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.

SD-MVS		99.41 59	99.52 14	99.05 239	99.74 100	99.68 64	99.46 243	99.52 133	99.11 47	99.88 42	99.91 26	99.43 1	97.70 475	98.72 188	99.93 32	99.77 100
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
TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 102	99.39 286	98.91 83	99.78 81	99.85 88	99.36 2	99.94 91	98.84 170	99.88 74	99.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PC_three_1452									98.18 175	99.84 55	99.70 218	99.31 3	98.52 458	98.30 249	99.80 125	99.81 79

MED-MVS		99.70 3	99.64 4	99.90 8	99.88 13	99.81 33	99.69 63	99.87 6	99.48 3	99.90 34	99.89 45	99.30 4	99.95 76	98.83 173	99.89 67	99.93 22

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 22	99.82 53	99.81 33	99.59 126	99.51 156	98.62 113	99.79 76	99.83 109	99.28 5	99.97 29	98.48 224	99.90 56	99.84 54
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		99.59 15	99.50 19	99.88 16	99.51 230	99.88 10	99.87 8	99.51 156	98.99 69	99.88 42	99.81 135	99.27 6	99.96 41	98.85 167	99.80 125	99.81 79

OPU-MVS				99.64 102	99.56 209	99.72 56	99.60 115				99.70 218	99.27 6	99.42 347	98.24 253	99.80 125	99.79 92

SED-MVS		99.61 10	99.52 14	99.88 16	99.84 38	99.90 2	99.60 115	99.48 205	99.08 56	99.91 31	99.81 135	99.20 8	99.96 41	98.91 154	99.85 93	99.79 92

test_241102_ONE					99.84 38	99.90 2		99.48 205	99.07 58	99.91 31	99.74 201	99.20 8	99.76 261

MSLP-MVS++		99.46 42	99.47 24	99.44 176	99.60 195	99.16 156	99.41 271	99.71 16	98.98 72	99.45 190	99.78 177	99.19 10	99.54 328	99.28 97	99.84 101	99.63 189

SMA-MVS		99.44 50	99.30 61	99.85 43	99.73 107	99.83 22	99.56 152	99.47 227	97.45 292	99.78 81	99.82 120	99.18 11	99.91 135	98.79 181	99.89 67	99.81 79
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
APDe-MVS		99.66 7	99.57 10	99.92 1	99.77 78	99.89 6	99.75 43	99.56 89	99.02 62	99.88 42	99.85 88	99.18 11	99.96 41	99.22 105	99.92 38	99.90 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS_fast		99.51 29	99.40 37	99.85 43	99.91 1	99.79 41	99.76 38	99.56 89	97.72 258	99.76 91	99.75 195	99.13 13	99.92 123	99.07 130	99.92 38	99.85 47

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 47	99.58 136	99.65 39	97.84 242	99.71 112	99.80 153	99.12 14	99.97 29	98.33 245	99.87 78	99.83 64

test_one_0601					99.81 57	99.88 10		99.49 193	98.97 76	99.65 140	99.81 135	99.09 15

test_0728_THIRD									98.99 69	99.81 69	99.80 153	99.09 15	99.96 41	98.85 167	99.90 56	99.88 36

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 38	99.66 83	99.67 27	98.15 177	99.68 119	99.69 229	99.06 17	99.96 41	98.69 193	99.87 78	99.84 54

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 190	99.67 137	98.61 254	99.07 385	99.33 325	99.00 67	99.82 68	99.81 135	99.06 17	99.84 199	99.09 128	99.42 181	99.65 177

pcd_1.5k_mvsjas		8.27 470	11.03 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	99.01 19	0.00 505	0.00 503	0.00 503	0.00 501

PS-MVSNAJss		98.92 176	98.92 155	98.90 264	98.78 409	98.53 260	99.78 33	99.54 108	98.07 203	99.00 306	99.76 190	99.01 19	99.37 354	99.13 120	97.23 356	98.81 329

PS-MVSNAJ		99.32 78	99.32 53	99.30 206	99.57 205	98.94 199	98.97 413	99.46 240	98.92 82	99.71 112	99.24 384	99.01 19	99.98 20	99.35 76	99.66 159	98.97 320

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 102	99.78 70	99.15 161	99.61 113	99.45 251	99.01 64	99.89 39	99.82 120	99.01 19	99.92 123	99.56 49	99.95 22	99.85 47

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 152	99.55 99	99.15 38	99.90 34	99.90 36	99.00 23	99.97 29	99.11 123	99.91 45	99.86 43

patch_mono-2		99.26 91	99.62 7	98.16 366	99.81 57	94.59 449	99.52 183	99.64 42	99.33 29	99.73 97	99.90 36	99.00 23	99.99 4	99.69 34	99.98 4	99.89 30

EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 102	99.78 70	99.14 162	99.60 115	99.45 251	99.01 64	99.90 34	99.83 109	98.98 25	99.93 108	99.59 45	99.95 22	99.86 43

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 183	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 133	99.90 56	99.85 47

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 183	99.54 108	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 133	99.90 56	99.85 47

region2R		99.48 37	99.35 47	99.87 22	99.88 13	99.80 38	99.65 89	99.66 32	98.13 184	99.66 130	99.68 237	98.96 26	99.96 41	98.62 202	99.87 78	99.84 54

segment_acmp												98.96 26

CNVR-MVS		99.42 55	99.30 61	99.78 71	99.62 178	99.71 58	99.26 340	99.52 133	98.82 90	99.39 213	99.71 214	98.96 26	99.85 190	98.59 210	99.80 125	99.77 100

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 68	99.68 64	99.57 144	99.54 108	97.82 248	99.71 112	99.80 153	98.95 31	99.93 108	98.19 256	99.84 101	99.74 118

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 41	99.66 83	99.67 27	98.15 177	99.67 125	99.69 229	98.95 31	99.96 41	98.69 193	99.87 78	99.84 54

test_241102_TWO								99.48 205	99.08 56	99.88 42	99.81 135	98.94 33	99.96 41	98.91 154	99.84 101	99.88 36

DVP-MVS		99.57 20	99.47 24	99.88 16	99.85 31	99.89 6	99.57 144	99.37 303	99.10 48	99.81 69	99.80 153	98.94 33	99.96 41	98.93 151	99.86 86	99.81 79
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
test0726					99.85 31	99.89 6	99.62 107	99.50 180	99.10 48	99.86 52	99.82 120	98.94 33

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 209	99.53 221	98.91 206	99.02 399	99.45 251	98.80 95	99.71 112	99.26 382	98.94 33	99.98 20	99.34 81	99.23 200	98.98 318

CP-MVS		99.45 46	99.32 53	99.85 43	99.83 47	99.75 51	99.69 63	99.52 133	98.07 203	99.53 177	99.63 262	98.93 37	99.97 29	98.74 185	99.91 45	99.83 64

ZNCC-MVS		99.47 40	99.33 51	99.87 22	99.87 20	99.81 33	99.64 96	99.67 27	98.08 202	99.55 174	99.64 256	98.91 38	99.96 41	98.72 188	99.90 56	99.82 72

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 68	99.74 54	99.29 320	99.40 283	98.79 96	99.52 179	99.62 267	98.91 38	99.90 148	98.64 199	99.75 142	99.82 72

HPM-MVS		99.42 55	99.28 68	99.83 56	99.90 4	99.72 56	99.81 20	99.54 108	97.59 273	99.68 119	99.63 262	98.91 38	99.94 91	98.58 211	99.91 45	99.84 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				99.54 126	99.75 92	98.95 195		99.51 156	97.07 330	99.43 198	99.70 218	98.87 41	99.94 91	97.76 302	99.64 162	99.72 138

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 82	99.83 22	99.63 102	99.54 108	98.36 142	99.79 76	99.82 120	98.86 42	99.95 76	98.62 202	99.81 120	99.78 98

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 189	99.09 167	98.94 419	99.48 205	99.10 48	99.96 27	99.91 26	98.85 43	99.96 41	99.72 32	99.58 169	99.82 72

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 169	99.59 89	99.36 296	99.46 240	99.07 58	99.79 76	99.82 120	98.85 43	99.92 123	98.68 195	99.87 78	99.82 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TestfortrainingZip				99.69 89	99.58 199	99.62 83	99.69 63	99.38 294	98.98 72	99.84 55	99.75 195	98.84 45	99.78 254		99.21 201	99.66 170

9.14			99.10 98		99.72 111		99.40 279	99.51 156	97.53 283	99.64 145	99.78 177	98.84 45	99.91 135	97.63 315	99.82 117

CDPH-MVS		99.13 126	98.91 158	99.80 64	99.75 92	99.71 58	99.15 368	99.41 276	96.60 370	99.60 160	99.55 291	98.83 47	99.90 148	97.48 333	99.83 113	99.78 98

ACMMP_NAP		99.47 40	99.34 49	99.88 16	99.87 20	99.86 18	99.47 239	99.48 205	98.05 210	99.76 91	99.86 81	98.82 48	99.93 108	98.82 180	99.91 45	99.84 54

test_fmvsmvis_n_1920		99.65 8	99.61 8	99.77 74	99.38 280	99.37 124	99.58 136	99.62 51	99.41 23	99.87 48	99.92 18	98.81 49	100.00 1	99.97 2	99.93 32	99.94 17

XVS		99.53 27	99.42 32	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 217	99.74 201	98.81 49	99.94 91	98.79 181	99.86 86	99.84 54

X-MVStestdata		96.55 391	95.45 410	99.87 22	99.85 31	99.83 22	99.69 63	99.68 24	98.98 72	99.37 217	64.01 502	98.81 49	99.94 91	98.79 181	99.86 86	99.84 54

MP-MVS-pluss		99.37 68	99.20 85	99.88 16	99.90 4	99.87 17	99.30 315	99.52 133	97.18 318	99.60 160	99.79 170	98.79 52	99.95 76	98.83 173	99.91 45	99.83 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TestfortrainingZip a		99.70 3	99.63 6	99.92 1	99.88 13	99.90 2	99.69 63	99.79 11	99.48 3	99.93 29	99.89 45	98.78 53	99.93 108	99.32 84	99.88 74	99.93 22

mPP-MVS		99.44 50	99.30 61	99.86 34	99.88 13	99.79 41	99.69 63	99.48 205	98.12 192	99.50 182	99.75 195	98.78 53	99.97 29	98.57 214	99.89 67	99.83 64

