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 47	99.69 2	99.57 20	99.02 21	99.62 15	99.36 26	98.53 11	99.52 225	98.58 42	99.95 5	99.66 36
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 39	99.08 16	97.87 209	99.67 5	96.47 126	99.92 5	97.88 64	99.98 2	99.85 6

mvs5depth		98.06 58	98.58 29	96.51 238	98.97 132	89.65 315	99.43 4	99.81 2	99.30 9	98.36 138	99.86 2	93.15 258	99.88 22	98.50 44	99.84 49	99.99 1

TDRefinement		98.90 8	98.86 11	99.02 9	99.54 28	98.06 8	99.34 5	99.44 32	98.85 27	99.00 62	99.20 40	97.42 51	99.59 200	97.21 96	99.76 70	99.40 134

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 45	99.77 5	96.34 69	99.18 6	99.20 58	99.67 3	99.73 6	99.65 8	99.15 3	99.86 27	97.22 95	99.92 15	99.77 15

OurMVSNet-221017-0		98.61 19	98.61 27	98.63 47	99.77 5	96.35 68	99.17 7	99.05 106	98.05 60	99.61 16	99.52 12	93.72 245	99.88 22	98.72 38	99.88 28	99.65 39

DVP-MVS++		97.96 67	97.90 85	98.12 96	97.75 330	95.40 112	99.03 8	98.89 156	96.62 125	98.62 105	98.30 172	96.97 84	99.75 84	95.70 173	99.25 258	99.21 188

FOURS1					99.59 18	98.20 7	99.03 8	99.25 50	98.96 24	98.87 79

tt0320		99.07 6	99.29 4	98.43 62	99.55 24	95.92 87	98.97 10	99.53 26	99.67 3	99.79 2	99.71 3	98.33 14	99.78 58	98.11 52	99.92 15	99.57 58

tt0320-xc		99.10 4	99.31 3	98.49 57	99.57 20	96.09 79	98.91 11	99.55 24	99.67 3	99.78 3	99.69 4	98.63 10	99.77 69	98.02 58	99.93 11	99.60 46

sc_t1		99.09 5	99.28 5	98.53 54	99.72 8	96.21 73	98.87 12	99.19 60	99.71 2	99.76 4	99.65 8	98.64 9	99.79 53	98.07 56	99.90 25	99.58 50

pmmvs6		99.07 6	99.24 7	98.56 51	99.81 2	96.38 65	98.87 12	99.30 41	99.01 22	99.63 14	99.66 6	99.27 2	99.68 150	97.75 73	99.89 26	99.62 44

Anonymous20231211		98.55 24	98.76 16	97.94 111	98.79 163	94.37 161	98.84 14	99.15 72	99.37 6	99.67 10	99.43 20	95.61 173	99.72 110	98.12 51	99.86 35	99.73 26

mmtdpeth		98.33 36	98.53 31	97.71 125	99.07 111	93.44 199	98.80 15	99.78 4	99.10 15	96.61 300	99.63 10	95.42 182	99.73 100	98.53 43	99.86 35	99.95 2

MIMVSNet1		98.51 28	98.45 36	98.67 43	99.72 8	96.71 53	98.76 16	98.89 156	98.49 40	99.38 31	99.14 52	95.44 181	99.84 33	96.47 128	99.80 62	99.47 105

EPP-MVSNet		96.84 192	96.58 214	97.65 133	99.18 91	93.78 185	98.68 17	96.34 383	97.91 63	97.30 241	98.06 216	88.46 345	99.85 30	93.85 296	99.40 218	99.32 157

v7n		98.73 14	98.99 8	97.95 110	99.64 14	94.20 169	98.67 18	99.14 75	99.08 16	99.42 28	99.23 38	96.53 121	99.91 13	99.27 10	99.93 11	99.73 26

MVSFormer		96.14 243	96.36 235	95.49 324	97.68 338	87.81 375	98.67 18	99.02 119	96.50 136	94.48 391	96.15 376	86.90 365	99.92 5	98.73 36	99.13 275	98.74 293

test_djsdf		98.73 14	98.74 19	98.69 42	99.63 15	96.30 71	98.67 18	99.02 119	96.50 136	99.32 36	99.44 19	97.43 50	99.92 5	98.73 36	99.95 5	99.86 5

tt0805		97.44 143	97.56 135	97.11 182	99.55 24	96.36 67	98.66 21	95.66 397	98.31 47	97.09 262	95.45 403	97.17 66	98.50 438	98.67 39	97.45 408	96.48 453

anonymousdsp		98.72 17	98.63 23	98.99 13	99.62 16	97.29 40	98.65 22	99.19 60	95.62 203	99.35 35	99.37 24	97.38 52	99.90 17	98.59 41	99.91 19	99.77 15

HPM-MVS		98.11 53	97.83 97	98.92 24	99.42 45	97.46 34	98.57 23	99.05 106	95.43 217	97.41 238	97.50 281	97.98 23	99.79 53	95.58 187	99.57 143	99.50 87
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
IS-MVSNet		96.93 184	96.68 205	97.70 127	99.25 71	94.00 176	98.57 23	96.74 377	98.36 45	98.14 173	97.98 227	88.23 349	99.71 126	93.10 322	99.72 88	99.38 142

WR-MVS_H		98.65 18	98.62 25	98.75 34	99.51 32	96.61 59	98.55 25	99.17 65	99.05 19	99.17 46	98.79 91	95.47 179	99.89 20	97.95 62	99.91 19	99.75 24

FE-MVS		92.95 377	92.22 382	95.11 341	97.21 382	88.33 357	98.54 26	93.66 431	89.91 396	96.21 327	98.14 198	70.33 466	99.50 230	87.79 421	98.24 368	97.51 417

test2506		89.86 425	89.16 430	91.97 448	98.95 133	76.83 485	98.54 26	61.07 503	96.20 154	97.07 263	99.16 49	55.19 492	99.69 143	96.43 133	99.83 54	99.38 142

mvs_tets		98.90 8	98.94 9	98.75 34	99.69 11	96.48 63	98.54 26	99.22 55	96.23 152	99.71 7	99.48 15	98.77 7	99.93 3	98.89 30	99.95 5	99.84 8

CS-MVS		98.09 54	98.01 72	98.32 72	98.45 231	96.69 55	98.52 29	99.69 8	98.07 59	96.07 334	97.19 306	96.88 97	99.86 27	97.50 84	99.73 83	98.41 332

Gipuma		98.07 57	98.31 49	97.36 163	99.76 7	96.28 72	98.51 30	99.10 86	98.76 29	96.79 283	99.34 29	96.61 115	98.82 403	96.38 135	99.50 181	96.98 432
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	95.47 111	98.49 31	99.13 77	99.22 12	99.22 43	98.96 74	97.35 53	99.92 5	97.79 70	99.93 11	99.79 13

3Dnovator	96.53 2	97.61 121	97.64 123	97.50 147	97.74 333	93.65 192	98.49 31	98.88 163	96.86 117	97.11 256	98.55 132	95.82 160	99.73 100	95.94 161	99.42 213	99.13 208

DTE-MVSNet		98.79 11	98.86 11	98.59 49	99.55 24	96.12 77	98.48 33	99.10 86	99.36 7	99.29 38	99.06 61	97.27 57	99.93 3	97.71 75	99.91 19	99.70 31

jajsoiax		98.77 12	98.79 15	98.74 37	99.66 13	96.48 63	98.45 34	99.12 78	95.83 193	99.67 10	99.37 24	98.25 17	99.92 5	98.77 33	99.94 8	99.82 9

PEN-MVS		98.75 13	98.85 13	98.44 61	99.58 19	95.67 98	98.45 34	99.15 72	99.33 8	99.30 37	99.00 68	97.27 57	99.92 5	97.64 79	99.92 15	99.75 24

LS3D		97.77 103	97.50 145	98.57 50	96.24 410	97.58 27	98.45 34	98.85 172	98.58 36	97.51 227	97.94 231	95.74 167	99.63 182	95.19 219	98.97 294	98.51 324

balanced_ft_v1		96.29 233	96.60 212	95.38 332	96.77 397	88.73 346	98.44 37	98.44 254	94.97 240	95.91 340	98.77 95	91.03 309	99.75 84	96.16 148	98.91 305	97.65 408

SPE-MVS-test		97.91 83	97.84 94	98.14 94	98.52 215	96.03 84	98.38 38	99.67 9	98.11 57	95.50 362	96.92 332	96.81 103	99.87 25	96.87 113	99.76 70	98.51 324

FC-MVSNet-test		98.16 48	98.37 40	97.56 138	99.49 36	93.10 210	98.35 39	99.21 56	98.43 42	98.89 74	98.83 90	94.30 229	99.81 43	97.87 65	99.91 19	99.77 15

HPM-MVS_fast		98.32 38	98.13 57	98.88 26	99.54 28	97.48 33	98.35 39	99.03 115	95.88 188	97.88 206	98.22 189	98.15 20	99.74 94	96.50 127	99.62 115	99.42 127

ab-mvs		96.59 213	96.59 213	96.60 227	98.64 189	92.21 235	98.35 39	97.67 329	94.45 267	96.99 269	98.79 91	94.96 205	99.49 236	90.39 386	99.07 286	98.08 369

EGC-MVSNET		83.08 458	77.93 463	98.53 54	99.57 20	97.55 29	98.33 42	98.57 242	4.71 500	10.38 501	98.90 85	95.60 174	99.50 230	95.69 175	99.61 125	98.55 317

test1111		94.53 329	94.81 304	93.72 401	99.06 113	81.94 457	98.31 43	83.87 493	96.37 143	98.49 120	99.17 48	81.49 408	99.73 100	96.64 117	99.86 35	99.49 95

ECVR-MVS		94.37 335	94.48 322	94.05 396	98.95 133	83.10 447	98.31 43	82.48 495	96.20 154	98.23 162	99.16 49	81.18 411	99.66 168	95.95 160	99.83 54	99.38 142

EC-MVSNet		97.90 85	97.94 84	97.79 119	98.66 188	95.14 133	98.31 43	99.66 11	97.57 78	95.95 338	97.01 325	96.99 81	99.82 38	97.66 78	99.64 110	98.39 335

pm-mvs1		98.47 31	98.67 21	97.86 115	99.52 31	94.58 151	98.28 46	99.00 131	97.57 78	99.27 39	99.22 39	98.32 15	99.50 230	97.09 103	99.75 80	99.50 87

SixPastTwentyTwo		97.49 137	97.57 134	97.26 172	99.56 22	92.33 229	98.28 46	96.97 368	98.30 49	99.45 24	99.35 28	88.43 346	99.89 20	98.01 59	99.76 70	99.54 72

FA-MVS(test-final)		94.91 305	94.89 296	94.99 349	97.51 358	88.11 368	98.27 48	95.20 412	92.40 345	96.68 292	98.60 125	83.44 397	99.28 334	93.34 314	98.53 349	97.59 414

CP-MVSNet		98.42 33	98.46 33	98.30 75	99.46 40	95.22 130	98.27 48	98.84 176	99.05 19	99.01 60	98.65 118	95.37 184	99.90 17	97.57 81	99.91 19	99.77 15

GG-mvs-BLEND				90.60 459	91.00 491	84.21 440	98.23 50	72.63 502		82.76 490	84.11 491	56.14 485	96.79 479	72.20 490	92.09 479	90.78 491

GBi-Net		96.99 177	96.80 198	97.56 138	97.96 291	93.67 188	98.23 50	98.66 227	95.59 205	97.99 191	99.19 41	89.51 335	99.73 100	94.60 262	99.44 200	99.30 162

test1		96.99 177	96.80 198	97.56 138	97.96 291	93.67 188	98.23 50	98.66 227	95.59 205	97.99 191	99.19 41	89.51 335	99.73 100	94.60 262	99.44 200	99.30 162

FMVSNet1		97.95 71	98.08 63	97.56 138	99.14 103	93.67 188	98.23 50	98.66 227	97.41 91	99.00 62	99.19 41	95.47 179	99.73 100	95.83 170	99.76 70	99.30 162

ACMH	93.61 9	98.44 32	98.76 16	97.51 143	99.43 43	93.54 194	98.23 50	99.05 106	97.40 92	99.37 32	99.08 60	98.79 6	99.47 245	97.74 74	99.71 91	99.50 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TransMVSNet (Re)		98.38 35	98.67 21	97.51 143	99.51 32	93.39 203	98.20 55	98.87 165	98.23 53	99.48 21	99.27 34	98.47 13	99.55 216	96.52 126	99.53 163	99.60 46

gg-mvs-nofinetune		88.28 443	86.96 448	92.23 445	92.84 487	84.44 435	98.19 56	74.60 499	99.08 16	87.01 486	99.47 16	56.93 482	98.23 456	78.91 478	95.61 459	94.01 481

QAPM		95.88 255	95.57 275	96.80 213	97.90 298	91.84 252	98.18 57	98.73 209	88.41 415	96.42 312	98.13 200	94.73 207	99.75 84	88.72 410	98.94 300	98.81 276

NR-MVSNet		97.96 67	97.86 92	98.26 78	98.73 173	95.54 104	98.14 58	98.73 209	97.79 65	99.42 28	97.83 243	94.40 225	99.78 58	95.91 164	99.76 70	99.46 107

MIMVSNet		93.42 365	92.86 365	95.10 343	98.17 268	88.19 360	98.13 59	93.69 428	92.07 347	95.04 376	98.21 190	80.95 414	99.03 381	81.42 470	98.06 375	98.07 371

PS-MVSNAJss		98.53 27	98.63 23	98.21 86	99.68 12	94.82 141	98.10 60	99.21 56	96.91 115	99.75 5	99.45 18	95.82 160	99.92 5	98.80 32	99.96 4	99.89 4

ACMMP		98.05 59	97.75 110	98.93 21	99.23 75	97.60 25	98.09 61	98.96 142	95.75 198	97.91 203	98.06 216	96.89 95	99.76 76	95.32 211	99.57 143	99.43 125
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 65	98.08 62	99.09 91	98.46 41	98.68 102	98.73 101	97.88 27	99.80 50	97.43 87	99.59 135	99.48 101

APDe-MVS		98.14 49	98.03 69	98.47 60	98.72 176	96.04 81	98.07 63	99.10 86	95.96 180	98.59 110	98.69 112	96.94 86	99.81 43	96.64 117	99.58 140	99.57 58
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 98	99.33 60	95.21 132	98.04 64	99.46 30	97.32 98	97.82 213	99.11 54	96.75 106	99.86 27	97.84 67	99.36 228	99.15 200
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	96.13 3	97.73 106	97.59 132	98.15 93	98.11 278	95.60 100	98.04 64	98.70 218	98.13 56	96.93 275	98.45 144	95.30 188	99.62 187	95.64 180	98.96 297	99.24 182

MVSMamba_PlusPlus		97.43 145	97.98 75	95.78 298	98.88 149	89.70 312	98.03 66	98.85 172	99.18 13	96.84 282	99.12 53	93.04 262	99.91 13	98.38 47	99.55 153	97.73 403

