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.

SIFT-PCN-Cal		98.24 394	98.51 350	97.43 488	99.65 254	98.64 373	97.09 507	99.35 391	98.16 414	99.69 201	99.52 339	95.59 411	99.83 337	97.57 375	100.00 1	93.81 542

ELoFTR		99.25 216	99.26 202	99.21 346	99.86 60	98.66 366	99.00 292	99.93 43	98.56 365	99.83 110	99.83 83	97.34 343	99.92 154	99.03 191	100.00 1	99.04 430

SIFT-NCMNet		98.18 401	98.46 357	97.36 493	99.67 247	99.19 280	96.33 532	98.99 455	98.83 327	99.62 248	99.63 266	95.41 420	99.33 519	97.64 368	100.00 1	93.54 546

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 87	99.01 286	99.99 12	99.99 3	99.98 14	99.88 50	99.97 2	99.99 7	99.96 9	100.00 1	99.98 5

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 70	99.12 245	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 99	99.70 109	99.17 220	99.97 21	99.99 3	99.96 34	99.82 91	99.94 4	100.00 1	99.95 14	100.00 1	99.80 67

test_vis3_rt		99.89 3	99.90 4	99.87 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 113	100.00 1	99.89 41	99.79 22	99.88 242	99.98 1	100.00 1	99.98 5

IterMVS-SCA-FT		99.00 300	99.16 219	98.51 437	99.75 182	95.90 502	98.07 442	99.84 105	99.84 76	99.89 72	99.73 177	96.01 403	99.99 7	99.33 126	100.00 1	99.63 176

new-patchmatchnet		99.35 191	99.57 105	98.71 426	99.82 99	96.62 484	98.55 384	99.75 183	99.50 192	99.88 82	99.87 56	99.31 89	99.88 242	99.43 106	100.00 1	99.62 188

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 95	99.70 130	99.92 59	99.93 22	99.45 63	99.97 44	99.36 119	100.00 1	99.85 50

UA-Net		99.78 37	99.76 49	99.86 30	99.72 202	99.71 101	99.91 4	99.95 38	99.96 28	99.71 193	99.91 31	99.15 115	99.97 44	99.50 95	100.00 1	99.90 30

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 48	99.85 95	99.95 32	99.98 14	99.92 27	99.28 93	99.98 26	99.75 56	100.00 1	99.94 18

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 57	99.70 38	99.86 89	99.89 56	99.98 14	99.90 36	99.94 4	99.98 26	99.75 56	100.00 1	99.90 30

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 54	99.72 33	99.88 74	99.92 45	99.98 14	99.93 22	99.94 4	99.98 26	99.77 55	100.00 1	99.92 25

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 21	99.99 3	100.00 1	99.98 13	99.78 23	100.00 1	99.92 30	100.00 1	99.87 45

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 26	99.77 19	99.80 143	99.73 113	99.97 24	99.92 27	99.77 25	99.98 26	99.43 106	100.00 1	99.90 30

IterMVS		98.97 304	99.16 219	98.42 442	99.74 193	95.64 507	98.06 444	99.83 115	99.83 82	99.85 101	99.74 172	96.10 402	99.99 7	99.27 138	100.00 1	99.63 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 49	100.00 1	99.97 14	99.61 41	99.97 44	99.75 56	100.00 1	99.84 55

PDCNetPlus		98.55 361	98.50 353	98.69 427	99.64 256	96.12 497	97.67 477	100.00 1	98.34 400	99.79 133	99.75 164	92.45 467	99.98 26	98.92 215	99.99 19	99.96 13

fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 112	99.53 176	99.15 229	99.89 68	99.99 3	99.98 14	99.86 63	99.13 120	99.98 26	99.93 25	99.99 19	99.92 25

fmvsm_s_conf0.5_n_10		99.77 44	99.73 54	99.88 19	99.81 112	99.75 79	99.06 268	99.85 95	99.99 3	99.97 24	99.84 76	99.12 123	99.98 26	99.95 14	99.99 19	99.90 30

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 60	99.80 51	98.94 314	99.96 30	99.98 18	99.96 34	99.78 134	99.88 11	99.98 26	99.96 9	99.99 19	99.90 30

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 90	99.59 160	98.97 305	99.92 47	99.99 3	99.97 24	99.84 76	99.90 9	99.94 98	99.94 20	99.99 19	99.92 25

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 99	99.75 79	99.02 281	99.87 80	99.98 18	99.98 14	99.81 98	99.07 134	99.97 44	99.91 33	99.99 19	99.92 25

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 146	99.78 57	99.00 292	99.97 21	99.96 28	99.97 24	99.56 321	99.92 8	99.93 120	99.91 33	99.99 19	99.83 59

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 46	99.86 18	99.08 262	99.97 21	99.98 18	99.96 34	99.79 121	99.90 9	99.99 7	99.96 9	99.99 19	99.90 30

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 112	99.71 101	98.97 305	99.92 47	99.98 18	99.97 24	99.86 63	99.53 58	99.95 81	99.88 41	99.99 19	99.89 38

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 70	98.92 318	99.98 13	99.99 3	99.99 7	99.88 50	99.43 67	99.94 98	99.94 20	99.99 19	99.99 2

mmtdpeth		99.78 37	99.83 21	99.66 153	99.85 75	99.05 308	99.79 15	99.97 21	100.00 1	99.43 318	99.94 19	99.64 35	99.94 98	99.83 46	99.99 19	99.98 5

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 212	99.94 3	100.00 1	99.97 25	99.89 72	99.99 12	99.63 37	99.97 44	99.87 44	99.99 19	100.00 1

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 46	99.64 136	99.12 245	99.91 57	99.98 18	99.95 45	99.67 235	99.67 34	99.99 7	99.94 20	99.99 19	99.88 41

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 46	99.66 123	99.11 250	99.91 57	99.98 18	99.96 34	99.64 250	99.60 44	99.99 7	99.95 14	99.99 19	99.88 41

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 41	99.10 254	99.98 13	99.99 3	99.98 14	99.91 31	99.68 33	99.93 120	99.93 25	99.99 19	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 57	99.07 267	99.98 13	99.99 3	99.98 14	99.90 36	99.88 11	99.92 154	99.93 25	99.99 19	99.98 5

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 75	99.78 57	99.03 277	99.96 30	99.99 3	99.97 24	99.84 76	99.78 23	99.92 154	99.92 30	99.99 19	99.92 25

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 305	99.98 13	99.99 3	99.96 34	99.85 68	99.93 7	99.99 7	99.94 20	99.99 19	99.93 21

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 46	99.55 173	99.17 220	99.98 13	99.99 3	99.96 34	99.84 76	99.96 3	99.99 7	99.96 9	99.99 19	99.88 41

test_vis1_n_1920		99.72 53	99.88 7	99.27 334	99.93 24	97.84 438	99.34 149	100.00 1	99.99 3	99.99 7	99.82 91	99.87 13	99.99 7	99.97 4	99.99 19	99.97 10

test_fmvs2		99.72 53	99.85 17	99.34 309	99.91 31	98.08 425	99.48 109	100.00 1	99.90 49	99.99 7	99.91 31	99.50 62	99.98 26	99.98 1	99.99 19	99.96 13

test_fmvs3		99.83 21	99.93 2	99.53 232	99.96 7	98.62 376	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 7	99.98 1	99.99 19	99.98 5

test_f		99.75 49	99.88 7	99.37 295	99.96 7	98.21 410	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 50	99.94 98	99.97 4	99.99 19	99.97 10

test2506		94.73 506	94.59 506	95.15 526	99.59 276	85.90 556	99.75 25	74.01 559	99.89 56	99.71 193	99.86 63	79.00 539	99.90 205	99.52 91	99.99 19	99.65 158

test1111		97.74 428	98.16 395	96.49 518	99.60 270	89.86 554	99.71 37	91.21 551	99.89 56	99.88 82	99.87 56	93.73 446	99.90 205	99.56 83	99.99 19	99.70 107

ECVR-MVS		97.73 429	98.04 403	96.78 510	99.59 276	90.81 548	99.72 33	90.43 553	99.89 56	99.86 96	99.86 63	93.60 448	99.89 227	99.46 101	99.99 19	99.65 158

pmmvs-eth3d		99.48 135	99.47 132	99.51 238	99.77 159	99.41 219	98.81 340	99.66 240	99.42 221	99.75 165	99.66 241	99.20 107	99.76 415	98.98 199	99.99 19	99.36 341

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 26	99.82 10	99.82 122	99.84 76	99.94 48	99.91 31	99.13 120	99.96 69	99.83 46	99.99 19	99.83 59

v8		99.68 64	99.69 60	99.65 160	99.80 123	99.40 220	99.66 57	99.76 178	99.64 160	99.93 53	99.85 68	98.66 204	99.84 314	99.88 41	99.99 19	99.71 104

v10		99.69 59	99.69 60	99.66 153	99.81 112	99.39 224	99.66 57	99.75 183	99.60 177	99.92 59	99.87 56	98.75 190	99.86 278	99.90 37	99.99 19	99.73 95

CHOSEN 1792x2688		99.39 176	99.30 188	99.65 160	99.88 46	99.25 259	98.78 347	99.88 74	98.66 353	99.96 34	99.79 121	97.45 337	99.93 120	99.34 123	99.99 19	99.78 77

PVSNet_Blended_VisFu		99.40 172	99.38 161	99.44 263	99.90 37	98.66 366	98.94 314	99.91 57	97.97 430	99.79 133	99.73 177	99.05 143	99.97 44	99.15 164	99.99 19	99.68 126

IterMVS-LS		99.41 170	99.47 132	99.25 341	99.81 112	98.09 421	98.85 329	99.76 178	99.62 165	99.83 110	99.64 250	98.54 225	99.97 44	99.15 164	99.99 19	99.68 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DeepC-MVS	98.90 4	99.62 94	99.61 89	99.67 145	99.72 202	99.44 205	99.24 194	99.71 207	99.27 246	99.93 53	99.90 36	99.70 31	99.93 120	98.99 197	99.99 19	99.64 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 47	99.90 49	99.97 24	99.87 56	99.81 20	99.95 81	99.54 87	99.99 19	99.80 67
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
FE-MVSNET2		99.68 64	99.67 65	99.72 122	99.86 60	99.68 117	99.46 116	99.88 74	99.62 165	99.87 92	99.85 68	99.06 141	99.85 297	99.44 104	99.98 54	99.63 176

Elysia		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 170	99.94 36	99.91 62	99.76 156	98.55 220	99.99 7	99.70 61	99.98 54	99.72 99

StellarMVS		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 170	99.94 36	99.91 62	99.76 156	98.55 220	99.99 7	99.70 61	99.98 54	99.72 99

LuminaMVS		99.39 176	99.28 197	99.73 113	99.83 90	99.49 184	99.00 292	99.05 449	99.81 92	99.89 72	99.79 121	96.54 380	99.97 44	99.64 73	99.98 54	99.73 95

VortexMVS		99.13 262	99.24 208	98.79 415	99.67 247	96.60 486	99.24 194	99.80 143	99.85 72	99.93 53	99.84 76	95.06 424	99.89 227	99.80 52	99.98 54	99.89 38

fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 195	99.74 193	98.93 329	98.85 329	99.96 30	99.96 28	99.97 24	99.76 156	99.82 18	99.96 69	99.95 14	99.98 54	99.90 30

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 137	99.72 95	98.84 332	99.96 30	99.96 28	99.96 34	99.72 187	99.71 28	99.99 7	99.93 25	99.98 54	99.85 50

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 72	99.75 182	99.56 169	98.98 303	99.94 41	99.92 45	99.97 24	99.72 187	99.84 16	99.92 154	99.91 33	99.98 54	99.89 38

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 99	99.76 70	98.88 323	99.92 47	99.98 18	99.98 14	99.85 68	99.42 69	99.94 98	99.93 25	99.98 54	99.94 18

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 75	99.82 41	99.03 277	99.96 30	99.99 3	99.97 24	99.84 76	99.58 50	99.93 120	99.92 30	99.98 54	99.93 21

MM		99.18 246	99.05 259	99.55 221	99.35 390	98.81 349	99.05 269	97.79 514	99.99 3	99.48 305	99.59 306	96.29 394	99.95 81	99.94 20	99.98 54	99.88 41

test_fmvs1_n		99.68 64	99.81 28	99.28 329	99.95 15	97.93 434	99.49 107	100.00 1	99.82 86	99.99 7	99.89 41	99.21 105	99.98 26	99.97 4	99.98 54	99.93 21

mvsany_test3		99.85 12	99.88 7	99.75 98	99.95 15	99.37 231	99.53 92	99.98 13	99.77 108	99.99 7	99.95 16	99.85 14	99.94 98	99.95 14	99.98 54	99.94 18

Anonymous20240521		99.44 155	99.42 152	99.49 244	99.89 40	98.96 323	99.62 67	99.76 178	99.85 72	99.82 112	99.88 50	96.39 387	99.97 44	99.59 78	99.98 54	99.55 236

D2MVS		99.22 232	99.19 216	99.29 326	99.69 231	98.74 358	98.81 340	99.41 370	98.55 367	99.68 208	99.69 216	98.13 285	99.87 258	98.82 225	99.98 54	99.24 371

CHOSEN 280x420		98.41 379	98.41 366	98.40 443	99.34 399	95.89 503	96.94 517	99.44 363	98.80 333	99.25 369	99.52 339	93.51 449	99.98 26	98.94 212	99.98 54	99.32 355

MGCNet		98.61 351	98.30 381	99.52 234	97.88 533	98.95 324	98.76 349	94.11 546	99.84 76	99.32 351	99.57 317	95.57 413	99.95 81	99.68 66	99.98 54	99.68 126

v1192		99.57 102	99.57 105	99.57 210	99.77 159	99.22 270	99.04 274	99.60 285	99.18 263	99.87 92	99.72 187	99.08 131	99.85 297	99.89 40	99.98 54	99.66 149

v1144		99.54 116	99.53 120	99.59 198	99.79 137	99.28 250	99.10 254	99.61 273	99.20 260	99.84 104	99.73 177	98.67 202	99.84 314	99.86 45	99.98 54	99.64 170

OurMVSNet-221017-0		99.75 49	99.71 56	99.84 38	99.96 7	99.83 33	99.83 7	99.85 95	99.80 96	99.93 53	99.93 22	98.54 225	99.93 120	99.59 78	99.98 54	99.76 86

UGNet		99.38 179	99.34 175	99.49 244	98.90 477	98.90 334	99.70 38	99.35 391	99.86 66	98.57 458	99.81 98	98.50 237	99.93 120	99.38 115	99.98 54	99.66 149
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
MIMVSNet1		99.66 77	99.62 85	99.80 64	99.94 18	99.87 15	99.69 45	99.77 170	99.78 103	99.93 53	99.89 41	97.94 302	99.92 154	99.65 70	99.98 54	99.62 188

Vis-MVSNet		99.75 49	99.74 53	99.79 72	99.88 46	99.66 123	99.69 45	99.92 47	99.67 144	99.77 151	99.75 164	99.61 41	99.98 26	99.35 122	99.98 54	99.72 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320		99.79 34	99.79 34	99.81 54	99.82 99	99.84 26	99.82 10	99.90 64	99.94 36	99.94 48	99.94 19	99.07 134	99.92 154	99.68 66	99.97 77	99.67 135

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 259	99.93 24	98.40 398	99.30 167	99.98 13	99.94 36	99.99 7	99.89 41	99.80 21	99.97 44	99.96 9	99.97 77	99.97 10

test_fmvs1		99.48 135	99.65 74	98.97 381	99.54 316	97.16 469	99.11 250	99.98 13	99.78 103	99.96 34	99.81 98	98.72 195	99.97 44	99.95 14	99.97 77	99.79 75

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 40	99.91 4	99.89 5	99.71 207	99.93 43	99.95 45	99.89 41	99.71 28	99.96 69	99.51 93	99.97 77	99.84 55

CANet		99.11 270	99.05 259	99.28 329	98.83 488	98.56 382	98.71 360	99.41 370	99.25 251	99.23 373	99.22 433	97.66 327	99.94 98	99.19 152	99.97 77	99.33 351