APD-MVS		99.27 88	99.08 104	99.84 55	99.75 92	99.79 41	99.50 204	99.50 180	97.16 320	99.77 85	99.82 120	98.78 53	99.94 91	97.56 324	99.86 86	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAPA-MVS	97.07 15	97.74 328	97.34 350	98.94 254	99.70 122	97.53 323	99.25 342	99.51 156	91.90 468	99.30 237	99.63 262	98.78 53	99.64 311	88.09 478	99.87 78	99.65 177
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TEST9					99.67 137	99.65 75	99.05 391	99.41 276	96.22 396	98.95 315	99.49 314	98.77 57	99.91 135

train_agg		99.02 161	98.77 184	99.77 74	99.67 137	99.65 75	99.05 391	99.41 276	96.28 390	98.95 315	99.49 314	98.76 58	99.91 135	97.63 315	99.72 148	99.75 113

test_8					99.67 137	99.61 86	99.03 396	99.41 276	96.28 390	98.93 318	99.48 320	98.76 58	99.91 135

API-MVS		99.04 158	99.03 116	99.06 237	99.40 274	99.31 136	99.55 167	99.56 89	98.54 121	99.33 231	99.39 346	98.76 58	99.78 254	96.98 372	99.78 134	98.07 453

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 43	99.86 25	99.61 86	99.56 152	99.63 46	99.48 3	99.98 13	99.83 109	98.75 61	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 43	99.84 38	99.63 82	99.56 152	99.63 46	99.47 6	99.98 13	99.82 120	98.75 61	99.99 4	99.97 2	99.97 9	99.94 17

RE-MVS-def			99.34 49		99.76 82	99.82 28	99.63 102	99.52 133	98.38 138	99.76 91	99.82 120	98.75 61		98.61 205	99.81 120	99.77 100

DP-MVS Recon		99.12 134	98.95 150	99.65 96	99.74 100	99.70 60	99.27 331	99.57 84	96.40 386	99.42 201	99.68 237	98.75 61	99.80 242	97.98 279	99.72 148	99.44 260

Test By Simon												98.75 61

ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 290	99.70 18	99.18 35	99.83 64	99.83 109	98.74 66	99.93 108	98.83 173	99.89 67	99.83 64

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 68	99.62 107	99.69 22	98.12 192	99.63 148	99.84 103	98.73 67	99.96 41	98.55 220	99.83 113	99.81 79
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
DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 70	99.88 10	99.36 296	99.51 156	98.73 103	99.88 42	99.84 103	98.72 68	99.96 41	98.16 260	99.87 78	99.88 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		99.34 75	99.19 87	99.79 68	99.61 189	99.65 75	99.30 315	99.48 205	98.86 85	99.21 262	99.63 262	98.72 68	99.90 148	98.25 252	99.63 164	99.80 88

DeepPCF-MVS	98.18 3	98.81 198	99.37 43	97.12 433	99.60 195	91.75 475	98.61 453	99.44 260	99.35 27	99.83 64	99.85 88	98.70 70	99.81 235	99.02 137	99.91 45	99.81 79

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 92	99.83 22	99.59 126	99.62 51	98.21 169	99.73 97	99.79 170	98.68 71	99.96 41	98.44 231	99.77 137	99.79 92

test_prior2							98.96 414		98.34 144	99.01 302	99.52 304	98.68 71		97.96 280	99.74 145

DPM-MVS		98.95 174	98.71 192	99.66 92	99.63 169	99.55 97	98.64 452	99.10 385	97.93 229	99.42 201	99.55 291	98.67 73	99.80 242	95.80 411	99.68 156	99.61 194

原ACMM1				99.65 96	99.73 107	99.33 131		99.47 227	97.46 289	99.12 280	99.66 248	98.67 73	99.91 135	97.70 312	99.69 153	99.71 149

CS-MVS		99.50 31	99.48 22	99.54 126	99.76 82	99.42 119	99.90 1	99.55 99	98.56 119	99.78 81	99.70 218	98.65 75	99.79 248	99.65 41	99.78 134	99.41 265

HPM-MVS++		99.39 66	99.23 81	99.87 22	99.75 92	99.84 20	99.43 260	99.51 156	98.68 110	99.27 247	99.53 300	98.64 76	99.96 41	98.44 231	99.80 125	99.79 92

test_fmvsmconf_n		99.70 3	99.64 4	99.87 22	99.80 63	99.66 71	99.48 229	99.64 42	99.45 13	99.92 30	99.92 18	98.62 77	99.99 4	99.96 13	99.99 1	99.96 7

test_fmvsm_n_1920		99.69 6	99.66 3	99.78 71	99.84 38	99.44 117	99.58 136	99.69 22	99.43 19	99.98 13	99.91 26	98.62 77	100.00 1	99.97 2	99.95 22	99.90 27

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 349	99.56 168	99.54 296	98.58 79	99.96 41	96.93 377	99.75 142

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 209	99.52 106	99.58 136	99.80 10	97.12 324	99.62 152	99.73 207	98.58 79	99.90 148	98.61 205	99.91 45	99.68 161

dcpmvs_2		99.23 97	99.58 9	98.16 366	99.83 47	94.68 446	99.76 38	99.52 133	99.07 58	99.98 13	99.88 58	98.56 81	99.93 108	99.67 37	99.98 4	99.87 41

SPE-MVS-test		99.49 33	99.48 22	99.54 126	99.78 70	99.30 139	99.89 2	99.58 77	98.56 119	99.73 97	99.69 229	98.55 82	99.82 230	99.69 34	99.85 93	99.48 244

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 82	99.82 28	99.63 102	99.52 133	98.38 138	99.76 91	99.82 120	98.53 83	99.95 76	98.61 205	99.81 120	99.77 100

GST-MVS		99.40 64	99.24 77	99.85 43	99.86 25	99.79 41	99.60 115	99.67 27	97.97 226	99.63 148	99.68 237	98.52 84	99.95 76	98.38 238	99.86 86	99.81 79

MVS_111021_LR		99.41 59	99.33 51	99.65 96	99.77 78	99.51 108	98.94 419	99.85 8	98.82 90	99.65 140	99.74 201	98.51 85	99.80 242	98.83 173	99.89 67	99.64 184

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 111	99.47 114	98.95 417	99.85 8	98.82 90	99.54 175	99.73 207	98.51 85	99.74 267	98.91 154	99.88 74	99.77 100

旧先验1					99.74 100	99.59 89		99.54 108			99.69 229	98.47 87			99.68 156	99.73 128

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 111	99.40 122	99.05 391	99.66 32	99.14 40	99.57 167	99.80 153	98.46 88	99.94 91	99.57 48	99.84 101	99.60 197
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
PAPR		98.63 220	98.34 231	99.51 146	99.40 274	99.03 176	98.80 436	99.36 305	96.33 387	99.00 306	99.12 399	98.46 88	99.84 199	95.23 426	99.37 190	99.66 170

MTAPA		99.52 28	99.39 39	99.89 12	99.90 4	99.86 18	99.66 83	99.47 227	98.79 96	99.68 119	99.81 135	98.43 90	99.97 29	98.88 157	99.90 56	99.83 64

新几何1				99.75 77	99.75 92	99.59 89		99.54 108	96.76 354	99.29 240	99.64 256	98.43 90	99.94 91	96.92 379	99.66 159	99.72 138

F-COLMAP		99.19 100	99.04 113	99.64 102	99.78 70	99.27 144	99.42 267	99.54 108	97.29 309	99.41 206	99.59 276	98.42 92	99.93 108	98.19 256	99.69 153	99.73 128

lecture		99.60 14	99.50 19	99.89 12	99.89 8	99.90 2	99.75 43	99.59 72	99.06 61	99.88 42	99.85 88	98.41 93	99.96 41	99.28 97	99.84 101	99.83 64

ETV-MVS		99.26 91	99.21 83	99.40 183	99.46 254	99.30 139	99.56 152	99.52 133	98.52 123	99.44 195	99.27 380	98.41 93	99.86 182	99.10 126	99.59 168	99.04 310

test12				99.75 77	99.64 165	99.61 86		99.29 348		99.21 262		98.38 95	99.89 163		99.74 145	99.74 118

CSCG		99.32 78	99.32 53	99.32 199	99.85 31	98.29 280	99.71 58	99.66 32	98.11 194	99.41 206	99.80 153	98.37 96	99.96 41	98.99 139	99.96 17	99.72 138

PAPM_NR		99.04 158	98.84 176	99.66 92	99.74 100	99.44 117	99.39 283	99.38 294	97.70 262	99.28 241	99.28 377	98.34 97	99.85 190	96.96 374	99.45 179	99.69 155

TAMVS		99.12 134	99.08 104	99.24 219	99.46 254	98.55 258	99.51 193	99.46 240	98.09 198	99.45 190	99.82 120	98.34 97	99.51 330	98.70 190	98.93 244	99.67 165

MP-MVS		99.33 77	99.15 92	99.87 22	99.88 13	99.82 28	99.66 83	99.46 240	98.09 198	99.48 186	99.74 201	98.29 99	99.96 41	97.93 282	99.87 78	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test222					99.75 92	99.49 110	98.91 423	99.49 193	96.42 384	99.34 230	99.65 250	98.28 100			99.69 153	99.72 138

PLC	97.94 4	99.02 161	98.85 174	99.53 134	99.66 149	99.01 179	99.24 347	99.52 133	96.85 348	99.27 247	99.48 320	98.25 101	99.91 135	97.76 302	99.62 165	99.65 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSP-MVS		99.42 55	99.27 72	99.88 16	99.89 8	99.80 38	99.67 76	99.50 180	98.70 107	99.77 85	99.49 314	98.21 102	99.95 76	98.46 229	99.77 137	99.88 36
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
EC-MVSNet		99.44 50	99.39 39	99.58 117	99.56 209	99.49 110	99.88 4	99.58 77	98.38 138	99.73 97	99.69 229	98.20 103	99.70 290	99.64 43	99.82 117	99.54 221

