98.09 98	98.86 156	96.41 73	94.38 360	98.56 257	94.05 293	96.93 300	97.48 297	87.73 389	98.55 453	95.86 177	99.48 206	99.31 166

CANet		95.86 270	95.65 286	96.49 254	96.41 435	90.82 318	94.36 361	98.41 280	94.94 248	92.62 492	96.73 368	92.68 286	99.71 127	95.12 241	99.60 142	98.94 267

WR-MVS		96.90 192	96.81 202	97.16 188	98.56 218	92.20 275	94.33 362	98.12 324	97.34 99	98.20 174	97.33 316	92.81 282	99.75 85	94.79 269	99.81 60	99.54 74

SP-LightGlue		95.19 315	94.96 313	95.89 312	95.10 498	94.93 166	94.29 363	98.47 268	94.91 252	94.92 419	95.51 442	86.69 407	95.61 517	97.08 107	97.67 444	97.12 454

HQP-NCC					97.85 314		94.26 364		93.18 332	92.86 483

ACMP_Plane					97.85 314		94.26 364		93.18 332	92.86 483

HQP-MVS		95.17 318	94.58 342	96.92 212	97.85 314	92.47 262	94.26 364	98.43 276	93.18 332	92.86 483	95.08 452	90.33 337	99.23 356	90.51 412	98.74 364	99.05 241

viewmamba		96.62 219	96.92 194	95.74 320	97.85 314	88.83 384	94.25 367	99.00 135	95.69 205	97.18 274	97.90 247	95.34 191	99.29 337	96.20 153	98.85 342	99.11 226

PLC	91.02 16	94.05 373	92.90 401	97.51 148	98.00 301	95.12 160	94.25 367	98.25 300	86.17 485	91.48 503	95.25 450	91.01 324	99.19 362	85.02 498	96.69 482	98.22 381
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MatchFormer		93.37 399	93.14 392	94.07 427	96.06 457	92.91 247	94.24 369	94.92 451	85.51 492	98.29 159	97.79 262	85.70 419	96.13 514	86.23 478	99.51 190	93.18 522

1112_ss		94.12 369	93.42 386	96.23 284	98.59 212	90.85 317	94.24 369	98.85 181	85.49 493	92.97 478	94.94 456	86.01 415	99.64 179	91.78 374	97.92 423	98.20 383

MS-PatchMatch		94.83 333	94.91 318	94.57 403	96.81 418	87.10 439	94.23 371	97.34 376	88.74 453	97.14 277	97.11 337	91.94 312	98.23 478	92.99 346	97.92 423	98.37 357

Fast-Effi-MVS+		95.49 294	95.07 306	96.75 229	97.67 360	92.82 248	94.22 372	98.60 248	91.61 384	93.42 470	92.90 490	96.73 109	99.70 136	92.60 353	97.89 428	97.74 426

CMPMVS	73.10 23	92.74 419	91.39 441	96.77 228	93.57 529	94.67 174	94.21 373	97.67 357	80.36 529	93.61 461	96.60 376	82.85 448	97.35 497	84.86 500	98.78 354	98.29 373
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
DenseAffine		96.06 257	95.57 289	97.53 147	98.44 241	95.79 107	94.20 374	98.14 321	92.44 362	97.95 214	97.18 328	88.87 368	97.96 486	93.41 332	99.52 184	98.85 288

dp		88.08 495	88.05 487	88.16 525	92.85 535	68.81 556	94.17 375	92.88 486	85.47 494	91.38 504	96.14 409	68.87 519	98.81 421	86.88 471	83.80 545	96.87 464

JIA-IIPM		91.79 446	90.69 458	95.11 365	93.80 526	90.98 311	94.16 376	91.78 504	96.38 148	90.30 516	99.30 33	72.02 509	98.90 409	88.28 450	90.17 537	95.45 503

D2MVS		95.18 316	95.17 301	95.21 360	97.76 344	87.76 423	94.15 377	97.94 337	89.77 437	96.99 294	97.68 278	87.45 392	99.14 373	95.03 248	99.81 60	98.74 308

TSAR-MVS + GP.		96.47 230	96.12 254	97.49 157	97.74 349	95.23 149	94.15 377	96.90 401	93.26 324	98.04 198	96.70 370	94.41 230	98.89 410	94.77 272	99.14 299	98.37 357

PVSNet_BlendedMVS		95.02 327	94.93 316	95.27 357	97.79 339	87.40 431	94.14 379	98.68 234	88.94 450	94.51 429	98.01 233	93.04 276	99.30 333	89.77 426	99.49 201	99.11 226

TinyColmap		96.00 262	96.34 243	94.96 378	97.90 311	87.91 415	94.13 380	98.49 265	94.41 278	98.16 181	97.76 265	96.29 143	98.68 440	90.52 411	99.42 231	98.30 370

CNLPA		95.04 324	94.47 348	96.75 229	97.81 330	95.25 148	94.12 381	97.89 342	94.41 278	94.57 427	95.69 432	90.30 340	98.35 472	86.72 473	98.76 362	96.64 474

SP-SuperGlue		95.41 301	95.38 294	95.51 343	94.92 506	94.67 174	94.09 382	97.93 339	95.45 219	95.62 391	96.26 398	89.54 351	95.26 519	96.70 121	97.92 423	96.61 477

BH-untuned		94.69 341	94.75 331	94.52 406	97.95 307	87.53 426	94.07 383	97.01 396	93.99 296	97.10 281	95.65 434	92.65 288	98.95 406	87.60 460	96.74 478	97.09 456

fmvsm_l_mol_unc0.5_1		97.76 105	98.18 57	96.49 254	99.02 124	90.21 340	94.06 384	99.63 17	96.81 124	99.74 6	99.60 11	95.96 156	99.66 169	98.92 30	99.86 35	99.60 47

onestephybrid01		96.25 246	96.31 245	96.07 298	97.54 376	90.01 347	94.06 384	98.77 212	94.74 255	96.32 345	97.74 271	94.03 243	99.20 360	94.81 267	98.79 352	98.98 256