FIs		97.93 78	98.07 64	97.48 151	99.38 52	92.95 214	98.03 66	99.11 81	98.04 61	98.62 105	98.66 114	93.75 244	99.78 58	97.23 94	99.84 49	99.73 26

sd_testset		97.97 65	98.12 58	97.51 143	99.41 46	93.44 199	97.96 68	98.25 278	98.58 36	98.78 87	99.39 21	98.21 18	99.56 211	92.65 328	99.86 35	99.52 80

COLMAP_ROB	94.48 6	98.25 44	98.11 60	98.64 46	99.21 85	97.35 38	97.96 68	99.16 66	98.34 46	98.78 87	98.52 135	97.32 54	99.45 260	94.08 282	99.67 104	99.13 208
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
balanced_conf03		96.88 189	97.29 159	95.63 311	97.66 343	89.47 320	97.95 70	98.89 156	95.94 183	97.77 216	98.55 132	92.23 288	99.68 150	97.05 107	99.61 125	97.73 403

usedtu_dtu_shiyan2		97.54 132	97.26 162	98.37 68	99.54 28	96.04 81	97.94 71	98.06 308	97.36 96	98.62 105	98.20 191	95.52 176	99.73 100	90.90 365	99.18 268	99.33 155

VDDNet		96.98 180	96.84 194	97.41 159	99.40 49	93.26 207	97.94 71	95.31 409	99.26 11	98.39 134	99.18 45	87.85 356	99.62 187	95.13 229	99.09 283	99.35 154

CP-MVS		97.92 79	97.56 135	98.99 13	98.99 128	97.82 18	97.93 73	98.96 142	96.11 165	96.89 278	97.45 283	96.85 100	99.78 58	95.19 219	99.63 112	99.38 142

mvsmamba		94.91 305	94.41 327	96.40 257	97.65 345	91.30 265	97.92 74	95.32 408	91.50 366	95.54 360	98.38 154	83.06 400	99.68 150	92.46 333	97.84 384	98.23 357

ANet_high		98.31 39	98.94 9	96.41 254	99.33 60	89.64 316	97.92 74	99.56 22	99.27 10	99.66 12	99.50 14	97.67 36	99.83 35	97.55 82	99.98 2	99.77 15

nrg030		98.54 25	98.62 25	98.32 72	99.22 78	95.66 99	97.90 76	99.08 95	98.31 47	99.02 59	98.74 100	97.68 35	99.61 195	97.77 72	99.85 46	99.70 31

ambc				96.56 234	98.23 258	91.68 256	97.88 77	98.13 299		98.42 129	98.56 131	94.22 231	99.04 378	94.05 285	99.35 233	98.95 250

Anonymous20240529		97.96 67	98.04 68	97.71 125	98.69 185	94.28 167	97.86 78	98.31 275	98.79 28	99.23 42	98.86 89	95.76 166	99.61 195	95.49 190	99.36 228	99.23 184

sasdasda		97.23 161	97.21 167	97.30 167	97.65 345	94.39 158	97.84 79	99.05 106	97.42 87	96.68 292	93.85 430	97.63 40	99.33 313	96.29 141	98.47 355	98.18 363

canonicalmvs		97.23 161	97.21 167	97.30 167	97.65 345	94.39 158	97.84 79	99.05 106	97.42 87	96.68 292	93.85 430	97.63 40	99.33 313	96.29 141	98.47 355	98.18 363

tfpnnormal		97.72 108	97.97 76	96.94 198	99.26 68	92.23 234	97.83 81	98.45 251	98.25 52	99.13 50	98.66 114	96.65 112	99.69 143	93.92 293	99.62 115	98.91 261

MGCFI-Net		97.20 163	97.23 165	97.08 187	97.68 338	93.71 187	97.79 82	99.09 91	97.40 92	96.59 301	93.96 428	97.67 36	99.35 308	96.43 133	98.50 354	98.17 365

Anonymous20240521		97.07 173	97.51 143	95.76 299	99.35 58	88.18 363	97.78 83	98.40 261	97.11 104	98.34 142	99.04 63	89.58 331	99.79 53	98.09 54	99.93 11	99.30 162

XVS		97.96 67	97.63 125	98.94 18	99.15 96	97.66 22	97.77 84	98.83 183	97.42 87	96.32 317	97.64 265	96.49 124	99.72 110	95.66 178	99.37 224	99.45 111

X-MVStestdata		92.86 378	90.83 410	98.94 18	99.15 96	97.66 22	97.77 84	98.83 183	97.42 87	96.32 317	36.50 498	96.49 124	99.72 110	95.66 178	99.37 224	99.45 111

VPA-MVSNet		98.27 42	98.46 33	97.70 127	99.06 113	93.80 183	97.76 86	99.00 131	98.40 44	99.07 56	98.98 71	96.89 95	99.75 84	97.19 99	99.79 64	99.55 70

MED-MVS test				98.17 87	99.36 54	95.35 117	97.75 87	99.30 41	94.02 285	98.88 76	97.54 273		99.73 100	95.36 206	99.53 163	99.44 121

MED-MVS		97.95 71	97.87 91	98.17 87	99.36 54	95.35 117	97.75 87	99.30 41	96.16 163	98.88 76	97.54 273	96.99 81	99.73 100	95.36 206	99.53 163	99.44 121

TestfortrainingZip a		97.99 63	97.86 92	98.38 67	99.36 54	95.77 93	97.75 87	99.30 41	94.02 285	98.88 76	97.54 273	96.99 81	99.73 100	97.40 88	99.53 163	99.65 39

TestfortrainingZip				97.39 161	97.24 381	94.58 151	97.75 87	97.64 337	96.08 169	96.48 309	96.31 369	92.56 277	99.27 337		96.62 432	98.31 346

dcpmvs_2		97.12 170	97.99 74	94.51 378	99.11 105	84.00 441	97.75 87	99.65 12	97.38 94	99.14 49	98.42 148	95.16 195	99.96 2	95.52 189	99.78 68	99.58 50

UGNet		96.81 197	96.56 217	97.58 137	96.64 400	93.84 182	97.75 87	97.12 356	96.47 140	93.62 418	98.88 87	93.22 256	99.53 222	95.61 184	99.69 97	99.36 150
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 83	97.53 140	99.04 7	99.22 78	97.87 17	97.74 93	98.78 201	96.04 174	97.10 257	97.73 259	96.53 121	99.78 58	95.16 224	99.50 181	99.46 107

OpenMVS	94.22 8	95.48 278	95.20 280	96.32 263	97.16 384	91.96 248	97.74 93	98.84 176	87.26 427	94.36 393	98.01 223	93.95 238	99.67 160	90.70 377	98.75 329	97.35 424

RRT-MVS		95.78 260	96.25 240	94.35 386	96.68 399	84.47 434	97.72 95	99.11 81	97.23 101	97.27 243	98.72 102	86.39 371	99.79 53	95.49 190	97.67 396	98.80 277

testf1		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 34	97.69 74	98.92 71	98.77 95	97.80 30	99.25 342	96.27 143	99.69 97	98.76 291

APD_test2		98.57 21	98.45 36	98.93 21	99.79 3	98.78 2	97.69 96	99.42 34	97.69 74	98.92 71	98.77 95	97.80 30	99.25 342	96.27 143	99.69 97	98.76 291

MonoMVSNet		93.30 371	93.96 345	91.33 455	94.14 475	81.33 462	97.68 98	96.69 379	95.38 219	96.32 317	98.42 148	84.12 393	96.76 481	90.78 370	92.12 478	95.89 460

MSP-MVS		97.45 141	96.92 189	99.03 8	99.26 68	97.70 21	97.66 99	98.89 156	95.65 201	98.51 117	96.46 360	92.15 290	99.81 43	95.14 227	98.58 348	99.58 50
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		95.32 288	94.88 298	96.62 224	98.03 281	91.47 260	97.65 100	90.72 467	99.11 14	97.89 205	98.31 166	79.20 423	99.48 239	93.91 294	99.12 278	98.93 257

K. test v3		96.44 225	96.28 239	96.95 197	99.41 46	91.53 257	97.65 100	90.31 472	98.89 26	98.93 70	99.36 26	84.57 389	99.92 5	97.81 68	99.56 146	99.39 140

TSAR-MVS + MP.		97.42 147	97.23 165	98.00 107	99.38 52	95.00 137	97.63 102	98.20 285	93.00 327	98.16 170	98.06 216	95.89 155	99.72 110	95.67 177	99.10 282	99.28 170
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_fmvs3		97.38 150	97.56 135	96.84 210	98.63 198	92.81 217	97.60 103	99.61 17	90.87 381	98.76 92	99.66 6	94.03 235	97.90 464	99.24 11	99.68 101	99.81 10

region2R		97.92 79	97.59 132	98.92 24	99.22 78	97.55 29	97.60 103	98.84 176	96.00 177	97.22 246	97.62 267	96.87 99	99.76 76	95.48 194	99.43 210	99.46 107

HFP-MVS		97.94 75	97.64 123	98.83 28	99.15 96	97.50 32	97.59 105	98.84 176	96.05 172	97.49 229	97.54 273	97.07 72	99.70 135	95.61 184	99.46 194	99.30 162

ACMMPR		97.95 71	97.62 127	98.94 18	99.20 87	97.56 28	97.59 105	98.83 183	96.05 172	97.46 235	97.63 266	96.77 105	99.76 76	95.61 184	99.46 194	99.49 95

RPSCF		97.87 90	97.51 143	98.95 17	99.15 96	98.43 6	97.56 107	99.06 100	96.19 158	98.48 122	98.70 111	94.72 208	99.24 346	94.37 271	99.33 243	99.17 196

KD-MVS_self_test		97.86 92	98.07 64	97.25 173	99.22 78	92.81 217	97.55 108	98.94 147	97.10 105	98.85 80	98.88 87	95.03 200	99.67 160	97.39 90	99.65 108	99.26 175

SR-MVS-dyc-post		98.14 49	97.84 94	99.02 9	98.81 157	98.05 9	97.55 108	98.86 168	97.77 66	98.20 164	98.07 211	96.60 117	99.76 76	95.49 190	99.20 263	99.26 175

RE-MVS-def			97.88 90		98.81 157	98.05 9	97.55 108	98.86 168	97.77 66	98.20 164	98.07 211	96.94 86		95.49 190	99.20 263	99.26 175

APD-MVS_3200maxsize		98.13 52	97.90 85	98.79 32	98.79 163	97.31 39	97.55 108	98.92 150	97.72 71	98.25 160	98.13 200	97.10 68	99.75 84	95.44 198	99.24 261	99.32 157

ACMH+	93.58 10	98.23 45	98.31 49	97.98 109	99.39 50	95.22 130	97.55 108	99.20 58	98.21 54	99.25 41	98.51 137	98.21 18	99.40 282	94.79 252	99.72 88	99.32 157

Vis-MVSNet (Re-imp)		95.11 297	94.85 300	95.87 295	99.12 104	89.17 326	97.54 113	94.92 417	96.50 136	96.58 302	97.27 301	83.64 396	99.48 239	88.42 415	99.67 104	98.97 247

MP-MVS		97.64 117	97.18 171	99.00 12	99.32 62	97.77 20	97.49 114	98.73 209	96.27 147	95.59 358	97.75 255	96.30 138	99.78 58	93.70 305	99.48 189	99.45 111
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SD_0403		93.73 355	93.43 353	94.64 367	97.85 300	86.35 402	97.47 115	97.94 312	93.50 303	93.71 414	96.73 345	93.77 243	98.84 401	73.48 488	96.39 438	98.72 296

ZNCC-MVS		97.92 79	97.62 127	98.83 28	99.32 62	97.24 42	97.45 116	98.84 176	95.76 196	96.93 275	97.43 285	97.26 61	99.79 53	96.06 150	99.53 163	99.45 111

tttt0517		93.31 370	92.56 376	95.57 315	98.71 180	87.86 372	97.44 117	87.17 487	95.79 195	97.47 234	96.84 336	64.12 473	99.81 43	96.20 146	99.32 245	99.02 236

v10		97.55 131	97.97 76	96.31 264	98.60 202	89.64 316	97.44 117	99.02 119	96.60 127	98.72 97	99.16 49	93.48 251	99.72 110	98.76 34	99.92 15	99.58 50

v8		97.60 122	98.06 67	96.23 269	98.71 180	89.44 321	97.43 119	98.82 191	97.29 100	98.74 94	99.10 56	93.86 239	99.68 150	98.61 40	99.94 8	99.56 66

PMVS	89.60 17	96.71 208	96.97 183	95.95 290	99.51 32	97.81 19	97.42 120	97.49 343	97.93 62	95.95 338	98.58 127	96.88 97	96.91 477	89.59 398	99.36 228	93.12 486
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
usedtu_blend_shiyan5		93.74 354	93.08 359	95.71 306	94.99 457	89.17 326	97.38 121	98.93 149	96.40 141	94.75 381	87.24 485	80.36 417	99.40 282	91.84 343	95.85 448	98.55 317

SR-MVS		98.00 62	97.66 119	99.01 11	98.77 169	97.93 14	97.38 121	98.83 183	97.32 98	98.06 183	97.85 240	96.65 112	99.77 69	95.00 238	99.11 279	99.32 157

Elysia		98.19 46	98.37 40	97.66 131	99.28 64	93.52 195	97.35 123	98.90 152	98.63 32	99.45 24	98.32 164	94.31 227	99.91 13	99.19 14	99.88 28	99.54 72

StellarMVS		98.19 46	98.37 40	97.66 131	99.28 64	93.52 195	97.35 123	98.90 152	98.63 32	99.45 24	98.32 164	94.31 227	99.91 13	99.19 14	99.88 28	99.54 72

FMVSNet5		93.39 366	92.35 379	96.50 239	95.83 431	90.81 281	97.31 125	98.27 276	92.74 337	96.27 322	98.28 177	62.23 475	99.67 160	90.86 366	99.36 228	99.03 233

HY-MVS	91.43 15	92.58 385	91.81 388	94.90 354	96.49 404	88.87 340	97.31 125	94.62 419	85.92 442	90.50 463	96.84 336	85.05 384	99.40 282	83.77 462	95.78 456	96.43 454

CSCG		97.40 148	97.30 158	97.69 129	98.95 133	94.83 140	97.28 127	98.99 135	96.35 146	98.13 174	95.95 387	95.99 151	99.66 168	94.36 273	99.73 83	98.59 313

MTAPA		98.14 49	97.84 94	99.06 6	99.44 42	97.90 15	97.25 128	98.73 209	97.69 74	97.90 204	97.96 228	95.81 164	99.82 38	96.13 149	99.61 125	99.45 111

CPTT-MVS		96.69 209	96.08 248	98.49 57	98.89 148	96.64 58	97.25 128	98.77 202	92.89 334	96.01 337	97.13 313	92.23 288	99.67 160	92.24 335	99.34 238	99.17 196

EU-MVSNet		94.25 336	94.47 323	93.60 404	98.14 274	82.60 452	97.24 130	92.72 443	85.08 451	98.48 122	98.94 77	82.59 404	98.76 411	97.47 86	99.53 163	99.44 121