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 57	99.85 72	99.94 48	99.95 16	99.73 27	99.90 205	99.65 70	99.97 77	99.69 119

v144192		99.55 111	99.54 116	99.58 202	99.78 146	99.20 277	99.11 250	99.62 265	99.18 263	99.89 72	99.72 187	98.66 204	99.87 258	99.88 41	99.97 77	99.66 149

v1921920		99.56 106	99.57 105	99.55 221	99.75 182	99.11 295	99.05 269	99.61 273	99.15 277	99.88 82	99.71 197	99.08 131	99.87 258	99.90 37	99.97 77	99.66 149

FC-MVSNet-test		99.70 57	99.65 74	99.86 30	99.88 46	99.86 18	99.72 33	99.78 165	99.90 49	99.82 112	99.83 83	98.45 244	99.87 258	99.51 93	99.97 77	99.86 47

v2v482		99.50 127	99.47 132	99.58 202	99.78 146	99.25 259	99.14 233	99.58 300	99.25 251	99.81 119	99.62 276	98.24 271	99.84 314	99.83 46	99.97 77	99.64 170

Patchmtry		98.78 333	98.54 347	99.49 244	98.89 480	99.19 280	99.32 158	99.67 235	99.65 156	99.72 188	99.79 121	91.87 474	99.95 81	98.00 320	99.97 77	99.33 351

PVSNet_BlendedMVS		99.03 288	99.01 274	99.09 365	99.54 316	97.99 428	98.58 376	99.82 122	97.62 456	99.34 346	99.71 197	98.52 234	99.77 408	97.98 321	99.97 77	99.52 268

FMVSNet1		99.66 77	99.63 82	99.73 113	99.78 146	99.77 63	99.68 48	99.70 216	99.67 144	99.82 112	99.83 83	98.98 155	99.90 205	99.24 139	99.97 77	99.53 257

HyFIR lowres test		98.91 315	98.64 332	99.73 113	99.85 75	99.47 189	98.07 442	99.83 115	98.64 356	99.89 72	99.60 296	92.57 461	100.00 1	99.33 126	99.97 77	99.72 99

dtuplus		99.52 122	99.55 112	99.43 267	99.76 164	98.90 334	98.71 360	99.89 68	99.67 144	99.79 133	99.77 146	99.25 101	99.81 377	99.18 155	99.96 91	99.57 228

E5new		99.68 64	99.67 65	99.70 133	99.87 55	99.62 144	99.41 122	99.84 105	99.68 136	99.77 151	99.81 98	99.59 46	99.78 395	99.13 174	99.96 91	99.70 107

E6new		99.68 64	99.67 65	99.70 133	99.86 60	99.62 144	99.41 122	99.84 105	99.68 136	99.77 151	99.81 98	99.59 46	99.78 395	99.13 174	99.96 91	99.70 107

E6		99.68 64	99.67 65	99.70 133	99.86 60	99.62 144	99.41 122	99.84 105	99.68 136	99.77 151	99.81 98	99.59 46	99.78 395	99.13 174	99.96 91	99.70 107

E5		99.68 64	99.67 65	99.70 133	99.87 55	99.62 144	99.41 122	99.84 105	99.68 136	99.77 151	99.81 98	99.59 46	99.78 395	99.13 174	99.96 91	99.70 107

viewdifsd2359ckpt11		99.62 94	99.64 79	99.56 214	99.86 60	99.19 280	99.02 281	99.93 43	99.83 82	99.88 82	99.81 98	98.99 151	99.83 337	99.48 97	99.96 91	99.65 158

viewmacassd2359aftdt		99.63 86	99.61 89	99.68 141	99.84 81	99.61 154	99.14 233	99.87 80	99.71 123	99.75 165	99.77 146	99.54 55	99.72 438	98.91 216	99.96 91	99.70 107

viewmsd2359difaftdt		99.62 94	99.64 79	99.56 214	99.86 60	99.19 280	99.02 281	99.93 43	99.83 82	99.88 82	99.81 98	98.99 151	99.83 337	99.48 97	99.96 91	99.65 158

FE-MVSNET		99.45 151	99.36 169	99.71 128	99.84 81	99.64 136	99.16 226	99.91 57	98.65 354	99.73 182	99.73 177	98.54 225	99.82 360	98.71 250	99.96 91	99.67 135

AstraMVS		99.15 257	99.06 252	99.42 270	99.85 75	98.59 379	99.13 240	97.26 523	99.84 76	99.87 92	99.77 146	96.11 400	99.93 120	99.71 60	99.96 91	99.74 91

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 99	99.84 26	99.82 10	99.92 47	99.94 36	99.94 48	99.93 22	99.34 85	99.92 154	99.70 61	99.96 91	99.70 107

SSC-MVS3.2		99.64 85	99.67 65	99.56 214	99.75 182	98.98 317	98.96 309	99.87 80	99.88 61	99.84 104	99.64 250	99.32 88	99.91 186	99.78 54	99.96 91	99.80 67

SDMVSNet		99.77 44	99.77 45	99.76 87	99.80 123	99.65 129	99.63 64	99.86 89	99.97 25	99.89 72	99.89 41	99.52 60	99.99 7	99.42 111	99.96 91	99.65 158

sd_testset		99.78 37	99.78 39	99.80 64	99.80 123	99.76 70	99.80 14	99.79 152	99.97 25	99.89 72	99.89 41	99.53 58	99.99 7	99.36 119	99.96 91	99.65 158

test_vis1_n		99.68 64	99.79 34	99.36 301	99.94 18	98.18 413	99.52 94	100.00 1	99.86 66	100.00 1	99.88 50	98.99 151	99.96 69	99.97 4	99.96 91	99.95 15

patch_mono-2		99.51 124	99.46 138	99.64 167	99.70 223	99.11 295	99.04 274	99.87 80	99.71 123	99.47 307	99.79 121	98.24 271	99.98 26	99.38 115	99.96 91	99.83 59

dcpmvs_2		99.61 98	99.64 79	99.53 232	99.79 137	98.82 348	99.58 82	99.97 21	99.95 32	99.96 34	99.76 156	98.44 245	99.99 7	99.34 123	99.96 91	99.78 77

ppachtmachnet_test		98.89 321	99.12 230	98.20 457	99.66 250	95.24 516	97.63 479	99.68 230	99.08 285	99.78 139	99.62 276	98.65 206	99.88 242	98.02 316	99.96 91	99.48 286

Anonymous20231211		99.62 94	99.57 105	99.76 87	99.61 267	99.60 158	99.81 13	99.73 194	99.82 86	99.90 67	99.90 36	97.97 301	99.86 278	99.42 111	99.96 91	99.80 67

nrg030		99.70 57	99.66 72	99.82 46	99.76 164	99.84 26	99.61 73	99.70 216	99.93 43	99.78 139	99.68 229	99.10 125	99.78 395	99.45 103	99.96 91	99.83 59

v1240		99.56 106	99.58 100	99.51 238	99.80 123	99.00 313	99.00 292	99.65 250	99.15 277	99.90 67	99.75 164	99.09 127	99.88 242	99.90 37	99.96 91	99.67 135

PS-CasMVS		99.66 77	99.58 100	99.89 11	99.80 123	99.85 21	99.66 57	99.73 194	99.62 165	99.84 104	99.71 197	98.62 208	99.96 69	99.30 131	99.96 91	99.86 47

casdiffmvs_mvg		99.68 64	99.68 63	99.69 139	99.81 112	99.59 160	99.29 175	99.90 64	99.71 123	99.79 133	99.73 177	99.54 55	99.84 314	99.36 119	99.96 91	99.65 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TAMVS		99.49 132	99.45 141	99.63 175	99.48 350	99.42 212	99.45 117	99.57 303	99.66 151	99.78 139	99.83 83	97.85 309	99.86 278	99.44 104	99.96 91	99.61 203

test_0402		99.22 232	99.14 224	99.45 259	99.79 137	99.43 209	99.28 177	99.68 230	99.54 185	99.40 332	99.56 321	99.07 134	99.82 360	96.01 478	99.96 91	99.11 405

viewmamba		99.49 132	99.51 122	99.42 270	99.75 182	98.90 334	98.85 329	99.85 95	99.69 133	99.73 182	99.67 235	98.79 182	99.82 360	99.28 136	99.95 116	99.54 248

hybridnocas07		99.43 159	99.44 146	99.39 286	99.75 182	98.85 345	98.76 349	99.85 95	99.71 123	99.70 197	99.68 229	98.47 239	99.77 408	99.13 174	99.95 116	99.55 236

casdiffseed414692147		99.68 64	99.68 63	99.67 145	99.86 60	99.65 129	99.32 158	99.87 80	99.75 111	99.77 151	99.80 109	99.61 41	99.68 466	99.21 146	99.95 116	99.67 135

E4		99.61 98	99.59 96	99.66 153	99.84 81	99.53 176	99.08 262	99.84 105	99.65 156	99.74 176	99.80 109	99.45 63	99.77 408	98.93 213	99.95 116	99.69 119

diffmvs_AUTHOR		99.48 135	99.48 130	99.47 252	99.80 123	98.89 337	98.71 360	99.82 122	99.79 100	99.66 223	99.63 266	98.87 173	99.88 242	99.13 174	99.95 116	99.62 188

SSM_0404		99.57 102	99.58 100	99.54 227	99.76 164	99.28 250	99.19 211	99.84 105	99.80 96	99.78 139	99.70 207	99.44 65	99.93 120	98.74 241	99.95 116	99.41 325

reproduce_monomvs		97.40 447	97.46 435	97.20 499	99.05 461	91.91 539	99.20 205	99.18 436	99.84 76	99.86 96	99.75 164	80.67 529	99.83 337	99.69 64	99.95 116	99.85 50

WBMVS		97.50 443	97.18 449	98.48 439	98.85 485	95.89 503	98.44 404	99.52 337	99.53 187	99.52 290	99.42 369	80.10 532	99.86 278	99.24 139	99.95 116	99.68 126

our_test_3		98.85 327	99.09 244	98.13 459	99.66 250	94.90 521	97.72 472	99.58 300	99.07 287	99.64 233	99.62 276	98.19 280	99.93 120	98.41 283	99.95 116	99.55 236

CANet_DTU		98.91 315	98.85 309	99.09 365	98.79 494	98.13 416	98.18 424	99.31 406	99.48 197	98.86 428	99.51 343	96.56 377	99.95 81	99.05 188	99.95 116	99.19 387

pmmvs5		99.19 242	99.11 233	99.42 270	99.76 164	98.88 339	98.55 384	99.73 194	98.82 329	99.72 188	99.62 276	96.56 377	99.82 360	99.32 128	99.95 116	99.56 232

V42		99.56 106	99.54 116	99.63 175	99.79 137	99.46 197	99.39 129	99.59 291	99.24 253	99.86 96	99.70 207	98.55 220	99.82 360	99.79 53	99.95 116	99.60 208

EU-MVSNet		99.39 176	99.62 85	98.72 422	99.88 46	96.44 488	99.56 87	99.85 95	99.90 49	99.90 67	99.85 68	98.09 290	99.83 337	99.58 81	99.95 116	99.90 30

PMMVS2		99.48 135	99.45 141	99.57 210	99.76 164	98.99 315	98.09 439	99.90 64	98.95 304	99.78 139	99.58 309	99.57 52	99.93 120	99.48 97	99.95 116	99.79 75

DTE-MVSNet		99.68 64	99.61 89	99.88 19	99.80 123	99.87 15	99.67 53	99.71 207	99.72 117	99.84 104	99.78 134	98.67 202	99.97 44	99.30 131	99.95 116	99.80 67

WR-MVS_H		99.61 98	99.53 120	99.87 26	99.80 123	99.83 33	99.67 53	99.75 183	99.58 181	99.85 101	99.69 216	98.18 282	99.94 98	99.28 136	99.95 116	99.83 59

K. test v3		98.87 323	98.60 336	99.69 139	99.93 24	99.46 197	99.74 27	94.97 541	99.78 103	99.88 82	99.88 50	93.66 447	99.97 44	99.61 76	99.95 116	99.64 170

TDRefinement		99.72 53	99.70 57	99.77 80	99.90 37	99.85 21	99.86 6	99.92 47	99.69 133	99.78 139	99.92 27	99.37 78	99.88 242	98.93 213	99.95 116	99.60 208

Gipuma		99.57 102	99.59 96	99.49 244	99.98 3	99.71 101	99.72 33	99.84 105	99.81 92	99.94 48	99.78 134	98.91 167	99.71 443	98.41 283	99.95 116	99.05 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
hybridcas		99.65 83	99.63 82	99.70 133	99.85 75	99.67 120	99.30 167	99.87 80	99.67 144	99.81 119	99.77 146	99.21 105	99.81 377	99.24 139	99.94 135	99.61 203

hybrid		99.42 163	99.43 149	99.37 295	99.75 182	98.77 355	98.72 357	99.84 105	99.61 170	99.65 227	99.68 229	98.53 230	99.79 391	99.16 163	99.94 135	99.54 248

viewdifsd2359ckpt07		99.51 124	99.50 125	99.52 234	99.80 123	99.19 280	98.92 318	99.88 74	99.72 117	99.64 233	99.62 276	99.06 141	99.81 377	98.96 204	99.94 135	99.56 232

viewmambaseed2359dif		99.47 145	99.50 125	99.37 295	99.70 223	98.80 352	98.67 363	99.92 47	99.49 194	99.77 151	99.71 197	99.08 131	99.78 395	99.20 150	99.94 135	99.54 248

KinetiMVS		99.66 77	99.63 82	99.76 87	99.89 40	99.57 168	99.37 140	99.82 122	99.95 32	99.90 67	99.63 266	98.57 216	99.97 44	99.65 70	99.94 135	99.74 91

guyue		99.12 265	99.02 268	99.41 280	99.84 81	98.56 382	99.19 211	98.30 497	99.82 86	99.84 104	99.75 164	94.84 428	99.92 154	99.68 66	99.94 135	99.74 91

sc_t1		99.81 28	99.80 32	99.82 46	99.88 46	99.88 12	99.83 7	99.79 152	99.94 36	99.93 53	99.92 27	99.35 84	99.92 154	99.64 73	99.94 135	99.68 126

v148		99.40 172	99.41 156	99.39 286	99.76 164	98.94 326	99.09 259	99.59 291	99.17 270	99.81 119	99.61 286	98.41 249	99.69 454	99.32 128	99.94 135	99.53 257

casdiffmvs		99.63 86	99.61 89	99.67 145	99.79 137	99.59 160	99.13 240	99.85 95	99.79 100	99.76 160	99.72 187	99.33 87	99.82 360	99.21 146	99.94 135	99.59 215
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PEN-MVS		99.66 77	99.59 96	99.89 11	99.83 90	99.87 15	99.66 57	99.73 194	99.70 130	99.84 104	99.73 177	98.56 219	99.96 69	99.29 134	99.94 135	99.83 59

CP-MVSNet		99.54 116	99.43 149	99.87 26	99.76 164	99.82 41	99.57 85	99.61 273	99.54 185	99.80 126	99.64 250	97.79 313	99.95 81	99.21 146	99.94 135	99.84 55

baseline		99.63 86	99.62 85	99.66 153	99.80 123	99.62 144	99.44 119	99.80 143	99.71 123	99.72 188	99.69 216	99.15 115	99.83 337	99.32 128	99.94 135	99.53 257

FMVSNet2		99.35 191	99.28 197	99.55 221	99.49 345	99.35 238	99.45 117	99.57 303	99.44 210	99.70 197	99.74 172	97.21 350	99.87 258	99.03 191	99.94 135	99.44 312

ACMMP++_ref															99.94 135

onestephybrid01		99.45 151	99.46 138	99.42 270	99.69 231	98.88 339	98.76 349	99.81 135	99.78 103	99.67 216	99.73 177	98.61 210	99.84 314	99.17 159	99.93 149	99.52 268

Casviewmamba		99.63 86	99.60 93	99.73 113	99.84 81	99.72 95	99.36 144	99.87 80	99.67 144	99.74 176	99.73 177	99.07 134	99.83 337	99.14 171	99.93 149	99.62 188

DKM		99.12 265	98.98 288	99.54 227	99.71 207	99.48 188	98.53 389	99.88 74	99.18 263	98.99 412	99.64 250	96.25 395	99.75 426	98.66 258	99.93 149	99.40 328

E2		99.54 116	99.51 122	99.62 184	99.78 146	99.47 189	99.01 286	99.82 122	99.55 183	99.69 201	99.77 146	99.26 97	99.76 415	98.82 225	99.93 149	99.62 188