ArgMatch-SfM		95.74 278	95.15 302	97.49 157	97.82 328	95.16 157	94.03 386	98.41 280	89.33 441	97.58 241	96.65 373	90.07 344	98.89 410	93.17 343	99.30 275	98.44 350

pmmvs5		94.63 347	94.34 354	95.50 344	97.63 367	88.34 400	94.02 387	97.13 385	87.15 475	95.22 408	97.15 329	87.50 391	99.27 345	93.99 307	99.26 282	98.88 283

thres200		91.00 458	90.42 462	92.77 479	97.47 386	83.98 493	94.01 388	91.18 512	95.12 237	95.44 401	91.21 514	73.93 499	99.31 329	77.76 535	97.63 449	95.01 506

xiu_mvs_v1_base_debu		95.62 288	95.96 266	94.60 400	98.01 297	88.42 395	93.99 389	98.21 304	92.98 343	95.91 373	94.53 465	96.39 134	99.72 111	95.43 211	98.19 408	95.64 499

xiu_mvs_v1_base		95.62 288	95.96 266	94.60 400	98.01 297	88.42 395	93.99 389	98.21 304	92.98 343	95.91 373	94.53 465	96.39 134	99.72 111	95.43 211	98.19 408	95.64 499

xiu_mvs_v1_base_debi		95.62 288	95.96 266	94.60 400	98.01 297	88.42 395	93.99 389	98.21 304	92.98 343	95.91 373	94.53 465	96.39 134	99.72 111	95.43 211	98.19 408	95.64 499

test_vis1_rt		94.03 375	93.65 378	95.17 363	95.76 475	93.42 232	93.97 392	98.33 293	84.68 504	93.17 474	95.89 425	92.53 297	94.79 525	93.50 331	94.97 518	97.31 451

CDS-MVSNet		94.88 332	94.12 365	97.14 190	97.64 366	93.57 224	93.96 393	97.06 392	90.05 433	96.30 351	96.55 378	86.10 414	99.47 248	90.10 420	99.31 271	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	94.54 345	94.97 377	93.53 530	94.33 193	93.94 394	97.84 347	93.35 320	96.58 328	95.54 439	88.87 368	94.71 528	93.73 322	97.44 458	95.87 494

CANet_DTU		94.65 345	94.21 361	95.96 305	95.90 463	89.68 356	93.92 395	97.83 350	93.19 331	90.12 519	95.64 435	88.52 372	99.57 211	93.27 339	99.47 209	98.62 323

WTY-MVS		93.55 393	93.00 398	95.19 361	97.81 330	87.86 417	93.89 396	96.00 422	89.02 448	94.07 444	95.44 445	86.27 413	99.33 319	87.69 458	96.82 474	98.39 354

sss		94.22 364	93.72 376	95.74 320	97.71 353	89.95 348	93.84 397	96.98 397	88.38 460	93.75 454	95.74 431	87.94 382	98.89 410	91.02 389	98.10 412	98.37 357

baseline2		89.65 477	88.44 483	93.25 457	95.62 481	82.71 500	93.82 398	85.94 544	88.89 451	87.35 538	92.54 498	71.23 511	99.33 319	86.01 481	94.60 523	97.72 429

XVG-OURS		97.12 175	96.74 208	98.26 79	98.99 130	97.45 36	93.82 398	99.05 110	95.19 233	98.32 154	97.70 276	95.22 198	98.41 466	94.27 293	98.13 411	98.93 271

MVS_111021_LR		96.82 202	96.55 227	97.62 138	98.27 264	95.34 143	93.81 400	98.33 293	94.59 266	96.56 331	96.63 375	96.61 117	98.73 429	94.80 268	99.34 261	98.78 295

BH-RMVSNet		94.56 352	94.44 351	94.91 380	97.57 371	87.44 428	93.78 401	96.26 417	93.69 306	96.41 341	96.50 383	92.10 307	99.00 397	85.96 483	97.71 440	98.31 367

dtuplus		95.73 279	95.86 275	95.33 355	97.72 351	87.82 420	93.74 402	98.60 248	92.12 368	97.27 264	97.92 244	94.35 233	99.13 377	92.24 361	98.83 346	99.05 241

SP-MNN		94.33 362	94.22 360	94.67 395	94.94 505	92.73 256	93.74 402	96.59 415	92.73 354	93.75 454	95.38 447	88.24 378	95.08 522	94.86 265	97.78 432	96.20 489

diffmvs_AUTHOR		96.50 226	96.81 202	95.57 335	98.03 293	88.26 402	93.73 404	99.14 79	94.92 251	97.24 267	97.84 254	94.62 222	99.33 319	96.44 138	99.37 245	99.13 215

CDPH-MVS		95.45 299	94.65 334	97.84 119	98.28 261	94.96 164	93.73 404	98.33 293	85.03 500	95.44 401	96.60 376	95.31 194	99.44 266	90.01 421	99.13 301	99.11 226

hybridnocas07		96.00 262	96.21 251	95.39 353	97.56 373	87.89 416	93.70 406	98.93 154	93.96 298	96.48 336	97.65 280	93.38 264	99.19 362	95.39 216	98.81 350	99.08 233

PatchMatch-RL		94.61 348	93.81 373	97.02 205	98.19 274	95.72 110	93.66 407	97.23 379	88.17 463	94.94 417	95.62 436	91.43 317	98.57 450	87.36 467	97.68 443	96.76 472

hybrid		95.77 274	95.95 269	95.23 359	97.54 376	87.44 428	93.65 408	98.86 175	93.17 335	96.06 367	97.65 280	93.14 271	99.20 360	94.94 260	98.57 384	99.04 243

UWE-MVS-28		83.78 508	82.36 511	88.03 526	90.72 544	71.58 552	93.64 409	77.87 551	87.62 470	85.91 542	92.89 491	59.94 527	95.99 516	56.06 551	96.56 487	96.52 479

TEST9					97.84 321	95.23 149	93.62 410	98.39 284	86.81 480	93.78 451	95.99 418	94.68 219	99.52 227

train_agg		95.46 298	94.66 333	97.88 116	97.84 321	95.23 149	93.62 410	98.39 284	87.04 476	93.78 451	95.99 418	94.58 224	99.52 227	91.76 375	98.90 334	98.89 279

viewmambaseed2359dif		95.68 283	95.85 276	95.17 363	97.51 379	87.41 430	93.61 412	98.58 254	91.06 408	96.68 318	97.66 279	94.71 216	99.11 381	93.93 310	98.94 326	98.99 253

test_prior4						95.38 134	93.61 412

ArgMatch-Sym		95.60 291	94.97 312	97.48 159	97.70 354	95.41 131	93.60 414	97.89 342	89.33 441	97.70 234	96.03 417	91.00 326	98.66 442	92.25 360	99.18 293	98.39 354

test_8					97.81 330	95.07 161	93.54 415	98.38 286	87.04 476	93.71 456	95.96 421	94.58 224	99.52 227