XXY-MVS		97.54 132	97.70 112	97.07 188	99.46 40	92.21 235	97.22 131	99.00 131	94.93 243	98.58 111	98.92 81	97.31 55	99.41 280	94.44 266	99.43 210	99.59 49

APD_test1		97.95 71	97.68 116	98.75 34	99.60 17	98.60 5	97.21 132	99.08 95	96.57 134	98.07 182	98.38 154	96.22 143	99.14 360	94.71 259	99.31 248	98.52 323

GST-MVS		97.82 97	97.49 147	98.81 30	99.23 75	97.25 41	97.16 133	98.79 197	95.96 180	97.53 225	97.40 287	96.93 88	99.77 69	95.04 233	99.35 233	99.42 127

SteuartSystems-ACMMP		98.02 61	97.76 108	98.79 32	99.43 43	97.21 44	97.15 134	98.90 152	96.58 131	98.08 180	97.87 239	97.02 79	99.76 76	95.25 214	99.59 135	99.40 134
Skip Steuart: Steuart Systems R&D Blog.
FMVSNet2		96.72 206	96.67 206	96.87 206	97.96 291	91.88 250	97.15 134	98.06 308	95.59 205	98.50 119	98.62 120	89.51 335	99.65 171	94.99 244	99.60 132	99.07 226

AllTest		97.20 163	96.92 189	98.06 100	99.08 109	96.16 75	97.14 136	99.16 66	94.35 271	97.78 214	98.07 211	95.84 157	99.12 364	91.41 351	99.42 213	98.91 261

DP-MVS		97.87 90	97.89 88	97.81 118	98.62 200	94.82 141	97.13 137	98.79 197	98.98 23	98.74 94	98.49 138	95.80 165	99.49 236	95.04 233	99.44 200	99.11 219

GeoE		97.75 104	97.70 112	97.89 113	98.88 149	94.53 153	97.10 138	98.98 138	95.75 198	97.62 220	97.59 269	97.61 42	99.77 69	96.34 138	99.44 200	99.36 150

PGM-MVS		97.88 88	97.52 141	98.96 16	99.20 87	97.62 24	97.09 139	99.06 100	95.45 213	97.55 224	97.94 231	97.11 67	99.78 58	94.77 255	99.46 194	99.48 101

LPG-MVS_test		97.94 75	97.67 117	98.74 37	99.15 96	97.02 45	97.09 139	99.02 119	95.15 228	98.34 142	98.23 186	97.91 25	99.70 135	94.41 268	99.73 83	99.50 87

SF-MVS		97.60 122	97.39 150	98.22 83	98.93 140	95.69 96	97.05 141	99.10 86	95.32 221	97.83 212	97.88 236	96.44 129	99.72 110	94.59 265	99.39 222	99.25 181

FE-MVSNET2		97.69 110	97.97 76	96.85 207	99.19 89	91.46 261	97.04 142	99.11 81	95.85 191	98.73 96	99.02 66	96.66 109	99.68 150	96.31 140	99.86 35	99.40 134

reproduce_model		98.54 25	98.33 47	99.15 3	99.06 113	98.04 11	97.04 142	99.09 91	98.42 43	99.03 57	98.71 109	96.93 88	99.83 35	97.09 103	99.63 112	99.56 66

VDD-MVS		97.37 152	97.25 163	97.74 123	98.69 185	94.50 156	97.04 142	95.61 401	98.59 35	98.51 117	98.72 102	92.54 281	99.58 203	96.02 155	99.49 184	99.12 214

wuyk23d		93.25 373	95.20 280	87.40 476	96.07 422	95.38 114	97.04 142	94.97 415	95.33 220	99.70 9	98.11 205	98.14 21	91.94 494	77.76 482	99.68 101	74.89 494

LCM-MVSNet-Re		97.33 155	97.33 156	97.32 166	98.13 277	93.79 184	96.99 146	99.65 12	96.74 122	99.47 23	98.93 78	96.91 92	99.84 33	90.11 389	99.06 289	98.32 344

MAR-MVS		94.21 339	93.03 361	97.76 122	96.94 393	97.44 36	96.97 147	97.15 354	87.89 424	92.00 452	92.73 447	92.14 291	99.12 364	83.92 459	97.51 404	96.73 446
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		95.67 268	95.89 261	95.03 346	98.18 265	89.89 308	96.94 148	99.28 46	88.25 419	98.20 164	98.92 81	86.69 368	97.19 472	97.70 77	98.82 318	98.00 383

KinetiMVS		97.82 97	98.02 70	97.24 175	99.24 72	92.32 231	96.92 149	98.38 264	98.56 39	99.03 57	98.33 161	93.22 256	99.83 35	98.74 35	99.71 91	99.57 58

SDMVSNet		97.97 65	98.26 55	97.11 182	99.41 46	92.21 235	96.92 149	98.60 235	98.58 36	98.78 87	99.39 21	97.80 30	99.62 187	94.98 245	99.86 35	99.52 80

h-mvs33		96.29 233	95.63 273	98.26 78	98.50 223	96.11 78	96.90 151	97.09 360	96.58 131	97.21 248	98.19 192	84.14 391	99.78 58	95.89 165	96.17 445	98.89 265

test0726					99.24 72	95.51 106	96.89 152	98.89 156	95.92 185	98.64 103	98.31 166	97.06 73

NormalMVS		96.87 190	96.39 232	98.30 75	99.48 37	95.57 101	96.87 153	98.90 152	96.94 113	96.85 280	97.88 236	85.36 381	99.76 76	95.63 181	99.59 135	99.57 58

SymmetryMVS		96.43 227	95.85 263	98.17 87	98.58 206	95.57 101	96.87 153	95.29 410	96.94 113	96.85 280	97.88 236	85.36 381	99.76 76	95.63 181	99.27 254	99.19 192

baseline		97.44 143	97.78 106	96.43 249	98.52 215	90.75 282	96.84 155	99.03 115	96.51 135	97.86 210	98.02 221	96.67 108	99.36 304	97.09 103	99.47 191	99.19 192

API-MVS		95.09 299	95.01 290	95.31 333	96.61 401	94.02 175	96.83 156	97.18 353	95.60 204	95.79 349	94.33 424	94.54 220	98.37 449	85.70 444	98.52 350	93.52 483

test_vis3_rt		97.04 174	96.98 182	97.23 176	98.44 232	95.88 88	96.82 157	99.67 9	90.30 390	99.27 39	99.33 31	94.04 234	96.03 485	97.14 101	97.83 385	99.78 14

reproduce-ours		98.48 29	98.27 53	99.12 4	98.99 128	98.02 12	96.81 158	99.02 119	98.29 50	98.97 66	98.61 121	97.27 57	99.82 38	96.86 114	99.61 125	99.51 84

our_new_method		98.48 29	98.27 53	99.12 4	98.99 128	98.02 12	96.81 158	99.02 119	98.29 50	98.97 66	98.61 121	97.27 57	99.82 38	96.86 114	99.61 125	99.51 84

test_fmvs1_n		95.21 292	95.28 278	94.99 349	98.15 272	89.13 332	96.81 158	99.43 33	86.97 433	97.21 248	98.92 81	83.00 401	97.13 473	98.09 54	98.94 300	98.72 296

test_fmvs2		96.38 230	96.45 228	96.16 278	97.85 300	91.30 265	96.81 158	99.45 31	89.24 403	98.49 120	99.38 23	88.68 343	97.62 469	98.83 31	99.32 245	99.57 58

SED-MVS		97.94 75	97.90 85	98.07 98	99.22 78	95.35 117	96.79 162	98.83 183	96.11 165	99.08 54	98.24 184	97.87 28	99.72 110	95.44 198	99.51 177	99.14 206

OPU-MVS				97.64 134	98.01 285	95.27 125	96.79 162				97.35 296	96.97 84	98.51 437	91.21 357	99.25 258	99.14 206

BP-MVS1		95.36 284	94.86 299	96.89 204	98.35 241	91.72 254	96.76 164	95.21 411	96.48 139	96.23 325	97.19 306	75.97 443	99.80 50	97.91 63	99.60 132	99.15 200

PHI-MVS		96.96 183	96.53 223	98.25 81	97.48 361	96.50 62	96.76 164	98.85 172	93.52 302	96.19 329	96.85 335	95.94 152	99.42 270	93.79 300	99.43 210	98.83 274

DVP-MVS		97.78 102	97.65 120	98.16 90	99.24 72	95.51 106	96.74 166	98.23 281	95.92 185	98.40 132	98.28 177	97.06 73	99.71 126	95.48 194	99.52 172	99.26 175
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 81	99.23 75	95.49 110	96.74 166	98.89 156					99.75 84	95.48 194	99.52 172	99.53 77

Anonymous202405211		96.34 232	95.98 255	97.43 156	98.25 255	93.85 181	96.74 166	94.41 422	97.72 71	98.37 135	98.03 220	87.15 363	99.53 222	94.06 283	99.07 286	98.92 260

SMA-MVS		97.48 138	97.11 173	98.60 48	98.83 155	96.67 56	96.74 166	98.73 209	91.61 359	98.48 122	98.36 156	96.53 121	99.68 150	95.17 222	99.54 159	99.45 111
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 89	96.73 170	99.05 106	98.67 30	98.84 82	98.45 144	97.58 43	99.88 22	96.45 131	99.86 35	99.54 72

test_0402		97.84 93	97.97 76	97.47 152	99.19 89	94.07 172	96.71 171	98.73 209	98.66 31	98.56 113	98.41 150	96.84 101	99.69 143	94.82 250	99.81 58	98.64 305

test_fmvsmconf0.01_n		98.57 21	98.74 19	98.06 100	99.39 50	94.63 148	96.70 172	99.82 1	95.44 215	99.64 13	99.52 12	98.96 4	99.74 94	99.38 7	99.86 35	99.81 10

SSC-MVS		95.92 253	97.03 180	92.58 436	99.28 64	78.39 474	96.68 173	95.12 413	98.90 25	99.11 51	98.66 114	91.36 305	99.68 150	95.00 238	99.16 271	99.67 34

ACMM	93.33 11	98.05 59	97.79 102	98.85 27	99.15 96	97.55 29	96.68 173	98.83 183	95.21 224	98.36 138	98.13 200	98.13 22	99.62 187	96.04 153	99.54 159	99.39 140
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		93.14 375	92.64 374	94.62 370	97.34 374	87.20 388	96.67 175	93.02 438	94.71 251	96.51 308	95.83 390	81.64 407	98.60 430	90.00 392	88.06 486	98.07 371

SSM_0404		97.47 139	97.75 110	96.64 223	98.81 157	91.26 267	96.57 176	99.16 66	96.95 111	98.44 128	98.09 207	97.05 75	99.72 110	95.21 217	99.44 200	98.95 250

fmvsm_s_conf0.1_n_a		97.80 100	98.01 72	97.18 177	99.17 92	92.51 225	96.57 176	99.15 72	93.68 297	98.89 74	99.30 32	96.42 131	99.37 300	99.03 25	99.83 54	99.66 36

MTMP							96.55 178	74.60 499

SD-MVS		97.37 152	97.70 112	96.35 259	98.14 274	95.13 134	96.54 179	98.92 150	95.94 183	99.19 45	98.08 209	97.74 33	95.06 488	95.24 215	99.54 159	98.87 271
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		97.59 125	97.96 82	96.45 243	99.01 123	90.45 293	96.50 180	99.23 51	96.19 158	98.27 152	98.72 102	97.49 45	99.47 245	96.64 117	99.62 115	99.42 127

E6new		97.59 125	97.97 76	96.45 243	99.01 123	90.45 293	96.50 180	99.23 51	96.20 154	98.27 152	98.72 102	97.49 45	99.47 245	96.64 117	99.62 115	99.42 127

E6		97.59 125	97.97 76	96.45 243	99.01 123	90.45 293	96.50 180	99.23 51	96.20 154	98.27 152	98.72 102	97.49 45	99.47 245	96.64 117	99.62 115	99.42 127

E5		97.59 125	97.96 82	96.45 243	99.01 123	90.45 293	96.50 180	99.23 51	96.19 158	98.27 152	98.72 102	97.49 45	99.47 245	96.64 117	99.62 115	99.42 127

HQP_MVS		96.66 211	96.33 237	97.68 130	98.70 182	94.29 164	96.50 180	98.75 206	96.36 144	96.16 331	96.77 342	91.91 300	99.46 252	92.59 330	99.20 263	99.28 170

plane_prior2							96.50 180		96.36 144

GDP-MVS		95.39 283	94.89 296	96.90 203	98.26 254	91.91 249	96.48 186	99.28 46	95.06 233	96.54 307	97.12 315	74.83 447	99.82 38	97.19 99	99.27 254	98.96 248

Effi-MVS+-dtu		96.81 197	96.09 247	98.99 13	96.90 395	98.69 4	96.42 187	98.09 302	95.86 190	95.15 371	95.54 400	94.26 230	99.81 43	94.06 283	98.51 353	98.47 329

SSM_0407		97.39 149	97.67 117	96.54 237	98.51 217	90.96 274	96.40 188	99.16 66	96.95 111	98.27 152	98.09 207	97.05 75	99.67 160	95.21 217	99.40 218	98.98 244

guyue		96.21 239	96.29 238	95.98 287	98.80 160	89.14 331	96.40 188	94.34 424	95.99 179	98.58 111	98.13 200	87.42 361	99.64 177	97.39 90	99.55 153	99.16 199

MM		96.87 190	96.62 208	97.62 135	97.72 335	93.30 204	96.39 190	92.61 446	97.90 64	96.76 288	98.64 119	90.46 318	99.81 43	99.16 18	99.94 8	99.76 21

thres100view900		91.76 403	91.26 403	93.26 411	98.21 259	84.50 433	96.39 190	90.39 469	96.87 116	96.33 316	93.08 438	73.44 457	99.42 270	78.85 479	97.74 389	95.85 461

XVG-ACMP-BASELINE		97.58 130	97.28 161	98.49 57	99.16 93	96.90 49	96.39 190	98.98 138	95.05 234	98.06 183	98.02 221	95.86 156	99.56 211	94.37 271	99.64 110	99.00 237

Patchmtry		95.03 302	94.59 317	96.33 260	94.83 463	90.82 279	96.38 193	97.20 351	96.59 130	97.49 229	98.57 129	77.67 430	99.38 295	92.95 325	99.62 115	98.80 277

fmvsm_s_conf0.1_n		97.73 106	98.02 70	96.85 207	99.09 108	91.43 264	96.37 194	99.11 81	94.19 277	99.01 60	99.25 35	96.30 138	99.38 295	99.00 26	99.88 28	99.73 26

ACMMP_NAP		97.89 87	97.63 125	98.67 43	99.35 58	96.84 50	96.36 195	98.79 197	95.07 232	97.88 206	98.35 158	97.24 63	99.72 110	96.05 152	99.58 140	99.45 111

VNet		96.84 192	96.83 195	96.88 205	98.06 280	92.02 246	96.35 196	97.57 342	97.70 73	97.88 206	97.80 249	92.40 286	99.54 219	94.73 257	98.96 297	99.08 224