E3		99.54 116	99.51 122	99.62 184	99.78 146	99.47 189	99.01 286	99.82 122	99.55 183	99.69 201	99.77 146	99.25 101	99.76 415	98.82 225	99.93 149	99.62 188

eth_miper_zixun_eth		98.68 346	98.71 325	98.60 431	99.10 454	96.84 481	97.52 488	99.54 321	98.94 305	99.58 263	99.48 355	96.25 395	99.76 415	98.01 319	99.93 149	99.21 379

FIs		99.65 83	99.58 100	99.84 38	99.84 81	99.85 21	99.66 57	99.75 183	99.86 66	99.74 176	99.79 121	98.27 269	99.85 297	99.37 118	99.93 149	99.83 59

pmmvs4		99.13 262	99.06 252	99.36 301	99.57 296	99.10 302	98.01 448	99.25 419	98.78 337	99.58 263	99.44 366	98.24 271	99.76 415	98.74 241	99.93 149	99.22 376

XXY-MVS		99.71 56	99.67 65	99.81 54	99.89 40	99.72 95	99.59 80	99.82 122	99.39 227	99.82 112	99.84 76	99.38 76	99.91 186	99.38 115	99.93 149	99.80 67

PatchmatchNet1														98.28 292	99.92 158	99.44 312
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
SIFT-ConvMatch		98.16 405	98.37 371	97.52 481	99.54 316	99.20 277	96.97 515	98.47 485	98.09 420	99.14 392	99.40 377	95.93 406	99.05 531	97.87 333	99.92 158	94.31 535

usedtu_dtu_shiyan1		98.87 323	98.71 325	99.35 305	99.59 276	98.88 339	97.17 503	99.64 258	98.94 305	99.27 363	99.22 433	95.57 413	99.83 337	99.08 184	99.92 158	99.35 344

FE-MVSNET3		98.87 323	98.71 325	99.35 305	99.59 276	98.88 339	97.17 503	99.64 258	98.94 305	99.27 363	99.22 433	95.57 413	99.83 337	99.08 184	99.92 158	99.35 344

viewmanbaseed2359cas		99.50 127	99.47 132	99.61 191	99.73 197	99.52 181	99.03 277	99.83 115	99.49 194	99.65 227	99.64 250	99.18 109	99.71 443	98.73 246	99.92 158	99.58 221

pm-mvs1		99.79 34	99.79 34	99.78 76	99.91 31	99.83 33	99.76 23	99.87 80	99.73 113	99.89 72	99.87 56	99.63 37	99.87 258	99.54 87	99.92 158	99.63 176

EI-MVSNet		99.38 179	99.44 146	99.21 346	99.58 286	98.09 421	99.26 187	99.46 357	99.62 165	99.75 165	99.67 235	98.54 225	99.85 297	99.15 164	99.92 158	99.68 126

TranMVSNet+NR-MVSNet		99.54 116	99.47 132	99.76 87	99.58 286	99.64 136	99.30 167	99.63 262	99.61 170	99.71 193	99.56 321	98.76 188	99.96 69	99.14 171	99.92 158	99.68 126

lessismore_v0				99.64 167	99.86 60	99.38 226		90.66 552		99.89 72	99.83 83	94.56 434	99.97 44	99.56 83	99.92 158	99.57 228

SixPastTwentyTwo		99.42 163	99.30 188	99.76 87	99.92 29	99.67 120	99.70 38	99.14 442	99.65 156	99.89 72	99.90 36	96.20 398	99.94 98	99.42 111	99.92 158	99.67 135

MVSTER		98.47 372	98.22 388	99.24 343	99.06 460	98.35 404	99.08 262	99.46 357	99.27 246	99.75 165	99.66 241	88.61 507	99.85 297	99.14 171	99.92 158	99.52 268

N_pmnet		98.73 340	98.53 348	99.35 305	99.72 202	98.67 363	98.34 410	94.65 542	98.35 396	99.79 133	99.68 229	98.03 294	99.93 120	98.28 292	99.92 158	99.44 312

CSCG		99.37 184	99.29 194	99.60 195	99.71 207	99.46 197	99.43 121	99.85 95	98.79 335	99.41 327	99.60 296	98.92 164	99.92 154	98.02 316	99.92 158	99.43 319

CMPMVS	77.52 23	98.50 368	98.19 393	99.41 280	98.33 518	99.56 169	99.01 286	99.59 291	95.44 515	99.57 266	99.80 109	95.64 409	99.46 515	96.47 459	99.92 158	99.21 379
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LoFTR		99.29 206	99.26 202	99.36 301	99.70 223	99.05 308	98.66 365	99.95 38	98.85 322	99.86 96	99.75 164	98.14 284	99.93 120	98.54 272	99.91 172	99.10 408

SIFT-UMatch		98.07 410	98.27 384	97.46 487	99.57 296	98.99 315	96.93 518	99.02 451	98.53 371	99.26 367	99.23 432	95.43 419	99.31 520	96.51 454	99.91 172	94.09 539

viewcassd2359sk11		99.48 135	99.45 141	99.58 202	99.73 197	99.42 212	98.96 309	99.80 143	99.44 210	99.63 238	99.74 172	99.09 127	99.76 415	98.72 248	99.91 172	99.57 228

EG-PatchMatch MVS		99.57 102	99.56 110	99.62 184	99.77 159	99.33 241	99.26 187	99.76 178	99.32 238	99.80 126	99.78 134	99.29 91	99.87 258	99.15 164	99.91 172	99.66 149

dtuonly		98.93 314	99.11 233	98.38 445	99.72 202	95.75 505	97.07 510	99.91 57	99.04 290	99.65 227	99.41 371	98.32 263	99.83 337	98.97 201	99.90 176	99.55 236

MatchFormer		99.03 288	99.02 268	99.08 370	99.56 310	98.47 391	98.57 380	99.90 64	98.13 416	99.80 126	99.75 164	98.34 259	99.84 314	97.18 413	99.90 176	98.92 451

viewdifsd2359ckpt13		99.42 163	99.37 164	99.57 210	99.72 202	99.46 197	99.01 286	99.80 143	99.20 260	99.51 297	99.60 296	98.92 164	99.70 447	98.65 261	99.90 176	99.55 236

mamba_0408		99.54 116	99.55 112	99.54 227	99.71 207	99.24 264	99.27 182	99.79 152	99.72 117	99.78 139	99.64 250	99.36 81	99.93 120	98.74 241	99.90 176	99.45 297

SSM_04072		99.55 111	99.55 112	99.55 221	99.71 207	99.24 264	99.27 182	99.79 152	99.72 117	99.78 139	99.64 250	99.36 81	99.97 44	98.74 241	99.90 176	99.45 297

SSM_0407		99.56 106	99.56 110	99.54 227	99.71 207	99.24 264	99.15 229	99.84 105	99.80 96	99.78 139	99.70 207	99.44 65	99.93 120	98.74 241	99.90 176	99.45 297

MVSMamba_PlusPlus		99.55 111	99.58 100	99.47 252	99.68 240	99.40 220	99.52 94	99.70 216	99.92 45	99.77 151	99.86 63	98.28 267	99.96 69	99.54 87	99.90 176	99.05 428

miper_lstm_enhance		98.65 349	98.60 336	98.82 414	99.20 432	97.33 464	97.78 468	99.66 240	99.01 295	99.59 261	99.50 346	94.62 433	99.85 297	98.12 310	99.90 176	99.26 368

SPE-MVS-test		99.68 64	99.70 57	99.64 167	99.57 296	99.83 33	99.78 17	99.97 21	99.92 45	99.50 300	99.38 385	99.57 52	99.95 81	99.69 64	99.90 176	99.15 396

EI-MVSNet-UG-set		99.48 135	99.50 125	99.42 270	99.57 296	98.65 370	99.24 194	99.46 357	99.68 136	99.80 126	99.66 241	98.99 151	99.89 227	99.19 152	99.90 176	99.72 99

diffmvs		99.34 196	99.32 181	99.39 286	99.67 247	98.77 355	98.57 380	99.81 135	99.61 170	99.48 305	99.41 371	98.47 239	99.86 278	98.97 201	99.90 176	99.53 257
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet1		98.95 310	98.99 285	98.84 409	99.64 256	97.14 471	98.22 422	99.32 402	98.92 313	99.59 261	99.66 241	97.40 339	99.83 337	98.27 294	99.90 176	99.55 236

GBi-Net		99.42 163	99.31 183	99.73 113	99.49 345	99.77 63	99.68 48	99.70 216	99.44 210	99.62 248	99.83 83	97.21 350	99.90 205	98.96 204	99.90 176	99.53 257

FMVSNet5		97.80 426	97.25 446	99.42 270	98.83 488	98.97 320	99.38 132	99.80 143	98.87 319	99.25 369	99.69 216	80.60 531	99.91 186	98.96 204	99.90 176	99.38 334

test1		99.42 163	99.31 183	99.73 113	99.49 345	99.77 63	99.68 48	99.70 216	99.44 210	99.62 248	99.83 83	97.21 350	99.90 205	98.96 204	99.90 176	99.53 257

FMVSNet3		98.80 332	98.63 334	99.32 317	99.13 444	98.72 359	99.10 254	99.48 351	99.23 255	99.62 248	99.64 250	92.57 461	99.86 278	98.96 204	99.90 176	99.39 332

SIFT-PointCN		98.28 389	98.47 355	97.71 478	99.70 223	98.91 333	96.98 514	99.70 216	97.90 438	99.36 338	99.35 399	95.51 416	99.83 337	97.84 342	99.89 192	94.39 534

E3new		99.42 163	99.37 164	99.56 214	99.68 240	99.38 226	98.93 317	99.79 152	99.30 241	99.55 279	99.69 216	98.88 171	99.76 415	98.63 263	99.89 192	99.53 257

cl____		98.54 363	98.41 366	98.92 391	99.03 465	97.80 442	97.46 490	99.59 291	98.90 315	99.60 258	99.46 362	93.85 443	99.78 395	97.97 323	99.89 192	99.17 392

DIV-MVS_self_test		98.54 363	98.42 365	98.92 391	99.03 465	97.80 442	97.46 490	99.59 291	98.90 315	99.60 258	99.46 362	93.87 442	99.78 395	97.97 323	99.89 192	99.18 389

CS-MVS		99.67 76	99.70 57	99.58 202	99.53 325	99.84 26	99.79 15	99.96 30	99.90 49	99.61 255	99.41 371	99.51 61	99.95 81	99.66 69	99.89 192	98.96 443

EI-MVSNet-Vis-set		99.47 145	99.49 129	99.42 270	99.57 296	98.66 366	99.24 194	99.46 357	99.67 144	99.79 133	99.65 248	98.97 157	99.89 227	99.15 164	99.89 192	99.71 104

DSMNet-mixed		99.48 135	99.65 74	98.95 384	99.71 207	97.27 466	99.50 102	99.82 122	99.59 179	99.41 327	99.85 68	99.62 40	100.00 1	99.53 90	99.89 192	99.59 215

Vis-MVSNet (Re-imp)		98.77 335	98.58 341	99.34 309	99.78 146	98.88 339	99.61 73	99.56 308	99.11 283	99.24 372	99.56 321	93.00 457	99.78 395	97.43 385	99.89 192	99.35 344

EPP-MVSNet		99.17 251	99.00 278	99.66 153	99.80 123	99.43 209	99.70 38	99.24 423	99.48 197	99.56 274	99.77 146	94.89 427	99.93 120	98.72 248	99.89 192	99.63 176

CLD-MVS		98.76 336	98.57 342	99.33 312	99.57 296	98.97 320	97.53 486	99.55 315	96.41 500	99.27 363	99.13 445	99.07 134	99.78 395	96.73 440	99.89 192	99.23 374
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMH	98.42 6	99.59 101	99.54 116	99.72 122	99.86 60	99.62 144	99.56 87	99.79 152	98.77 340	99.80 126	99.85 68	99.64 35	99.85 297	98.70 252	99.89 192	99.70 107
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DenseAffine		99.17 251	99.06 252	99.49 244	99.76 164	99.33 241	98.43 405	99.97 21	99.11 283	99.17 386	99.61 286	97.05 359	99.76 415	98.56 269	99.88 203	99.38 334

viewdifsd2359ckpt09		99.24 220	99.16 219	99.49 244	99.70 223	99.22 270	98.88 323	99.81 135	98.70 348	99.38 335	99.37 389	98.22 276	99.76 415	98.48 275	99.88 203	99.51 271

testf1		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 68	99.43 217	99.88 82	99.80 109	99.26 97	99.90 205	98.81 229	99.88 203	99.32 355

APD_test2		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 68	99.43 217	99.88 82	99.80 109	99.26 97	99.90 205	98.81 229	99.88 203	99.32 355

BridgeMVS		99.50 127	99.50 125	99.50 240	99.42 373	99.49 184	99.52 94	99.75 183	99.86 66	99.78 139	99.71 197	98.20 279	99.90 205	99.39 114	99.88 203	99.10 408

GeoE		99.69 59	99.66 72	99.78 76	99.76 164	99.76 70	99.60 79	99.82 122	99.46 205	99.75 165	99.56 321	99.63 37	99.95 81	99.43 106	99.88 203	99.62 188

c3_l		98.72 341	98.71 325	98.72 422	99.12 446	97.22 468	97.68 476	99.56 308	98.90 315	99.54 283	99.48 355	96.37 388	99.73 436	97.88 330	99.88 203	99.21 379

VPA-MVSNet		99.66 77	99.62 85	99.79 72	99.68 240	99.75 79	99.62 67	99.69 225	99.85 72	99.80 126	99.81 98	98.81 177	99.91 186	99.47 100	99.88 203	99.70 107

MDA-MVSNet_test_wron		98.95 310	98.99 285	98.85 407	99.64 256	97.16 469	98.23 421	99.33 400	98.93 310	99.56 274	99.66 241	97.39 341	99.83 337	98.29 291	99.88 203	99.55 236

XVG-OURS		99.21 237	99.06 252	99.65 160	99.82 99	99.62 144	97.87 464	99.74 189	98.36 390	99.66 223	99.68 229	99.71 28	99.90 205	96.84 434	99.88 203	99.43 319

CDS-MVSNet		99.22 232	99.13 226	99.50 240	99.35 390	99.11 295	98.96 309	99.54 321	99.46 205	99.61 255	99.70 207	96.31 391	99.83 337	99.34 123	99.88 203	99.55 236
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		99.03 288	98.85 309	99.55 221	99.80 123	99.25 259	99.73 30	99.15 440	99.37 229	99.61 255	99.71 197	94.73 431	99.81 377	97.70 356	99.88 203	99.58 221

USDC		98.96 307	98.93 296	99.05 374	99.54 316	97.99 428	97.07 510	99.80 143	98.21 410	99.75 165	99.77 146	98.43 246	99.64 486	97.90 328	99.88 203	99.51 271

ACMH+	98.40 8	99.50 127	99.43 149	99.71 128	99.86 60	99.76 70	99.32 158	99.77 170	99.53 187	99.77 151	99.76 156	99.26 97	99.78 395	97.77 344	99.88 203	99.60 208

mvsany_test1		99.44 155	99.45 141	99.40 283	99.37 383	98.64 373	97.90 463	99.59 291	99.27 246	99.92 59	99.82 91	99.74 26	99.93 120	99.55 85	99.87 217	99.63 176

SD-MVS		99.01 297	99.30 188	98.15 458	99.50 340	99.40 220	98.94 314	99.61 273	99.22 259	99.75 165	99.82 91	99.54 55	95.51 550	97.48 381	99.87 217	99.54 248
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
UniMVSNet (Re)		99.37 184	99.26 202	99.68 141	99.51 334	99.58 165	98.98 303	99.60 285	99.43 217	99.70 197	99.36 394	97.70 319	99.88 242	99.20 150	99.87 217	99.59 215

WR-MVS		99.11 270	98.93 296	99.66 153	99.30 411	99.42 212	98.42 406	99.37 386	99.04 290	99.57 266	99.20 439	96.89 366	99.86 278	98.66 258	99.87 217	99.70 107

NR-MVSNet		99.40 172	99.31 183	99.68 141	99.43 368	99.55 173	99.73 30	99.50 346	99.46 205	99.88 82	99.36 394	97.54 333	99.87 258	98.97 201	99.87 217	99.63 176