TR-MVS		92.54 425	92.20 422	93.57 445	96.49 429	86.66 445	93.51 416	94.73 454	89.96 434	94.95 416	93.87 476	90.24 342	98.61 447	81.18 523	94.88 519	95.45 503

PMatch-SfM		95.65 287	95.03 309	97.51 148	97.96 303	95.00 162	93.49 417	98.51 262	92.24 366	97.80 229	98.03 229	83.97 439	99.19 362	94.77 272	98.50 390	98.35 363

新几何2							93.43 418

diffmvs		96.04 258	96.23 249	95.46 347	97.35 393	88.03 413	93.42 419	99.08 99	94.09 292	96.66 322	96.93 352	93.85 250	99.29 337	96.01 165	98.67 373	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	96.54 229	97.27 179	98.35 253	93.66 222	93.42 419	98.36 289	94.74 255	96.58 328	96.76 367	96.54 122	98.99 399	94.87 262	99.27 279	99.15 207

PMatch-Up-SfM		95.95 264	95.43 293	97.51 148	97.90 311	95.17 156	93.40 421	98.78 210	92.45 360	98.24 170	98.07 219	87.10 401	99.18 365	94.87 262	98.10 412	98.19 384

UnsupCasMVSNet_bld		94.72 340	94.26 357	96.08 297	98.62 208	90.54 326	93.38 422	98.05 335	90.30 426	97.02 290	96.80 364	89.54 351	99.16 371	88.44 447	96.18 496	98.56 330

旧先验2							93.35 423		77.95 540	95.77 388			98.67 441	90.74 404

test_prior2							93.33 424		94.21 284	94.02 447	96.25 400	93.64 257		91.90 367	98.96 323

WB-MVSnew		91.50 450	91.29 443	92.14 494	94.85 507	80.32 520	93.29 425	88.77 532	88.57 457	94.03 446	92.21 502	92.56 291	98.28 476	80.21 526	97.08 465	97.81 420

IMVS_0404		95.66 286	96.03 260	94.55 404	97.83 324	86.11 455	93.24 426	98.82 200	94.48 271	95.51 399	97.14 330	93.49 260	98.78 423	95.00 250	98.78 354	98.78 295

SCA		93.38 398	93.52 382	92.96 472	96.24 440	81.40 513	93.24 426	94.00 465	91.58 391	94.57 427	96.97 349	87.94 382	99.42 274	89.47 431	97.66 447	98.06 398

无先验							93.20 428	97.91 340	80.78 526				99.40 286	87.71 456		97.94 410

MG-MVS		94.08 372	94.00 368	94.32 419	97.09 409	85.89 460	93.19 429	95.96 424	92.52 357	94.93 418	97.51 295	89.54 351	98.77 425	87.52 464	97.71 440	98.31 367

ALIKED-NN		90.94 460	89.58 469	95.02 372	94.61 512	96.31 80	93.16 430	97.27 377	79.38 532	86.25 541	95.27 449	83.42 443	94.29 533	79.08 529	97.77 433	94.46 511

nomal-1		90.42 463	88.88 479	95.06 369	96.01 458	88.66 390	93.13 431	92.16 497	91.23 404	90.46 512	91.32 513	61.17 526	98.72 432	87.70 457	96.70 481	97.79 423

MVS-HIRNet		88.40 491	90.20 465	82.99 529	97.01 411	60.04 557	93.11 432	85.61 545	84.45 508	88.72 531	99.09 59	84.72 430	98.23 478	82.52 517	96.59 486	90.69 540

new-patchmatchnet		95.67 284	96.58 220	92.94 473	97.48 382	80.21 521	92.96 433	98.19 313	94.83 253	98.82 87	98.79 92	93.31 266	99.51 231	95.83 179	99.04 316	99.12 221

ETVMVS		87.62 499	85.75 506	93.22 460	96.15 451	83.26 497	92.94 434	90.37 524	91.39 400	90.37 514	88.45 532	51.93 551	98.64 444	73.76 540	96.38 491	97.75 425

MDA-MVSNet-bldmvs		95.69 281	95.67 284	95.74 320	98.48 235	88.76 388	92.84 435	97.25 378	96.00 182	97.59 240	97.95 240	91.38 318	99.46 255	93.16 344	96.35 492	98.99 253

原ACMM2							92.82 436

testdata1							92.77 437		93.78 302

Test_1112_low_res		93.53 394	92.86 402	95.54 342	98.60 210	88.86 383	92.75 438	98.69 232	82.66 516	92.65 489	96.92 355	84.75 429	99.56 213	90.94 392	97.76 436	98.19 384

USDC		94.56 352	94.57 344	94.55 404	97.78 342	86.43 449	92.75 438	98.65 245	85.96 487	96.91 303	97.93 243	90.82 328	98.74 428	90.71 405	99.59 145	98.47 346

test222					98.17 280	93.24 239	92.74 440	97.61 369	75.17 544	94.65 426	96.69 371	90.96 327			98.66 375	97.66 431

jason		94.39 360	94.04 367	95.41 350	98.29 258	87.85 419	92.74 440	96.75 407	85.38 497	95.29 406	96.15 406	88.21 381	99.65 173	94.24 294	99.34 261	98.74 308
jason: jason.
testing91		89.67 476	88.55 481	93.04 467	95.90 463	81.80 509	92.71 442	93.71 469	93.71 304	90.18 517	90.15 522	57.11 534	99.22 358	87.17 470	96.32 493	98.12 390

testing99		89.21 482	88.04 488	92.70 481	95.78 473	81.00 517	92.65 443	92.03 499	93.20 330	89.90 522	90.08 524	55.25 543	99.14 373	87.54 462	95.95 501	97.97 407

Patchmatch-RL test		94.66 344	94.49 346	95.19 361	98.54 221	88.91 381	92.57 444	98.74 220	91.46 398	98.32 154	97.75 268	77.31 483	98.81 421	96.06 158	99.61 135	97.85 416

DeepPCF-MVS	94.58 5	96.90 192	96.43 236	98.31 74	97.48 382	97.23 44	92.56 445	98.60 248	92.84 350	98.54 120	97.40 304	96.64 116	98.78 423	94.40 288	99.41 236	98.93 271