V42		97.04 174	97.16 172	96.68 222	98.59 204	91.05 270	96.33 197	98.36 267	94.60 255	97.99 191	98.30 172	93.32 253	99.62 187	97.40 88	99.53 163	99.38 142

test_fmvsmvis_n_1920		98.08 55	98.47 32	96.93 199	99.03 121	93.29 205	96.32 198	99.65 12	95.59 205	99.71 7	99.01 67	97.66 38	99.60 198	99.44 5	99.83 54	97.90 389

APD-MVS		97.00 176	96.53 223	98.41 64	98.55 211	96.31 70	96.32 198	98.77 202	92.96 332	97.44 237	97.58 271	95.84 157	99.74 94	91.96 338	99.35 233	99.19 192
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n_11		97.90 85	98.34 45	96.60 227	98.75 171	90.50 291	96.28 200	99.56 22	97.05 106	99.15 48	99.11 54	96.31 136	99.69 143	98.97 29	99.84 49	99.62 44

AstraMVS		96.41 229	96.48 227	96.20 272	98.91 145	89.69 313	96.28 200	93.29 436	96.11 165	98.70 99	98.36 156	89.41 338	99.66 168	97.60 80	99.63 112	99.26 175

VPNet		97.26 159	97.49 147	96.59 229	99.47 39	90.58 284	96.27 202	98.53 244	97.77 66	98.46 125	98.41 150	94.59 216	99.68 150	94.61 261	99.29 251	99.52 80

thres600view7		92.03 398	91.43 396	93.82 398	98.19 262	84.61 432	96.27 202	90.39 469	96.81 119	96.37 315	93.11 434	73.44 457	99.49 236	80.32 474	97.95 379	97.36 422

EPNet		93.72 356	92.62 375	97.03 193	87.61 501	92.25 233	96.27 202	91.28 460	96.74 122	87.65 483	97.39 291	85.00 385	99.64 177	92.14 336	99.48 189	99.20 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DSMNet-mixed		92.19 392	91.83 387	93.25 412	96.18 415	83.68 445	96.27 202	93.68 430	76.97 490	92.54 448	99.18 45	89.20 341	98.55 434	83.88 460	98.60 347	97.51 417

IMVS_0407		96.35 231	96.88 193	94.74 365	97.83 309	86.11 405	96.25 206	98.82 191	94.48 262	97.57 222	97.14 309	96.08 148	99.33 313	95.00 238	98.78 321	98.78 280

fmvsm_s_conf0.5_n_a		97.65 116	97.83 97	97.13 181	98.80 160	92.51 225	96.25 206	99.06 100	93.67 298	98.64 103	99.00 68	96.23 142	99.36 304	98.99 27	99.80 62	99.53 77

ACMP	92.54 13	97.47 139	97.10 174	98.55 52	99.04 120	96.70 54	96.24 208	98.89 156	93.71 294	97.97 197	97.75 255	97.44 49	99.63 182	93.22 319	99.70 95	99.32 157
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS	95.41 4	97.82 97	97.70 112	98.16 90	98.78 167	95.72 94	96.23 209	99.02 119	93.92 290	98.62 105	98.99 70	97.69 34	99.62 187	96.18 147	99.87 33	99.15 200
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PM-MVS		97.36 154	97.10 174	98.14 94	98.91 145	96.77 52	96.20 210	98.63 233	93.82 291	98.54 114	98.33 161	93.98 236	99.05 376	95.99 158	99.45 197	98.61 312

test_fmvsmconf0.1_n		98.41 34	98.54 30	98.03 105	99.16 93	94.61 149	96.18 211	99.73 5	95.05 234	99.60 17	99.34 29	98.68 8	99.72 110	99.21 12	99.85 46	99.76 21

MVS_Test		96.27 235	96.79 200	94.73 366	96.94 393	86.63 397	96.18 211	98.33 271	94.94 241	96.07 334	98.28 177	95.25 190	99.26 339	97.21 96	97.90 382	98.30 349

CR-MVSNet		93.29 372	92.79 368	94.78 362	95.44 446	88.15 364	96.18 211	97.20 351	84.94 456	94.10 401	98.57 129	77.67 430	99.39 291	95.17 222	95.81 452	96.81 443

RPMNet		94.68 319	94.60 315	94.90 354	95.44 446	88.15 364	96.18 211	98.86 168	97.43 86	94.10 401	98.49 138	79.40 422	99.76 76	95.69 175	95.81 452	96.81 443

LuminaMVS		96.76 201	96.58 214	97.30 167	98.94 136	92.96 213	96.17 215	96.15 385	95.54 209	98.96 68	98.18 195	87.73 357	99.80 50	97.98 60	99.61 125	99.15 200

test_fmvsm_n_1920		98.08 55	98.29 52	97.43 156	98.88 149	93.95 178	96.17 215	99.57 20	95.66 200	99.52 20	98.71 109	97.04 77	99.64 177	99.21 12	99.87 33	98.69 301

fmvsm_s_conf0.5_n		97.62 120	97.89 88	96.80 213	98.79 163	91.44 263	96.14 217	99.06 100	94.19 277	98.82 84	98.98 71	96.22 143	99.38 295	98.98 28	99.86 35	99.58 50

WB-MVS		95.50 275	96.62 208	92.11 447	99.21 85	77.26 484	96.12 218	95.40 407	98.62 34	98.84 82	98.26 182	91.08 308	99.50 230	93.37 312	98.70 336	99.58 50

EIA-MVS		96.04 247	95.77 268	96.85 207	97.80 318	92.98 212	96.12 218	99.16 66	94.65 253	93.77 412	91.69 460	95.68 169	99.67 160	94.18 278	98.85 314	97.91 388

Effi-MVS+		96.19 241	96.01 252	96.71 219	97.43 367	92.19 239	96.12 218	99.10 86	95.45 213	93.33 430	94.71 416	97.23 64	99.56 211	93.21 320	97.54 402	98.37 337

FE-MVSNET		96.59 213	96.65 207	96.41 254	98.94 136	90.51 290	96.07 221	99.05 106	92.94 333	98.03 187	98.00 225	93.08 260	99.42 270	94.04 286	99.74 82	99.30 162

alignmvs		96.01 250	95.52 276	97.50 147	97.77 327	94.71 143	96.07 221	96.84 371	97.48 84	96.78 287	94.28 425	85.50 380	99.40 282	96.22 145	98.73 333	98.40 333

fmvsm_l_conf0.5_n_3		98.29 41	98.46 33	97.79 119	98.90 147	94.05 174	96.06 223	99.63 16	96.07 170	99.37 32	98.93 78	98.29 16	99.68 150	99.11 22	99.79 64	99.65 39

VortexMVS		96.04 247	96.56 217	94.49 380	97.60 352	84.36 436	96.05 224	98.67 224	94.74 247	98.95 69	98.78 94	87.13 364	99.50 230	97.37 92	99.76 70	99.60 46

PatchT		93.75 353	93.57 351	94.29 390	95.05 456	87.32 386	96.05 224	92.98 439	97.54 81	94.25 394	98.72 102	75.79 444	99.24 346	95.92 163	95.81 452	96.32 455

ME-MVS		97.53 135	97.32 157	98.16 90	98.70 182	95.35 117	96.04 226	98.60 235	96.16 163	97.99 191	97.54 273	95.94 152	99.70 135	95.36 206	99.53 163	99.44 121

Patchmatch-test		93.60 361	93.25 357	94.63 369	96.14 420	87.47 381	96.04 226	94.50 421	93.57 299	96.47 310	96.97 327	76.50 438	98.61 428	90.67 379	98.41 361	97.81 397

thisisatest0530		92.71 382	91.76 391	95.56 320	98.42 235	88.23 359	96.03 228	87.35 486	94.04 284	96.56 304	95.47 402	64.03 474	99.77 69	94.78 254	99.11 279	98.68 304

9.14			96.69 204		98.53 214		96.02 229	98.98 138	93.23 313	97.18 251	97.46 282	96.47 126	99.62 187	92.99 323	99.32 245

DeepC-MVS_fast	94.34 7	96.74 202	96.51 225	97.44 155	97.69 337	94.15 170	96.02 229	98.43 255	93.17 322	97.30 241	97.38 293	95.48 178	99.28 334	93.74 302	99.34 238	98.88 269
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
IMVS_0403		96.27 235	96.77 201	94.76 363	97.83 309	86.11 405	96.00 231	98.82 191	94.48 262	97.49 229	97.14 309	95.38 183	99.40 282	95.00 238	98.78 321	98.78 280

ttmdpeth		94.05 346	94.15 338	93.75 400	95.81 433	85.32 417	96.00 231	94.93 416	92.07 347	94.19 397	99.09 58	85.73 377	96.41 484	90.98 361	98.52 350	99.53 77

test_fmvsmconf_n		98.30 40	98.41 39	97.99 108	98.94 136	94.60 150	96.00 231	99.64 15	94.99 239	99.43 27	99.18 45	98.51 12	99.71 126	99.13 20	99.84 49	99.67 34

fmvsm_s_conf0.5_n_10		97.74 105	98.11 60	96.62 224	98.72 176	90.95 277	95.99 234	99.50 28	96.22 153	99.20 44	98.93 78	95.13 197	99.77 69	99.49 3	99.76 70	99.15 200

114514_t		93.96 349	93.22 358	96.19 274	99.06 113	90.97 273	95.99 234	98.94 147	73.88 493	93.43 427	96.93 330	92.38 287	99.37 300	89.09 405	99.28 252	98.25 356

FMVSNet3		95.26 291	94.94 291	96.22 271	96.53 403	90.06 303	95.99 234	97.66 331	94.11 281	97.99 191	97.91 235	80.22 421	99.63 182	94.60 262	99.44 200	98.96 248

HPM-MVS++		96.99 177	96.38 234	98.81 30	98.64 189	97.59 26	95.97 237	98.20 285	95.51 210	95.06 373	96.53 356	94.10 233	99.70 135	94.29 274	99.15 272	99.13 208

casdiffmvs_mvg		97.83 94	98.11 60	97.00 195	98.57 208	92.10 243	95.97 237	99.18 62	97.67 77	99.00 62	98.48 142	97.64 39	99.50 230	96.96 110	99.54 159	99.40 134
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		96.07 245	96.50 226	94.80 360	99.26 68	87.69 378	95.96 239	98.58 240	95.08 231	98.02 189	96.25 372	97.92 24	97.60 470	88.68 412	98.74 330	99.11 219

EG-PatchMatch MVS		97.69 110	97.79 102	97.40 160	99.06 113	93.52 195	95.96 239	98.97 141	94.55 259	98.82 84	98.76 99	97.31 55	99.29 330	97.20 98	99.44 200	99.38 142

fmvsm_s_conf0.5_n_3		97.88 88	98.37 40	96.41 254	98.73 173	89.82 310	95.94 241	99.49 29	96.81 119	99.09 53	99.03 65	97.09 70	99.65 171	99.37 8	99.76 70	99.76 21

PAPM_NR		94.61 323	94.17 337	95.96 288	98.36 240	91.23 268	95.93 242	97.95 311	92.98 328	93.42 428	94.43 423	90.53 316	98.38 447	87.60 425	96.29 442	98.27 353

UniMVSNet (Re)		97.83 94	97.65 120	98.35 71	98.80 160	95.86 90	95.92 243	99.04 114	97.51 82	98.22 163	97.81 248	94.68 212	99.78 58	97.14 101	99.75 80	99.41 133

test_vis1_n_1920		95.77 261	96.41 231	93.85 397	98.55 211	84.86 428	95.91 244	99.71 7	92.72 338	97.67 217	98.90 85	87.44 360	98.73 413	97.96 61	98.85 314	97.96 385

fmvsm_l_conf0.5_n		97.68 113	97.81 100	97.27 170	98.92 142	92.71 222	95.89 245	99.41 37	93.36 308	99.00 62	98.44 146	96.46 128	99.65 171	99.09 23	99.76 70	99.45 111

fmvsm_s_conf0.5_n_9		97.98 64	98.32 48	96.96 196	98.92 142	91.45 262	95.87 246	99.53 26	97.44 85	99.56 18	99.05 62	95.34 185	99.67 160	99.52 2	99.70 95	99.77 15

1314		92.38 388	92.30 380	92.64 435	95.42 448	85.15 422	95.86 247	96.97 368	85.40 449	90.62 460	93.06 439	91.12 307	97.80 467	86.74 436	95.49 461	94.97 473

MVS		90.02 420	89.20 427	92.47 439	94.71 464	86.90 393	95.86 247	96.74 377	64.72 495	90.62 460	92.77 445	92.54 281	98.39 446	79.30 477	95.56 460	92.12 487

fmvsm_l_conf0.5_n_a		97.60 122	97.76 108	97.11 182	98.92 142	92.28 232	95.83 249	99.32 39	93.22 314	98.91 73	98.49 138	96.31 136	99.64 177	99.07 24	99.76 70	99.40 134

casdiffmvs		97.50 136	97.81 100	96.56 234	98.51 217	91.04 271	95.83 249	99.09 91	97.23 101	98.33 145	98.30 172	97.03 78	99.37 300	96.58 125	99.38 223	99.28 170
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		91.89 400	91.45 395	93.21 415	89.01 496	84.87 427	95.82 251	95.05 414	91.50 366	98.75 93	99.19 41	57.56 480	95.11 487	97.78 71	98.37 362	99.64 43

tpmvs		90.79 415	90.87 408	90.57 460	92.75 488	76.30 486	95.79 252	93.64 432	91.04 378	91.91 453	96.26 371	77.19 436	98.86 400	89.38 402	89.85 483	96.56 450

fmvsm_s_conf0.5_n_6		97.45 141	97.79 102	96.44 247	98.58 206	90.31 299	95.77 253	99.33 38	94.52 260	98.85 80	98.44 146	95.68 169	99.62 187	99.15 19	99.81 58	99.38 142

fmvsm_s_conf0.5_n_8		97.66 115	98.12 58	96.27 266	98.79 163	89.43 322	95.76 254	99.42 34	97.49 83	99.16 47	99.04 63	94.56 219	99.69 143	99.18 16	99.73 83	99.70 31

mvsany_test3		96.21 239	95.93 259	97.05 189	97.40 369	94.33 163	95.76 254	94.20 425	89.10 404	99.36 34	99.60 11	93.97 237	97.85 465	95.40 205	98.63 343	98.99 241

MSLP-MVS++		96.42 228	96.71 203	95.57 315	97.82 313	90.56 286	95.71 256	98.84 176	94.72 250	96.71 291	97.39 291	94.91 206	98.10 461	95.28 212	99.02 291	98.05 378

tfpn200view9		91.55 405	91.00 405	93.21 415	98.02 283	84.35 437	95.70 257	90.79 465	96.26 148	95.90 344	92.13 455	73.62 454	99.42 270	78.85 479	97.74 389	95.85 461