LPG-MVS_test		99.22 232	99.05 259	99.74 103	99.82 99	99.63 142	99.16 226	99.73 194	97.56 457	99.64 233	99.69 216	99.37 78	99.89 227	96.66 444	99.87 217	99.69 119

LGP-MVS_train				99.74 103	99.82 99	99.63 142		99.73 194	97.56 457	99.64 233	99.69 216	99.37 78	99.89 227	96.66 444	99.87 217	99.69 119

COLMAP_ROB	98.06 12	99.45 151	99.37 164	99.70 133	99.83 90	99.70 109	99.38 132	99.78 165	99.53 187	99.67 216	99.78 134	99.19 108	99.86 278	97.32 392	99.87 217	99.55 236
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SIFT-NCM-Cal		98.18 401	98.41 366	97.48 483	99.57 296	99.28 250	97.26 499	98.08 502	98.30 405	99.23 373	99.39 382	97.13 355	99.04 532	96.86 430	99.86 225	94.12 538

RoMa-SfM		99.32 201	99.23 211	99.59 198	99.77 159	99.53 176	98.89 321	99.88 74	98.78 337	99.65 227	99.52 339	97.78 314	99.90 205	98.96 204	99.86 225	99.35 344

BP-MVS1		98.72 341	98.46 357	99.50 240	99.53 325	99.00 313	99.34 149	98.53 480	99.65 156	99.73 182	99.38 385	90.62 493	99.96 69	99.50 95	99.86 225	99.55 236

test20.03		99.55 111	99.54 116	99.58 202	99.79 137	99.37 231	99.02 281	99.89 68	99.60 177	99.82 112	99.62 276	98.81 177	99.89 227	99.43 106	99.86 225	99.47 290

Baseline_NR-MVSNet		99.49 132	99.37 164	99.82 46	99.91 31	99.84 26	98.83 335	99.86 89	99.68 136	99.65 227	99.88 50	97.67 323	99.87 258	99.03 191	99.86 225	99.76 86

EC-MVSNet		99.69 59	99.69 60	99.68 141	99.71 207	99.91 4	99.76 23	99.96 30	99.86 66	99.51 297	99.39 382	99.57 52	99.93 120	99.64 73	99.86 225	99.20 384

MSDG		99.08 275	98.98 288	99.37 295	99.60 270	99.13 292	97.54 484	99.74 189	98.84 326	99.53 288	99.55 330	99.10 125	99.79 391	97.07 419	99.86 225	99.18 389

dtuonlycased		99.24 220	99.47 132	98.56 436	99.90 37	96.17 496	97.62 481	99.85 95	99.66 151	99.86 96	99.50 346	99.39 71	99.93 120	99.55 85	99.85 232	99.59 215

EGC-MVSNET		89.05 513	85.52 516	99.64 167	99.89 40	99.78 57	99.56 87	99.52 337	24.19 552	49.96 554	99.83 83	99.15 115	99.92 154	97.71 353	99.85 232	99.21 379

Patchmatch-RL test		98.60 354	98.36 373	99.33 312	99.77 159	99.07 305	98.27 417	99.87 80	98.91 314	99.74 176	99.72 187	90.57 495	99.79 391	98.55 270	99.85 232	99.11 405

APDe-MVS		99.48 135	99.36 169	99.85 32	99.55 314	99.81 47	99.50 102	99.69 225	98.99 297	99.75 165	99.71 197	98.79 182	99.93 120	98.46 277	99.85 232	99.80 67
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMP	97.51 14	99.05 284	98.84 311	99.67 145	99.78 146	99.55 173	98.88 323	99.66 240	97.11 485	99.47 307	99.60 296	99.07 134	99.89 227	96.18 473	99.85 232	99.58 221
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PMVS	92.94 21	98.82 329	98.81 316	98.85 407	99.84 81	97.99 428	99.20 205	99.47 354	99.71 123	99.42 321	99.82 91	98.09 290	99.47 513	93.88 524	99.85 232	99.07 426
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		99.35 191	99.31 183	99.47 252	99.74 193	99.06 307	99.28 177	99.74 189	99.23 255	99.72 188	99.53 335	97.63 332	99.88 242	99.11 180	99.84 238	99.48 286

HPM-MVS_fast		99.43 159	99.30 188	99.80 64	99.83 90	99.81 47	99.52 94	99.70 216	98.35 396	99.51 297	99.50 346	99.31 89	99.88 242	98.18 305	99.84 238	99.69 119

XVG-ACMP-BASELINE		99.23 223	99.10 242	99.63 175	99.82 99	99.58 165	98.83 335	99.72 203	98.36 390	99.60 258	99.71 197	98.92 164	99.91 186	97.08 418	99.84 238	99.40 328

new_pmnet		98.88 322	98.89 305	98.84 409	99.70 223	97.62 448	98.15 430	99.50 346	97.98 429	99.62 248	99.54 332	98.15 283	99.94 98	97.55 376	99.84 238	98.95 445

Test_1112_low_res		98.95 310	98.73 322	99.63 175	99.68 240	99.15 289	98.09 439	99.80 143	97.14 483	99.46 311	99.40 377	96.11 400	99.89 227	99.01 196	99.84 238	99.84 55

1112_ss		99.05 284	98.84 311	99.67 145	99.66 250	99.29 248	98.52 391	99.82 122	97.65 455	99.43 318	99.16 442	96.42 384	99.91 186	99.07 187	99.84 238	99.80 67

3Dnovator	99.15 2	99.43 159	99.36 169	99.65 160	99.39 377	99.42 212	99.70 38	99.56 308	99.23 255	99.35 342	99.80 109	99.17 111	99.95 81	98.21 300	99.84 238	99.59 215

LF4IMVS		99.01 297	98.92 300	99.27 334	99.71 207	99.28 250	98.59 374	99.77 170	98.32 403	99.39 334	99.41 371	98.62 208	99.84 314	96.62 450	99.84 238	98.69 474

SD_0403		97.42 446	96.90 462	98.98 380	99.54 316	97.90 436	99.52 94	99.54 321	99.34 234	97.87 499	98.85 484	98.72 195	99.64 486	78.93 550	99.83 246	99.40 328

ACMMP_NAP		99.28 208	99.11 233	99.79 72	99.75 182	99.81 47	98.95 312	99.53 332	98.27 407	99.53 288	99.73 177	98.75 190	99.87 258	97.70 356	99.83 246	99.68 126

AllTest		99.21 237	99.07 250	99.63 175	99.78 146	99.64 136	99.12 245	99.83 115	98.63 357	99.63 238	99.72 187	98.68 199	99.75 426	96.38 464	99.83 246	99.51 271

TestCases				99.63 175	99.78 146	99.64 136		99.83 115	98.63 357	99.63 238	99.72 187	98.68 199	99.75 426	96.38 464	99.83 246	99.51 271

PM-MVS		99.36 189	99.29 194	99.58 202	99.83 90	99.66 123	98.95 312	99.86 89	98.85 322	99.81 119	99.73 177	98.40 253	99.92 154	98.36 286	99.83 246	99.17 392

EPNet		98.13 406	97.77 426	99.18 352	94.57 554	97.99 428	99.24 194	97.96 507	99.74 112	97.29 518	99.62 276	93.13 454	99.97 44	98.59 265	99.83 246	99.58 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended		98.70 344	98.59 338	99.02 376	99.54 316	97.99 428	97.58 483	99.82 122	95.70 512	99.34 346	98.98 470	98.52 234	99.77 408	97.98 321	99.83 246	99.30 362

MVS-HIRNet		97.86 421	98.22 388	96.76 512	99.28 416	91.53 543	98.38 408	92.60 549	99.13 279	99.31 356	99.96 15	97.18 354	99.68 466	98.34 288	99.83 246	99.07 426

RPSCF		99.18 246	99.02 268	99.64 167	99.83 90	99.85 21	99.44 119	99.82 122	98.33 402	99.50 300	99.78 134	97.90 304	99.65 484	96.78 437	99.83 246	99.44 312

TinyColmap		98.97 304	98.93 296	99.07 371	99.46 360	98.19 411	97.75 469	99.75 183	98.79 335	99.54 283	99.70 207	98.97 157	99.62 489	96.63 448	99.83 246	99.41 325

reproduce_model		99.50 127	99.40 157	99.83 41	99.60 270	99.83 33	99.12 245	99.68 230	99.49 194	99.80 126	99.79 121	99.01 148	99.93 120	98.24 297	99.82 256	99.73 95

test_vis1_rt		99.45 151	99.46 138	99.41 280	99.71 207	98.63 375	98.99 300	99.96 30	99.03 292	99.95 45	99.12 449	98.75 190	99.84 314	99.82 50	99.82 256	99.77 81

MP-MVS-pluss		99.14 259	98.92 300	99.80 64	99.83 90	99.83 33	98.61 369	99.63 262	96.84 494	99.44 314	99.58 309	98.81 177	99.91 186	97.70 356	99.82 256	99.67 135
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDA-MVSNet-bldmvs		99.06 280	99.05 259	99.07 371	99.80 123	97.83 439	98.89 321	99.72 203	99.29 242	99.63 238	99.70 207	96.47 382	99.89 227	98.17 307	99.82 256	99.50 277

jason		99.16 253	99.11 233	99.32 317	99.75 182	98.44 395	98.26 419	99.39 380	98.70 348	99.74 176	99.30 410	98.54 225	99.97 44	98.48 275	99.82 256	99.55 236
jason: jason.
HPM-MVS		99.25 216	99.07 250	99.78 76	99.81 112	99.75 79	99.61 73	99.67 235	97.72 452	99.35 342	99.25 424	99.23 103	99.92 154	97.21 408	99.82 256	99.67 135
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		98.49 370	98.11 399	99.64 167	99.73 197	99.58 165	99.24 194	99.76 178	89.94 542	99.42 321	99.56 321	97.76 317	99.86 278	97.74 349	99.82 256	99.47 290

CP-MVS		99.23 223	99.05 259	99.75 98	99.66 250	99.66 123	99.38 132	99.62 265	98.38 388	99.06 405	99.27 418	98.79 182	99.94 98	97.51 380	99.82 256	99.66 149

PHI-MVS		99.11 270	98.95 294	99.59 198	99.13 444	99.59 160	99.17 220	99.65 250	97.88 442	99.25 369	99.46 362	98.97 157	99.80 387	97.26 401	99.82 256	99.37 338

wuyk23d		97.58 436	99.13 226	92.93 529	99.69 231	99.49 184	99.52 94	99.77 170	97.97 430	99.96 34	99.79 121	99.84 16	99.94 98	95.85 488	99.82 256	79.36 549

reproduce-ours		99.46 147	99.35 173	99.82 46	99.56 310	99.83 33	99.05 269	99.65 250	99.45 208	99.78 139	99.78 134	98.93 161	99.93 120	98.11 311	99.81 266	99.70 107

our_new_method		99.46 147	99.35 173	99.82 46	99.56 310	99.83 33	99.05 269	99.65 250	99.45 208	99.78 139	99.78 134	98.93 161	99.93 120	98.11 311	99.81 266	99.70 107

CVMVSNet		98.61 351	98.88 306	97.80 472	99.58 286	93.60 531	99.26 187	99.64 258	99.66 151	99.72 188	99.67 235	93.26 452	99.93 120	99.30 131	99.81 266	99.87 45

UniMVSNet_NR-MVSNet		99.37 184	99.25 206	99.72 122	99.47 356	99.56 169	98.97 305	99.61 273	99.43 217	99.67 216	99.28 416	97.85 309	99.95 81	99.17 159	99.81 266	99.65 158

DU-MVS		99.33 199	99.21 213	99.71 128	99.43 368	99.56 169	98.83 335	99.53 332	99.38 228	99.67 216	99.36 394	97.67 323	99.95 81	99.17 159	99.81 266	99.63 176

DeepPCF-MVS	98.42 6	99.18 246	99.02 268	99.67 145	99.22 427	99.75 79	97.25 500	99.47 354	98.72 345	99.66 223	99.70 207	99.29 91	99.63 488	98.07 315	99.81 266	99.62 188

ACMM	98.09 11	99.46 147	99.38 161	99.72 122	99.80 123	99.69 114	99.13 240	99.65 250	98.99 297	99.64 233	99.72 187	99.39 71	99.86 278	98.23 298	99.81 266	99.60 208
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SIFT-CM-Cal		97.96 419	98.15 396	97.39 490	99.61 267	99.15 289	96.75 523	98.41 491	98.04 425	99.03 408	99.54 332	95.24 423	99.41 516	96.97 423	99.80 273	93.61 545

ZNCC-MVS		99.22 232	99.04 265	99.77 80	99.76 164	99.73 90	99.28 177	99.56 308	98.19 412	99.14 392	99.29 414	98.84 176	99.92 154	97.53 379	99.80 273	99.64 170

test_0728_THIRD									99.18 263	99.62 248	99.61 286	98.58 215	99.91 186	97.72 351	99.80 273	99.77 81

SteuartSystems-ACMMP		99.30 204	99.14 224	99.76 87	99.87 55	99.66 123	99.18 215	99.60 285	98.55 367	99.57 266	99.67 235	99.03 146	99.94 98	97.01 420	99.80 273	99.69 119
Skip Steuart: Steuart Systems R&D Blog.
DP-MVS		99.48 135	99.39 158	99.74 103	99.57 296	99.62 144	99.29 175	99.61 273	99.87 63	99.74 176	99.76 156	98.69 198	99.87 258	98.20 301	99.80 273	99.75 89

PCF-MVS	96.03 18	96.73 466	95.86 482	99.33 312	99.44 365	99.16 287	96.87 520	99.44 363	86.58 544	98.95 415	99.40 377	94.38 437	99.88 242	87.93 540	99.80 273	98.95 445
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MASt3R-SfM		98.45 375	98.51 350	98.26 456	99.32 405	97.43 460	97.43 492	99.69 225	94.97 522	99.75 165	99.41 371	98.49 238	99.75 426	97.73 350	99.79 279	97.61 520

aaatest				99.74 103	99.76 164	99.65 129	99.38 132	99.78 165	99.58 181	99.81 119	99.66 241		99.90 205	97.69 362	99.79 279	99.67 135

aaEdge-Enhanced		99.26 214	99.10 242	99.73 113	99.60 270	99.65 129	98.75 353	99.45 362	99.31 240	99.65 227	99.66 241	98.00 300	99.86 278	97.69 362	99.79 279	99.67 135

SMA-MVS		99.19 242	99.00 278	99.73 113	99.46 360	99.73 90	99.13 240	99.52 337	97.40 469	99.57 266	99.64 250	98.93 161	99.83 337	97.61 372	99.79 279	99.63 176
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
MTAPA		99.35 191	99.20 214	99.80 64	99.81 112	99.81 47	99.33 155	99.53 332	99.27 246	99.42 321	99.63 266	98.21 277	99.95 81	97.83 343	99.79 279	99.65 158

ACMMP++															99.79 279

ACMMP		99.25 216	99.08 246	99.74 103	99.79 137	99.68 117	99.50 102	99.65 250	98.07 423	99.52 290	99.69 216	98.57 216	99.92 154	97.18 413	99.79 279	99.63 176
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
OMC-MVS		98.90 318	98.72 324	99.44 263	99.39 377	99.42 212	98.58 376	99.64 258	97.31 474	99.44 314	99.62 276	98.59 213	99.69 454	96.17 474	99.79 279	99.22 376

tfpnnormal		99.43 159	99.38 161	99.60 195	99.87 55	99.75 79	99.59 80	99.78 165	99.71 123	99.90 67	99.69 216	98.85 175	99.90 205	97.25 405	99.78 287	99.15 396

HQP_MVS		98.90 318	98.68 330	99.55 221	99.58 286	99.24 264	98.80 343	99.54 321	98.94 305	99.14 392	99.25 424	97.24 347	99.82 360	95.84 489	99.78 287	99.60 208

plane_prior5								99.54 321					99.82 360	95.84 489	99.78 287	99.60 208

mPP-MVS		99.19 242	99.00 278	99.76 87	99.76 164	99.68 117	99.38 132	99.54 321	98.34 400	99.01 410	99.50 346	98.53 230	99.93 120	97.18 413	99.78 287	99.66 149