N_pmnet		95.18 316	94.23 358	98.06 101	97.85 314	96.55 66	92.49 446	91.63 505	89.34 440	98.09 190	97.41 303	90.33 337	99.06 389	91.58 378	99.31 271	98.56 330

testing11		88.93 484	87.63 494	92.80 478	95.87 465	81.49 511	92.48 447	91.54 506	91.62 383	88.27 534	90.24 520	55.12 546	99.11 381	87.30 468	96.28 495	97.81 420

Syy-MVS		92.09 439	91.80 432	92.93 474	95.19 495	82.65 501	92.46 448	91.35 508	90.67 417	91.76 500	87.61 534	85.64 421	98.50 459	94.73 275	96.84 472	97.65 432

myMVS_eth3d		87.16 504	85.61 507	91.82 497	95.19 495	79.32 523	92.46 448	91.35 508	90.67 417	91.76 500	87.61 534	41.96 555	98.50 459	82.66 516	96.84 472	97.65 432

BH-w/o		92.14 437	91.94 427	92.73 480	97.13 408	85.30 468	92.46 448	95.64 431	89.33 441	94.21 436	92.74 495	89.60 349	98.24 477	81.68 520	94.66 521	94.66 510

IterMVS-SCA-FT		95.86 270	96.19 252	94.85 385	97.68 356	85.53 463	92.42 451	97.63 368	96.99 111	98.36 146	98.54 136	87.94 382	99.75 85	97.07 108	99.08 310	99.27 179

IterMVS		95.42 300	95.83 278	94.20 423	97.52 378	83.78 495	92.41 452	97.47 373	95.49 218	98.06 195	98.49 141	87.94 382	99.58 205	96.02 163	99.02 317	99.23 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing222		87.35 501	85.50 508	92.93 474	95.79 472	82.83 499	92.40 453	90.10 528	92.80 352	88.87 530	89.02 527	48.34 554	98.70 435	75.40 539	96.74 478	97.27 452

DELS-MVS		96.17 252	96.23 249	95.99 302	97.55 375	90.04 345	92.38 454	98.52 260	94.13 288	96.55 333	97.06 340	94.99 209	99.58 205	95.62 192	99.28 277	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		93.34 400	92.55 415	95.73 324	95.69 478	89.08 376	92.36 455	97.11 387	91.47 396	95.42 403	88.94 530	82.26 452	99.48 242	93.84 315	95.81 506	98.62 323

blended_shiyan6		93.34 400	92.54 416	95.73 324	95.68 479	89.08 376	92.35 456	97.10 388	91.47 396	95.37 405	88.96 529	82.26 452	99.48 242	93.83 316	95.85 502	98.62 323

new_pmnet		92.34 430	91.69 438	94.32 419	96.23 442	89.16 371	92.27 457	92.88 486	84.39 509	95.29 406	96.35 392	85.66 420	96.74 510	84.53 502	97.56 450	97.05 457

myMVS_eth3d28		88.32 492	87.73 492	90.11 514	96.42 433	74.96 546	92.21 458	92.37 495	93.56 311	90.14 518	89.61 525	56.13 539	98.05 485	81.84 518	97.26 464	97.33 450

CHOSEN 1792x2688		94.10 370	93.41 387	96.18 290	99.16 93	90.04 345	92.15 459	98.68 234	79.90 530	96.22 356	97.83 255	87.92 386	99.42 274	89.18 435	99.65 114	99.08 233

blend_shiyan4		88.73 488	86.43 503	95.61 332	95.31 492	89.17 368	92.13 460	97.10 388	91.59 390	94.15 441	87.38 536	52.97 550	99.40 286	91.84 370	75.42 550	98.27 374

xiu_mvs_v2_base		94.22 364	94.63 337	92.99 471	97.32 398	84.84 480	92.12 461	97.84 347	91.96 374	94.17 439	93.43 479	96.07 154	99.71 127	91.27 383	97.48 454	94.42 513

lupinMVS		93.77 380	93.28 388	95.24 358	97.68 356	87.81 421	92.12 461	96.05 420	84.52 506	94.48 431	95.06 454	86.90 403	99.63 184	93.62 329	99.13 301	98.27 374

pmmvs4		94.82 334	94.19 362	96.70 232	97.42 389	92.75 254	92.09 463	96.76 406	86.80 481	95.73 389	97.22 324	89.28 362	98.89 410	93.28 338	99.14 299	98.46 348

SP-NN		92.63 423	92.38 417	93.37 448	93.30 531	92.36 264	92.04 464	94.24 463	91.60 388	89.19 527	93.92 475	87.21 398	91.28 545	93.73 322	96.17 497	96.48 481

PAPR		92.22 435	91.27 445	95.07 368	95.73 477	88.81 385	91.97 465	97.87 344	85.80 490	90.91 505	92.73 496	91.16 320	98.33 473	79.48 527	95.76 511	98.08 392

UWE-MVS		87.57 500	86.72 501	90.13 513	95.21 494	73.56 548	91.94 466	83.78 548	88.73 454	93.00 477	92.87 492	55.22 544	99.25 350	81.74 519	97.96 421	97.59 438

gbinet_0.2-2-1-0.02		92.86 416	91.78 434	96.13 295	94.34 515	90.06 343	91.90 467	96.63 414	91.73 378	94.24 435	86.22 543	80.26 468	99.56 213	93.87 313	96.80 476	98.77 304

PS-MVSNAJ		94.10 370	94.47 348	93.00 470	97.35 393	84.88 477	91.86 468	97.84 347	91.96 374	94.17 439	92.50 500	95.82 165	99.71 127	91.27 383	97.48 454	94.40 514

c3_l		95.20 314	95.32 295	94.83 387	96.19 445	86.43 449	91.83 469	98.35 292	93.47 316	97.36 260	97.26 322	88.69 370	99.28 342	95.41 214	99.36 250	98.78 295

icg_test_0407_2		95.88 268	96.39 239	94.36 414	97.83 324	86.11 455	91.82 470	98.82 200	94.48 271	97.57 242	97.14 330	96.08 152	98.20 481	95.00 250	98.78 354	98.78 295

test0.0.03 1		90.11 465	89.21 473	92.83 477	93.89 525	86.87 443	91.74 471	88.74 533	92.02 372	94.71 425	91.14 515	73.92 500	94.48 531	83.75 512	92.94 529	97.16 453