Anonymous20231206		95.27 290	95.06 289	95.88 294	98.72 176	89.37 323	95.70 257	97.85 318	88.00 422	96.98 272	97.62 267	91.95 297	99.34 311	89.21 403	99.53 163	98.94 253

thres400		91.68 404	91.00 405	93.71 402	98.02 283	84.35 437	95.70 257	90.79 465	96.26 148	95.90 344	92.13 455	73.62 454	99.42 270	78.85 479	97.74 389	97.36 422

reproduce_monomvs		92.05 397	92.26 381	91.43 453	95.42 448	75.72 489	95.68 260	97.05 363	94.47 266	97.95 200	98.35 158	55.58 489	99.05 376	96.36 136	99.44 200	99.51 84

test20.03		96.58 216	96.61 210	96.48 241	98.49 224	91.72 254	95.68 260	97.69 328	96.81 119	98.27 152	97.92 234	94.18 232	98.71 416	90.78 370	99.66 107	99.00 237

hse-mvs2		95.77 261	95.09 286	97.79 119	97.84 306	95.51 106	95.66 262	95.43 406	96.58 131	97.21 248	96.16 375	84.14 391	99.54 219	95.89 165	96.92 417	98.32 344

UniMVSNet_NR-MVSNet		97.83 94	97.65 120	98.37 68	98.72 176	95.78 91	95.66 262	99.02 119	98.11 57	98.31 148	97.69 262	94.65 214	99.85 30	97.02 108	99.71 91	99.48 101

fmvsm_s_conf0.5_n_4		97.43 145	97.77 107	96.39 258	98.48 226	89.89 308	95.65 264	99.26 48	94.73 249	98.72 97	98.58 127	95.58 175	99.57 209	99.28 9	99.67 104	99.73 26

dmvs_re		92.08 396	91.27 401	94.51 378	97.16 384	92.79 220	95.65 264	92.64 445	94.11 281	92.74 441	90.98 467	83.41 398	94.44 492	80.72 473	94.07 471	96.29 456

DU-MVS		97.79 101	97.60 131	98.36 70	98.73 173	95.78 91	95.65 264	98.87 165	97.57 78	98.31 148	97.83 243	94.69 210	99.85 30	97.02 108	99.71 91	99.46 107

EPMVS		89.26 431	88.55 433	91.39 454	92.36 489	79.11 473	95.65 264	79.86 496	88.60 413	93.12 433	96.53 356	70.73 465	98.10 461	90.75 372	89.32 484	96.98 432

MVP-Stereo		95.69 265	95.28 278	96.92 200	98.15 272	93.03 211	95.64 268	98.20 285	90.39 389	96.63 299	97.73 259	91.63 302	99.10 371	91.84 343	97.31 412	98.63 307
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
fmvsm_s_conf0.5_n_5		97.63 119	97.83 97	97.04 191	98.77 169	92.33 229	95.63 269	99.58 18	93.53 301	99.10 52	98.66 114	96.44 129	99.65 171	99.12 21	99.68 101	99.12 214

test_cas_vis1_n_1920		95.34 286	95.67 270	94.35 386	98.21 259	86.83 395	95.61 270	99.26 48	90.45 388	98.17 169	98.96 74	84.43 390	98.31 452	96.74 116	99.17 270	97.90 389

test_f		95.82 259	95.88 262	95.66 310	97.61 350	93.21 209	95.61 270	98.17 291	86.98 432	98.42 129	99.47 16	90.46 318	94.74 490	97.71 75	98.45 357	99.03 233

F-COLMAP		95.30 289	94.38 328	98.05 104	98.64 189	96.04 81	95.61 270	98.66 227	89.00 407	93.22 431	96.40 365	92.90 267	99.35 308	87.45 430	97.53 403	98.77 289

AUN-MVS		93.95 351	92.69 372	97.74 123	97.80 318	95.38 114	95.57 273	95.46 405	91.26 374	92.64 445	96.10 381	74.67 448	99.55 216	93.72 304	96.97 416	98.30 349

fmvsm_s_conf0.1_n_2		97.68 113	98.18 56	96.20 272	99.06 113	89.08 334	95.51 274	99.72 6	96.06 171	99.48 21	99.24 36	95.18 193	99.60 198	99.45 4	99.88 28	99.94 3

v144192		96.69 209	96.90 191	96.03 284	98.25 255	88.92 338	95.49 275	98.77 202	93.05 325	98.09 178	98.29 176	92.51 284	99.70 135	98.11 52	99.56 146	99.47 105

Fast-Effi-MVS+-dtu		96.44 225	96.12 245	97.39 161	97.18 383	94.39 158	95.46 276	98.73 209	96.03 176	94.72 384	94.92 413	96.28 141	99.69 143	93.81 299	97.98 377	98.09 368

viewmacassd2359aftdt		97.25 160	97.52 141	96.43 249	98.83 155	90.49 292	95.45 277	99.18 62	95.44 215	97.98 196	98.47 143	96.90 94	99.37 300	95.93 162	99.55 153	99.43 125

Baseline_NR-MVSNet		97.72 108	97.79 102	97.50 147	99.56 22	93.29 205	95.44 278	98.86 168	98.20 55	98.37 135	99.24 36	94.69 210	99.55 216	95.98 159	99.79 64	99.65 39

LF4IMVS		96.07 245	95.63 273	97.36 163	98.19 262	95.55 103	95.44 278	98.82 191	92.29 346	95.70 355	96.55 354	92.63 275	98.69 419	91.75 349	99.33 243	97.85 393

v1921920		96.72 206	96.96 185	95.99 285	98.21 259	88.79 343	95.42 280	98.79 197	93.22 314	98.19 168	98.26 182	92.68 272	99.70 135	98.34 49	99.55 153	99.49 95

plane_prior						94.29 164	95.42 280		94.31 273						98.93 303

v1144		96.84 192	97.08 176	96.13 280	98.42 235	89.28 325	95.41 282	98.67 224	94.21 275	97.97 197	98.31 166	93.06 261	99.65 171	98.06 57	99.62 115	99.45 111

ETV-MVS		96.13 244	95.90 260	96.82 211	97.76 328	93.89 179	95.40 283	98.95 144	95.87 189	95.58 359	91.00 466	96.36 135	99.72 110	93.36 313	98.83 317	96.85 439

fmvsm_l_conf0.5_n_9		97.92 79	98.37 40	96.57 232	98.94 136	90.54 287	95.39 284	99.58 18	96.82 118	99.56 18	98.77 95	97.23 64	99.61 195	99.17 17	99.86 35	99.57 58

v1240		96.74 202	97.02 181	95.91 293	98.18 265	88.52 348	95.39 284	98.88 163	93.15 323	98.46 125	98.40 153	92.80 269	99.71 126	98.45 45	99.49 184	99.49 95

MP-MVS-pluss		97.69 110	97.36 154	98.70 41	99.50 35	96.84 50	95.38 286	98.99 135	92.45 343	98.11 175	98.31 166	97.25 62	99.77 69	96.60 123	99.62 115	99.48 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MGCNet		95.71 264	95.18 282	97.33 165	94.85 461	92.82 215	95.36 287	90.89 464	95.51 210	95.61 357	97.82 246	88.39 347	99.78 58	98.23 50	99.91 19	99.40 134

v1192		96.83 195	97.06 178	96.15 279	98.28 249	89.29 324	95.36 287	98.77 202	93.73 293	98.11 175	98.34 160	93.02 266	99.67 160	98.35 48	99.58 140	99.50 87

v2v482		96.78 199	97.06 178	95.95 290	98.57 208	88.77 344	95.36 287	98.26 277	95.18 227	97.85 211	98.23 186	92.58 276	99.63 182	97.80 69	99.69 97	99.45 111

test_fmvs1		94.51 330	94.60 315	94.26 391	95.91 425	87.92 370	95.35 290	99.02 119	86.56 437	96.79 283	98.52 135	82.64 403	97.00 476	97.87 65	98.71 334	97.88 391

EI-MVSNet-Vis-set		97.32 156	97.39 150	97.11 182	97.36 371	92.08 244	95.34 291	97.65 333	97.74 69	98.29 151	98.11 205	95.05 198	99.68 150	97.50 84	99.50 181	99.56 66

fmvsm_s_conf0.5_n_2		97.59 125	98.07 64	96.17 276	98.78 167	89.10 333	95.33 292	99.55 24	95.96 180	99.41 30	99.10 56	95.18 193	99.59 200	99.43 6	99.86 35	99.81 10

EI-MVSNet-UG-set		97.32 156	97.40 149	97.09 186	97.34 374	92.01 247	95.33 292	97.65 333	97.74 69	98.30 150	98.14 198	95.04 199	99.69 143	97.55 82	99.52 172	99.58 50

CostFormer		89.75 426	89.25 424	91.26 456	94.69 465	78.00 478	95.32 294	91.98 452	81.50 473	90.55 462	96.96 329	71.06 463	98.89 395	88.59 413	92.63 476	96.87 437

viewdifsd2359ckpt13		96.47 223	96.42 230	96.61 226	98.35 241	91.50 259	95.31 295	98.84 176	93.21 316	96.73 289	97.58 271	95.28 189	99.26 339	94.02 288	98.45 357	99.07 226

PVSNet_Blended_VisFu		95.95 252	95.80 266	96.42 251	99.28 64	90.62 283	95.31 295	99.08 95	88.40 416	96.97 273	98.17 197	92.11 292	99.78 58	93.64 306	99.21 262	98.86 272

UnsupCasMVSNet_eth		95.91 254	95.73 269	96.44 247	98.48 226	91.52 258	95.31 295	98.45 251	95.76 196	97.48 232	97.54 273	89.53 334	98.69 419	94.43 267	94.61 468	99.13 208

EI-MVSNet		96.63 212	96.93 187	95.74 301	97.26 379	88.13 366	95.29 298	97.65 333	96.99 107	97.94 201	98.19 192	92.55 279	99.58 203	96.91 111	99.56 146	99.50 87

CVMVSNet		92.33 390	92.79 368	90.95 457	97.26 379	75.84 488	95.29 298	92.33 449	81.86 470	96.27 322	98.19 192	81.44 409	98.46 442	94.23 277	98.29 366	98.55 317

E4		97.28 158	97.55 138	96.46 242	98.86 153	90.53 289	95.28 300	99.18 62	95.82 194	98.01 190	98.59 126	96.78 104	99.46 252	95.86 169	99.56 146	99.38 142

viewdifsd2359ckpt09		96.23 238	96.04 250	96.82 211	98.29 246	92.06 245	95.25 301	99.03 115	91.51 365	96.19 329	97.01 325	94.41 223	99.40 282	93.76 301	98.90 306	99.00 237

OPM-MVS		97.54 132	97.25 163	98.41 64	99.11 105	96.61 59	95.24 302	98.46 250	94.58 258	98.10 177	98.07 211	97.09 70	99.39 291	95.16 224	99.44 200	99.21 188
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TAPA-MVS	93.32 12	94.93 304	94.23 333	97.04 191	98.18 265	94.51 154	95.22 303	98.73 209	81.22 475	96.25 324	95.95 387	93.80 242	98.98 386	89.89 394	98.87 311	97.62 411
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPE-MVS		97.64 117	97.35 155	98.50 56	98.85 154	96.18 74	95.21 304	98.99 135	95.84 192	98.78 87	98.08 209	96.84 101	99.81 43	93.98 290	99.57 143	99.52 80
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mamba_0408		97.17 165	97.38 152	96.55 236	98.51 217	90.96 274	95.19 305	99.06 100	96.60 127	98.27 152	97.78 250	96.58 118	99.72 110	95.04 233	99.40 218	98.98 244

SSM_04072		97.14 166	97.38 152	96.42 251	98.51 217	90.96 274	95.19 305	99.06 100	96.60 127	98.27 152	97.78 250	96.58 118	99.31 322	95.04 233	99.40 218	98.98 244

MVSTER		94.21 339	93.93 346	95.05 345	95.83 431	86.46 398	95.18 307	97.65 333	92.41 344	97.94 201	98.00 225	72.39 459	99.58 203	96.36 136	99.56 146	99.12 214

testing3-2		90.09 419	90.38 418	89.24 467	98.07 279	69.88 500	95.12 308	90.71 468	96.65 124	93.60 421	94.03 427	55.81 488	99.33 313	90.69 378	98.71 334	98.51 324

PatchmatchNet		91.98 399	91.87 386	92.30 443	94.60 466	79.71 470	95.12 308	93.59 433	89.52 400	93.61 419	97.02 322	77.94 428	99.18 353	90.84 367	94.57 470	98.01 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmanbaseed2359cas		96.77 200	96.94 186	96.27 266	98.41 237	90.24 300	95.11 310	99.03 115	94.28 274	97.45 236	97.85 240	95.92 154	99.32 321	95.18 221	99.19 267	99.24 182

IterMVS-LS		96.92 185	97.29 159	95.79 297	98.51 217	88.13 366	95.10 311	98.66 227	96.99 107	98.46 125	98.68 113	92.55 279	99.74 94	96.91 111	99.79 64	99.50 87
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		96.58 216	96.97 183	95.42 327	98.63 198	87.57 379	95.09 312	97.90 315	95.91 187	98.24 161	97.96 228	93.42 252	99.39 291	96.04 153	99.52 172	99.29 169

tpm2		88.47 439	87.69 442	90.79 458	94.98 460	77.34 482	95.09 312	91.83 453	77.51 489	89.40 475	96.41 363	67.83 470	98.73 413	83.58 464	92.60 477	96.29 456

OpenMVS_ROB	91.80 14	93.64 360	93.05 360	95.42 327	97.31 378	91.21 269	95.08 314	96.68 380	81.56 472	96.88 279	96.41 363	90.44 320	99.25 342	85.39 450	97.67 396	95.80 463

E2		96.97 181	97.19 169	96.33 260	98.64 189	90.34 297	95.07 315	99.12 78	95.00 237	97.66 218	98.31 166	96.19 145	99.43 266	95.35 209	99.35 233	99.23 184

E3		96.97 181	97.19 169	96.33 260	98.64 189	90.34 297	95.07 315	99.12 78	95.00 237	97.66 218	98.31 166	96.19 145	99.43 266	95.35 209	99.35 233	99.23 184

TAMVS		95.49 276	94.94 291	97.16 178	98.31 244	93.41 202	95.07 315	96.82 373	91.09 376	97.51 227	97.82 246	89.96 327	99.42 270	88.42 415	99.44 200	98.64 305

tpmrst		90.31 417	90.61 415	89.41 466	94.06 476	72.37 497	95.06 318	93.69 428	88.01 421	92.32 450	96.86 334	77.45 432	98.82 403	91.04 359	87.01 487	97.04 431

ADS-MVSNet2		91.47 407	90.51 416	94.36 384	95.51 444	85.63 411	95.05 319	95.70 396	83.46 464	92.69 442	96.84 336	79.15 424	99.41 280	85.66 446	90.52 480	98.04 379

ADS-MVSNet		90.95 414	90.26 419	93.04 420	95.51 444	82.37 453	95.05 319	93.41 434	83.46 464	92.69 442	96.84 336	79.15 424	98.70 417	85.66 446	90.52 480	98.04 379

tpm		91.08 412	90.85 409	91.75 450	95.33 450	78.09 476	95.03 321	91.27 461	88.75 410	93.53 423	97.40 287	71.24 461	99.30 326	91.25 356	93.87 472	97.87 392