RoMa-HiRes		99.38 179	99.30 188	99.64 167	99.81 112	99.47 189	99.11 250	99.94 41	99.03 292	99.55 279	99.56 321	97.71 318	99.92 154	99.19 152	99.77 291	99.54 248

ALIKED-MNN		98.03 412	97.78 425	98.78 417	98.84 487	98.97 320	98.16 429	99.74 189	97.31 474	96.60 529	98.85 484	96.61 375	99.48 512	94.16 518	99.77 291	97.91 517

TestfortrainingZip a		99.55 111	99.45 141	99.85 32	99.76 164	99.82 41	99.38 132	99.62 265	99.77 108	99.87 92	99.78 134	98.12 287	99.88 242	98.96 204	99.77 291	99.85 50

OPM-MVS		99.26 214	99.13 226	99.63 175	99.70 223	99.61 154	98.58 376	99.48 351	98.50 375	99.52 290	99.63 266	99.14 118	99.76 415	97.89 329	99.77 291	99.51 271
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVS_111021_LR		99.13 262	99.03 267	99.42 270	99.58 286	99.32 244	97.91 462	99.73 194	98.68 350	99.31 356	99.48 355	99.09 127	99.66 477	97.70 356	99.77 291	99.29 365

test-260524					99.64 256	99.70 109		99.58 300		99.69 201		97.64 330	99.87 258	98.68 255	99.76 296

DKM-HiRes		98.95 310	98.73 322	99.62 184	99.82 99	99.47 189	98.50 393	99.81 135	99.41 222	97.76 506	99.58 309	95.04 425	99.83 337	98.89 217	99.76 296	99.58 221

SIFT-NN-PointCN		97.97 417	98.24 386	97.14 504	99.59 276	98.71 360	96.75 523	99.56 308	97.02 488	97.91 496	99.27 418	96.85 368	98.39 541	97.47 382	99.76 296	94.31 535

MED-MVS		99.51 124	99.42 152	99.80 64	99.76 164	99.65 129	99.38 132	99.78 165	99.77 108	99.81 119	99.78 134	99.02 147	99.90 205	97.69 362	99.76 296	99.85 50

NormalMVS		99.09 274	98.91 304	99.62 184	99.78 146	99.11 295	99.36 144	99.77 170	99.82 86	99.68 208	99.53 335	93.30 450	99.99 7	99.24 139	99.76 296	99.74 91

lecture		99.56 106	99.48 130	99.81 54	99.78 146	99.86 18	99.50 102	99.70 216	99.59 179	99.75 165	99.71 197	98.94 160	99.92 154	98.59 265	99.76 296	99.66 149

MIMVSNet		98.43 377	98.20 390	99.11 362	99.53 325	98.38 402	99.58 82	98.61 475	98.96 301	99.33 348	99.76 156	90.92 485	99.81 377	97.38 388	99.76 296	99.15 396

MVS_111021_HR		99.12 265	99.02 268	99.40 283	99.50 340	99.11 295	97.92 460	99.71 207	98.76 343	99.08 401	99.47 359	99.17 111	99.54 503	97.85 337	99.76 296	99.54 248

DPE-MVS		99.14 259	98.92 300	99.82 46	99.57 296	99.77 63	98.74 354	99.60 285	98.55 367	99.76 160	99.69 216	98.23 275	99.92 154	96.39 463	99.75 304	99.76 86
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + MP.		99.34 196	99.24 208	99.63 175	99.82 99	99.37 231	99.26 187	99.35 391	98.77 340	99.57 266	99.70 207	99.27 96	99.88 242	97.71 353	99.75 304	99.65 158
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HFP-MVS		99.25 216	99.08 246	99.76 87	99.73 197	99.70 109	99.31 164	99.59 291	98.36 390	99.36 338	99.37 389	98.80 181	99.91 186	97.43 385	99.75 304	99.68 126

ACMMPR		99.23 223	99.06 252	99.76 87	99.74 193	99.69 114	99.31 164	99.59 291	98.36 390	99.35 342	99.38 385	98.61 210	99.93 120	97.43 385	99.75 304	99.67 135

MP-MVS		99.06 280	98.83 313	99.76 87	99.76 164	99.71 101	99.32 158	99.50 346	98.35 396	98.97 413	99.48 355	98.37 255	99.92 154	95.95 484	99.75 304	99.63 176
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
QAPM		98.40 381	97.99 406	99.65 160	99.39 377	99.47 189	99.67 53	99.52 337	91.70 539	98.78 439	99.80 109	98.55 220	99.95 81	94.71 512	99.75 304	99.53 257

DeepC-MVS_fast	98.47 5	99.23 223	99.12 230	99.56 214	99.28 416	99.22 270	98.99 300	99.40 377	99.08 285	99.58 263	99.64 250	98.90 170	99.83 337	97.44 384	99.75 304	99.63 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ALIKED-LG		98.78 333	98.66 331	99.14 358	99.02 471	99.40 220	98.74 354	99.79 152	98.62 361	99.18 385	99.38 385	97.54 333	99.77 408	95.94 486	99.74 311	98.25 499

GDP-MVS		98.81 331	98.57 342	99.50 240	99.53 325	99.12 294	99.28 177	99.86 89	99.53 187	99.57 266	99.32 404	90.88 488	99.98 26	99.46 101	99.74 311	99.42 324

GST-MVS		99.16 253	98.96 292	99.75 98	99.73 197	99.73 90	99.20 205	99.55 315	98.22 409	99.32 351	99.35 399	98.65 206	99.91 186	96.86 430	99.74 311	99.62 188

region2R		99.23 223	99.05 259	99.77 80	99.76 164	99.70 109	99.31 164	99.59 291	98.41 383	99.32 351	99.36 394	98.73 194	99.93 120	97.29 396	99.74 311	99.67 135

PGM-MVS		99.20 239	99.01 274	99.77 80	99.75 182	99.71 101	99.16 226	99.72 203	97.99 428	99.42 321	99.60 296	98.81 177	99.93 120	96.91 427	99.74 311	99.66 149

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 21	99.75 25	99.86 89	99.70 130	99.91 62	99.89 41	99.60 44	99.87 258	99.59 78	99.74 311	99.71 104

TSAR-MVS + GP.		99.12 265	99.04 265	99.38 290	99.34 399	99.16 287	98.15 430	99.29 410	98.18 413	99.63 238	99.62 276	99.18 109	99.68 466	98.20 301	99.74 311	99.30 362

ArgMatch-SfM		99.14 259	99.06 252	99.36 301	99.59 276	99.14 291	98.45 403	99.81 135	98.67 352	99.50 300	99.42 369	98.55 220	99.84 314	97.85 337	99.73 318	99.11 405

KD-MVS_self_test		99.63 86	99.59 96	99.76 87	99.84 81	99.90 7	99.37 140	99.79 152	99.83 82	99.88 82	99.85 68	98.42 248	99.90 205	99.60 77	99.73 318	99.49 282

balanced_ft_v1		99.37 184	99.36 169	99.38 290	99.10 454	99.38 226	99.68 48	99.72 203	99.72 117	99.36 338	99.77 146	97.66 327	99.94 98	99.52 91	99.73 318	98.83 462

XVS		99.27 212	99.11 233	99.75 98	99.71 207	99.71 101	99.37 140	99.61 273	99.29 242	98.76 440	99.47 359	98.47 239	99.88 242	97.62 370	99.73 318	99.67 135

X-MVStestdata		96.09 487	94.87 502	99.75 98	99.71 207	99.71 101	99.37 140	99.61 273	99.29 242	98.76 440	61.30 561	98.47 239	99.88 242	97.62 370	99.73 318	99.67 135

VDD-MVS		99.20 239	99.11 233	99.44 263	99.43 368	98.98 317	99.50 102	98.32 496	99.80 96	99.56 274	99.69 216	96.99 363	99.85 297	98.99 197	99.73 318	99.50 277

ab-mvs		99.33 199	99.28 197	99.47 252	99.57 296	99.39 224	99.78 17	99.43 367	98.87 319	99.57 266	99.82 91	98.06 293	99.87 258	98.69 254	99.73 318	99.15 396

TAPA-MVS	97.92 13	98.03 412	97.55 434	99.46 256	99.47 356	99.44 205	98.50 393	99.62 265	86.79 543	99.07 404	99.26 422	98.26 270	99.62 489	97.28 398	99.73 318	99.31 360
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
usedtu_dtu_shiyan2		99.44 155	99.33 180	99.78 76	99.86 60	99.76 70	99.54 90	99.79 152	99.66 151	99.66 223	99.79 121	96.76 371	99.96 69	99.15 164	99.72 326	99.62 188

DVP-MVS		99.32 201	99.17 218	99.77 80	99.69 231	99.80 51	99.14 233	99.31 406	99.16 272	99.62 248	99.61 286	98.35 257	99.91 186	97.88 330	99.72 326	99.61 203
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				99.83 41	99.70 223	99.79 54	99.14 233	99.61 273					99.92 154	97.88 330	99.72 326	99.77 81

3Dnovator+	98.92 3	99.35 191	99.24 208	99.67 145	99.35 390	99.47 189	99.62 67	99.50 346	99.44 210	99.12 396	99.78 134	98.77 187	99.94 98	97.87 333	99.72 326	99.62 188

ArgMatch-Sym		99.06 280	98.96 292	99.35 305	99.62 265	99.22 270	98.34 410	99.79 152	98.80 333	99.50 300	99.29 414	98.30 265	99.75 426	97.30 395	99.71 330	99.08 420

plane_prior						99.24 264	98.42 406		97.87 443						99.71 330

APD-MVS		98.87 323	98.59 338	99.71 128	99.50 340	99.62 144	99.01 286	99.57 303	96.80 496	99.54 283	99.63 266	98.29 266	99.91 186	95.24 503	99.71 330	99.61 203
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SIFT-UM-Cal		98.18 401	98.45 360	97.37 492	99.59 276	98.95 324	96.76 522	99.39 380	98.39 386	99.46 311	99.31 407	96.23 397	99.24 523	97.21 408	99.70 333	93.90 541

icg_test_0407_2		99.30 204	99.29 194	99.31 321	99.71 207	98.55 384	98.17 427	99.71 207	99.41 222	99.73 182	99.60 296	99.17 111	99.92 154	98.45 278	99.70 333	99.45 297

IMVS_0407		99.38 179	99.42 152	99.28 329	99.71 207	98.55 384	99.27 182	99.71 207	99.41 222	99.73 182	99.60 296	99.17 111	99.83 337	98.45 278	99.70 333	99.45 297

IMVS_0404		99.23 223	99.20 214	99.32 317	99.71 207	98.55 384	98.57 380	99.71 207	99.41 222	99.52 290	99.60 296	98.12 287	99.95 81	98.45 278	99.70 333	99.45 297

IMVS_0403		99.37 184	99.39 158	99.28 329	99.71 207	98.55 384	99.19 211	99.71 207	99.41 222	99.67 216	99.60 296	99.12 123	99.84 314	98.45 278	99.70 333	99.45 297

APD_test1		99.36 189	99.28 197	99.61 191	99.89 40	99.89 10	99.32 158	99.74 189	99.18 263	99.69 201	99.75 164	98.41 249	99.84 314	97.85 337	99.70 333	99.10 408

SED-MVS		99.40 172	99.28 197	99.77 80	99.69 231	99.82 41	99.20 205	99.54 321	99.13 279	99.82 112	99.63 266	98.91 167	99.92 154	97.85 337	99.70 333	99.58 221

IU-MVS					99.69 231	99.77 63		99.22 427	97.50 463	99.69 201				97.75 348	99.70 333	99.77 81

ambc				99.20 349	99.35 390	98.53 388	99.17 220	99.46 357		99.67 216	99.80 109	98.46 243	99.70 447	97.92 326	99.70 333	99.38 334

MSC_two_6792asdad				99.74 103	99.03 465	99.53 176		99.23 424					99.92 154	97.77 344	99.69 342	99.78 77

No_MVS				99.74 103	99.03 465	99.53 176		99.23 424					99.92 154	97.77 344	99.69 342	99.78 77

test_241102_TWO								99.54 321	99.13 279	99.76 160	99.63 266	98.32 263	99.92 154	97.85 337	99.69 342	99.75 89

MVSFormer		99.41 170	99.44 146	99.31 321	99.57 296	98.40 398	99.77 19	99.80 143	99.73 113	99.63 238	99.30 410	98.02 295	99.98 26	99.43 106	99.69 342	99.55 236

lupinMVS		98.96 307	98.87 307	99.24 343	99.57 296	98.40 398	98.12 435	99.18 436	98.28 406	99.63 238	99.13 445	98.02 295	99.97 44	98.22 299	99.69 342	99.35 344

SF-MVS		99.10 273	98.93 296	99.62 184	99.58 286	99.51 182	99.13 240	99.65 250	97.97 430	99.42 321	99.61 286	98.86 174	99.87 258	96.45 461	99.68 347	99.49 282

Anonymous20240529		99.42 163	99.34 175	99.65 160	99.53 325	99.60 158	99.63 64	99.39 380	99.47 202	99.76 160	99.78 134	98.13 285	99.86 278	98.70 252	99.68 347	99.49 282

MSLP-MVS++		99.05 284	99.09 244	98.91 396	99.21 429	98.36 403	98.82 339	99.47 354	98.85 322	98.90 423	99.56 321	98.78 185	99.09 529	98.57 268	99.68 347	99.26 368

DELS-MVS		99.34 196	99.30 188	99.48 250	99.51 334	99.36 235	98.12 435	99.53 332	99.36 233	99.41 327	99.61 286	99.22 104	99.87 258	99.21 146	99.68 347	99.20 384
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
PVSNet	97.47 15	98.42 378	98.44 362	98.35 446	99.46 360	96.26 493	96.70 526	99.34 395	97.68 454	99.00 411	99.13 445	97.40 339	99.72 438	97.59 374	99.68 347	99.08 420

LS3D		99.24 220	99.11 233	99.61 191	98.38 516	99.79 54	99.57 85	99.68 230	99.61 170	99.15 390	99.71 197	98.70 197	99.91 186	97.54 377	99.68 347	99.13 404

HQP3-MVS								99.37 386							99.67 353

CPTT-MVS		98.74 338	98.44 362	99.64 167	99.61 267	99.38 226	99.18 215	99.55 315	96.49 499	99.27 363	99.37 389	97.11 357	99.92 154	95.74 494	99.67 353	99.62 188

HQP-MVS		98.36 383	98.02 405	99.39 286	99.31 407	98.94 326	97.98 453	99.37 386	97.45 465	98.15 483	98.83 486	96.67 373	99.70 447	94.73 510	99.67 353	99.53 257

MVS_Test		99.28 208	99.31 183	99.19 350	99.35 390	98.79 353	99.36 144	99.49 350	99.17 270	99.21 379	99.67 235	98.78 185	99.66 477	99.09 182	99.66 356	99.10 408

CDPH-MVS		98.56 360	98.20 390	99.61 191	99.50 340	99.46 197	98.32 414	99.41 370	95.22 518	99.21 379	99.10 453	98.34 259	99.82 360	95.09 507	99.66 356	99.56 232

tttt0517		97.62 434	97.20 448	98.90 402	99.76 164	97.40 461	99.48 109	94.36 543	99.06 289	99.70 197	99.49 351	84.55 524	99.94 98	98.73 246	99.65 358	99.36 341

ITE_SJBPF				99.38 290	99.63 261	99.44 205		99.73 194	98.56 365	99.33 348	99.53 335	98.88 171	99.68 466	96.01 478	99.65 358	99.02 438

PRO-TEST		99.15 257	99.22 212	98.95 384	99.11 451	98.09 421	99.28 177	99.69 225	99.90 49	99.11 397	99.81 98	97.64 330	99.92 154	98.84 222	99.64 360	98.83 462

ttmdpeth		99.48 135	99.55 112	99.29 326	99.76 164	98.16 415	99.33 155	99.95 38	99.79 100	99.36 338	99.89 41	99.13 120	99.77 408	99.09 182	99.64 360	99.93 21

9.14			98.64 332		99.45 364		98.81 340	99.60 285	97.52 462	99.28 362	99.56 321	98.53 230	99.83 337	95.36 502	99.64 360

Patchmatch-test		98.10 408	97.98 408	98.48 439	99.27 418	96.48 487	99.40 127	99.07 446	98.81 331	99.23 373	99.57 317	90.11 500	99.87 258	96.69 441	99.64 360	99.09 414