UBG		88.29 493	87.17 496	91.63 499	96.08 454	78.21 528	91.61 472	91.50 507	89.67 438	89.71 523	88.97 528	59.01 529	98.91 407	81.28 522	96.72 480	97.77 424

SSC-MVS3.2		95.75 277	96.56 223	93.34 450	98.69 193	80.75 518	91.60 473	97.43 375	97.37 97	96.99 294	97.02 343	93.69 256	99.71 127	96.32 145	99.89 26	99.55 72

FPMVS		89.92 471	88.63 480	93.82 435	98.37 251	96.94 49	91.58 474	93.34 478	88.00 466	90.32 515	97.10 338	70.87 513	91.13 547	71.91 545	96.16 499	93.39 521

ET-MVSNet_ETH3D		91.12 454	89.67 468	95.47 346	96.41 435	89.15 372	91.54 475	90.23 526	89.07 447	86.78 540	92.84 493	69.39 517	99.44 266	94.16 297	96.61 485	97.82 418

WBMVS		91.11 455	90.72 457	92.26 492	95.99 459	77.98 532	91.47 476	95.90 426	91.63 382	95.90 377	96.45 385	59.60 528	99.46 255	89.97 423	99.59 145	99.33 159

PVSNet_Blended		93.96 376	93.65 378	94.91 380	97.79 339	87.40 431	91.43 477	98.68 234	84.50 507	94.51 429	94.48 468	93.04 276	99.30 333	89.77 426	98.61 380	98.02 404

CLD-MVS		95.47 297	95.07 306	96.69 233	98.27 264	92.53 259	91.36 478	98.67 237	91.22 405	95.78 386	94.12 472	95.65 177	98.98 401	90.81 397	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	94.93 316	94.75 392	95.99 459	86.12 454	91.35 479	98.49 265	93.40 317	97.12 279	97.25 323	86.87 405	99.35 314	95.08 243	98.82 348	98.78 295

cl____		94.73 336	94.64 335	95.01 373	95.85 467	87.00 440	91.33 480	98.08 328	93.34 321	97.10 281	97.33 316	84.01 438	99.30 333	95.14 238	99.56 160	98.71 315

DIV-MVS_self_test		94.73 336	94.64 335	95.01 373	95.86 466	87.00 440	91.33 480	98.08 328	93.34 321	97.10 281	97.34 315	84.02 437	99.31 329	95.15 237	99.55 167	98.72 311

miper_ehance_all_eth		94.69 341	94.70 332	94.64 396	95.77 474	86.22 452	91.32 482	98.24 302	91.67 381	97.05 288	96.65 373	88.39 375	99.22 358	94.88 261	98.34 402	98.49 345

usedtu_dtu_shiyan1		94.61 348	94.29 355	95.57 335	97.93 308	88.45 393	91.30 483	97.64 365	91.61 384	95.85 382	95.79 429	86.65 410	99.48 242	92.92 349	98.97 320	98.78 295

FE-MVSNET3		94.61 348	94.29 355	95.57 335	97.93 308	88.45 393	91.30 483	97.64 365	91.61 384	95.85 382	95.79 429	86.65 410	99.48 242	92.92 349	98.97 320	98.78 295

pmmvs3		90.00 468	88.90 478	93.32 454	94.20 521	85.34 466	91.25 485	92.56 494	78.59 537	93.82 450	95.17 451	67.36 521	98.69 437	89.08 437	98.03 417	95.92 491

SIFT-NCM-Cal		93.81 379	93.73 374	94.05 429	96.55 425	96.75 55	91.23 486	93.80 467	91.44 399	95.86 381	96.27 397	90.82 328	93.76 535	88.26 452	99.37 245	91.63 530

SIFT-MNN		93.13 411	92.91 400	93.79 437	96.42 433	96.49 68	91.23 486	93.73 468	92.18 367	95.52 398	96.08 415	84.66 431	93.04 542	87.49 465	98.94 326	91.84 526

HyFIR lowres test		93.72 385	92.65 411	96.91 214	98.93 142	91.81 291	91.23 486	98.52 260	82.69 514	96.46 339	96.52 382	80.38 464	99.90 17	90.36 416	98.79 352	99.03 245

DPM-MVS		93.68 388	92.77 408	96.42 266	97.91 310	92.54 258	91.17 489	97.47 373	84.99 502	93.08 476	94.74 461	89.90 346	99.00 397	87.54 462	98.09 414	97.72 429

CL-MVSNet_self_test		95.04 324	94.79 330	95.82 315	97.51 379	89.79 352	91.14 490	96.82 404	93.05 340	96.72 316	96.40 389	90.82 328	99.16 371	91.95 366	98.66 375	98.50 343

miper_lstm_enhance		94.81 335	94.80 329	94.85 385	96.16 448	86.45 448	91.14 490	98.20 307	93.49 315	97.03 289	97.37 313	84.97 428	99.26 347	95.28 223	99.56 160	98.83 289

dtuonlycased		95.11 320	95.70 283	93.35 449	99.05 119	81.45 512	91.13 492	98.48 267	93.11 339	97.98 209	97.27 320	96.15 150	99.32 327	89.61 428	98.50 390	99.27 179

cl22		93.25 406	92.84 404	94.46 411	94.30 517	86.00 459	91.09 493	96.64 413	90.74 414	95.79 384	96.31 395	78.24 475	98.77 425	94.15 298	98.34 402	98.62 323

MSDG		95.33 308	95.13 303	95.94 309	97.40 390	91.85 289	91.02 494	98.37 288	95.30 229	96.31 350	95.99 418	94.51 228	98.38 469	89.59 429	97.65 448	97.60 437

wanda-best-256-512		92.66 421	91.75 436	95.40 351	94.99 501	88.19 404	90.89 495	97.05 393	91.02 410	94.75 421	87.24 537	80.36 465	99.46 255	93.63 327	95.85 502	98.55 333

FE-blended-shiyan7		92.66 421	91.75 436	95.40 351	94.99 501	88.19 404	90.89 495	97.05 393	91.02 410	94.75 421	87.24 537	80.36 465	99.46 255	93.63 327	95.85 502	98.55 333