NCCC		96.52 218	95.99 254	98.10 97	97.81 314	95.68 97	95.00 322	98.20 285	95.39 218	95.40 366	96.36 367	93.81 241	99.45 260	93.55 310	98.42 360	99.17 196

test_post1							94.98 323				10.37 502	76.21 441	99.04 378	89.47 400

viewcassd2359sk11		96.73 204	96.89 192	96.24 268	98.46 230	90.20 301	94.94 324	99.07 99	94.43 268	97.33 240	98.05 219	95.69 168	99.40 282	94.98 245	99.11 279	99.12 214

fmvsm_s_conf0.5_n_7		97.13 167	97.50 145	96.04 283	98.43 233	89.03 337	94.92 325	99.00 131	94.51 261	98.42 129	98.96 74	94.97 204	99.54 219	98.42 46	99.85 46	99.56 66

AdaColmap		95.11 297	94.62 314	96.58 230	97.33 376	94.45 157	94.92 325	98.08 303	93.15 323	93.98 408	95.53 401	94.34 226	99.10 371	85.69 445	98.61 345	96.20 458

MDTV_nov1_ep13_2view						57.28 503	94.89 327		80.59 477	94.02 406		78.66 426		85.50 448		97.82 395

CNVR-MVS		96.92 185	96.55 220	98.03 105	98.00 289	95.54 104	94.87 328	98.17 291	94.60 255	96.38 314	97.05 320	95.67 171	99.36 304	95.12 230	99.08 284	99.19 192

OMC-MVS		96.48 222	96.00 253	97.91 112	98.30 245	96.01 85	94.86 329	98.60 235	91.88 353	97.18 251	97.21 305	96.11 147	99.04 378	90.49 385	99.34 238	98.69 301

E3new		96.50 219	96.61 210	96.17 276	98.28 249	90.09 302	94.85 330	99.02 119	93.95 289	97.01 267	97.74 258	95.19 192	99.39 291	94.70 260	98.77 327	99.04 232

viewdifsd2359ckpt11		97.13 167	97.62 127	95.67 308	98.64 189	88.36 354	94.84 331	98.95 144	96.24 150	98.70 99	98.61 121	96.66 109	99.29 330	96.46 129	99.45 197	99.36 150

viewmsd2359difaftdt		97.13 167	97.62 127	95.67 308	98.64 189	88.36 354	94.84 331	98.95 144	96.24 150	98.70 99	98.61 121	96.66 109	99.29 330	96.46 129	99.45 197	99.36 150

testing3		89.72 427	88.26 436	94.10 395	97.66 343	84.30 439	94.80 333	88.25 481	94.66 252	95.07 372	92.51 450	41.15 502	99.43 266	91.81 346	98.44 359	98.55 317

EPNet_dtu		91.39 408	90.75 411	93.31 410	90.48 494	82.61 451	94.80 333	92.88 440	93.39 307	81.74 492	94.90 414	81.36 410	99.11 367	88.28 417	98.87 311	98.21 360
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			91.28 400		94.31 469	73.51 495	94.80 333	93.16 437	86.75 436	93.45 426	97.40 287	76.37 439	98.55 434	88.85 408	96.43 436

pmmvs-eth3d		96.49 221	96.18 244	97.42 158	98.25 255	94.29 164	94.77 336	98.07 307	89.81 397	97.97 197	98.33 161	93.11 259	99.08 373	95.46 197	99.84 49	98.89 265

test_yl		94.40 332	94.00 342	95.59 313	96.95 391	89.52 318	94.75 337	95.55 403	96.18 161	96.79 283	96.14 378	81.09 412	99.18 353	90.75 372	97.77 386	98.07 371

DCV-MVSNet		94.40 332	94.00 342	95.59 313	96.95 391	89.52 318	94.75 337	95.55 403	96.18 161	96.79 283	96.14 378	81.09 412	99.18 353	90.75 372	97.77 386	98.07 371

dmvs_testset		87.30 451	86.99 447	88.24 472	96.71 398	77.48 481	94.68 339	86.81 489	92.64 339	89.61 474	87.01 488	85.91 375	93.12 493	61.04 495	88.49 485	94.13 480

MCST-MVS		96.24 237	95.80 266	97.56 138	98.75 171	94.13 171	94.66 340	98.17 291	90.17 393	96.21 327	96.10 381	95.14 196	99.43 266	94.13 281	98.85 314	99.13 208

XVG-OURS-SEG-HR		97.38 150	97.07 177	98.30 75	99.01 123	97.41 37	94.66 340	99.02 119	95.20 225	98.15 172	97.52 279	98.83 5	98.43 443	94.87 248	96.41 437	99.07 226

mvs_anonymous		95.36 284	96.07 249	93.21 415	96.29 409	81.56 459	94.60 342	97.66 331	93.30 311	96.95 274	98.91 84	93.03 265	99.38 295	96.60 123	97.30 413	98.69 301

DP-MVS Recon		95.55 274	95.13 284	96.80 213	98.51 217	93.99 177	94.60 342	98.69 219	90.20 392	95.78 351	96.21 374	92.73 271	98.98 386	90.58 381	98.86 313	97.42 421

viewdifsd2359ckpt07		97.10 172	97.55 138	95.76 299	98.64 189	88.58 347	94.54 344	99.11 81	96.96 110	98.54 114	98.18 195	96.91 92	99.44 263	95.58 187	99.49 184	99.26 175

save fliter					98.48 226	94.71 143	94.53 345	98.41 259	95.02 236

patch_mono-2		96.59 213	96.93 187	95.55 321	98.88 149	87.12 389	94.47 346	99.30 41	94.12 280	96.65 298	98.41 150	94.98 203	99.87 25	95.81 172	99.78 68	99.66 36

tpm cat1		88.01 445	87.33 444	90.05 465	94.48 467	76.28 487	94.47 346	94.35 423	73.84 494	89.26 476	95.61 399	73.64 453	98.30 453	84.13 458	86.20 488	95.57 468

CANet		95.86 257	95.65 272	96.49 240	96.41 407	90.82 279	94.36 348	98.41 259	94.94 241	92.62 447	96.73 345	92.68 272	99.71 126	95.12 230	99.60 132	98.94 253

WR-MVS		96.90 187	96.81 196	97.16 178	98.56 210	92.20 238	94.33 349	98.12 300	97.34 97	98.20 164	97.33 298	92.81 268	99.75 84	94.79 252	99.81 58	99.54 72

HQP-NCC					97.85 300		94.26 350		93.18 319	92.86 438

ACMP_Plane					97.85 300		94.26 350		93.18 319	92.86 438

HQP-MVS		95.17 296	94.58 318	96.92 200	97.85 300	92.47 227	94.26 350	98.43 255	93.18 319	92.86 438	95.08 407	90.33 321	99.23 348	90.51 383	98.74 330	99.05 231

PLC	91.02 16	94.05 346	92.90 364	97.51 143	98.00 289	95.12 135	94.25 353	98.25 278	86.17 439	91.48 457	95.25 405	91.01 310	99.19 352	85.02 454	96.69 430	98.22 359
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
1112_ss		94.12 342	93.42 354	96.23 269	98.59 204	90.85 278	94.24 354	98.85 172	85.49 446	92.97 436	94.94 411	86.01 374	99.64 177	91.78 347	97.92 380	98.20 361

MS-PatchMatch		94.83 309	94.91 295	94.57 374	96.81 396	87.10 390	94.23 355	97.34 348	88.74 411	97.14 253	97.11 316	91.94 298	98.23 456	92.99 323	97.92 380	98.37 337

Fast-Effi-MVS+		95.49 276	95.07 287	96.75 217	97.67 342	92.82 215	94.22 356	98.60 235	91.61 359	93.42 428	92.90 441	96.73 107	99.70 135	92.60 329	97.89 383	97.74 402

CMPMVS	73.10 23	92.74 381	91.39 397	96.77 216	93.57 482	94.67 146	94.21 357	97.67 329	80.36 479	93.61 419	96.60 352	82.85 402	97.35 471	84.86 455	98.78 321	98.29 352
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		88.08 444	88.05 437	88.16 474	92.85 486	68.81 501	94.17 358	92.88 440	85.47 447	91.38 458	96.14 378	68.87 469	98.81 405	86.88 435	83.80 490	96.87 437

JIA-IIPM		91.79 402	90.69 413	95.11 341	93.80 479	90.98 272	94.16 359	91.78 454	96.38 142	90.30 466	99.30 32	72.02 460	98.90 394	88.28 417	90.17 482	95.45 469

D2MVS		95.18 294	95.17 283	95.21 336	97.76 328	87.76 377	94.15 360	97.94 312	89.77 398	96.99 269	97.68 263	87.45 359	99.14 360	95.03 237	99.81 58	98.74 293

TSAR-MVS + GP.		96.47 223	96.12 245	97.49 150	97.74 333	95.23 127	94.15 360	96.90 370	93.26 312	98.04 186	96.70 347	94.41 223	98.89 395	94.77 255	99.14 273	98.37 337

PVSNet_BlendedMVS		95.02 303	94.93 293	95.27 334	97.79 323	87.40 384	94.14 362	98.68 221	88.94 408	94.51 389	98.01 223	93.04 262	99.30 326	89.77 396	99.49 184	99.11 219

TinyColmap		96.00 251	96.34 236	94.96 351	97.90 298	87.91 371	94.13 363	98.49 248	94.41 269	98.16 170	97.76 252	96.29 140	98.68 422	90.52 382	99.42 213	98.30 349

CNLPA		95.04 300	94.47 323	96.75 217	97.81 314	95.25 126	94.12 364	97.89 316	94.41 269	94.57 387	95.69 394	90.30 324	98.35 450	86.72 437	98.76 328	96.64 447

BH-untuned		94.69 317	94.75 307	94.52 377	97.95 294	87.53 380	94.07 365	97.01 366	93.99 287	97.10 257	95.65 396	92.65 274	98.95 391	87.60 425	96.74 427	97.09 429

pmmvs5		94.63 322	94.34 329	95.50 323	97.63 349	88.34 356	94.02 366	97.13 355	87.15 429	95.22 370	97.15 308	87.50 358	99.27 337	93.99 289	99.26 257	98.88 269

thres200		91.00 413	90.42 417	92.77 431	97.47 365	83.98 442	94.01 367	91.18 462	95.12 230	95.44 363	91.21 464	73.93 450	99.31 322	77.76 482	97.63 400	95.01 472

xiu_mvs_v1_base_debu		95.62 271	95.96 256	94.60 371	98.01 285	88.42 351	93.99 368	98.21 282	92.98 328	95.91 340	94.53 419	96.39 132	99.72 110	95.43 201	98.19 369	95.64 465

xiu_mvs_v1_base		95.62 271	95.96 256	94.60 371	98.01 285	88.42 351	93.99 368	98.21 282	92.98 328	95.91 340	94.53 419	96.39 132	99.72 110	95.43 201	98.19 369	95.64 465

xiu_mvs_v1_base_debi		95.62 271	95.96 256	94.60 371	98.01 285	88.42 351	93.99 368	98.21 282	92.98 328	95.91 340	94.53 419	96.39 132	99.72 110	95.43 201	98.19 369	95.64 465

test_vis1_rt		94.03 348	93.65 349	95.17 339	95.76 437	93.42 201	93.97 371	98.33 271	84.68 457	93.17 432	95.89 389	92.53 283	94.79 489	93.50 311	94.97 464	97.31 426

CDS-MVSNet		94.88 308	94.12 339	97.14 180	97.64 348	93.57 193	93.96 372	97.06 362	90.05 394	96.30 321	96.55 354	86.10 373	99.47 245	90.10 390	99.31 248	98.40 333
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		94.65 321	94.21 335	95.96 288	95.90 426	89.68 314	93.92 373	97.83 322	93.19 318	90.12 469	95.64 397	88.52 344	99.57 209	93.27 318	99.47 191	98.62 308

WTY-MVS		93.55 362	93.00 363	95.19 337	97.81 314	87.86 372	93.89 374	96.00 389	89.02 406	94.07 403	95.44 404	86.27 372	99.33 313	87.69 423	96.82 423	98.39 335

sss		94.22 337	93.72 348	95.74 301	97.71 336	89.95 307	93.84 375	96.98 367	88.38 417	93.75 413	95.74 393	87.94 351	98.89 395	91.02 360	98.10 373	98.37 337

baseline2		89.65 429	88.44 435	93.25 412	95.62 442	82.71 449	93.82 376	85.94 490	88.89 409	87.35 485	92.54 449	71.23 462	99.33 313	86.01 440	94.60 469	97.72 405

XVG-OURS		97.12 170	96.74 202	98.26 78	98.99 128	97.45 35	93.82 376	99.05 106	95.19 226	98.32 146	97.70 261	95.22 191	98.41 444	94.27 275	98.13 372	98.93 257

MVS_111021_LR		96.82 196	96.55 220	97.62 135	98.27 252	95.34 122	93.81 378	98.33 271	94.59 257	96.56 304	96.63 351	96.61 115	98.73 413	94.80 251	99.34 238	98.78 280

BH-RMVSNet		94.56 327	94.44 326	94.91 352	97.57 353	87.44 382	93.78 379	96.26 384	93.69 296	96.41 313	96.50 359	92.10 293	99.00 382	85.96 442	97.71 392	98.31 346

diffmvs_AUTHOR		96.50 219	96.81 196	95.57 315	98.03 281	88.26 358	93.73 380	99.14 75	94.92 244	97.24 245	97.84 242	94.62 215	99.33 313	96.44 132	99.37 224	99.13 208

CDPH-MVS		95.45 281	94.65 310	97.84 117	98.28 249	94.96 138	93.73 380	98.33 271	85.03 453	95.44 363	96.60 352	95.31 187	99.44 263	90.01 391	99.13 275	99.11 219

PatchMatch-RL		94.61 323	93.81 347	97.02 194	98.19 262	95.72 94	93.66 382	97.23 350	88.17 420	94.94 378	95.62 398	91.43 303	98.57 431	87.36 431	97.68 395	96.76 445

UWE-MVS-28		83.78 456	82.36 459	88.03 475	90.72 493	71.58 498	93.64 383	77.87 497	87.62 425	85.91 488	92.89 442	59.94 476	95.99 486	56.06 497	96.56 435	96.52 451

TEST9					97.84 306	95.23 127	93.62 384	98.39 262	86.81 434	93.78 410	95.99 383	94.68 212	99.52 225

train_agg		95.46 280	94.66 309	97.88 114	97.84 306	95.23 127	93.62 384	98.39 262	87.04 430	93.78 410	95.99 383	94.58 217	99.52 225	91.76 348	98.90 306	98.89 265

viewmambaseed2359dif		95.68 267	95.85 263	95.17 339	97.51 358	87.41 383	93.61 386	98.58 240	91.06 377	96.68 292	97.66 264	94.71 209	99.11 367	93.93 292	98.94 300	98.99 241

test_prior4						95.38 114	93.61 386

test_8					97.81 314	95.07 136	93.54 388	98.38 264	87.04 430	93.71 414	95.96 386	94.58 217	99.52 225