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 193	99.63 169	98.97 185	99.12 375	99.51 156	98.86 85	99.84 55	99.47 323	98.18 104	99.99 4	99.50 57	99.31 191	99.08 302

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 193	99.63 169	98.97 185	99.12 375	99.51 156	98.86 85	99.84 55	99.47 323	98.18 104	99.99 4	99.50 57	99.31 191	99.08 302

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 193	99.63 169	98.97 185	99.12 375	99.51 156	98.86 85	99.84 55	99.47 323	98.18 104	99.99 4	99.50 57	99.31 191	99.08 302

EIA-MVS		99.18 103	99.09 103	99.45 171	99.49 244	99.18 153	99.67 76	99.53 124	97.66 267	99.40 211	99.44 330	98.10 107	99.81 235	98.94 148	99.62 165	99.35 275

MVSMamba_PlusPlus		99.46 42	99.41 36	99.64 102	99.68 134	99.50 109	99.75 43	99.50 180	98.27 153	99.87 48	99.92 18	98.09 108	99.94 91	99.65 41	99.95 22	99.47 250

CNLPA		99.14 122	98.99 137	99.59 114	99.58 199	99.41 121	99.16 365	99.44 260	98.45 131	99.19 269	99.49 314	98.08 109	99.89 163	97.73 306	99.75 142	99.48 244

114514_t		98.93 175	98.67 196	99.72 86	99.85 31	99.53 102	99.62 107	99.59 72	92.65 460	99.71 112	99.78 177	98.06 110	99.90 148	98.84 170	99.91 45	99.74 118

BridgeMVS		99.46 42	99.39 39	99.67 91	99.55 213	99.58 94	99.74 48	99.51 156	98.42 135	99.87 48	99.84 103	98.05 111	99.91 135	99.58 47	99.94 30	99.52 227

CDS-MVSNet		99.09 146	99.03 116	99.25 216	99.42 264	98.73 240	99.45 247	99.46 240	98.11 194	99.46 189	99.77 186	98.01 112	99.37 354	98.70 190	98.92 246	99.66 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MG-MVS		99.13 126	99.02 126	99.45 171	99.57 205	98.63 250	99.07 385	99.34 317	98.99 69	99.61 157	99.82 120	97.98 113	99.87 175	97.00 370	99.80 125	99.85 47

EI-MVSNet		98.67 215	98.67 196	98.68 305	99.35 287	97.97 299	99.50 204	99.38 294	96.93 345	99.20 266	99.83 109	97.87 114	99.36 358	98.38 238	97.56 332	98.71 348

IterMVS-LS		98.46 227	98.42 226	98.58 314	99.59 197	98.00 297	99.37 290	99.43 271	96.94 344	99.07 291	99.59 276	97.87 114	99.03 421	98.32 247	95.62 397	98.71 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		98.98 170	98.80 179	99.53 134	99.76 82	99.19 151	98.75 441	99.55 99	97.25 312	99.47 187	99.77 186	97.82 116	99.87 175	96.93 377	99.90 56	99.54 221

OMC-MVS		99.08 148	99.04 113	99.20 223	99.67 137	98.22 284	99.28 326	99.52 133	98.07 203	99.66 130	99.81 135	97.79 117	99.78 254	97.79 297	99.81 120	99.60 197

LS3D		99.27 88	99.12 96	99.74 80	99.18 335	99.75 51	99.56 152	99.57 84	98.45 131	99.49 185	99.85 88	97.77 118	99.94 91	98.33 245	99.84 101	99.52 227

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 172	99.47 239	99.93 2	97.66 267	99.71 112	99.86 81	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

1314		98.68 214	98.54 219	99.11 234	98.89 392	98.65 247	99.27 331	99.49 193	96.89 346	97.99 415	99.56 288	97.72 120	99.83 221	97.74 305	99.27 194	98.84 328

MVS_Test		99.10 145	98.97 142	99.48 162	99.49 244	99.14 162	99.67 76	99.34 317	97.31 307	99.58 164	99.76 190	97.65 121	99.82 230	98.87 160	99.07 233	99.46 255

PVSNet_BlendedMVS		98.86 185	98.80 179	99.03 241	99.76 82	98.79 235	99.28 326	99.91 3	97.42 298	99.67 125	99.37 352	97.53 122	99.88 168	98.98 140	97.29 354	98.42 431

PVSNet_Blended		99.08 148	98.97 142	99.42 181	99.76 82	98.79 235	98.78 438	99.91 3	96.74 355	99.67 125	99.49 314	97.53 122	99.88 168	98.98 140	99.85 93	99.60 197

UA-Net		99.42 55	99.29 65	99.80 64	99.62 178	99.55 97	99.50 204	99.70 18	98.79 96	99.77 85	99.96 1	97.45 124	99.96 41	98.92 153	99.90 56	99.89 30

MVSFormer		99.17 108	99.12 96	99.29 209	99.51 230	98.94 199	99.88 4	99.46 240	97.55 279	99.80 74	99.65 250	97.39 125	99.28 371	99.03 135	99.85 93	99.65 177

lupinMVS		99.13 126	99.01 133	99.46 170	99.51 230	98.94 199	99.05 391	99.16 378	97.86 236	99.80 74	99.56 288	97.39 125	99.86 182	98.94 148	99.85 93	99.58 212

DP-MVS		99.16 110	98.95 150	99.78 71	99.77 78	99.53 102	99.41 271	99.50 180	97.03 336	99.04 299	99.88 58	97.39 125	99.92 123	98.66 197	99.90 56	99.87 41

sss		99.17 108	99.05 111	99.53 134	99.62 178	98.97 185	99.36 296	99.62 51	97.83 243	99.67 125	99.65 250	97.37 128	99.95 76	99.19 109	99.19 204	99.68 161

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 183	99.65 39	99.10 48	99.98 13	99.92 18	97.35 129	99.96 41	99.94 21	99.92 38	99.95 11

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 261	99.65 75	99.50 204	99.61 60	99.45 13	99.87 48	99.92 18	97.31 130	99.97 29	99.95 16	99.99 1	99.97 4

mvs_anonymous		99.03 160	98.99 137	99.16 227	99.38 280	98.52 264	99.51 193	99.38 294	97.79 249	99.38 215	99.81 135	97.30 131	99.45 336	99.35 76	98.99 241	99.51 236

miper_ehance_all_eth		98.18 253	98.10 249	98.41 342	99.23 322	97.72 315	98.72 444	99.31 339	96.60 370	98.88 325	99.29 375	97.29 132	99.13 403	97.60 317	95.99 385	98.38 436

E3new		99.18 103	99.08 104	99.48 162	99.63 169	98.94 199	99.46 243	99.50 180	98.06 207	99.72 102	99.84 103	97.27 133	99.84 199	99.10 126	99.13 212	99.67 165

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 172	99.66 32	99.46 9	99.98 13	99.89 45	97.27 133	99.99 4	99.97 2	99.95 22	99.95 11

CPTT-MVS		99.11 140	98.90 160	99.74 80	99.80 63	99.46 115	99.59 126	99.49 193	97.03 336	99.63 148	99.69 229	97.27 133	99.96 41	97.82 293	99.84 101	99.81 79

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 230	99.67 68	99.50 204	99.64 42	99.43 19	99.98 13	99.78 177	97.26 136	99.95 76	99.95 16	99.93 32	99.92 25

PMMVS		98.80 201	98.62 209	99.34 193	99.27 311	98.70 243	98.76 440	99.31 339	97.34 304	99.21 262	99.07 401	97.20 137	99.82 230	98.56 217	98.87 253	99.52 227

EPP-MVSNet		99.13 126	98.99 137	99.53 134	99.65 160	99.06 173	99.81 20	99.33 325	97.43 296	99.60 160	99.88 58	97.14 138	99.84 199	99.13 120	98.94 243	99.69 155

viewcassd2359sk11		99.18 103	99.08 104	99.49 158	99.65 160	98.95 195	99.48 229	99.51 156	98.10 197	99.72 102	99.87 72	97.13 139	99.84 199	99.13 120	99.14 209	99.69 155

icg_test_0407_2		98.79 202	98.86 171	98.57 315	99.55 213	96.93 362	99.07 385	99.44 260	98.05 210	99.66 130	99.80 153	97.13 139	99.18 395	98.15 262	98.92 246	99.60 197

IMVS_0407		98.86 185	98.91 158	98.72 299	99.55 213	96.93 362	99.50 204	99.44 260	98.05 210	99.66 130	99.80 153	97.13 139	99.65 307	98.15 262	98.92 246	99.60 197

c3_l		98.12 260	98.04 258	98.38 346	99.30 302	97.69 319	98.81 435	99.33 325	96.67 360	98.83 336	99.34 362	97.11 142	98.99 431	97.58 319	95.34 404	98.48 423

sasdasda		99.02 161	98.86 171	99.51 146	99.42 264	99.32 132	99.80 25	99.48 205	98.63 111	99.31 233	98.81 429	97.09 143	99.75 264	99.27 100	97.90 313	99.47 250

canonicalmvs		99.02 161	98.86 171	99.51 146	99.42 264	99.32 132	99.80 25	99.48 205	98.63 111	99.31 233	98.81 429	97.09 143	99.75 264	99.27 100	97.90 313	99.47 250

MAR-MVS		98.86 185	98.63 204	99.54 126	99.37 283	99.66 71	99.45 247	99.54 108	96.61 367	99.01 302	99.40 342	97.09 143	99.86 182	97.68 314	99.53 173	99.10 297
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
miper_enhance_ethall		98.16 255	98.08 253	98.41 342	98.96 384	97.72 315	98.45 467	99.32 335	96.95 342	98.97 311	99.17 391	97.06 146	99.22 387	97.86 288	95.99 385	98.29 440

MGCFI-Net		99.01 166	98.85 174	99.50 151	99.42 264	99.26 145	99.82 16	99.48 205	98.60 116	99.28 241	98.81 429	97.04 147	99.76 261	99.29 95	97.87 316	99.47 250

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 239	99.63 46	99.45 13	99.98 13	99.89 45	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

jason		99.13 126	99.03 116	99.45 171	99.46 254	98.87 220	99.12 375	99.26 359	98.03 219	99.79 76	99.65 250	97.02 148	99.85 190	99.02 137	99.90 56	99.65 177
jason: jason.
our_test_3		97.65 345	97.68 302	97.55 421	98.62 432	94.97 439	98.84 431	99.30 344	96.83 351	98.19 405	99.34 362	97.01 150	99.02 425	95.00 430	96.01 383	98.64 383