IB-MVS	85.98 20	88.63 489	86.95 500	93.68 442	95.12 497	84.82 481	90.85 497	90.17 527	87.55 471	88.48 533	91.34 512	58.01 530	99.59 202	87.24 469	93.80 528	96.63 476
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		93.47 395	93.03 396	94.79 389	94.05 524	92.12 277	90.82 498	90.01 529	85.02 501	97.26 266	98.28 185	93.57 258	97.03 502	92.51 357	95.75 512	95.23 505

test123		12.59 523	15.49 526	3.87 540	6.07 564	2.55 566	90.75 499	2.59 567	2.52 557	5.20 561	13.02 557	4.96 563	1.85 561	5.20 559	9.09 559	7.23 556

SIFT-UMatch		93.66 389	93.67 377	93.63 443	96.30 438	96.15 90	90.62 500	94.47 459	92.12 368	97.39 259	96.18 403	87.74 388	93.63 537	88.59 445	99.64 118	91.12 534

ppachtmachnet_test		94.49 356	94.84 325	93.46 447	96.16 448	82.10 505	90.59 501	97.48 372	90.53 419	97.01 292	97.59 286	91.01 324	99.36 310	93.97 309	99.18 293	98.94 267

SIFT-ConvMatch		93.72 385	93.47 383	94.48 410	96.22 444	96.63 63	90.58 502	93.91 466	91.70 379	97.70 234	96.17 404	89.03 365	95.12 520	86.29 477	99.65 114	91.69 529

PMMVS		92.39 428	91.08 448	96.30 280	93.12 533	92.81 250	90.58 502	95.96 424	79.17 534	91.85 499	92.27 501	90.29 341	98.66 442	89.85 425	96.68 483	97.43 444

our_test_3		94.20 368	94.58 342	93.07 465	96.16 448	81.20 515	90.42 504	96.84 402	90.72 415	97.14 277	97.13 334	90.47 333	99.11 381	94.04 304	98.25 406	98.91 275

SIFT-NN-NCMNet		92.32 432	91.79 433	93.89 433	96.32 437	96.91 50	90.32 505	90.69 521	90.36 424	91.72 502	95.43 446	88.98 366	94.27 534	84.23 503	98.06 415	90.49 542

YYNet1		94.73 336	94.84 325	94.41 413	97.47 386	85.09 474	90.29 506	95.85 428	92.52 357	97.53 245	97.76 265	91.97 310	99.18 365	93.31 337	96.86 471	98.95 264

MDA-MVSNet_test_wron		94.73 336	94.83 327	94.42 412	97.48 382	85.15 472	90.28 507	95.87 427	92.52 357	97.48 252	97.76 265	91.92 313	99.17 370	93.32 336	96.80 476	98.94 267

SIFT-NN-PointCN		92.48 427	92.19 423	93.33 453	95.40 490	95.65 116	90.19 508	93.07 482	88.67 455	92.90 479	95.95 422	89.38 360	93.20 540	85.21 494	98.94 326	91.15 533

SIFT-NN-UMatch		92.28 434	91.93 428	93.34 450	96.13 453	96.04 96	90.05 509	92.08 498	90.41 421	92.88 481	95.29 448	87.36 397	93.63 537	85.33 492	97.87 429	90.34 543

GA-MVS		92.83 418	92.15 424	94.87 384	96.97 412	87.27 434	90.03 510	96.12 419	91.83 377	94.05 445	94.57 463	76.01 490	98.97 405	92.46 358	97.34 461	98.36 362

miper_enhance_ethall		93.14 409	92.78 407	94.20 423	93.65 527	85.29 469	89.97 511	97.85 345	85.05 499	96.15 364	94.56 464	85.74 417	99.14 373	93.74 320	98.34 402	98.17 388

test-LLR		89.97 470	89.90 466	90.16 511	94.24 519	74.98 543	89.89 512	89.06 530	92.02 372	89.97 520	90.77 518	73.92 500	98.57 450	91.88 368	97.36 459	96.92 461

TESTMET0.1,1		87.20 503	86.57 502	89.07 518	93.62 528	72.84 550	89.89 512	87.01 542	85.46 495	89.12 528	90.20 521	56.00 540	97.72 493	90.91 393	96.92 468	96.64 474

test-mter		87.92 497	87.17 496	90.16 511	94.24 519	74.98 543	89.89 512	89.06 530	86.44 484	89.97 520	90.77 518	54.96 547	98.57 450	91.88 368	97.36 459	96.92 461

PCF-MVS	89.43 18	92.12 438	90.64 459	96.57 245	97.80 334	93.48 229	89.88 515	98.45 271	74.46 545	96.04 368	95.68 433	90.71 331	99.31 329	73.73 541	99.01 319	96.91 463
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SIFT-CM-Cal		93.31 402	93.10 393	93.95 432	96.19 445	96.32 79	89.81 516	93.40 477	91.16 406	97.19 273	96.07 416	88.24 378	94.58 530	86.11 479	99.69 100	90.94 537

SIFT-UM-Cal		93.74 382	93.73 374	93.78 438	95.97 461	96.07 94	89.78 517	96.67 412	91.69 380	97.77 232	96.09 414	89.51 355	94.75 526	86.68 474	99.39 241	90.52 541

MASt3R-SfM		91.42 452	90.88 452	93.06 466	92.40 538	92.08 281	89.76 518	93.15 481	78.62 536	95.98 370	97.33 316	82.42 451	91.17 546	90.23 418	97.98 419	95.92 491

SIFT-PointCN		93.04 413	92.72 409	94.01 431	95.80 471	95.33 146	89.76 518	92.60 493	90.24 429	96.32 345	95.87 426	87.45 392	94.70 529	86.65 475	99.77 72	92.01 525

thisisatest0515		90.43 462	89.18 476	94.17 425	97.07 410	85.44 464	89.75 520	87.58 539	88.28 461	93.69 459	91.72 508	65.27 522	99.58 205	90.59 409	98.67 373	97.50 443

SIFT-PCN-Cal		93.02 414	92.95 399	93.23 459	95.63 480	94.57 182	89.68 521	94.71 455	90.40 422	97.02 290	95.84 427	88.33 377	93.66 536	85.26 493	99.65 114	91.45 532

PatchmatchNet2					0.00 566	78.83 526	89.63 522	94.76 453	87.65 469
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
KD-MVS_2432*1600		88.93 484	87.74 490	92.49 485	88.04 551	81.99 506	89.63 522	95.62 432	91.35 401	95.06 412	93.11 481	56.58 536	98.63 445	85.19 495	95.07 516	96.85 466

miper_refine_blended		88.93 484	87.74 490	92.49 485	88.04 551	81.99 506	89.63 522	95.62 432	91.35 401	95.06 412	93.11 481	56.58 536	98.63 445	85.19 495	95.07 516	96.85 466