TR-MVS		92.54 386	92.20 383	93.57 405	96.49 404	86.66 396	93.51 389	94.73 418	89.96 395	94.95 377	93.87 429	90.24 326	98.61 428	81.18 472	94.88 465	95.45 469

新几何2							93.43 390

diffmvs		96.04 247	96.23 241	95.46 326	97.35 372	88.03 369	93.42 391	99.08 95	94.09 283	96.66 296	96.93 330	93.85 240	99.29 330	96.01 157	98.67 338	99.06 229
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		96.73 204	96.54 222	97.27 170	98.35 241	93.66 191	93.42 391	98.36 267	94.74 247	96.58 302	96.76 344	96.54 120	98.99 384	94.87 248	99.27 254	99.15 200

UnsupCasMVSNet_bld		94.72 316	94.26 332	96.08 282	98.62 200	90.54 287	93.38 393	98.05 310	90.30 390	97.02 266	96.80 341	89.54 332	99.16 358	88.44 414	96.18 444	98.56 315

旧先验2							93.35 394		77.95 487	95.77 353			98.67 423	90.74 375

test_prior2							93.33 395		94.21 275	94.02 406	96.25 372	93.64 247		91.90 340	98.96 297

WB-MVSnew		91.50 406	91.29 399	92.14 446	94.85 461	80.32 468	93.29 396	88.77 479	88.57 414	94.03 405	92.21 453	92.56 277	98.28 454	80.21 475	97.08 415	97.81 397

IMVS_0404		95.66 270	96.03 251	94.55 375	97.83 309	86.11 405	93.24 397	98.82 191	94.48 262	95.51 361	97.14 309	93.49 250	98.78 407	95.00 238	98.78 321	98.78 280

SCA		93.38 367	93.52 352	92.96 425	96.24 410	81.40 461	93.24 397	94.00 426	91.58 364	94.57 387	96.97 327	87.94 351	99.42 270	89.47 400	97.66 398	98.06 375

无先验							93.20 399	97.91 314	80.78 476				99.40 282	87.71 422		97.94 387

MG-MVS		94.08 345	94.00 342	94.32 388	97.09 387	85.89 410	93.19 400	95.96 391	92.52 340	94.93 379	97.51 280	89.54 332	98.77 409	87.52 429	97.71 392	98.31 346

MVS-HIRNet		88.40 440	90.20 420	82.99 477	97.01 389	60.04 502	93.11 401	85.61 491	84.45 461	88.72 479	99.09 58	84.72 388	98.23 456	82.52 466	96.59 434	90.69 492

new-patchmatchnet		95.67 268	96.58 214	92.94 426	97.48 361	80.21 469	92.96 402	98.19 290	94.83 245	98.82 84	98.79 91	93.31 254	99.51 229	95.83 170	99.04 290	99.12 214

ETVMVS		87.62 448	85.75 455	93.22 414	96.15 419	83.26 446	92.94 403	90.37 471	91.39 371	90.37 464	88.45 480	51.93 498	98.64 425	73.76 486	96.38 439	97.75 401

MDA-MVSNet-bldmvs		95.69 265	95.67 270	95.74 301	98.48 226	88.76 345	92.84 404	97.25 349	96.00 177	97.59 221	97.95 230	91.38 304	99.46 252	93.16 321	96.35 440	98.99 241

原ACMM2							92.82 405

testdata1							92.77 406		93.78 292

Test_1112_low_res		93.53 363	92.86 365	95.54 322	98.60 202	88.86 341	92.75 407	98.69 219	82.66 467	92.65 444	96.92 332	84.75 387	99.56 211	90.94 363	97.76 388	98.19 362

USDC		94.56 327	94.57 320	94.55 375	97.78 326	86.43 400	92.75 407	98.65 232	85.96 441	96.91 277	97.93 233	90.82 313	98.74 412	90.71 376	99.59 135	98.47 329

test222					98.17 268	93.24 208	92.74 409	97.61 341	75.17 491	94.65 386	96.69 348	90.96 312			98.66 340	97.66 407

jason		94.39 334	94.04 341	95.41 329	98.29 246	87.85 374	92.74 409	96.75 376	85.38 450	95.29 368	96.15 376	88.21 350	99.65 171	94.24 276	99.34 238	98.74 293
jason: jason.
testing91		89.67 428	88.55 433	93.04 420	95.90 426	81.80 458	92.71 411	93.71 427	93.71 294	90.18 467	90.15 472	57.11 481	99.22 350	87.17 434	96.32 441	98.12 367

testing99		89.21 432	88.04 438	92.70 433	95.78 435	81.00 465	92.65 412	92.03 450	93.20 317	89.90 472	90.08 474	55.25 490	99.14 360	87.54 427	95.95 447	97.97 384

Patchmatch-RL test		94.66 320	94.49 321	95.19 337	98.54 213	88.91 339	92.57 413	98.74 208	91.46 370	98.32 146	97.75 255	77.31 435	98.81 405	96.06 150	99.61 125	97.85 393

DeepPCF-MVS	94.58 5	96.90 187	96.43 229	98.31 74	97.48 361	97.23 43	92.56 414	98.60 235	92.84 335	98.54 114	97.40 287	96.64 114	98.78 407	94.40 270	99.41 217	98.93 257

N_pmnet		95.18 294	94.23 333	98.06 100	97.85 300	96.55 61	92.49 415	91.63 455	89.34 401	98.09 178	97.41 286	90.33 321	99.06 375	91.58 350	99.31 248	98.56 315

testing11		88.93 434	87.63 443	92.80 430	95.87 428	81.49 460	92.48 416	91.54 456	91.62 358	88.27 481	90.24 470	55.12 493	99.11 367	87.30 432	96.28 443	97.81 397

Syy-MVS		92.09 395	91.80 389	92.93 427	95.19 453	82.65 450	92.46 417	91.35 458	90.67 385	91.76 455	87.61 482	85.64 379	98.50 438	94.73 257	96.84 421	97.65 408

myMVS_eth3d		87.16 453	85.61 456	91.82 449	95.19 453	79.32 471	92.46 417	91.35 458	90.67 385	91.76 455	87.61 482	41.96 501	98.50 438	82.66 465	96.84 421	97.65 408

BH-w/o		92.14 393	91.94 385	92.73 432	97.13 386	85.30 418	92.46 417	95.64 398	89.33 402	94.21 396	92.74 446	89.60 330	98.24 455	81.68 469	94.66 467	94.66 475

IterMVS-SCA-FT		95.86 257	96.19 243	94.85 357	97.68 338	85.53 413	92.42 420	97.63 340	96.99 107	98.36 138	98.54 134	87.94 351	99.75 84	97.07 106	99.08 284	99.27 174

IterMVS		95.42 282	95.83 265	94.20 392	97.52 357	83.78 444	92.41 421	97.47 345	95.49 212	98.06 183	98.49 138	87.94 351	99.58 203	96.02 155	99.02 291	99.23 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing222		87.35 450	85.50 457	92.93 427	95.79 434	82.83 448	92.40 422	90.10 475	92.80 336	88.87 478	89.02 476	48.34 500	98.70 417	75.40 485	96.74 427	97.27 427

DELS-MVS		96.17 242	96.23 241	95.99 285	97.55 356	90.04 305	92.38 423	98.52 245	94.13 279	96.55 306	97.06 319	94.99 202	99.58 203	95.62 183	99.28 252	98.37 337
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		93.34 368	92.55 377	95.73 304	95.69 440	89.08 334	92.36 424	97.11 357	91.47 368	95.42 365	88.94 479	82.26 405	99.48 239	93.84 297	95.81 452	98.62 308

blended_shiyan6		93.34 368	92.54 378	95.73 304	95.68 441	89.08 334	92.35 425	97.10 358	91.47 368	95.37 367	88.96 478	82.26 405	99.48 239	93.83 298	95.85 448	98.62 308

new_pmnet		92.34 389	91.69 394	94.32 388	96.23 412	89.16 329	92.27 426	92.88 440	84.39 462	95.29 368	96.35 368	85.66 378	96.74 482	84.53 457	97.56 401	97.05 430

myMVS_eth3d28		88.32 441	87.73 441	90.11 464	96.42 406	74.96 493	92.21 427	92.37 448	93.56 300	90.14 468	89.61 475	56.13 486	98.05 463	81.84 467	97.26 414	97.33 425

CHOSEN 1792x2688		94.10 343	93.41 355	96.18 275	99.16 93	90.04 305	92.15 428	98.68 221	79.90 480	96.22 326	97.83 243	87.92 355	99.42 270	89.18 404	99.65 108	99.08 224

blend_shiyan4		88.73 437	86.43 452	95.61 312	95.31 451	89.17 326	92.13 429	97.10 358	91.59 363	94.15 400	87.38 484	52.97 497	99.40 282	91.84 343	75.42 495	98.27 353

xiu_mvs_v2_base		94.22 337	94.63 313	92.99 424	97.32 377	84.84 429	92.12 430	97.84 320	91.96 351	94.17 398	93.43 432	96.07 150	99.71 126	91.27 354	97.48 405	94.42 477

lupinMVS		93.77 352	93.28 356	95.24 335	97.68 338	87.81 375	92.12 430	96.05 387	84.52 459	94.48 391	95.06 409	86.90 365	99.63 182	93.62 309	99.13 275	98.27 353

pmmvs4		94.82 310	94.19 336	96.70 220	97.42 368	92.75 221	92.09 432	96.76 375	86.80 435	95.73 354	97.22 304	89.28 339	98.89 395	93.28 317	99.14 273	98.46 331

PAPR		92.22 391	91.27 401	95.07 344	95.73 439	88.81 342	91.97 433	97.87 317	85.80 444	90.91 459	92.73 447	91.16 306	98.33 451	79.48 476	95.76 457	98.08 369

UWE-MVS		87.57 449	86.72 450	90.13 463	95.21 452	73.56 494	91.94 434	83.78 494	88.73 412	93.00 435	92.87 443	55.22 491	99.25 342	81.74 468	97.96 378	97.59 414

gbinet_0.2-2-1-0.02		92.86 378	91.78 390	96.13 280	94.34 468	90.06 303	91.90 435	96.63 382	91.73 355	94.24 395	86.22 490	80.26 420	99.56 211	93.87 295	96.80 425	98.77 289

PS-MVSNAJ		94.10 343	94.47 323	93.00 423	97.35 372	84.88 426	91.86 436	97.84 320	91.96 351	94.17 398	92.50 451	95.82 160	99.71 126	91.27 354	97.48 405	94.40 478

c3_l		95.20 293	95.32 277	94.83 359	96.19 414	86.43 400	91.83 437	98.35 270	93.47 305	97.36 239	97.26 302	88.69 342	99.28 334	95.41 204	99.36 228	98.78 280

icg_test_0407_2		95.88 255	96.39 232	94.36 384	97.83 309	86.11 405	91.82 438	98.82 191	94.48 262	97.57 222	97.14 309	96.08 148	98.20 459	95.00 238	98.78 321	98.78 280

test0.0.03 1		90.11 418	89.21 426	92.83 429	93.89 478	86.87 394	91.74 439	88.74 480	92.02 349	94.71 385	91.14 465	73.92 451	94.48 491	83.75 463	92.94 474	97.16 428

UBG		88.29 442	87.17 445	91.63 451	96.08 421	78.21 475	91.61 440	91.50 457	89.67 399	89.71 473	88.97 477	59.01 478	98.91 392	81.28 471	96.72 429	97.77 400

SSC-MVS3.2		95.75 263	96.56 217	93.34 408	98.69 185	80.75 466	91.60 441	97.43 347	97.37 95	96.99 269	97.02 322	93.69 246	99.71 126	96.32 139	99.89 26	99.55 70

FPMVS		89.92 424	88.63 432	93.82 398	98.37 239	96.94 48	91.58 442	93.34 435	88.00 422	90.32 465	97.10 317	70.87 464	91.13 495	71.91 491	96.16 446	93.39 485

ET-MVSNet_ETH3D		91.12 409	89.67 423	95.47 325	96.41 407	89.15 330	91.54 443	90.23 473	89.07 405	86.78 487	92.84 444	69.39 468	99.44 263	94.16 279	96.61 433	97.82 395

WBMVS		91.11 410	90.72 412	92.26 444	95.99 423	77.98 479	91.47 444	95.90 393	91.63 357	95.90 344	96.45 361	59.60 477	99.46 252	89.97 393	99.59 135	99.33 155

PVSNet_Blended		93.96 349	93.65 349	94.91 352	97.79 323	87.40 384	91.43 445	98.68 221	84.50 460	94.51 389	94.48 422	93.04 262	99.30 326	89.77 396	98.61 345	98.02 381

CLD-MVS		95.47 279	95.07 287	96.69 221	98.27 252	92.53 224	91.36 446	98.67 224	91.22 375	95.78 351	94.12 426	95.65 172	98.98 386	90.81 368	99.72 88	98.57 314
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		94.89 307	94.93 293	94.75 364	95.99 423	86.12 404	91.35 447	98.49 248	93.40 306	97.12 255	97.25 303	86.87 367	99.35 308	95.08 232	98.82 318	98.78 280

cl____		94.73 312	94.64 311	95.01 347	95.85 430	87.00 391	91.33 448	98.08 303	93.34 309	97.10 257	97.33 298	84.01 395	99.30 326	95.14 227	99.56 146	98.71 300

DIV-MVS_self_test		94.73 312	94.64 311	95.01 347	95.86 429	87.00 391	91.33 448	98.08 303	93.34 309	97.10 257	97.34 297	84.02 394	99.31 322	95.15 226	99.55 153	98.72 296

miper_ehance_all_eth		94.69 317	94.70 308	94.64 367	95.77 436	86.22 403	91.32 450	98.24 280	91.67 356	97.05 264	96.65 350	88.39 347	99.22 350	94.88 247	98.34 363	98.49 328

usedtu_dtu_shiyan1		94.61 323	94.29 330	95.57 315	97.93 295	88.45 349	91.30 451	97.64 337	91.61 359	95.85 347	95.79 391	86.65 369	99.48 239	92.92 326	98.97 294	98.78 280

FE-MVSNET3		94.61 323	94.29 330	95.57 315	97.93 295	88.45 349	91.30 451	97.64 337	91.61 359	95.85 347	95.79 391	86.65 369	99.48 239	92.92 326	98.97 294	98.78 280

pmmvs3		90.00 421	88.90 431	93.32 409	94.20 474	85.34 416	91.25 453	92.56 447	78.59 484	93.82 409	95.17 406	67.36 471	98.69 419	89.08 406	98.03 376	95.92 459

HyFIR lowres test		93.72 356	92.65 373	96.91 202	98.93 140	91.81 253	91.23 454	98.52 245	82.69 466	96.46 311	96.52 358	80.38 416	99.90 17	90.36 387	98.79 320	99.03 233

DPM-MVS		93.68 358	92.77 371	96.42 251	97.91 297	92.54 223	91.17 455	97.47 345	84.99 455	93.08 434	94.74 415	89.90 328	99.00 382	87.54 427	98.09 374	97.72 405