SymmetryMVS		99.01 297	98.82 314	99.58 202	99.65 254	99.11 295	99.36 144	99.20 433	99.82 86	99.68 208	99.53 335	93.30 450	99.99 7	99.24 139	99.63 364	99.64 170

sss		98.90 318	98.77 321	99.27 334	99.48 350	98.44 395	98.72 357	99.32 402	97.94 436	99.37 337	99.35 399	96.31 391	99.91 186	98.85 220	99.63 364	99.47 290

GLUNet-SfM		95.26 503	95.06 500	95.87 525	94.84 552	90.39 551	90.24 546	99.92 47	92.30 536	99.16 387	99.25 424	94.69 432	98.01 543	85.55 547	99.62 366	99.21 379

cl22		97.56 437	97.28 443	98.40 443	98.37 517	96.75 482	97.24 501	99.37 386	97.31 474	99.41 327	99.22 433	87.30 510	99.37 518	97.70 356	99.62 366	99.08 420

miper_ehance_all_eth		98.59 357	98.59 338	98.59 432	98.98 472	97.07 472	97.49 489	99.52 337	98.50 375	99.52 290	99.37 389	96.41 386	99.71 443	97.86 335	99.62 366	99.00 440

miper_enhance_ethall		98.03 412	97.94 414	98.32 449	98.27 520	96.43 489	96.95 516	99.41 370	96.37 502	99.43 318	98.96 474	94.74 430	99.69 454	97.71 353	99.62 366	98.83 462

SCA		98.11 407	98.36 373	97.36 493	99.20 432	92.99 533	98.17 427	98.49 484	98.24 408	99.10 400	99.57 317	96.01 403	99.94 98	96.86 430	99.62 366	99.14 401

MS-PatchMatch		99.00 300	98.97 290	99.09 365	99.11 451	98.19 411	98.76 349	99.33 400	98.49 377	99.44 314	99.58 309	98.21 277	99.69 454	98.20 301	99.62 366	99.39 332

APD-MVS_3200maxsize		99.31 203	99.16 219	99.74 103	99.53 325	99.75 79	99.27 182	99.61 273	99.19 262	99.57 266	99.64 250	98.76 188	99.90 205	97.29 396	99.62 366	99.56 232

EPNet_dtu		97.62 434	97.79 424	97.11 505	96.67 546	92.31 537	98.51 392	98.04 504	99.24 253	95.77 536	99.47 359	93.78 445	99.66 477	98.98 199	99.62 366	99.37 338
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SR-MVS-dyc-post		99.27 212	99.11 233	99.73 113	99.54 316	99.74 87	99.26 187	99.62 265	99.16 272	99.52 290	99.64 250	98.41 249	99.91 186	97.27 399	99.61 374	99.54 248

RE-MVS-def			99.13 226		99.54 316	99.74 87	99.26 187	99.62 265	99.16 272	99.52 290	99.64 250	98.57 216		97.27 399	99.61 374	99.54 248

MG-MVS		98.52 365	98.39 369	98.94 386	99.15 441	97.39 462	98.18 424	99.21 430	98.89 318	99.23 373	99.63 266	97.37 342	99.74 433	94.22 517	99.61 374	99.69 119

DVP-MVS++		99.38 179	99.25 206	99.77 80	99.03 465	99.77 63	99.74 27	99.61 273	99.18 263	99.76 160	99.61 286	99.00 149	99.92 154	97.72 351	99.60 377	99.62 188

PC_three_1452									97.56 457	99.68 208	99.41 371	99.09 127	97.09 546	96.66 444	99.60 377	99.62 188

OPU-MVS				99.29 326	99.12 446	99.44 205	99.20 205				99.40 377	99.00 149	98.84 536	96.54 452	99.60 377	99.58 221

HPM-MVS++		98.96 307	98.70 329	99.74 103	99.52 332	99.71 101	98.86 327	99.19 434	98.47 379	98.59 455	99.06 457	98.08 292	99.91 186	96.94 425	99.60 377	99.60 208

mvsmamba		99.08 275	98.95 294	99.45 259	99.36 386	99.18 286	99.39 129	98.81 464	99.37 229	99.35 342	99.70 207	96.36 389	99.94 98	98.66 258	99.59 381	99.22 376

CNVR-MVS		98.99 303	98.80 319	99.56 214	99.25 422	99.43 209	98.54 387	99.27 414	98.58 364	98.80 435	99.43 367	98.53 230	99.70 447	97.22 407	99.59 381	99.54 248

Anonymous202405211		98.75 337	98.46 357	99.63 175	99.34 399	99.66 123	99.47 112	97.65 515	99.28 245	99.56 274	99.50 346	93.15 453	99.84 314	98.62 264	99.58 383	99.40 328

MVP-Stereo		99.16 253	99.08 246	99.43 267	99.48 350	99.07 305	99.08 262	99.55 315	98.63 357	99.31 356	99.68 229	98.19 280	99.78 395	98.18 305	99.58 383	99.45 297
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVStest1		98.22 398	98.09 400	98.62 429	99.04 464	96.23 494	99.20 205	99.92 47	99.44 210	99.98 14	99.87 56	85.87 521	99.67 472	99.91 33	99.57 385	99.95 15

ADS-MVSNet2		97.78 427	97.66 432	98.12 460	99.14 442	95.36 512	99.22 202	98.75 467	96.97 489	98.25 474	99.64 250	90.90 486	99.94 98	96.51 454	99.56 386	99.08 420

ADS-MVSNet		97.72 432	97.67 431	97.86 470	99.14 442	94.65 522	99.22 202	98.86 459	96.97 489	98.25 474	99.64 250	90.90 486	99.84 314	96.51 454	99.56 386	99.08 420

LCM-MVSNet-Re		99.28 208	99.15 223	99.67 145	99.33 404	99.76 70	99.34 149	99.97 21	98.93 310	99.91 62	99.79 121	98.68 199	99.93 120	96.80 436	99.56 386	99.30 362

API-MVS		98.38 382	98.39 369	98.35 446	98.83 488	99.26 256	99.14 233	99.18 436	98.59 363	98.66 448	98.78 490	98.61 210	99.57 498	94.14 519	99.56 386	96.21 529

xiu_mvs_v1_base_debu		99.23 223	99.34 175	98.91 396	99.59 276	98.23 407	98.47 398	99.66 240	99.61 170	99.68 208	98.94 477	99.39 71	99.97 44	99.18 155	99.55 390	98.51 486

xiu_mvs_v1_base		99.23 223	99.34 175	98.91 396	99.59 276	98.23 407	98.47 398	99.66 240	99.61 170	99.68 208	98.94 477	99.39 71	99.97 44	99.18 155	99.55 390	98.51 486

xiu_mvs_v1_base_debi		99.23 223	99.34 175	98.91 396	99.59 276	98.23 407	98.47 398	99.66 240	99.61 170	99.68 208	98.94 477	99.39 71	99.97 44	99.18 155	99.55 390	98.51 486

OpenMVS	98.12 10	98.23 396	97.89 419	99.26 338	99.19 434	99.26 256	99.65 62	99.69 225	91.33 540	98.14 487	99.77 146	98.28 267	99.96 69	95.41 500	99.55 390	98.58 481

MVE	92.54 22	96.66 469	96.11 476	98.31 451	99.68 240	97.55 450	97.94 458	95.60 540	99.37 229	90.68 547	98.70 496	96.56 377	98.61 539	86.94 545	99.55 390	98.77 470
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SR-MVS		99.19 242	99.00 278	99.74 103	99.51 334	99.72 95	99.18 215	99.60 285	98.85 322	99.47 307	99.58 309	98.38 254	99.92 154	96.92 426	99.54 395	99.57 228

thisisatest0530		97.45 444	96.95 458	98.94 386	99.68 240	97.73 444	99.09 259	94.19 545	98.61 362	99.56 274	99.30 410	84.30 526	99.93 120	98.27 294	99.54 395	99.16 394

tt0805		99.63 86	99.57 105	99.81 54	99.87 55	99.88 12	99.58 82	98.70 469	99.72 117	99.91 62	99.60 296	99.43 67	99.81 377	99.81 51	99.53 397	99.73 95

MSP-MVS		99.04 287	98.79 320	99.81 54	99.78 146	99.73 90	99.35 148	99.57 303	98.54 370	99.54 283	98.99 467	96.81 369	99.93 120	96.97 423	99.53 397	99.77 81
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
AdaColmap		98.60 354	98.35 375	99.38 290	99.12 446	99.22 270	98.67 363	99.42 369	97.84 447	98.81 433	99.27 418	97.32 345	99.81 377	95.14 505	99.53 397	99.10 408

ETV-MVS		99.18 246	99.18 217	99.16 353	99.34 399	99.28 250	99.12 245	99.79 152	99.48 197	98.93 417	98.55 505	99.40 70	99.93 120	98.51 274	99.52 400	98.28 496

SSC-MVS		99.52 122	99.42 152	99.83 41	99.86 60	99.65 129	99.52 94	99.81 135	99.87 63	99.81 119	99.79 121	96.78 370	99.99 7	99.83 46	99.51 401	99.86 47

EIA-MVS		99.12 265	99.01 274	99.45 259	99.36 386	99.62 144	99.34 149	99.79 152	98.41 383	98.84 430	98.89 481	98.75 190	99.84 314	98.15 309	99.51 401	98.89 456

MCST-MVS		99.02 291	98.81 316	99.65 160	99.58 286	99.49 184	98.58 376	99.07 446	98.40 385	99.04 407	99.25 424	98.51 236	99.80 387	97.31 393	99.51 401	99.65 158

mvs_anonymous		99.28 208	99.39 158	98.94 386	99.19 434	97.81 440	99.02 281	99.55 315	99.78 103	99.85 101	99.80 109	98.24 271	99.86 278	99.57 82	99.50 404	99.15 396

CNLPA		98.57 359	98.34 376	99.28 329	99.18 437	99.10 302	98.34 410	99.41 370	98.48 378	98.52 461	98.98 470	97.05 359	99.78 395	95.59 496	99.50 404	98.96 443

ZD-MVS					99.43 368	99.61 154		99.43 367	96.38 501	99.11 397	99.07 456	97.86 307	99.92 154	94.04 521	99.49 406

test_prior2							97.95 457		97.87 443	98.05 489	99.05 458	97.90 304		95.99 481	99.49 406

SIFT-MNN		97.55 439	97.74 427	96.98 508	99.38 380	98.85 345	96.92 519	98.61 475	98.36 390	98.63 451	99.10 453	92.51 464	97.85 544	96.63 448	99.48 408	94.25 537

SP-LightGlue		98.62 350	98.51 350	98.94 386	98.69 505	99.01 312	98.34 410	99.54 321	99.27 246	97.72 509	99.15 444	95.88 407	99.54 503	98.53 273	99.47 409	98.27 497

pmmvs3		98.08 409	97.80 422	98.91 396	99.41 375	97.69 446	97.87 464	99.66 240	95.87 507	99.50 300	99.51 343	90.35 497	99.97 44	98.55 270	99.47 409	99.08 420

test12				99.54 227	99.29 413	99.33 241		99.16 439		98.43 466		97.54 333	99.82 360		99.47 409	99.48 286

agg_prior2														94.58 513	99.46 412	99.50 277

test9_res														95.10 506	99.44 413	99.50 277

train_agg		98.35 386	97.95 410	99.57 210	99.35 390	99.35 238	98.11 437	99.41 370	94.90 523	97.92 494	98.99 467	98.02 295	99.85 297	95.38 501	99.44 413	99.50 277

VPNet		99.46 147	99.37 164	99.71 128	99.82 99	99.59 160	99.48 109	99.70 216	99.81 92	99.69 201	99.58 309	97.66 327	99.86 278	99.17 159	99.44 413	99.67 135

DP-MVS Recon		98.50 368	98.23 387	99.31 321	99.49 345	99.46 197	98.56 383	99.63 262	94.86 525	98.85 429	99.37 389	97.81 311	99.59 496	96.08 475	99.44 413	98.88 457

PMatch-Up-SfM		99.08 275	99.02 268	99.27 334	99.81 112	99.04 310	98.13 433	99.83 115	99.16 272	99.26 367	99.69 216	97.22 349	99.83 337	98.67 257	99.43 417	98.94 448

LFMVS		98.46 374	98.19 393	99.26 338	99.24 424	98.52 390	99.62 67	96.94 526	99.87 63	99.31 356	99.58 309	91.04 483	99.81 377	98.68 255	99.42 418	99.45 297

Fast-Effi-MVS+		99.02 291	98.87 307	99.46 256	99.38 380	99.50 183	99.04 274	99.79 152	97.17 481	98.62 452	98.74 492	99.34 85	99.95 81	98.32 290	99.41 419	98.92 451

PatchmatchNet		97.65 433	97.80 422	97.18 500	98.82 491	92.49 536	99.17 220	98.39 492	98.12 417	98.79 437	99.58 309	90.71 492	99.89 227	97.23 406	99.41 419	99.16 394
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0515		96.98 460	96.42 469	98.66 428	99.42 373	97.47 454	97.27 498	94.30 544	97.24 477	99.15 390	98.86 483	85.01 522	99.87 258	97.10 416	99.39 421	98.63 475

原ACMM1				99.37 295	99.47 356	98.87 344		99.27 414	96.74 498	98.26 473	99.32 404	97.93 303	99.82 360	95.96 483	99.38 422	99.43 319

test222					99.51 334	99.08 304	97.83 466	99.29 410	95.21 519	98.68 447	99.31 407	97.28 346			99.38 422	99.43 319

F-COLMAP		98.74 338	98.45 360	99.62 184	99.57 296	99.47 189	98.84 332	99.65 250	96.31 503	98.93 417	99.19 441	97.68 322	99.87 258	96.52 453	99.37 424	99.53 257

DPM-MVS		98.28 389	97.94 414	99.32 317	99.36 386	99.11 295	97.31 497	98.78 466	96.88 492	98.84 430	99.11 452	97.77 315	99.61 494	94.03 522	99.36 425	99.23 374

旧先验1					99.49 345	99.29 248		99.26 416			99.39 382	97.67 323			99.36 425	99.46 295

dmvs_re		98.69 345	98.48 354	99.31 321	99.55 314	99.42 212	99.54 90	98.38 493	99.32 238	98.72 443	98.71 494	96.76 371	99.21 524	96.01 478	99.35 427	99.31 360

PS-MVSNAJ		99.00 300	99.08 246	98.76 419	99.37 383	98.10 420	98.00 451	99.51 342	99.47 202	99.41 327	98.50 508	99.28 93	99.97 44	98.83 223	99.34 428	98.20 504

testing3		96.48 475	95.63 488	99.01 377	99.23 426	97.81 440	98.90 320	99.10 445	98.72 345	97.84 502	97.92 521	72.44 551	99.85 297	97.21 408	99.33 429	99.35 344

xiu_mvs_v2_base		99.02 291	99.11 233	98.77 418	99.37 383	98.09 421	98.13 433	99.51 342	99.47 202	99.42 321	98.54 506	99.38 76	99.97 44	98.83 223	99.33 429	98.24 500

新几何1				99.52 234	99.50 340	99.22 270		99.26 416	95.66 513	98.60 454	99.28 416	97.67 323	99.89 227	95.95 484	99.32 431	99.45 297

VDDNet		98.97 304	98.82 314	99.42 270	99.71 207	98.81 349	99.62 67	98.68 470	99.81 92	99.38 335	99.80 109	94.25 438	99.85 297	98.79 232	99.32 431	99.59 215

FA-MVS(test-final)		98.52 365	98.32 378	99.10 364	99.48 350	98.67 363	99.77 19	98.60 478	97.35 472	99.63 238	99.80 109	93.07 455	99.84 314	97.92 326	99.30 433	98.78 468

VNet		99.18 246	99.06 252	99.56 214	99.24 424	99.36 235	99.33 155	99.31 406	99.67 144	99.47 307	99.57 317	96.48 381	99.84 314	99.15 164	99.30 433	99.47 290

PatchMatch-RL		98.68 346	98.47 355	99.30 325	99.44 365	99.28 250	98.14 432	99.54 321	97.12 484	99.11 397	99.25 424	97.80 312	99.70 447	96.51 454	99.30 433	98.93 449