MVS		97.28 372	96.55 385	99.48 162	98.78 409	98.95 195	99.27 331	99.39 286	83.53 489	98.08 410	99.54 296	96.97 151	99.87 175	94.23 440	99.16 205	99.63 189

Fast-Effi-MVS+-dtu		98.77 207	98.83 178	98.60 310	99.41 269	96.99 357	99.52 183	99.49 193	98.11 194	99.24 254	99.34 362	96.96 152	99.79 248	97.95 281	99.45 179	99.02 313

viewmanbaseed2359cas		99.18 103	99.07 108	99.50 151	99.62 178	99.01 179	99.50 204	99.52 133	98.25 161	99.68 119	99.82 120	96.93 153	99.80 242	99.15 119	99.11 219	99.70 152

1112_ss		98.98 170	98.77 184	99.59 114	99.68 134	99.02 177	99.25 342	99.48 205	97.23 315	99.13 278	99.58 280	96.93 153	99.90 148	98.87 160	98.78 261	99.84 54

mamba_0408		99.08 148	98.96 146	99.44 176	99.62 178	98.88 216	99.25 342	99.47 227	98.05 210	99.37 217	99.81 135	96.85 155	99.85 190	98.98 140	99.25 197	99.60 197

SSM_04072		99.06 153	98.96 146	99.35 192	99.62 178	98.88 216	99.25 342	99.47 227	98.05 210	99.37 217	99.81 135	96.85 155	99.58 322	98.98 140	99.25 197	99.60 197

SSM_0407		99.13 126	99.03 116	99.43 179	99.62 178	98.88 216	99.51 193	99.50 180	98.14 181	99.37 217	99.85 88	96.85 155	99.83 221	99.19 109	99.25 197	99.60 197

SSM_0404		99.16 110	99.06 109	99.44 176	99.65 160	98.96 189	99.49 221	99.50 180	98.14 181	99.62 152	99.85 88	96.85 155	99.85 190	99.19 109	99.26 196	99.52 227

WTY-MVS		99.06 153	98.88 167	99.61 110	99.62 178	99.16 156	99.37 290	99.56 89	98.04 217	99.53 177	99.62 267	96.84 159	99.94 91	98.85 167	98.49 279	99.72 138

diffmvs_AUTHOR		99.19 100	99.10 98	99.48 162	99.64 165	98.85 224	99.32 309	99.48 205	98.50 125	99.81 69	99.81 135	96.82 160	99.88 168	99.40 71	99.12 217	99.71 149

IMVS_0403		98.86 185	98.89 164	98.78 294	99.55 213	96.93 362	99.58 136	99.44 260	98.05 210	99.68 119	99.80 153	96.81 161	99.80 242	98.15 262	98.92 246	99.60 197

FC-MVSNet-test		98.75 208	98.62 209	99.15 231	99.08 362	99.45 116	99.86 11	99.60 67	98.23 166	98.70 356	99.82 120	96.80 162	99.22 387	99.07 130	96.38 374	98.79 330

Effi-MVS+-dtu		98.78 203	98.89 164	98.47 333	99.33 293	96.91 367	99.57 144	99.30 344	98.47 128	99.41 206	98.99 414	96.78 163	99.74 267	98.73 187	99.38 183	98.74 344

Test_1112_low_res		98.89 178	98.66 199	99.57 121	99.69 127	98.95 195	99.03 396	99.47 227	96.98 338	99.15 276	99.23 385	96.77 164	99.89 163	98.83 173	98.78 261	99.86 43

FIs		98.78 203	98.63 204	99.23 221	99.18 335	99.54 99	99.83 15	99.59 72	98.28 151	98.79 343	99.81 135	96.75 165	99.37 354	99.08 129	96.38 374	98.78 332

PVSNet	96.02 17	98.85 194	98.84 176	98.89 268	99.73 107	97.28 332	98.32 474	99.60 67	97.86 236	99.50 182	99.57 285	96.75 165	99.86 182	98.56 217	99.70 152	99.54 221

MGCNet		99.15 114	98.96 146	99.73 83	98.92 388	99.37 124	99.37 290	96.92 483	99.51 2	99.66 130	99.78 177	96.69 167	99.97 29	99.84 28	99.97 9	99.84 54

nrg030		98.64 219	98.42 226	99.28 213	99.05 368	99.69 63	99.81 20	99.46 240	98.04 217	99.01 302	99.82 120	96.69 167	99.38 351	99.34 81	94.59 419	98.78 332

viewdifsd2359ckpt13		99.06 153	98.93 154	99.45 171	99.63 169	98.96 189	99.50 204	99.51 156	97.83 243	99.28 241	99.80 153	96.68 169	99.71 283	99.05 132	99.12 217	99.68 161

CHOSEN 280x420		99.12 134	99.13 94	99.08 235	99.66 149	97.89 307	98.43 468	99.71 16	98.88 84	99.62 152	99.76 190	96.63 170	99.70 290	99.46 67	99.99 1	99.66 170

E3		99.15 114	99.03 116	99.49 158	99.62 178	98.91 206	99.49 221	99.52 133	98.13 184	99.72 102	99.88 58	96.61 171	99.84 199	99.17 115	99.13 212	99.72 138

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 12	99.83 47	99.74 54	99.51 193	99.62 51	99.46 9	99.99 2	99.90 36	96.60 172	99.98 20	99.95 16	99.95 22	99.96 7

fmvsm_s_conf0.5_n		99.51 29	99.40 37	99.85 43	99.84 38	99.65 75	99.51 193	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

eth_miper_zixun_eth		98.05 273	97.96 266	98.33 349	99.26 314	97.38 329	98.56 460	99.31 339	96.65 362	98.88 325	99.52 304	96.58 174	99.12 408	97.39 343	95.53 401	98.47 425

cdsmvs_eth3d_5k		24.64 468	32.85 471	0.00 486	0.00 509	0.00 511	0.00 497	99.51 156	0.00 504	0.00 505	99.56 288	96.58 174	0.00 505	0.00 503	0.00 503	0.00 501

E2		99.15 114	99.03 116	99.49 158	99.65 160	98.93 204	99.49 221	99.52 133	98.14 181	99.72 102	99.88 58	96.57 176	99.84 199	99.17 115	99.13 212	99.72 138

mvsmamba		99.06 153	98.96 146	99.36 190	99.47 252	98.64 249	99.70 59	99.05 394	97.61 272	99.65 140	99.83 109	96.54 177	99.92 123	99.19 109	99.62 165	99.51 236

IS-MVSNet		99.05 157	98.87 168	99.57 121	99.73 107	99.32 132	99.75 43	99.20 373	98.02 222	99.56 168	99.86 81	96.54 177	99.67 299	98.09 267	99.13 212	99.73 128

diffmvs		99.14 122	99.02 126	99.51 146	99.61 189	98.96 189	99.28 326	99.49 193	98.46 129	99.72 102	99.71 214	96.50 179	99.88 168	99.31 86	99.11 219	99.67 165
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MM		99.40 64	99.28 68	99.74 80	99.67 137	99.31 136	99.52 183	98.87 422	99.55 1	99.74 95	99.80 153	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

CANet		99.25 95	99.14 93	99.59 114	99.41 269	99.16 156	99.35 301	99.57 84	98.82 90	99.51 181	99.61 271	96.46 181	99.95 76	99.59 45	99.98 4	99.65 177

ppachtmachnet_test		97.49 362	97.45 330	97.61 419	98.62 432	95.24 431	98.80 436	99.46 240	96.11 406	98.22 403	99.62 267	96.45 182	98.97 439	93.77 444	95.97 388	98.61 401

HY-MVS	97.30 7	98.85 194	98.64 203	99.47 168	99.42 264	99.08 170	99.62 107	99.36 305	97.39 301	99.28 241	99.68 237	96.44 183	99.92 123	98.37 240	98.22 297	99.40 268

UniMVSNet_NR-MVSNet		98.22 247	97.97 265	98.96 250	98.92 388	98.98 182	99.48 229	99.53 124	97.76 253	98.71 350	99.46 327	96.43 184	99.22 387	98.57 214	92.87 446	98.69 357

viewdifsd2359ckpt09		99.01 166	98.87 168	99.40 183	99.62 178	98.79 235	99.44 254	99.51 156	97.76 253	99.35 226	99.69 229	96.42 185	99.75 264	98.97 145	99.11 219	99.66 170

LuminaMVS		99.23 97	99.10 98	99.61 110	99.35 287	99.31 136	99.46 243	99.13 382	98.61 114	99.86 52	99.89 45	96.41 186	99.91 135	99.67 37	99.51 174	99.63 189

Effi-MVS+		98.81 198	98.59 215	99.48 162	99.46 254	99.12 165	98.08 481	99.50 180	97.50 287	99.38 215	99.41 338	96.37 187	99.81 235	99.11 123	98.54 276	99.51 236

E4		99.13 126	99.01 133	99.49 158	99.68 134	98.90 211	99.52 183	99.52 133	98.13 184	99.71 112	99.90 36	96.32 188	99.84 199	99.21 107	99.11 219	99.75 113

AdaColmap		99.01 166	98.80 179	99.66 92	99.56 209	99.54 99	99.18 363	99.70 18	98.18 175	99.35 226	99.63 262	96.32 188	99.90 148	97.48 333	99.77 137	99.55 219

E6new		99.15 114	99.03 116	99.50 151	99.66 149	98.90 211	99.60 115	99.53 124	98.13 184	99.72 102	99.91 26	96.31 190	99.84 199	99.30 89	99.10 226	99.76 107

E6		99.15 114	99.03 116	99.50 151	99.66 149	98.90 211	99.60 115	99.53 124	98.13 184	99.72 102	99.91 26	96.31 190	99.84 199	99.30 89	99.10 226	99.76 107

UniMVSNet (Re)		98.29 244	98.00 262	99.13 233	99.00 375	99.36 127	99.49 221	99.51 156	97.95 227	98.97 311	99.13 396	96.30 192	99.38 351	98.36 242	93.34 438	98.66 379