SIFT-NN-CMatch		92.54 425	92.03 426	94.07 427	96.08 454	96.27 84	89.47 525	90.90 514	90.26 428	92.89 480	94.83 460	90.17 343	94.95 524	84.92 499	98.78 354	90.99 536

dtuonly		92.30 433	93.44 384	88.89 519	95.60 482	69.49 555	89.18 526	98.09 326	88.17 463	94.19 437	96.35 392	88.98 366	98.72 432	91.74 377	98.69 371	98.45 349

testmvs		12.33 524	15.23 527	3.64 541	5.77 565	2.23 567	88.99 527	3.62 565	2.30 558	5.29 560	13.09 556	4.52 564	1.95 560	5.16 560	8.32 560	6.75 557

SIFT-NN		89.78 473	89.23 471	91.41 502	95.04 500	94.89 167	88.98 528	90.76 518	89.26 444	89.11 529	92.97 488	81.45 456	88.25 548	78.47 534	97.06 466	91.08 535

cascas		91.89 444	91.35 442	93.51 446	94.27 518	85.60 462	88.86 529	98.61 247	79.32 533	92.16 496	91.44 511	89.22 363	98.12 482	90.80 398	97.47 456	96.82 469

PAPM		87.64 498	85.84 505	93.04 467	96.54 426	84.99 476	88.42 530	95.57 436	79.52 531	83.82 543	93.05 487	80.57 463	98.41 466	62.29 548	92.79 530	95.71 498

SIFT-NCMNet		93.23 408	93.19 391	93.34 450	95.31 492	95.59 118	88.29 531	95.60 435	91.60 388	98.43 136	96.34 394	89.80 348	93.57 539	83.82 510	99.57 155	90.85 538

PDCNetPlus		89.44 480	88.28 484	92.93 474	91.75 541	85.02 475	87.69 532	99.67 9	82.69 514	95.89 380	97.02 343	51.15 552	95.27 518	88.79 440	99.86 35	98.50 343

PVSNet	86.72 19	91.10 456	90.97 451	91.49 500	97.56 373	78.04 530	87.17 533	94.60 457	84.65 505	92.34 494	92.20 503	87.37 396	98.47 462	85.17 497	97.69 442	97.96 408

0.4-1-1-0.1		83.64 509	80.50 512	93.08 464	90.32 546	85.42 465	86.48 534	87.71 538	83.60 511	80.38 549	75.45 548	53.19 549	98.91 407	86.46 476	80.88 547	94.93 509

PMMVS2		93.66 389	94.07 366	92.45 488	97.57 371	80.67 519	86.46 535	96.00 422	93.99 296	97.10 281	97.38 311	89.90 346	97.82 491	88.76 441	99.47 209	98.86 286

CHOSEN 280x420		89.98 469	89.19 475	92.37 489	95.60 482	81.13 516	86.22 536	97.09 390	81.44 524	87.44 537	93.15 480	73.99 498	99.47 248	88.69 443	99.07 312	96.52 479

dongtai		63.43 515	63.37 518	63.60 533	83.91 555	53.17 559	85.14 537	43.40 562	77.91 541	80.96 547	79.17 547	36.36 557	77.10 553	37.88 554	45.63 555	60.54 549

kuosan		54.81 517	54.94 520	54.42 534	74.43 556	50.03 560	84.98 538	44.27 561	61.80 549	62.49 555	70.43 551	35.16 558	58.04 555	19.30 556	41.61 556	55.19 550

0.3-1-1-0.015		82.33 512	78.89 514	92.66 482	88.57 548	84.69 482	84.76 539	88.02 537	82.48 517	77.55 551	72.96 549	49.60 553	98.87 415	86.05 480	80.02 549	94.43 512

XFeat-MNN		88.85 487	88.16 486	90.91 507	88.38 549	89.73 353	84.46 540	91.81 503	83.72 510	95.56 396	92.95 489	74.60 497	92.68 543	84.01 505	97.99 418	90.32 544

tmp_tt		57.23 516	62.50 519	41.44 535	34.77 561	49.21 561	83.93 541	60.22 559	15.31 554	71.11 553	79.37 546	70.09 516	44.86 557	64.76 547	82.93 546	30.25 551

0.4-1-1-0.2		82.53 511	79.25 513	92.37 489	88.10 550	83.96 494	83.72 542	88.15 536	82.14 519	78.97 550	72.49 550	53.22 548	98.84 417	85.99 482	80.50 548	94.30 515

PVSNet_0	81.89 21	84.49 506	83.21 510	88.34 522	95.76 475	74.97 545	83.49 543	92.70 490	78.47 538	87.94 535	86.90 542	83.38 445	96.63 511	73.44 543	66.86 552	93.40 520

E-PMN		89.52 478	89.78 467	88.73 520	93.14 532	77.61 533	83.26 544	92.02 500	94.82 254	93.71 456	93.11 481	75.31 493	96.81 506	85.81 484	96.81 475	91.77 528

EMVS		89.06 483	89.22 472	88.61 521	93.00 534	77.34 535	82.91 545	90.92 513	94.64 263	92.63 491	91.81 507	76.30 488	97.02 503	83.83 509	96.90 470	91.48 531

MVE	73.61 22	86.48 505	85.92 504	88.18 524	96.23 442	85.28 470	81.78 546	75.79 553	86.01 486	82.53 545	91.88 506	92.74 284	87.47 550	71.42 546	94.86 520	91.78 527
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
XFeat-NN		84.28 507	83.52 509	86.54 528	85.42 554	86.22 452	78.86 547	88.43 534	79.17 534	90.71 507	89.11 526	69.18 518	85.27 552	76.68 537	94.13 525	88.13 545

GLUNet-SfM		74.13 513	71.69 516	81.46 530	63.16 557	74.17 547	66.80 548	76.03 552	58.10 550	88.60 532	86.99 541	57.56 531	86.25 551	50.03 552	97.91 426	83.95 546

test_method		66.88 514	66.13 517	69.11 532	62.68 558	25.73 564	49.76 549	96.04 421	14.32 555	64.27 554	91.69 509	73.45 505	88.05 549	76.06 538	66.94 551	93.54 518