Effi-MVS+-dtu		99.07 279	98.92 300	99.52 234	98.89 480	99.78 57	99.15 229	99.66 240	99.34 234	98.92 420	99.24 430	97.69 321	99.98 26	98.11 311	99.28 436	98.81 465

testdata				99.42 270	99.51 334	98.93 329		99.30 409	96.20 504	98.87 427	99.40 377	98.33 262	99.89 227	96.29 467	99.28 436	99.44 312

OpenMVS_ROB	97.31 17	97.36 450	96.84 463	98.89 403	99.29 413	99.45 203	98.87 326	99.48 351	86.54 545	99.44 314	99.74 172	97.34 343	99.86 278	91.61 530	99.28 436	97.37 524

NCCC		98.82 329	98.57 342	99.58 202	99.21 429	99.31 245	98.61 369	99.25 419	98.65 354	98.43 466	99.26 422	97.86 307	99.81 377	96.55 451	99.27 439	99.61 203

SIFT-NN-CMatch		97.30 451	97.34 441	97.18 500	99.54 316	98.85 345	96.02 534	95.77 539	97.05 487	97.55 512	98.70 496	96.35 390	98.75 537	95.82 491	99.26 440	93.95 540

testing3-2		96.51 474	96.43 468	96.74 514	99.36 386	91.38 545	99.10 254	97.87 512	99.48 197	98.57 458	98.71 494	76.65 544	99.66 477	98.87 219	99.26 440	99.18 389

testgi		99.29 206	99.26 202	99.37 295	99.75 182	98.81 349	98.84 332	99.89 68	98.38 388	99.75 165	99.04 460	99.36 81	99.86 278	99.08 184	99.25 442	99.45 297

PLC	97.35 16	98.36 383	97.99 406	99.48 250	99.32 405	99.24 264	98.50 393	99.51 342	95.19 520	98.58 456	98.96 474	96.95 364	99.83 337	95.63 495	99.25 442	99.37 338
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Fast-Effi-MVS+-dtu		99.20 239	99.12 230	99.43 267	99.25 422	99.69 114	99.05 269	99.82 122	99.50 192	98.97 413	99.05 458	98.98 155	99.98 26	98.20 301	99.24 444	98.62 476

PMMVS		98.49 370	98.29 383	99.11 362	98.96 474	98.42 397	97.54 484	99.32 402	97.53 461	98.47 464	98.15 517	97.88 306	99.82 360	97.46 383	99.24 444	99.09 414

WB-MVS		99.44 155	99.32 181	99.80 64	99.81 112	99.61 154	99.47 112	99.81 135	99.82 86	99.71 193	99.72 187	96.60 376	99.98 26	99.75 56	99.23 446	99.82 66

EPMVS		96.53 472	96.32 470	97.17 502	98.18 524	92.97 534	99.39 129	89.95 554	98.21 410	98.61 453	99.59 306	86.69 519	99.72 438	96.99 421	99.23 446	98.81 465

SIFT-NN-NCMNet		97.22 453	97.27 445	97.07 506	99.64 256	99.20 277	96.53 528	95.91 532	96.91 491	97.38 514	98.95 476	96.01 403	98.29 542	94.87 508	99.21 448	93.73 544

SP-SuperGlue		98.66 348	98.63 334	98.73 421	98.44 514	99.02 311	98.22 422	99.44 363	99.37 229	98.17 482	99.30 410	96.95 364	99.12 526	98.59 265	99.20 449	98.06 508

SP-DiffGlue		98.47 372	98.43 364	98.59 432	97.44 542	98.59 379	98.01 448	99.36 390	99.00 296	99.06 405	99.20 439	97.01 361	99.25 522	97.64 368	99.15 450	97.92 516

alignmvs		98.28 389	97.96 409	99.25 341	99.12 446	98.93 329	99.03 277	98.42 488	99.64 160	98.72 443	97.85 522	90.86 489	99.62 489	98.88 218	99.13 451	99.19 387

FE-MVS		97.85 422	97.42 439	99.15 355	99.44 365	98.75 357	99.77 19	98.20 500	95.85 508	99.33 348	99.80 109	88.86 506	99.88 242	96.40 462	99.12 452	98.81 465

cascas		96.99 459	96.82 465	97.48 483	97.57 540	95.64 507	96.43 530	99.56 308	91.75 538	97.13 524	97.61 529	95.58 412	98.63 538	96.68 442	99.11 453	98.18 505

XFeat-MNN		96.67 468	96.56 467	96.98 508	96.73 545	95.62 509	94.54 541	98.93 458	97.42 468	98.18 478	98.67 499	91.60 477	99.12 526	93.88 524	99.10 454	96.21 529

BH-RMVSNet		98.41 379	98.14 397	99.21 346	99.21 429	98.47 391	98.60 371	98.26 498	98.35 396	98.93 417	99.31 407	97.20 353	99.66 477	94.32 515	99.10 454	99.51 271

RRT-MVS		99.08 275	99.00 278	99.33 312	99.27 418	98.65 370	99.62 67	99.93 43	99.66 151	99.67 216	99.82 91	95.27 422	99.93 120	98.64 262	99.09 456	99.41 325

UWE-MVS		96.21 485	95.78 484	97.49 482	98.53 510	93.83 529	98.04 445	93.94 547	98.96 301	98.46 465	98.17 516	79.86 533	99.87 258	96.99 421	99.06 457	98.78 468

MAR-MVS		98.24 394	97.92 416	99.19 350	98.78 496	99.65 129	99.17 220	99.14 442	95.36 516	98.04 490	98.81 489	97.47 336	99.72 438	95.47 499	99.06 457	98.21 502
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
GA-MVS		97.99 416	97.68 430	98.93 390	99.52 332	98.04 426	97.19 502	99.05 449	98.32 403	98.81 433	98.97 472	89.89 503	99.41 516	98.33 289	99.05 459	99.34 350

EMVS		96.96 461	97.28 443	95.99 524	98.76 499	91.03 546	95.26 539	98.61 475	99.34 234	98.92 420	98.88 482	93.79 444	99.66 477	92.87 526	99.05 459	97.30 525

PMatch-SfM		98.91 315	98.81 316	99.22 345	99.79 137	98.89 337	98.18 424	99.61 273	99.18 263	99.03 408	99.61 286	96.13 399	99.80 387	98.71 250	99.04 461	98.99 441

E-PMN		97.14 458	97.43 438	96.27 520	98.79 494	91.62 542	95.54 536	99.01 454	99.44 210	98.88 424	99.12 449	92.78 458	99.68 466	94.30 516	99.03 462	97.50 521

tpmrst		97.73 429	98.07 402	96.73 515	98.71 503	92.00 538	99.10 254	98.86 459	98.52 373	98.92 420	99.54 332	91.90 472	99.82 360	98.02 316	99.03 462	98.37 493

PatchT		98.45 375	98.32 378	98.83 411	98.94 475	98.29 405	99.24 194	98.82 462	99.84 76	99.08 401	99.76 156	91.37 478	99.94 98	98.82 225	99.00 464	98.26 498

WB-MVSnew		98.34 388	98.14 397	98.96 382	98.14 527	97.90 436	98.27 417	97.26 523	98.63 357	98.80 435	98.00 520	97.77 315	99.90 205	97.37 389	98.98 465	99.09 414

CL-MVSNet_self_test		98.71 343	98.56 346	99.15 355	99.22 427	98.66 366	97.14 506	99.51 342	98.09 420	99.54 283	99.27 418	96.87 367	99.74 433	98.43 282	98.96 466	99.03 433

ALIKED-NN		96.66 469	96.26 472	97.88 468	97.49 541	98.59 379	96.71 525	99.15 440	95.50 514	93.58 544	98.39 510	94.52 435	97.74 545	92.05 529	98.94 467	97.29 526

test_yl		98.25 392	97.95 410	99.13 360	99.17 438	98.47 391	99.00 292	98.67 472	98.97 299	99.22 377	99.02 465	91.31 479	99.69 454	97.26 401	98.93 468	99.24 371

DCV-MVSNet		98.25 392	97.95 410	99.13 360	99.17 438	98.47 391	99.00 292	98.67 472	98.97 299	99.22 377	99.02 465	91.31 479	99.69 454	97.26 401	98.93 468	99.24 371

MGCFI-Net		99.02 291	99.01 274	99.06 373	99.11 451	98.60 377	99.63 64	99.67 235	99.63 162	98.58 456	97.65 526	99.07 134	99.57 498	98.85 220	98.92 470	99.03 433

sasdasda		99.02 291	99.00 278	99.09 365	99.10 454	98.70 361	99.61 73	99.66 240	99.63 162	98.64 449	97.65 526	99.04 144	99.54 503	98.79 232	98.92 470	99.04 430

canonicalmvs		99.02 291	99.00 278	99.09 365	99.10 454	98.70 361	99.61 73	99.66 240	99.63 162	98.64 449	97.65 526	99.04 144	99.54 503	98.79 232	98.92 470	99.04 430

MDTV_nov1_ep13			97.73 428		98.70 504	90.83 547	99.15 229	98.02 505	98.51 374	98.82 432	99.61 286	90.98 484	99.66 477	96.89 429	98.92 470

PAPM_NR		98.36 383	98.04 403	99.33 312	99.48 350	98.93 329	98.79 346	99.28 413	97.54 460	98.56 460	98.57 503	97.12 356	99.69 454	94.09 520	98.90 474	99.38 334

FPMVS		96.32 480	95.50 489	98.79 415	99.60 270	98.17 414	98.46 402	98.80 465	97.16 482	96.28 532	99.63 266	82.19 527	99.09 529	88.45 538	98.89 475	99.10 408

tpm cat1		96.78 464	96.98 457	96.16 522	98.85 485	90.59 550	99.08 262	99.32 402	92.37 535	97.73 508	99.46 362	91.15 482	99.69 454	96.07 476	98.80 476	98.21 502

test-LLR		97.15 456	96.95 458	97.74 475	98.18 524	95.02 519	97.38 493	96.10 528	98.00 426	97.81 503	98.58 501	90.04 501	99.91 186	97.69 362	98.78 477	98.31 494

test-mter		96.23 483	95.73 486	97.74 475	98.18 524	95.02 519	97.38 493	96.10 528	97.90 438	97.81 503	98.58 501	79.12 538	99.91 186	97.69 362	98.78 477	98.31 494

TESTMET0.1,1		96.24 482	95.84 483	97.41 489	98.24 521	93.84 528	97.38 493	95.84 536	98.43 380	97.81 503	98.56 504	79.77 535	99.89 227	97.77 344	98.77 479	98.52 485

CR-MVSNet		98.35 386	98.20 390	98.83 411	99.05 461	98.12 417	99.30 167	99.67 235	97.39 470	99.16 387	99.79 121	91.87 474	99.91 186	98.78 238	98.77 479	98.44 491

RPMNet		98.60 354	98.53 348	98.83 411	99.05 461	98.12 417	99.30 167	99.62 265	99.86 66	99.16 387	99.74 172	92.53 463	99.92 154	98.75 240	98.77 479	98.44 491

WTY-MVS		98.59 357	98.37 371	99.26 338	99.43 368	98.40 398	98.74 354	99.13 444	98.10 418	99.21 379	99.24 430	94.82 429	99.90 205	97.86 335	98.77 479	99.49 282

SP-MNN		97.94 420	97.82 421	98.31 451	98.30 519	97.67 447	97.81 467	97.93 509	98.14 415	97.16 523	98.64 500	96.31 391	99.21 524	97.34 390	98.75 483	98.05 510

UBG		96.53 472	95.95 479	98.29 454	98.87 483	96.31 492	98.48 397	98.07 503	98.83 327	97.32 516	96.54 550	79.81 534	99.62 489	96.84 434	98.74 484	98.95 445

Effi-MVS+		99.06 280	98.97 290	99.34 309	99.31 407	98.98 317	98.31 415	99.91 57	98.81 331	98.79 437	98.94 477	99.14 118	99.84 314	98.79 232	98.74 484	99.20 384

PAPR		97.56 437	97.07 453	99.04 375	98.80 492	98.11 419	97.63 479	99.25 419	94.56 529	98.02 492	98.25 514	97.43 338	99.68 466	90.90 533	98.74 484	99.33 351

Syy-MVS		98.17 404	97.85 420	99.15 355	98.50 512	98.79 353	98.60 371	99.21 430	97.89 440	96.76 526	96.37 553	95.47 418	99.57 498	99.10 181	98.73 487	99.09 414

myMVS_eth3d		95.63 499	94.73 503	98.34 448	98.50 512	96.36 490	98.60 371	99.21 430	97.89 440	96.76 526	96.37 553	72.10 552	99.57 498	94.38 514	98.73 487	99.09 414

tpmvs		97.39 448	97.69 429	96.52 517	98.41 515	91.76 540	99.30 167	98.94 457	97.74 449	97.85 501	99.55 330	92.40 468	99.73 436	96.25 469	98.73 487	98.06 508

dp		96.86 462	97.07 453	96.24 521	98.68 506	90.30 553	99.19 211	98.38 493	97.35 472	98.23 476	99.59 306	87.23 511	99.82 360	96.27 468	98.73 487	98.59 479

XVG-OURS-SEG-HR		99.16 253	98.99 285	99.66 153	99.84 81	99.64 136	98.25 420	99.73 194	98.39 386	99.63 238	99.43 367	99.70 31	99.90 205	97.34 390	98.64 491	99.44 312

thres600view7		96.60 471	96.16 475	97.93 466	99.63 261	96.09 500	99.18 215	97.57 516	98.77 340	98.72 443	97.32 533	87.04 513	99.72 438	88.57 537	98.62 492	97.98 513

thres200		96.09 487	95.68 487	97.33 496	99.48 350	96.22 495	98.53 389	97.57 516	98.06 424	98.37 469	96.73 547	86.84 517	99.61 494	86.99 544	98.57 493	96.16 531

1314		98.00 415	97.90 418	98.27 455	98.90 477	97.45 457	99.30 167	99.06 448	94.98 521	97.21 520	99.12 449	98.43 246	99.67 472	95.58 497	98.56 494	97.71 518

dmvs_testset		97.27 452	96.83 464	98.59 432	99.46 360	97.55 450	99.25 193	96.84 527	98.78 337	97.24 519	97.67 525	97.11 357	98.97 533	86.59 546	98.54 495	99.27 366

thres100view900		96.39 477	96.03 478	97.47 485	99.63 261	95.93 501	99.18 215	97.57 516	98.75 344	98.70 446	97.31 534	87.04 513	99.67 472	87.62 541	98.51 496	96.81 527

tfpn200view9		96.30 481	95.89 480	97.53 480	99.58 286	96.11 498	99.00 292	97.54 519	98.43 380	98.52 461	96.98 539	86.85 515	99.67 472	87.62 541	98.51 496	96.81 527

thres400		96.40 476	95.89 480	97.92 467	99.58 286	96.11 498	99.00 292	97.54 519	98.43 380	98.52 461	96.98 539	86.85 515	99.67 472	87.62 541	98.51 496	97.98 513

SIFT-NN-UMatch		97.18 455	97.24 447	97.01 507	99.57 296	98.65 370	96.33 532	97.31 522	97.07 486	97.48 513	98.73 493	94.39 436	98.87 535	95.75 493	98.50 499	93.50 547

UWE-MVS-28		95.64 498	95.47 490	96.14 523	97.98 530	90.39 551	98.49 396	95.81 538	99.02 294	98.03 491	98.19 515	84.49 525	99.28 521	88.75 536	98.47 500	98.75 472

TestfortrainingZip				99.38 290	99.17 438	99.25 259	99.38 132	98.82 462	98.93 310	99.68 208	99.49 351	98.11 289	99.56 502		98.44 501	99.32 355

myMVS_eth3d28		96.23 483	95.74 485	97.70 479	98.86 484	95.59 510	98.66 365	98.14 501	98.96 301	97.67 510	97.06 538	76.78 543	98.92 534	97.10 416	98.41 502	98.58 481

MVS		95.72 497	94.63 505	98.99 378	98.56 509	97.98 433	99.30 167	98.86 459	72.71 549	97.30 517	99.08 455	98.34 259	99.74 433	89.21 534	98.33 503	99.26 368