LCM-MVSNet-Re		97.83 311	98.15 243	96.87 442	99.30 302	92.25 473	99.59 126	98.26 461	97.43 296	96.20 454	99.13 396	96.27 193	98.73 454	98.17 259	98.99 241	99.64 184

PAPM		97.59 349	97.09 371	99.07 236	99.06 365	98.26 282	98.30 475	99.10 385	94.88 430	98.08 410	99.34 362	96.27 193	99.64 311	89.87 471	98.92 246	99.31 281

E5new		99.14 122	99.02 126	99.50 151	99.69 127	98.91 206	99.60 115	99.53 124	98.13 184	99.72 102	99.91 26	96.26 195	99.84 199	99.30 89	99.10 226	99.76 107

E5		99.14 122	99.02 126	99.50 151	99.69 127	98.91 206	99.60 115	99.53 124	98.13 184	99.72 102	99.91 26	96.26 195	99.84 199	99.30 89	99.10 226	99.76 107

Fast-Effi-MVS+		98.70 212	98.43 225	99.51 146	99.51 230	99.28 142	99.52 183	99.47 227	96.11 406	99.01 302	99.34 362	96.20 197	99.84 199	97.88 285	98.82 258	99.39 269

viewdifsd2359ckpt07		99.11 140	99.00 136	99.43 179	99.63 169	98.73 240	99.45 247	99.54 108	98.33 146	99.62 152	99.81 135	96.17 198	99.87 175	99.27 100	99.14 209	99.69 155

MonoMVSNet		98.38 236	98.47 224	98.12 371	98.59 437	96.19 398	99.72 54	98.79 433	97.89 233	99.44 195	99.52 304	96.13 199	98.90 447	98.64 199	97.54 334	99.28 283

EPNet_dtu		98.03 276	97.96 266	98.23 362	98.27 446	95.54 421	99.23 350	98.75 436	99.02 62	97.82 424	99.71 214	96.11 200	99.48 331	93.04 455	99.65 161	99.69 155
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline		99.15 114	99.02 126	99.53 134	99.66 149	99.14 162	99.72 54	99.48 205	98.35 143	99.42 201	99.84 103	96.07 201	99.79 248	99.51 56	99.14 209	99.67 165

SD_0403		97.55 351	97.53 318	97.62 416	99.61 189	93.64 464	99.72 54	99.44 260	98.03 219	98.62 371	99.39 346	96.06 202	99.57 323	87.88 480	99.01 240	99.66 170

D2MVS		98.41 232	98.50 222	98.15 369	99.26 314	96.62 381	99.40 279	99.61 60	97.71 259	98.98 309	99.36 355	96.04 203	99.67 299	98.70 190	97.41 349	98.15 449

casdiffmvs_mvg		99.15 114	99.02 126	99.55 125	99.66 149	99.09 167	99.64 96	99.56 89	98.26 156	99.45 190	99.87 72	96.03 204	99.81 235	99.54 51	99.15 208	99.73 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmambaseed2359dif		99.01 166	98.90 160	99.32 199	99.58 199	98.51 266	99.33 306	99.54 108	97.85 239	99.44 195	99.85 88	96.01 205	99.79 248	99.41 70	99.13 212	99.67 165

miper_lstm_enhance		98.00 283	97.91 272	98.28 358	99.34 292	97.43 327	98.88 425	99.36 305	96.48 379	98.80 341	99.55 291	95.98 206	98.91 445	97.27 352	95.50 402	98.51 421

EPNet		98.86 185	98.71 192	99.30 206	97.20 465	98.18 285	99.62 107	98.91 415	99.28 32	98.63 368	99.81 135	95.96 207	99.99 4	99.24 104	99.72 148	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
AllTest		98.87 182	98.72 190	99.31 201	99.86 25	98.48 271	99.56 152	99.61 60	97.85 239	99.36 223	99.85 88	95.95 208	99.85 190	96.66 390	99.83 113	99.59 208

TestCases				99.31 201	99.86 25	98.48 271		99.61 60	97.85 239	99.36 223	99.85 88	95.95 208	99.85 190	96.66 390	99.83 113	99.59 208

3Dnovator	97.25 9	99.24 96	99.05 111	99.81 60	99.12 351	99.66 71	99.84 12	99.74 13	99.09 55	98.92 319	99.90 36	95.94 210	99.98 20	98.95 147	99.92 38	99.79 92

casdiffmvs		99.13 126	98.98 140	99.56 123	99.65 160	99.16 156	99.56 152	99.50 180	98.33 146	99.41 206	99.86 81	95.92 211	99.83 221	99.45 68	99.16 205	99.70 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RPSCF		98.22 247	98.62 209	96.99 436	99.82 53	91.58 476	99.72 54	99.44 260	96.61 367	99.66 130	99.89 45	95.92 211	99.82 230	97.46 336	99.10 226	99.57 215

pmmvs4		98.13 258	97.90 273	98.81 289	98.61 434	98.87 220	98.99 407	99.21 372	96.44 382	99.06 296	99.58 280	95.90 213	99.11 409	97.18 362	96.11 381	98.46 428

HyFIR lowres test		99.11 140	98.92 155	99.65 96	99.90 4	99.37 124	99.02 399	99.91 3	97.67 266	99.59 163	99.75 195	95.90 213	99.73 273	99.53 53	99.02 239	99.86 43

viewmacassd2359aftdt		99.08 148	98.94 152	99.50 151	99.66 149	98.96 189	99.51 193	99.54 108	98.27 153	99.42 201	99.89 45	95.88 215	99.80 242	99.20 108	99.11 219	99.76 107

COLMAP_ROB	97.56 6	98.86 185	98.75 186	99.17 226	99.88 13	98.53 260	99.34 304	99.59 72	97.55 279	98.70 356	99.89 45	95.83 216	99.90 148	98.10 266	99.90 56	99.08 302
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 102	99.82 53	99.23 149	99.62 107	99.55 99	98.94 79	99.63 148	99.95 3	95.82 217	99.94 91	99.37 75	99.97 9	99.73 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AstraMVS		99.09 146	99.03 116	99.25 216	99.66 149	98.13 289	99.57 144	98.24 463	98.82 90	99.91 31	99.88 58	95.81 218	99.90 148	99.72 32	99.67 158	99.74 118

NormalMVS		99.27 88	99.19 87	99.52 141	99.89 8	98.83 229	99.65 89	99.52 133	99.10 48	99.84 55	99.76 190	95.80 219	99.99 4	99.30 89	99.84 101	99.74 118

SymmetryMVS		99.15 114	99.02 126	99.52 141	99.72 111	98.83 229	99.65 89	99.34 317	99.10 48	99.84 55	99.76 190	95.80 219	99.99 4	99.30 89	98.72 264	99.73 128

QAPM		98.67 215	98.30 235	99.80 64	99.20 329	99.67 68	99.77 35	99.72 14	94.74 434	98.73 348	99.90 36	95.78 221	99.98 20	96.96 374	99.88 74	99.76 107

BH-untuned		98.42 230	98.36 229	98.59 311	99.49 244	96.70 375	99.27 331	99.13 382	97.24 314	98.80 341	99.38 349	95.75 222	99.74 267	97.07 368	99.16 205	99.33 279

test_djsdf		98.67 215	98.57 216	98.98 247	98.70 423	98.91 206	99.88 4	99.46 240	97.55 279	99.22 259	99.88 58	95.73 223	99.28 371	99.03 135	97.62 327	98.75 340

DIV-MVS_self_test		98.01 281	97.85 280	98.48 328	99.24 320	97.95 304	98.71 445	99.35 312	96.50 375	98.60 374	99.54 296	95.72 224	99.03 421	97.21 356	95.77 391	98.46 428

3Dnovator+	97.12 13	99.18 103	98.97 142	99.82 57	99.17 343	99.68 64	99.81 20	99.51 156	99.20 34	98.72 349	99.89 45	95.68 225	99.97 29	98.86 165	99.86 86	99.81 79

cl____		98.01 281	97.84 281	98.55 321	99.25 318	97.97 299	98.71 445	99.34 317	96.47 381	98.59 375	99.54 296	95.65 226	99.21 392	97.21 356	95.77 391	98.46 428

WB-MVSnew		97.65 345	97.65 305	97.63 415	98.78 409	97.62 321	99.13 372	98.33 460	97.36 303	99.07 291	98.94 420	95.64 227	99.15 398	92.95 456	98.68 266	96.12 487

fmvsm_s_conf0.5_n_7		99.34 75	99.29 65	99.48 162	99.70 122	98.63 250	99.42 267	99.63 46	99.46 9	99.98 13	99.88 58	95.59 228	99.96 41	99.97 2	99.98 4	99.85 47

VNet		99.11 140	98.90 160	99.73 83	99.52 227	99.56 95	99.41 271	99.39 286	99.01 64	99.74 95	99.78 177	95.56 229	99.92 123	99.52 55	98.18 302	99.72 138

WR-MVS_H		98.13 258	97.87 278	98.90 264	99.02 372	98.84 226	99.70 59	99.59 72	97.27 310	98.40 388	99.19 390	95.53 230	99.23 381	98.34 244	93.78 434	98.61 401

CHOSEN 1792x2688		99.19 100	99.10 98	99.45 171	99.89 8	98.52 264	99.39 283	99.94 1	98.73 103	99.11 282	99.89 45	95.50 231	99.94 91	99.50 57	99.97 9	99.89 30

Vis-MVSNet (Re-imp)		98.87 182	98.72 190	99.31 201	99.71 117	98.88 216	99.80 25	99.44 260	97.91 231	99.36 223	99.78 177	95.49 232	99.43 345	97.91 283	99.11 219	99.62 192

VortexMVS		98.67 215	98.66 199	98.68 305	99.62 178	97.96 301	99.59 126	99.41 276	98.13 184	99.31 233	99.70 218	95.48 233	99.27 374	99.40 71	97.32 353	98.79 330

PatchMatch-RL		98.84 197	98.62 209	99.52 141	99.71 117	99.28 142	99.06 389	99.77 12	97.74 257	99.50 182	99.53 300	95.41 234	99.84 199	97.17 363	99.64 162	99.44 260