CL-MVSNet_self_test		95.04 300	94.79 306	95.82 296	97.51 358	89.79 311	91.14 456	96.82 373	93.05 325	96.72 290	96.40 365	90.82 313	99.16 358	91.95 339	98.66 340	98.50 327

miper_lstm_enhance		94.81 311	94.80 305	94.85 357	96.16 416	86.45 399	91.14 456	98.20 285	93.49 304	97.03 265	97.37 295	84.97 386	99.26 339	95.28 212	99.56 146	98.83 274

cl22		93.25 373	92.84 367	94.46 381	94.30 470	86.00 409	91.09 458	96.64 381	90.74 382	95.79 349	96.31 369	78.24 427	98.77 409	94.15 280	98.34 363	98.62 308

MSDG		95.33 287	95.13 284	95.94 292	97.40 369	91.85 251	91.02 459	98.37 266	95.30 222	96.31 320	95.99 383	94.51 221	98.38 447	89.59 398	97.65 399	97.60 413

wanda-best-256-512		92.66 383	91.75 392	95.40 330	94.99 457	88.19 360	90.89 460	97.05 363	91.02 379	94.75 381	87.24 485	80.36 417	99.46 252	93.63 307	95.85 448	98.55 317

FE-blended-shiyan7		92.66 383	91.75 392	95.40 330	94.99 457	88.19 360	90.89 460	97.05 363	91.02 379	94.75 381	87.24 485	80.36 417	99.46 252	93.63 307	95.85 448	98.55 317

IB-MVS	85.98 20	88.63 438	86.95 449	93.68 403	95.12 455	84.82 430	90.85 462	90.17 474	87.55 426	88.48 480	91.34 463	58.01 479	99.59 200	87.24 433	93.80 473	96.63 449
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		93.47 364	93.03 361	94.79 361	94.05 477	92.12 240	90.82 463	90.01 476	85.02 454	97.26 244	98.28 177	93.57 248	97.03 474	92.51 332	95.75 458	95.23 471

test123		12.59 466	15.49 469	3.87 483	6.07 506	2.55 508	90.75 464	2.59 508	2.52 501	5.20 503	13.02 500	4.96 505	1.85 503	5.20 500	9.09 500	7.23 498

ppachtmachnet_test		94.49 331	94.84 301	93.46 407	96.16 416	82.10 454	90.59 465	97.48 344	90.53 387	97.01 267	97.59 269	91.01 310	99.36 304	93.97 291	99.18 268	98.94 253

PMMVS		92.39 387	91.08 404	96.30 265	93.12 484	92.81 217	90.58 466	95.96 391	79.17 483	91.85 454	92.27 452	90.29 325	98.66 424	89.85 395	96.68 431	97.43 420

our_test_3		94.20 341	94.58 318	93.07 419	96.16 416	81.20 463	90.42 467	96.84 371	90.72 383	97.14 253	97.13 313	90.47 317	99.11 367	94.04 286	98.25 367	98.91 261

YYNet1		94.73 312	94.84 301	94.41 383	97.47 365	85.09 424	90.29 468	95.85 395	92.52 340	97.53 225	97.76 252	91.97 296	99.18 353	93.31 316	96.86 420	98.95 250

MDA-MVSNet_test_wron		94.73 312	94.83 303	94.42 382	97.48 361	85.15 422	90.28 469	95.87 394	92.52 340	97.48 232	97.76 252	91.92 299	99.17 357	93.32 315	96.80 425	98.94 253

GA-MVS		92.83 380	92.15 384	94.87 356	96.97 390	87.27 387	90.03 470	96.12 386	91.83 354	94.05 404	94.57 417	76.01 442	98.97 390	92.46 333	97.34 411	98.36 342

miper_enhance_ethall		93.14 375	92.78 370	94.20 392	93.65 480	85.29 419	89.97 471	97.85 318	85.05 452	96.15 333	94.56 418	85.74 376	99.14 360	93.74 302	98.34 363	98.17 365

test-LLR		89.97 423	89.90 421	90.16 461	94.24 472	74.98 490	89.89 472	89.06 477	92.02 349	89.97 470	90.77 468	73.92 451	98.57 431	91.88 341	97.36 409	96.92 434

TESTMET0.1,1		87.20 452	86.57 451	89.07 468	93.62 481	72.84 496	89.89 472	87.01 488	85.46 448	89.12 477	90.20 471	56.00 487	97.72 468	90.91 364	96.92 417	96.64 447

test-mter		87.92 446	87.17 445	90.16 461	94.24 472	74.98 490	89.89 472	89.06 477	86.44 438	89.97 470	90.77 468	54.96 494	98.57 431	91.88 341	97.36 409	96.92 434

PCF-MVS	89.43 18	92.12 394	90.64 414	96.57 232	97.80 318	93.48 198	89.88 475	98.45 251	74.46 492	96.04 336	95.68 395	90.71 315	99.31 322	73.73 487	99.01 293	96.91 436
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0515		90.43 416	89.18 429	94.17 394	97.07 388	85.44 414	89.75 476	87.58 485	88.28 418	93.69 417	91.72 459	65.27 472	99.58 203	90.59 380	98.67 338	97.50 419

KD-MVS_2432*1600		88.93 434	87.74 439	92.49 437	88.04 499	81.99 455	89.63 477	95.62 399	91.35 372	95.06 373	93.11 434	56.58 483	98.63 426	85.19 451	95.07 462	96.85 439

miper_refine_blended		88.93 434	87.74 439	92.49 437	88.04 499	81.99 455	89.63 477	95.62 399	91.35 372	95.06 373	93.11 434	56.58 483	98.63 426	85.19 451	95.07 462	96.85 439

testmvs		12.33 467	15.23 470	3.64 484	5.77 507	2.23 509	88.99 479	3.62 507	2.30 502	5.29 502	13.09 499	4.52 506	1.95 502	5.16 501	8.32 501	6.75 499

cascas		91.89 400	91.35 398	93.51 406	94.27 471	85.60 412	88.86 480	98.61 234	79.32 482	92.16 451	91.44 462	89.22 340	98.12 460	90.80 369	97.47 407	96.82 442

PAPM		87.64 447	85.84 454	93.04 420	96.54 402	84.99 425	88.42 481	95.57 402	79.52 481	83.82 489	93.05 440	80.57 415	98.41 444	62.29 494	92.79 475	95.71 464

PVSNet	86.72 19	91.10 411	90.97 407	91.49 452	97.56 355	78.04 477	87.17 482	94.60 420	84.65 458	92.34 449	92.20 454	87.37 362	98.47 441	85.17 453	97.69 394	97.96 385

0.4-1-1-0.1		83.64 457	80.50 460	93.08 418	90.32 495	85.42 415	86.48 483	87.71 484	83.60 463	80.38 495	75.45 494	53.19 496	98.91 392	86.46 438	80.88 492	94.93 474

PMMVS2		93.66 359	94.07 340	92.45 440	97.57 353	80.67 467	86.46 484	96.00 389	93.99 287	97.10 257	97.38 293	89.90 328	97.82 466	88.76 409	99.47 191	98.86 272

CHOSEN 280x420		89.98 422	89.19 428	92.37 441	95.60 443	81.13 464	86.22 485	97.09 360	81.44 474	87.44 484	93.15 433	73.99 449	99.47 245	88.69 411	99.07 286	96.52 451

dongtai		63.43 462	63.37 465	63.60 480	83.91 502	53.17 504	85.14 486	43.40 506	77.91 488	80.96 493	79.17 493	36.36 503	77.10 498	37.88 498	45.63 498	60.54 495

kuosan		54.81 464	54.94 467	54.42 481	74.43 503	50.03 505	84.98 487	44.27 505	61.80 496	62.49 500	70.43 497	35.16 504	58.04 500	19.30 499	41.61 499	55.19 496

0.3-1-1-0.015		82.33 460	78.89 462	92.66 434	88.57 497	84.69 431	84.76 488	88.02 483	82.48 468	77.55 497	72.96 495	49.60 499	98.87 399	86.05 439	80.02 494	94.43 476

tmp_tt		57.23 463	62.50 466	41.44 482	34.77 505	49.21 506	83.93 489	60.22 504	15.31 498	71.11 498	79.37 492	70.09 467	44.86 501	64.76 493	82.93 491	30.25 497

0.4-1-1-0.2		82.53 459	79.25 461	92.37 441	88.10 498	83.96 443	83.72 490	88.15 482	82.14 469	78.97 496	72.49 496	53.22 495	98.84 401	85.99 441	80.50 493	94.30 479

PVSNet_0	81.89 21	84.49 455	83.21 458	88.34 471	95.76 437	74.97 492	83.49 491	92.70 444	78.47 485	87.94 482	86.90 489	83.38 399	96.63 483	73.44 489	66.86 497	93.40 484

E-PMN		89.52 430	89.78 422	88.73 469	93.14 483	77.61 480	83.26 492	92.02 451	94.82 246	93.71 414	93.11 434	75.31 445	96.81 478	85.81 443	96.81 424	91.77 489

EMVS		89.06 433	89.22 425	88.61 470	93.00 485	77.34 482	82.91 493	90.92 463	94.64 254	92.63 446	91.81 458	76.30 440	97.02 475	83.83 461	96.90 419	91.48 490

MVE	73.61 22	86.48 454	85.92 453	88.18 473	96.23 412	85.28 420	81.78 494	75.79 498	86.01 440	82.53 491	91.88 457	92.74 270	87.47 497	71.42 492	94.86 466	91.78 488
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		66.88 461	66.13 464	69.11 479	62.68 504	25.73 507	49.76 495	96.04 388	14.32 499	64.27 499	91.69 460	73.45 456	88.05 496	76.06 484	66.94 496	93.54 482

mmdepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

monomultidepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

test_blank		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet_test		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

DCPMVS		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

cdsmvs_eth3d_5k		24.22 465	32.30 468	0.00 485	0.00 508	0.00 510	0.00 496	98.10 301	0.00 503	0.00 504	95.06 409	97.54 44	0.00 504	0.00 502	0.00 502	0.00 500

pcd_1.5k_mvsjas		7.98 468	10.65 471	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	95.82 160	0.00 504	0.00 502	0.00 502	0.00 500

sosnet-low-res		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

sosnet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uncertanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

Regformer		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

ab-mvs-re		7.91 469	10.55 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	94.94 411	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

WAC-MVS						79.32 471								85.41 449

MSC_two_6792asdad				98.22 83	97.75 330	95.34 122		98.16 295					99.75 84	95.87 167	99.51 177	99.57 58

PC_three_1452									87.24 428	98.37 135	97.44 284	97.00 80	96.78 480	92.01 337	99.25 258	99.21 188

No_MVS				98.22 83	97.75 330	95.34 122		98.16 295					99.75 84	95.87 167	99.51 177	99.57 58

test_one_0601					99.05 119	95.50 109		98.87 165	97.21 103	98.03 187	98.30 172	96.93 88

eth-test2					0.00 508

eth-test					0.00 508

ZD-MVS					98.43 233	95.94 86		98.56 243	90.72 383	96.66 296	97.07 318	95.02 201	99.74 94	91.08 358	98.93 303

IU-MVS					99.22 78	95.40 112		98.14 298	85.77 445	98.36 138				95.23 216	99.51 177	99.49 95

test_241102_TWO								98.83 183	96.11 165	98.62 105	98.24 184	96.92 91	99.72 110	95.44 198	99.49 184	99.49 95

test_241102_ONE					99.22 78	95.35 117		98.83 183	96.04 174	99.08 54	98.13 200	97.87 28	99.33 313

test_0728_THIRD									96.62 125	98.40 132	98.28 177	97.10 68	99.71 126	95.70 173	99.62 115	99.58 50

GSMVS																98.06 375

test_part2					99.03 121	96.07 80				98.08 180

sam_mvs1												77.80 429				98.06 375

sam_mvs												77.38 433

MTGPA								98.73 209

test_post											10.87 501	76.83 437	99.07 374

patchmatchnet-post											96.84 336	77.36 434	99.42 270

gm-plane-assit					91.79 490	71.40 499			81.67 471		90.11 473		98.99 384	84.86 455

test9_res														91.29 353	98.89 310	99.00 237

agg_prior2														90.34 388	98.90 306	99.10 223

agg_prior					97.80 318	94.96 138		98.36 267		93.49 424			99.53 222

TestCases				98.06 100	99.08 109	96.16 75		99.16 66	94.35 271	97.78 214	98.07 211	95.84 157	99.12 364	91.41 351	99.42 213	98.91 261

test_prior				97.46 153	97.79 323	94.26 168		98.42 258					99.34 311			98.79 279

新几何1				97.25 173	98.29 246	94.70 145		97.73 326	77.98 486	94.83 380	96.67 349	92.08 294	99.45 260	88.17 419	98.65 342	97.61 412

旧先验1					97.80 318	93.87 180		97.75 325			97.04 321	93.57 248			98.68 337	98.72 296

原ACMM1				96.58 230	98.16 270	92.12 240		98.15 297	85.90 443	93.49 424	96.43 362	92.47 285	99.38 295	87.66 424	98.62 344	98.23 357

testdata2													99.46 252	87.84 420

segment_acmp												95.34 185

testdata				95.70 307	98.16 270	90.58 284		97.72 327	80.38 478	95.62 356	97.02 322	92.06 295	98.98 386	89.06 407	98.52 350	97.54 416

test12				97.46 153	97.61 350	94.07 172		97.78 324		93.57 422		93.31 254	99.42 270		98.78 321	98.89 265

plane_prior7					98.70 182	94.67 146

plane_prior6					98.38 238	94.37 161						91.91 300

plane_prior5								98.75 206					99.46 252	92.59 330	99.20 263	99.28 170

plane_prior4											96.77 342

plane_prior3						94.51 154			95.29 223	96.16 331

plane_prior1					98.49 224

n2								0.00 509

nn								0.00 509

door-mid								98.17 291

lessismore_v0				97.05 189	99.36 54	92.12 240		84.07 492		98.77 91	98.98 71	85.36 381	99.74 94	97.34 93	99.37 224	99.30 162

LGP-MVS_train				98.74 37	99.15 96	97.02 45		99.02 119	95.15 228	98.34 142	98.23 186	97.91 25	99.70 135	94.41 268	99.73 83	99.50 87

test11								98.08 303

door								97.81 323

HQP5-MVS						92.47 227

BP-MVS														90.51 383

HQP4-MVS										92.87 437			99.23 348			99.06 229

HQP3-MVS								98.43 255							98.74 330

HQP2-MVS												90.33 321

NP-MVS					98.14 274	93.72 186					95.08 407

ACMMP++_ref															99.52 172

ACMMP++															99.55 153

Test By Simon												94.51 221

ITE_SJBPF				97.85 116	98.64 189	96.66 57		98.51 247	95.63 202	97.22 246	97.30 300	95.52 176	98.55 434	90.97 362	98.90 306	98.34 343

DeepMVS_CX				77.17 478	90.94 492	85.28 420		74.08 501	52.51 497	80.87 494	88.03 481	75.25 446	70.63 499	59.23 496	84.94 489	75.62 493

High-resolution multi-view benchmark