BH-untuned		98.22 398	98.09 400	98.58 435	99.38 380	97.24 467	98.55 384	98.98 456	97.81 448	99.20 384	98.76 491	97.01 361	99.65 484	94.83 509	98.33 503	98.86 459

testing11		96.05 489	95.41 492	97.97 464	98.78 496	95.27 515	98.59 374	98.23 499	98.86 321	96.56 530	96.91 542	75.20 547	99.69 454	97.26 401	98.29 505	98.93 449

test_method		91.72 511	92.32 511	89.91 531	93.49 555	70.18 559	90.28 545	99.56 308	61.71 551	95.39 538	99.52 339	93.90 441	99.94 98	98.76 239	98.27 506	99.62 188

testing91		96.00 490	95.32 495	98.02 461	98.76 499	95.39 511	98.38 408	98.65 474	98.82 329	96.84 525	96.71 548	75.06 548	99.71 443	96.46 460	98.23 507	98.98 442

gg-mvs-nofinetune		95.87 493	95.17 499	97.97 464	98.19 523	96.95 474	99.69 45	89.23 555	99.89 56	96.24 534	99.94 19	81.19 528	99.51 510	93.99 523	98.20 508	97.44 522

HY-MVS	98.23 9	98.21 400	97.95 410	98.99 378	99.03 465	98.24 406	99.61 73	98.72 468	96.81 495	98.73 442	99.51 343	94.06 440	99.86 278	96.91 427	98.20 508	98.86 459

UnsupCasMVSNet_bld		98.55 361	98.27 384	99.40 283	99.56 310	99.37 231	97.97 456	99.68 230	97.49 464	99.08 401	99.35 399	95.41 420	99.82 360	97.70 356	98.19 510	99.01 439

tpm2		96.35 479	96.22 474	96.73 515	98.88 482	91.75 541	99.21 204	98.51 482	93.27 532	97.89 497	99.21 437	84.83 523	99.70 447	96.04 477	98.18 511	98.75 472

testing222		95.60 501	94.59 506	98.61 430	98.66 507	97.45 457	98.54 387	97.90 511	98.53 371	96.54 531	96.47 552	70.62 554	99.81 377	95.91 487	98.15 512	98.56 484

SIFT-NN		94.78 505	94.89 501	94.45 527	98.23 522	97.29 465	94.93 540	95.84 536	95.82 510	94.78 541	97.12 536	90.26 498	92.28 552	88.91 535	98.14 513	93.77 543

tmp_tt		95.75 496	95.42 491	96.76 512	89.90 556	94.42 523	98.86 327	97.87 512	78.01 547	99.30 361	99.69 216	97.70 319	95.89 547	99.29 134	98.14 513	99.95 15

baseline2		96.83 463	96.28 471	98.46 441	99.09 458	96.91 477	98.83 335	93.87 548	97.23 478	96.23 535	98.36 511	88.12 509	99.90 205	96.68 442	98.14 513	98.57 483

ETVMVS		96.14 486	95.22 497	98.89 403	98.80 492	98.01 427	98.66 365	98.35 495	98.71 347	97.18 521	96.31 555	74.23 550	99.75 426	96.64 447	98.13 516	98.90 454

CostFormer		96.71 467	96.79 466	96.46 519	98.90 477	90.71 549	99.41 122	98.68 470	94.69 527	98.14 487	99.34 403	86.32 520	99.80 387	97.60 373	98.07 517	98.88 457

testing99		95.86 494	95.19 498	97.87 469	98.76 499	95.03 518	98.62 368	98.44 487	98.68 350	96.67 528	96.66 549	74.31 549	99.69 454	96.51 454	98.03 518	98.90 454

AUN-MVS		97.82 423	97.38 440	99.14 358	99.27 418	98.53 388	98.72 357	99.02 451	98.10 418	97.18 521	99.03 464	89.26 505	99.85 297	97.94 325	97.91 519	99.03 433

DeepMVS_CX				97.98 463	99.69 231	96.95 474		99.26 416	75.51 548	95.74 537	98.28 513	96.47 382	99.62 489	91.23 532	97.89 520	97.38 523

hse-mvs2		98.52 365	98.30 381	99.16 353	99.29 413	98.60 377	98.77 348	99.02 451	99.68 136	99.32 351	99.04 460	92.50 465	99.85 297	99.24 139	97.87 521	99.03 433

PAPM		95.61 500	94.71 504	98.31 451	99.12 446	96.63 483	96.66 527	98.46 486	90.77 541	96.25 533	98.68 498	93.01 456	99.69 454	81.60 548	97.86 522	98.62 476

JIA-IIPM		98.06 411	97.92 416	98.50 438	98.59 508	97.02 473	98.80 343	98.51 482	99.88 61	97.89 497	99.87 56	91.89 473	99.90 205	98.16 308	97.68 523	98.59 479

ET-MVSNet_ETH3D		96.78 464	96.07 477	98.91 396	99.26 421	97.92 435	97.70 475	96.05 531	97.96 433	92.37 546	98.43 509	87.06 512	99.90 205	98.27 294	97.56 524	98.91 453

gbinet_0.2-2-1-0.02		97.52 442	97.07 453	98.88 405	97.35 543	97.35 463	97.17 503	99.25 419	97.86 445	98.41 468	96.54 550	90.74 491	99.85 297	98.80 231	97.51 525	99.43 319

SP-NN		96.37 478	96.23 473	96.77 511	96.83 544	96.95 474	96.47 529	97.07 525	96.75 497	93.41 545	97.75 523	94.13 439	95.69 548	96.25 469	97.43 526	97.68 519

XFeat-NN		93.89 507	93.91 509	93.83 528	95.49 548	92.69 535	90.85 544	97.98 506	94.69 527	95.08 540	96.98 539	88.36 508	94.23 551	88.42 539	97.34 527	94.57 533

dongtai		89.37 512	88.91 515	90.76 530	99.19 434	77.46 557	95.47 537	87.82 557	92.28 537	94.17 543	98.82 488	71.22 553	95.54 549	63.85 551	97.34 527	99.27 366

TR-MVS		97.44 445	97.15 450	98.32 449	98.53 510	97.46 455	98.47 398	97.91 510	96.85 493	98.21 477	98.51 507	96.42 384	99.51 510	92.16 528	97.29 529	97.98 513

BH-w/o		97.20 454	97.01 456	97.76 473	99.08 459	95.69 506	98.03 447	98.52 481	95.76 511	97.96 493	98.02 518	95.62 410	99.47 513	92.82 527	97.25 530	98.12 507

KD-MVS_2432*1600		95.89 491	95.41 492	97.31 497	94.96 549	93.89 526	97.09 507	99.22 427	97.23 478	98.88 424	99.04 460	79.23 536	99.54 503	96.24 471	96.81 531	98.50 489

miper_refine_blended		95.89 491	95.41 492	97.31 497	94.96 549	93.89 526	97.09 507	99.22 427	97.23 478	98.88 424	99.04 460	79.23 536	99.54 503	96.24 471	96.81 531	98.50 489

UnsupCasMVSNet_eth		98.83 328	98.57 342	99.59 198	99.68 240	99.45 203	98.99 300	99.67 235	99.48 197	99.55 279	99.36 394	94.92 426	99.86 278	98.95 211	96.57 533	99.45 297

wanda-best-256-512		97.53 440	97.14 451	98.72 422	97.71 535	96.86 479	97.00 512	99.34 395	97.73 450	98.18 478	96.82 544	91.92 469	99.84 314	99.02 194	96.53 534	99.45 297

FE-blended-shiyan7		97.53 440	97.14 451	98.72 422	97.71 535	96.86 479	97.00 512	99.34 395	97.73 450	98.18 478	96.82 544	91.92 469	99.84 314	99.02 194	96.53 534	99.45 297

blended_shiyan6		97.82 423	97.46 435	98.92 391	98.08 528	97.46 455	97.73 470	99.34 395	97.96 433	98.33 471	97.35 531	92.78 458	99.84 314	99.04 189	96.53 534	99.46 295

usedtu_blend_shiyan5		97.97 417	97.65 433	98.92 391	97.71 535	97.49 452	99.53 92	99.81 135	99.52 191	98.18 478	96.82 544	91.92 469	99.83 337	98.79 232	96.53 534	99.45 297

h-mvs33		98.61 351	98.34 376	99.44 263	99.60 270	98.67 363	99.27 182	99.44 363	99.68 136	99.32 351	99.49 351	92.50 465	100.00 1	99.24 139	96.51 538	99.65 158

GG-mvs-BLEND				97.36 493	97.59 538	96.87 478	99.70 38	88.49 556		94.64 542	97.26 535	80.66 530	99.12 526	91.50 531	96.50 539	96.08 532

blended_shiyan8		97.82 423	97.45 437	98.92 391	98.06 529	97.45 457	97.73 470	99.35 391	97.96 433	98.35 470	97.34 532	92.76 460	99.84 314	99.04 189	96.49 540	99.47 290

tpm		97.15 456	96.95 458	97.75 474	98.91 476	94.24 525	99.32 158	97.96 507	97.71 453	98.29 472	99.32 404	86.72 518	99.92 154	98.10 314	96.24 541	99.09 414

MonoMVSNet		98.23 396	98.32 378	97.99 462	98.97 473	96.62 484	99.49 107	98.42 488	99.62 165	99.40 332	99.79 121	95.51 416	98.58 540	97.68 367	95.98 542	98.76 471

test0.0.03 1		97.37 449	96.91 461	98.74 420	97.72 534	97.57 449	97.60 482	97.36 521	98.00 426	99.21 379	98.02 518	90.04 501	99.79 391	98.37 285	95.89 543	98.86 459

kuosan		85.65 514	84.57 517	88.90 532	97.91 532	77.11 558	96.37 531	87.62 558	85.24 546	85.45 551	96.83 543	69.94 555	90.98 553	45.90 553	95.83 544	98.62 476

IB-MVS	95.41 20	95.30 502	94.46 508	97.84 471	98.76 499	95.33 513	97.33 496	96.07 530	96.02 506	95.37 539	97.41 530	76.17 545	99.96 69	97.54 377	95.44 545	98.22 501
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
baseline1		97.73 429	97.33 442	98.96 382	99.30 411	97.73 444	99.40 127	98.42 488	99.33 237	99.46 311	99.21 437	91.18 481	99.82 360	98.35 287	91.26 546	99.32 355

0.4-1-1-0.1		93.18 508	91.66 512	97.73 477	95.83 547	95.29 514	95.30 538	95.90 534	93.59 530	90.58 548	94.40 556	77.87 540	99.77 408	97.31 393	84.20 547	98.15 506

0.4-1-1-0.2		92.59 509	91.07 513	97.15 503	94.73 553	93.68 530	93.50 543	95.91 532	92.68 534	90.48 549	93.52 558	77.77 541	99.75 426	97.19 411	83.88 548	98.01 512

0.3-1-1-0.015		92.36 510	90.68 514	97.39 490	94.94 551	94.41 524	94.21 542	95.89 535	92.87 533	88.87 550	93.49 559	75.30 546	99.76 415	97.19 411	83.41 549	98.02 511

VLMVS_CLIP		76.68 515	76.70 518	76.61 533	60.81 557	61.63 560	78.48 547	91.77 550	64.66 550	83.93 552	93.59 557	55.35 556	75.94 554	79.82 549	81.86 550	92.28 548

PVSNet_0	95.53 19	95.85 495	95.31 496	97.47 485	98.78 496	93.48 532	95.72 535	99.40 377	96.18 505	97.37 515	97.73 524	95.73 408	99.58 497	95.49 498	81.40 551	99.36 341

blend_shiyan4		95.04 504	93.76 510	98.88 405	97.92 531	97.49 452	97.72 472	99.34 395	97.93 437	97.65 511	97.11 537	77.69 542	99.83 337	98.79 232	79.72 552	99.33 351

VLMVS		62.60 516	63.55 519	59.72 534	60.35 558	58.44 561	68.37 548	54.75 560	23.35 553	80.04 553	90.18 560	54.59 557	52.33 555	63.04 552	77.30 553	68.41 550

testmvs		28.94 518	33.33 520	15.79 536	26.03 559	9.81 563	96.77 521	15.67 561	11.55 555	23.87 556	50.74 564	19.03 559	8.53 557	23.21 555	33.07 554	29.03 552

test123		29.31 517	33.05 522	18.08 535	25.93 560	12.24 562	97.53 486	10.93 562	11.78 554	24.21 555	50.08 565	21.04 558	8.60 556	23.51 554	32.43 555	33.39 551

mmdepth		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

monomultidepth		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

test_blank		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

uanet_test		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

DCPMVS		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

cdsmvs_eth3d_5k		24.88 519	33.17 521	0.00 537	0.00 561	0.00 564	0.00 549	99.62 265	0.00 556	0.00 557	99.13 445	99.82 18	0.00 558	0.00 556	0.00 556	0.00 553

pcd_1.5k_mvsjas		16.61 520	22.14 523	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	99.28 93	0.00 558	0.00 556	0.00 556	0.00 553

sosnet-low-res		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

sosnet		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

uncertanet		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

Regformer		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

ab-mvs-re		8.26 531	11.02 534	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	99.16 442	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

uanet		8.33 521	11.11 524	0.00 537	0.00 561	0.00 564	0.00 549	0.00 563	0.00 556	0.00 557	100.00 1	0.00 560	0.00 558	0.00 556	0.00 556	0.00 553

PatchmatchNet2					0.00 561	95.19 517	97.64 478	99.19 434	98.09 420
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.93 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						96.36 490								95.20 504

FOURS1					99.83 90	99.89 10	99.74 27	99.71 207	99.69 133	99.63 238

test_one_0601					99.63 261	99.76 70		99.55 315	99.23 255	99.31 356	99.61 286	98.59 213

eth-test2					0.00 561

eth-test					0.00 561

test_241102_ONE					99.69 231	99.82 41		99.54 321	99.12 282	99.82 112	99.49 351	98.91 167	99.52 509

save fliter					99.53 325	99.25 259	98.29 416	99.38 385	99.07 287

test0726					99.69 231	99.80 51	99.24 194	99.57 303	99.16 272	99.73 182	99.65 248	98.35 257

GSMVS																99.14 401

test_part2					99.62 265	99.67 120				99.55 279

sam_mvs1												90.81 490				99.14 401

sam_mvs												90.52 496

MTGPA								99.53 332

test_post1							99.14 233				51.63 563	89.54 504	99.82 360	96.86 430

test_post											52.41 562	90.25 499	99.86 278

patchmatchnet-post											99.62 276	90.58 494	99.94 98

MTMP							99.09 259	98.59 479

gm-plane-assit					97.59 538	89.02 555			93.47 531		98.30 512		99.84 314	96.38 464

TEST9					99.35 390	99.35 238	98.11 437	99.41 370	94.83 526	97.92 494	98.99 467	98.02 295	99.85 297

test_8					99.34 399	99.31 245	98.08 441	99.40 377	94.90 523	97.87 499	98.97 472	98.02 295	99.84 314

agg_prior					99.35 390	99.36 235		99.39 380		97.76 506			99.85 297

test_prior4						99.19 280	98.00 451

test_prior				99.46 256	99.35 390	99.22 270		99.39 380					99.69 454			99.48 286

旧先验2							97.94 458		95.33 517	98.94 416			99.88 242	96.75 438

新几何2							98.04 445

无先验							98.01 448	99.23 424	95.83 509				99.85 297	95.79 492		99.44 312

原ACMM2							97.92 460

testdata2													99.89 227	95.99 481

segment_acmp												98.37 255

testdata1							97.72 472		97.86 445

plane_prior7					99.58 286	99.38 226

plane_prior6					99.47 356	99.26 256						97.24 347

plane_prior4											99.25 424

plane_prior3						99.31 245			98.36 390	99.14 392

plane_prior2							98.80 343		98.94 305

plane_prior1					99.51 334

n2								0.00 563

nn								0.00 563

door-mid								99.83 115

test11								99.29 410

door								99.77 170

HQP5-MVS						98.94 326

HQP-NCC					99.31 407		97.98 453		97.45 465	98.15 483

ACMP_Plane					99.31 407		97.98 453		97.45 465	98.15 483

BP-MVS														94.73 510

HQP4-MVS										98.15 483			99.70 447			99.53 257

HQP2-MVS												96.67 373

NP-MVS					99.40 376	99.13 292					98.83 486

MDTV_nov1_ep13_2view						91.44 544	99.14 233		97.37 471	99.21 379		91.78 476		96.75 438		99.03 433

Test By Simon												98.41 249

High-resolution multi-view benchmark