FA-MVS(test-final)		98.75 208	98.53 220	99.41 182	99.55 213	99.05 175	99.80 25	99.01 399	96.59 372	99.58 164	99.59 276	95.39 235	99.90 148	97.78 298	99.49 177	99.28 283

test_yl		98.86 185	98.63 204	99.54 126	99.49 244	99.18 153	99.50 204	99.07 391	98.22 167	99.61 157	99.51 308	95.37 236	99.84 199	98.60 208	98.33 286	99.59 208

DCV-MVSNet		98.86 185	98.63 204	99.54 126	99.49 244	99.18 153	99.50 204	99.07 391	98.22 167	99.61 157	99.51 308	95.37 236	99.84 199	98.60 208	98.33 286	99.59 208

guyue		99.16 110	99.04 113	99.52 141	99.69 127	98.92 205	99.59 126	98.81 429	98.73 103	99.90 34	99.87 72	95.34 238	99.88 168	99.66 40	99.81 120	99.74 118

tpmrst		98.33 240	98.48 223	97.90 390	99.16 345	94.78 442	99.31 313	99.11 384	97.27 310	99.45 190	99.59 276	95.33 239	99.84 199	98.48 224	98.61 268	99.09 301

MVP-Stereo		97.81 316	97.75 295	97.99 381	97.53 457	96.60 383	98.96 414	98.85 424	97.22 316	97.23 437	99.36 355	95.28 240	99.46 334	95.51 418	99.78 134	97.92 466
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CANet_DTU		98.97 172	98.87 168	99.25 216	99.33 293	98.42 277	99.08 384	99.30 344	99.16 37	99.43 198	99.75 195	95.27 241	99.97 29	98.56 217	99.95 22	99.36 274

XVG-OURS		98.73 211	98.68 195	98.88 273	99.70 122	97.73 314	98.92 421	99.55 99	98.52 123	99.45 190	99.84 103	95.27 241	99.91 135	98.08 271	98.84 256	99.00 314

BH-w/o		98.00 283	97.89 277	98.32 351	99.35 287	96.20 397	99.01 404	98.90 417	96.42 384	98.38 389	99.00 412	95.26 243	99.72 277	96.06 404	98.61 268	99.03 311

EU-MVSNet		97.98 285	98.03 259	97.81 405	98.72 420	96.65 380	99.66 83	99.66 32	98.09 198	98.35 394	99.82 120	95.25 244	98.01 468	97.41 342	95.30 405	98.78 332

fmvsm_s_conf0.5_n_9		99.41 59	99.28 68	99.81 60	99.84 38	99.52 106	99.48 229	99.62 51	99.46 9	99.99 2	99.92 18	95.24 245	99.96 41	99.97 2	99.97 9	99.96 7

GeoE		98.85 194	98.62 209	99.53 134	99.61 189	99.08 170	99.80 25	99.51 156	97.10 328	99.31 233	99.78 177	95.23 246	99.77 257	98.21 254	99.03 237	99.75 113

MDTV_nov1_ep13_2view						95.18 434	99.35 301		96.84 349	99.58 164		95.19 247		97.82 293		99.46 255

fmvsm_s_conf0.5_n_4		99.36 72	99.24 77	99.73 83	99.78 70	99.53 102	99.49 221	99.60 67	99.42 22	99.99 2	99.86 81	95.15 248	99.95 76	99.95 16	99.89 67	99.73 128

GDP-MVS		99.08 148	98.89 164	99.64 102	99.53 221	99.34 128	99.64 96	99.48 205	98.32 148	99.77 85	99.66 248	95.14 249	99.93 108	98.97 145	99.50 176	99.64 184

JIA-IIPM		97.50 357	97.02 373	98.93 256	98.73 418	97.80 312	99.30 315	98.97 403	91.73 469	98.91 320	94.86 489	95.10 250	99.71 283	97.58 319	97.98 310	99.28 283

NR-MVSNet		97.97 288	97.61 311	99.02 242	98.87 396	99.26 145	99.47 239	99.42 273	97.63 269	97.08 443	99.50 311	95.07 251	99.13 403	97.86 288	93.59 435	98.68 362

fmvsm_s_conf0.1_n_2		99.37 68	99.22 82	99.81 60	99.77 78	99.75 51	99.46 243	99.60 67	99.47 6	99.98 13	99.94 6	94.98 252	99.95 76	99.97 2	99.79 132	99.73 128

fmvsm_s_conf0.5_n_5		99.37 68	99.21 83	99.86 34	99.80 63	99.68 64	99.42 267	99.61 60	99.37 26	99.97 25	99.86 81	94.96 253	99.99 4	99.97 2	99.93 32	99.92 25

BP-MVS1		99.12 134	98.94 152	99.65 96	99.51 230	99.30 139	99.67 76	98.92 410	98.48 127	99.84 55	99.69 229	94.96 253	99.92 123	99.62 44	99.79 132	99.71 149

tpmvs		97.98 285	98.02 261	97.84 399	99.04 370	94.73 443	99.31 313	99.20 373	96.10 410	98.76 346	99.42 334	94.94 255	99.81 235	96.97 373	98.45 280	98.97 320

h-mvs33		97.70 336	97.28 359	98.97 249	99.70 122	97.27 333	99.36 296	99.45 251	98.94 79	99.66 130	99.64 256	94.93 256	99.99 4	99.48 64	84.36 474	99.65 177

hse-mvs2		97.50 357	97.14 367	98.59 311	99.49 244	97.05 348	99.28 326	99.22 368	98.94 79	99.66 130	99.42 334	94.93 256	99.65 307	99.48 64	83.80 477	99.08 302

fmvsm_s_conf0.5_n_10		99.41 59	99.24 77	99.92 1	99.83 47	99.84 20	99.53 181	99.56 89	99.45 13	99.99 2	99.92 18	94.92 258	99.99 4	99.97 2	99.97 9	99.95 11

v8		97.95 290	97.63 309	98.93 256	98.95 385	98.81 234	99.80 25	99.41 276	96.03 411	99.10 285	99.42 334	94.92 258	99.30 369	96.94 376	94.08 429	98.66 379

PatchmatchNet		98.31 241	98.36 229	98.19 364	99.16 345	95.32 430	99.27 331	98.92 410	97.37 302	99.37 217	99.58 280	94.90 260	99.70 290	97.43 341	99.21 201	99.54 221
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v7n		97.87 301	97.52 319	98.92 258	98.76 416	98.58 256	99.84 12	99.46 240	96.20 397	98.91 320	99.70 218	94.89 261	99.44 341	96.03 405	93.89 432	98.75 340

sam_mvs1												94.86 262				99.52 227

balanced_ft_v1		99.02 161	98.98 140	99.15 231	99.39 277	98.12 291	99.79 31	99.51 156	98.20 171	99.66 130	99.87 72	94.84 263	99.93 108	99.69 34	99.84 101	99.41 265

casdiffseed414692147		98.97 172	98.78 183	99.53 134	99.66 149	99.16 156	99.61 113	99.52 133	98.01 223	99.21 262	99.88 58	94.82 264	99.70 290	99.29 95	99.04 236	99.74 118

DU-MVS		98.08 266	97.79 285	98.96 250	98.87 396	98.98 182	99.41 271	99.45 251	97.87 235	98.71 350	99.50 311	94.82 264	99.22 387	98.57 214	92.87 446	98.68 362

Baseline_NR-MVSNet		97.76 322	97.45 330	98.68 305	99.09 359	98.29 280	99.41 271	98.85 424	95.65 416	98.63 368	99.67 243	94.82 264	99.10 412	98.07 274	92.89 445	98.64 383

test_fmvsmconf0.01_n		99.22 99	99.03 116	99.79 68	98.42 444	99.48 112	99.55 167	99.51 156	99.39 24	99.78 81	99.93 10	94.80 267	99.95 76	99.93 23	99.95 22	99.94 17

patchmatchnet-post											98.70 435	94.79 268	99.74 267

Patchmatch-RL test		95.84 406	95.81 404	95.95 452	95.61 483	90.57 479	98.24 476	98.39 458	95.10 425	95.20 462	98.67 436	94.78 269	97.77 473	96.28 402	90.02 462	99.51 236

alignmvs		98.81 198	98.56 218	99.58 117	99.43 262	99.42 119	99.51 193	98.96 405	98.61 114	99.35 226	98.92 424	94.78 269	99.77 257	99.35 76	98.11 307	99.54 221

MDTV_nov1_ep13			98.32 233		99.11 353	94.44 451	99.27 331	98.74 439	97.51 286	99.40 211	99.62 267	94.78 269	99.76 261	97.59 318	98.81 260

Vis-MVSNet		99.12 134	98.97 142	99.56 123	99.78 70	99.10 166	99.68 73	99.66 32	98.49 126	99.86 52	99.87 72	94.77 272	99.84 199	99.19 109	99.41 182	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
anonymousdsp		98.44 228	98.28 236	98.94 254	98.50 441	98.96 189	99.77 35	99.50 180	97.07 330	98.87 328	99.77 186	94.76 273	99.28 371	98.66 197	97.60 328	98.57 413

usedtu_dtu_shiyan1		98.09 262	97.82 282	98.89 268	98.70 423	98.90 211	98.57 456	99.47 227	96.78 352	98.87 328	99.05 404	94.75 274	99.23 381	97.45 338	96.74 364	98.53 417

FE-MVSNET3		98.09 262	97.82 282	98.89 268	98.70 423	98.90 211	98.57 456	99.47 227	96.78 352	98.87 328	99.05 404	94.75 274	99.23 381	97.45 338	96.74 364	98.53 417

v10		97.85 304	97.52 319	98.86 280	98.99 378	98.67 245	99.75 43	99.41 276	95.70 415	98.98 309	99.41 338	94.75 274	99.23 381	96.01 407	94.63 418	98.67 370

OpenMVS	96.50 16	98.47 226	98.12 247	99.52 141	99.04 370	99.53 102	99.82 16	99.72 14	94.56 437	98.08 410	99.88 58	94.73 277	99.98 20	97.47 335	99.76 140	99.06 308

sam_mvs												94.72 278

SSC-MVS		92.73 445	93.73 438	89.72 473	95.02 490	81.38 493	99.76 38	99.23 366	94.87 431	92.80 480	98.93 421	94.71 279	91.37 497	74.49 495	93.80 433	96.42 483