MVS_clip		42.92 518	47.56 521	28.98 537	56.50 559	40.01 562	44.33 550	12.68 563	16.97 553	74.98 552	81.47 545	34.48 559	17.21 558	43.66 553	63.00 553	29.72 552

VLMVS_CLIP		41.19 519	42.85 522	36.20 536	35.69 560	29.96 563	41.27 551	59.71 560	20.51 552	51.77 556	61.89 552	24.86 560	51.47 556	37.87 555	52.12 554	27.15 553

VLMVS		16.27 522	17.60 525	12.26 538	17.44 563	14.02 565	13.33 552	7.39 564	0.97 559	23.14 558	32.55 555	21.01 561	8.58 559	7.93 558	34.66 558	14.18 554

MVS_baseline		16.43 521	20.39 524	4.55 539	19.03 562	1.35 568	10.44 553	3.04 566	0.59 560	41.63 557	49.56 553	10.52 562	0.00 562	9.18 557	39.56 557	12.29 555

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		24.22 520	32.30 523	0.00 542	0.00 566	0.00 569	0.00 554	98.10 325	0.00 561	0.00 562	95.06 454	97.54 45	0.00 562	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		7.98 525	10.65 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	95.82 165	0.00 562	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

ab-mvs-re		7.91 526	10.55 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	94.94 456	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet1														91.55 379	99.31 271	98.56 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.05 390
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					98.88 151	95.35 137		98.76 217		98.18 179		95.58 180	99.73 101	96.66 122	99.51 190

WAC-MVS						79.32 523								85.41 490

MSC_two_6792asdad				98.22 84	97.75 346	95.34 143		98.16 318					99.75 85	95.87 175	99.51 190	99.57 60

PC_three_1452									87.24 474	98.37 143	97.44 301	97.00 83	96.78 508	92.01 364	99.25 283	99.21 195

No_MVS				98.22 84	97.75 346	95.34 143		98.16 318					99.75 85	95.87 175	99.51 190	99.57 60

test_one_0601					99.05 119	95.50 127		98.87 171	97.21 107	98.03 199	98.30 179	96.93 90

eth-test2					0.00 566

eth-test					0.00 566

ZD-MVS					98.43 244	95.94 102		98.56 257	90.72 415	96.66 322	97.07 339	95.02 208	99.74 95	91.08 387	98.93 331

IU-MVS					99.22 78	95.40 132		98.14 321	85.77 491	98.36 146				95.23 227	99.51 190	99.49 97

test_241102_TWO								98.83 192	96.11 170	98.62 110	98.24 192	96.92 93	99.72 111	95.44 208	99.49 201	99.49 97

test_241102_ONE					99.22 78	95.35 137		98.83 192	96.04 179	99.08 55	98.13 208	97.87 28	99.33 319

test_0728_THIRD									96.62 131	98.40 140	98.28 185	97.10 71	99.71 127	95.70 182	99.62 124	99.58 52

GSMVS																98.06 398

test_part2					99.03 122	96.07 94				98.08 192

sam_mvs1												77.80 477				98.06 398

sam_mvs												77.38 481

MTGPA								98.73 222

test_post											10.87 558	76.83 485	99.07 388

patchmatchnet-post											96.84 359	77.36 482	99.42 274

gm-plane-assit					91.79 540	71.40 553			81.67 521		90.11 523		98.99 399	84.86 500

test9_res														91.29 382	98.89 338	99.00 249

agg_prior2														90.34 417	98.90 334	99.10 231

agg_prior					97.80 334	94.96 164		98.36 289		93.49 466			99.53 224

TestCases				98.06 101	99.08 109	96.16 88		99.16 70	94.35 280	97.78 230	98.07 219	95.84 162	99.12 378	91.41 380	99.42 231	98.91 275

test_prior				97.46 162	97.79 339	94.26 199		98.42 279					99.34 317			98.79 294

新几何1				97.25 182	98.29 258	94.70 173		97.73 354	77.98 539	94.83 420	96.67 372	92.08 308	99.45 263	88.17 453	98.65 377	97.61 436

旧先验1					97.80 334	93.87 211		97.75 353			97.04 342	93.57 258			98.68 372	98.72 311

原ACMM1				96.58 243	98.16 282	92.12 277		98.15 320	85.90 489	93.49 466	96.43 386	92.47 299	99.38 299	87.66 459	98.62 379	98.23 379

testdata2													99.46 255	87.84 454

segment_acmp												95.34 191

testdata				95.70 327	98.16 282	90.58 323		97.72 355	80.38 528	95.62 391	97.02 343	92.06 309	98.98 401	89.06 438	98.52 386	97.54 440

test12				97.46 162	97.61 368	94.07 203		97.78 352		93.57 464		93.31 266	99.42 274		98.78 354	98.89 279

plane_prior7					98.70 190	94.67 174

plane_prior6					98.38 250	94.37 191						91.91 314

plane_prior5								98.75 218					99.46 255	92.59 354	99.20 288	99.28 175

plane_prior4											96.77 365

plane_prior3						94.51 184			95.29 230	96.16 361

plane_prior1					98.49 233

n2								0.00 568

nn								0.00 568

door-mid								98.17 314

lessismore_v0				97.05 199	99.36 54	92.12 277		84.07 546		98.77 95	98.98 72	85.36 423	99.74 95	97.34 94	99.37 245	99.30 167

LGP-MVS_train				98.74 37	99.15 96	97.02 46		99.02 123	95.15 235	98.34 150	98.23 194	97.91 25	99.70 136	94.41 286	99.73 86	99.50 89

test11								98.08 328

door								97.81 351

HQP5-MVS						92.47 262

BP-MVS														90.51 412

HQP4-MVS										92.87 482			99.23 356			99.06 239

HQP3-MVS								98.43 276							98.74 364

HQP2-MVS												90.33 337

NP-MVS					98.14 286	93.72 217					95.08 452

ACMMP++_ref															99.52 184

ACMMP++															99.55 167

Test By Simon												94.51 228

ITE_SJBPF				97.85 118	98.64 197	96.66 61		98.51 262	95.63 208	97.22 268	97.30 319	95.52 182	98.55 453	90.97 391	98.90 334	98.34 364

DeepMVS_CX				77.17 531	90.94 543	85.28 470		74.08 556	52.51 551	80.87 548	88.03 533	75.25 494	70.63 554	59.23 550	84.94 544	75.62 547

High-resolution multi-view benchmark