WB-MVS		93.10 443	94.10 432	90.12 472	95.51 487	81.88 492	99.73 52	99.27 357	95.05 426	93.09 479	98.91 425	94.70 280	91.89 496	76.62 493	94.02 431	96.58 482

v148		97.79 320	97.55 314	98.50 325	98.74 417	97.72 315	99.54 172	99.33 325	96.26 393	98.90 322	99.51 308	94.68 281	99.14 400	97.83 292	93.15 443	98.63 390

v1144		97.98 285	97.69 301	98.85 283	98.87 396	98.66 246	99.54 172	99.35 312	96.27 392	99.23 258	99.35 358	94.67 282	99.23 381	96.73 385	95.16 408	98.68 362

V42		98.06 268	97.79 285	98.86 280	98.98 381	98.84 226	99.69 63	99.34 317	96.53 374	99.30 237	99.37 352	94.67 282	99.32 366	97.57 323	94.66 417	98.42 431

IMVS_0404		98.53 223	98.52 221	98.55 321	99.55 213	96.93 362	99.20 359	99.44 260	98.05 210	98.96 313	99.80 153	94.66 284	99.13 403	98.15 262	98.92 246	99.60 197

test_post											65.99 500	94.65 285	99.73 273

fmvsm_s_conf0.5_n_3		99.37 68	99.20 85	99.87 22	99.75 92	99.70 60	99.48 229	99.66 32	99.45 13	99.99 2	99.93 10	94.64 286	99.97 29	99.94 21	99.97 9	99.95 11

baseline1		98.31 241	97.95 268	99.38 189	99.50 242	98.74 239	99.59 126	98.93 407	98.41 136	99.14 277	99.60 274	94.59 287	99.79 248	98.48 224	93.29 439	99.61 194

DSMNet-mixed		97.25 374	97.35 347	96.95 439	97.84 452	93.61 465	99.57 144	96.63 488	96.13 405	98.87 328	98.61 439	94.59 287	97.70 475	95.08 428	98.86 254	99.55 219

SDMVSNet		99.11 140	98.90 160	99.75 77	99.81 57	99.59 89	99.81 20	99.65 39	98.78 99	99.64 145	99.88 58	94.56 289	99.93 108	99.67 37	98.26 294	99.72 138

Patchmatch-test		97.93 291	97.65 305	98.77 295	99.18 335	97.07 346	99.03 396	99.14 381	96.16 401	98.74 347	99.57 285	94.56 289	99.72 277	93.36 450	99.11 219	99.52 227

PCF-MVS	97.08 14	97.66 344	97.06 372	99.47 168	99.61 189	99.09 167	98.04 482	99.25 362	91.24 471	98.51 379	99.70 218	94.55 291	99.91 135	92.76 460	99.85 93	99.42 262
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
KinetiMVS		99.12 134	98.92 155	99.70 87	99.67 137	99.40 122	99.67 76	99.63 46	98.73 103	99.94 28	99.81 135	94.54 292	99.96 41	98.40 236	99.93 32	99.74 118

PatchT		97.03 382	96.44 388	98.79 292	98.99 378	98.34 279	99.16 365	99.07 391	92.13 466	99.52 179	97.31 479	94.54 292	98.98 432	88.54 476	98.73 263	99.03 311

fmvsm_s_conf0.1_n		99.29 84	99.10 98	99.86 34	99.70 122	99.65 75	99.53 181	99.62 51	98.74 102	99.99 2	99.95 3	94.53 294	99.94 91	99.89 25	99.96 17	99.97 4

CVMVSNet		98.57 222	98.67 196	98.30 353	99.35 287	95.59 418	99.50 204	99.55 99	98.60 116	99.39 213	99.83 109	94.48 295	99.45 336	98.75 184	98.56 274	99.85 47

fmvsm_s_conf0.1_n_a		99.26 91	99.06 109	99.85 43	99.52 227	99.62 83	99.54 172	99.62 51	98.69 108	99.99 2	99.96 1	94.47 296	99.94 91	99.88 26	99.92 38	99.98 2

test-LLR		98.06 268	97.90 273	98.55 321	98.79 406	97.10 342	98.67 447	97.75 472	97.34 304	98.61 372	98.85 426	94.45 297	99.45 336	97.25 354	99.38 183	99.10 297

test0.0.03 1		97.71 335	97.42 340	98.56 319	98.41 445	97.82 311	98.78 438	98.63 452	97.34 304	98.05 414	98.98 416	94.45 297	98.98 432	95.04 429	97.15 360	98.89 325

viewdifsd2359ckpt11		98.78 203	98.74 188	98.89 268	99.67 137	97.04 351	99.50 204	99.58 77	98.26 156	99.56 168	99.90 36	94.36 299	99.87 175	99.49 61	98.32 290	99.77 100

viewmsd2359difaftdt		98.78 203	98.74 188	98.90 264	99.67 137	97.04 351	99.50 204	99.58 77	98.26 156	99.56 168	99.90 36	94.36 299	99.87 175	99.49 61	98.32 290	99.77 100

v144192		97.92 294	97.60 312	98.87 277	98.83 403	98.65 247	99.55 167	99.34 317	96.20 397	99.32 232	99.40 342	94.36 299	99.26 377	96.37 401	95.03 411	98.70 353

CR-MVSNet		98.17 254	97.93 271	98.87 277	99.18 335	98.49 269	99.22 354	99.33 325	96.96 340	99.56 168	99.38 349	94.33 302	99.00 429	94.83 433	98.58 271	99.14 294

Patchmtry		97.75 326	97.40 342	98.81 289	99.10 356	98.87 220	99.11 381	99.33 325	94.83 432	98.81 339	99.38 349	94.33 302	99.02 425	96.10 403	95.57 399	98.53 417

tpm cat1		97.39 366	97.36 345	97.50 423	99.17 343	93.73 460	99.43 260	99.31 339	91.27 470	98.71 350	99.08 400	94.31 304	99.77 257	96.41 399	98.50 278	99.00 314

TranMVSNet+NR-MVSNet		97.93 291	97.66 304	98.76 296	98.78 409	98.62 252	99.65 89	99.49 193	97.76 253	98.49 381	99.60 274	94.23 305	98.97 439	98.00 278	92.90 444	98.70 353

v2v482		98.06 268	97.77 290	98.92 258	98.90 391	98.82 232	99.57 144	99.36 305	96.65 362	99.19 269	99.35 358	94.20 306	99.25 378	97.72 308	94.97 412	98.69 357

XVG-OURS-SEG-HR		98.69 213	98.62 209	98.89 268	99.71 117	97.74 313	99.12 375	99.54 108	98.44 134	99.42 201	99.71 214	94.20 306	99.92 123	98.54 221	98.90 252	99.00 314

ab-mvs		98.86 185	98.63 204	99.54 126	99.64 165	99.19 151	99.44 254	99.54 108	97.77 252	99.30 237	99.81 135	94.20 306	99.93 108	99.17 115	98.82 258	99.49 241

fmvsm_s_conf0.5_n_11		99.32 78	99.16 91	99.80 64	99.83 47	99.70 60	99.57 144	99.56 89	99.45 13	99.99 2	99.93 10	94.18 309	99.99 4	99.96 13	99.98 4	99.73 128

test_post1							99.23 350				65.14 501	94.18 309	99.71 283	97.58 319

ADS-MVSNet2		98.02 278	98.07 256	97.87 392	99.33 293	95.19 433	99.23 350	99.08 388	96.24 394	99.10 285	99.67 243	94.11 311	98.93 444	96.81 382	99.05 234	99.48 244

ADS-MVSNet		98.20 250	98.08 253	98.56 319	99.33 293	96.48 386	99.23 350	99.15 379	96.24 394	99.10 285	99.67 243	94.11 311	99.71 283	96.81 382	99.05 234	99.48 244

RPMNet		96.72 388	95.90 401	99.19 224	99.18 335	98.49 269	99.22 354	99.52 133	88.72 480	99.56 168	97.38 476	94.08 313	99.95 76	86.87 485	98.58 271	99.14 294

fmvsm_s_conf0.5_n_2		99.32 78	99.13 94	99.89 12	99.80 63	99.77 48	99.44 254	99.58 77	99.47 6	99.99 2	99.93 10	94.04 314	99.96 41	99.96 13	99.93 32	99.93 22

v1192		97.81 316	97.44 335	98.91 262	98.88 393	98.68 244	99.51 193	99.34 317	96.18 399	99.20 266	99.34 362	94.03 315	99.36 358	95.32 424	95.18 407	98.69 357

dmvs_testset		95.02 426	96.12 395	91.72 467	99.10 356	80.43 495	99.58 136	97.87 471	97.47 288	95.22 461	98.82 428	93.99 316	95.18 492	88.09 478	94.91 415	99.56 218

v1921920		97.80 318	97.45 330	98.84 284	98.80 405	98.53 260	99.52 183	99.34 317	96.15 403	99.24 254	99.47 323	93.98 317	99.29 370	95.40 422	95.13 409	98.69 357

Anonymous20231206		96.22 397	96.03 398	96.79 444	97.31 463	94.14 456	99.63 102	99.08 388	96.17 400	97.04 444	99.06 403	93.94 318	97.76 474	86.96 484	95.06 410	98.47 425

WR-MVS		98.06 268	97.73 297	99.06 237	98.86 399	99.25 147	99.19 361	99.35 312	97.30 308	98.66 359	99.43 332	93.94 318	99.21 392	98.58 211	94.28 424	98.71 348

Syy-MVS		97.09 381	97.14 367	96.95 439	99.00 375	92.73 471	99.29 320	99.39 286	97.06 332	97.41 431	98.15 456	93.92 320	98.68 455	91.71 464	98.34 284	99.45 258

RRT-MVS		98.91 177	98.75 186	99.39 188	99.46 254	98.61 254	99.76 38	99.50 180	98.06 207	99.81 69	99.88 58	93.91 321	99.94 91	99.11 123	99.27 194	99.61 194

N_pmnet		94.95 429	95.83 403	92.31 465	98.47 442	79.33 497	99.12 375	92.81 503	93.87 442	97.68 427	99.13 396	93.87 322	99.01 428	91.38 466	96.19 379	98.59 410

MVSTER		98.49 224	98.32 233	99.00 245	99.35 287	99.02 177	99.54 172	99.38 294	97.41 299	99.20 266	99.73 207	93.86 323	99.36 358	98.87 160	97.56 332	98.62 392

FE-MVS		98.48 225	98.17 240	99.40 183	99.54 220	98.96 189	99.68 73	98.81 429	95.54 417	99.62 152	99.70 218	93.82 324	99.93 108	97.35 346	99.46 178	99.32 280

CP-MVSNet		98.09 262	97.78 288	99.01 243	98.97 383	99.24 148	99.67 76	99.46 240	97.25 312	98.48 382	99.64 256	93.79 325	99.06 417	98.63 201	94.10 428	98.74 344

cascas		97.69 337	97.43 339	98.48 328	98.60 435	97.30 331	98.18 479	99.39 286	92.96 456	98.41 387	98.78 433	93.77 326	99.27 374	98.16 260	98.61 268	98.86 326

v1240		97.69 337	97.32 354	98.79 292	98.85 400	98.43 275	99.48 229	99.36 305	96.11 406	99.27 247	99.36 355	93.76 327	99.24 380	94.46 436	95.23 406	98.70 353

test20.03		96.12 401	95.96 400	96.63 445	97.44 458	95.45 425	99.51 193	99.38 294	96.55 373	96.16 455	99.25 383	93.76 327	96.17 488	87.35 483	94.22 425	98.27 441

dmvs_re		98.08 266	98.16 241	97.85 396	99.55 213	94.67 447	99.70 59	98.92 410	98.15 177	99.06 296	99.35 358	93.67 329	99.25 378	97.77 301	97.25 355	99.64 184

baseline2		97.87 301	97.55 314	98.82 286	99.18 335	98.02 296	99.41 271	96.58 490	96.97 339	96.51 450	99.17 391	93.43 330	99.57 323	97.71 309	99.03 237	98.86 326

TransMVSNet (Re)		97.15 378	96.58 384	98.86 280	99.12 351	98.85 224	99.49 221	98.91 415	95.48 418	97.16 441	99.80 153	93.38 331	99.11 409	94.16 442	91.73 453	98.62 392

Elysia		98.88 179	98.65 201	99.58 117	99.58 199	99.34 128	99.65 89	99.52 133	98.26 156	99.83 64	99.87 72	93.37 332	99.90 148	97.81 295	99.91 45	99.49 241

StellarMVS		98.88 179	98.65 201	99.58 117	99.58 199	99.34 128	99.65 89	99.52 133	98.26 156	99.83 64	99.87 72	93.37 332	99.90 148	97.81 295	99.91 45	99.49 241

tfpnnormal		97.84 308	97.47 327	98.98 247	99.20 329	99.22 150	99.64 96	99.61 60	96.32 388	98.27 400	99.70 218	93.35 334	99.44 341	95.69 414	95.40 403	98.27 441

Anonymous20231211		97.88 299	97.54 317	98.90 264	99.71 117	98.53 260	99.48 229	99.57 84	94.16 440	98.81 339	99.68 237	93.23 335	99.42 347	98.84 170	94.42 422	98.76 338

XXY-MVS		98.38 236	98.09 252	99.24 219	99.26 314	99.32 132	99.56 152	99.55 99	97.45 292	98.71 350	99.83 109	93.23 335	99.63 317	98.88 157	96.32 376	98.76 338

jajsoiax		98.43 229	98.28 236	98.88 273	98.60 435	98.43 275	99.82 16	99.53 124	98.19 172	98.63 368	99.80 153	93.22 337	99.44 341	99.22 105	97.50 339	98.77 336

test_cas_vis1_n_1920		99.16 110	99.01 133	99.61 110	99.81 57	98.86 223	99.65 89	99.64 42	99.39 24	99.97 25	99.94 6	93.20 338	99.98 20	99.55 50	99.91 45	99.99 1

MDA-MVSNet_test_wron		95.45 414	94.60 423	98.01 378	98.16 448	97.21 338	99.11 381	99.24 365	93.49 449	80.73 495	98.98 416	93.02 339	98.18 463	94.22 441	94.45 421	98.64 383

ACMM	97.58 5	98.37 238	98.34 231	98.48 328	99.41 269	97.10 342	99.56 152	99.45 251	98.53 122	99.04 299	99.85 88	93.00 340	99.71 283	98.74 185	97.45 344	98.64 383
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet3		98.03 276	97.76 294	98.84 284	99.39 277	98.98 182	99.40 279	99.38 294	96.67 360	99.07 291	99.28 377	92.93 341	98.98 432	97.10 364	96.65 367	98.56 414

DTE-MVSNet		97.51 356	97.19 365	98.46 334	98.63 431	98.13 289	99.84 12	99.48 205	96.68 359	97.97 417	99.67 243	92.92 342	98.56 457	96.88 381	92.60 450	98.70 353

CLD-MVS		98.16 255	98.10 249	98.33 349	99.29 306	96.82 372	98.75 441	99.44 260	97.83 243	99.13 278	99.55 291	92.92 342	99.67 299	98.32 247	97.69 323	98.48 423
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
BH-RMVSNet		98.41 232	98.08 253	99.40 183	99.41 269	98.83 229	99.30 315	98.77 435	97.70 262	98.94 317	99.65 250	92.91 344	99.74 267	96.52 394	99.55 172	99.64 184

YYNet1		95.36 419	94.51 427	97.92 388	97.89 451	97.10 342	99.10 383	99.23 366	93.26 453	80.77 494	99.04 407	92.81 345	98.02 467	94.30 437	94.18 426	98.64 383

mvs_tets		98.40 235	98.23 238	98.91 262	98.67 428	98.51 266	99.66 83	99.53 124	98.19 172	98.65 365	99.81 135	92.75 346	99.44 341	99.31 86	97.48 343	98.77 336

IterMVS		97.83 311	97.77 290	98.02 377	99.58 199	96.27 394	99.02 399	99.48 205	97.22 316	98.71 350	99.70 218	92.75 346	99.13 403	97.46 336	96.00 384	98.67 370
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UGNet		98.87 182	98.69 194	99.40 183	99.22 326	98.72 242	99.44 254	99.68 24	99.24 33	99.18 273	99.42 334	92.74 348	99.96 41	99.34 81	99.94 30	99.53 226
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
IterMVS-SCA-FT		97.82 314	97.75 295	98.06 374	99.57 205	96.36 390	99.02 399	99.49 193	97.18 318	98.71 350	99.72 211	92.72 349	99.14 400	97.44 340	95.86 390	98.67 370

SCA		98.19 251	98.16 241	98.27 359	99.30 302	95.55 419	99.07 385	98.97 403	97.57 276	99.43 198	99.57 285	92.72 349	99.74 267	97.58 319	99.20 203	99.52 227

HQP_MVS		98.27 246	98.22 239	98.44 339	99.29 306	96.97 359	99.39 283	99.47 227	98.97 76	99.11 282	99.61 271	92.71 351	99.69 296	97.78 298	97.63 325	98.67 370

plane_prior6					99.27 311	96.98 358						92.71 351

CL-MVSNet_self_test		94.49 434	93.97 436	96.08 451	96.16 479	93.67 463	98.33 473	99.38 294	95.13 421	97.33 435	98.15 456	92.69 353	96.57 485	88.67 475	79.87 491	97.99 461

dp		97.75 326	97.80 284	97.59 420	99.10 356	93.71 461	99.32 309	98.88 420	96.48 379	99.08 290	99.55 291	92.67 354	99.82 230	96.52 394	98.58 271	99.24 289

PEN-MVS		97.76 322	97.44 335	98.72 299	98.77 414	98.54 259	99.78 33	99.51 156	97.06 332	98.29 399	99.64 256	92.63 355	98.89 448	98.09 267	93.16 442	98.72 346

LPG-MVS_test		98.22 247	98.13 246	98.49 326	99.33 293	97.05 348	99.58 136	99.55 99	97.46 289	99.24 254	99.83 109	92.58 356	99.72 277	98.09 267	97.51 337	98.68 362

LGP-MVS_train				98.49 326	99.33 293	97.05 348		99.55 99	97.46 289	99.24 254	99.83 109	92.58 356	99.72 277	98.09 267	97.51 337	98.68 362

VPA-MVSNet		98.29 244	97.95 268	99.30 206	99.16 345	99.54 99	99.50 204	99.58 77	98.27 153	99.35 226	99.37 352	92.53 358	99.65 307	99.35 76	94.46 420	98.72 346

TR-MVS		97.76 322	97.41 341	98.82 286	99.06 365	97.87 308	98.87 427	98.56 454	96.63 366	98.68 358	99.22 386	92.49 359	99.65 307	95.40 422	97.79 320	98.95 324

pm-mvs1		97.68 340	97.28 359	98.88 273	99.06 365	98.62 252	99.50 204	99.45 251	96.32 388	97.87 422	99.79 170	92.47 360	99.35 361	97.54 326	93.54 436	98.67 370

HQP2-MVS												92.47 360

HQP-MVS		98.02 278	97.90 273	98.37 347	99.19 332	96.83 370	98.98 410	99.39 286	98.24 163	98.66 359	99.40 342	92.47 360	99.64 311	97.19 360	97.58 330	98.64 383

EPMVS		97.82 314	97.65 305	98.35 348	98.88 393	95.98 401	99.49 221	94.71 496	97.57 276	99.26 252	99.48 320	92.46 363	99.71 283	97.87 287	99.08 232	99.35 275

PS-CasMVS		97.93 291	97.59 313	98.95 252	98.99 378	99.06 173	99.68 73	99.52 133	97.13 322	98.31 396	99.68 237	92.44 364	99.05 418	98.51 222	94.08 429	98.75 340

cl22		97.85 304	97.64 308	98.48 328	99.09 359	97.87 308	98.60 455	99.33 325	97.11 327	98.87 328	99.22 386	92.38 365	99.17 397	98.21 254	95.99 385	98.42 431

CostFormer		97.72 332	97.73 297	97.71 412	99.15 349	94.02 457	99.54 172	99.02 398	94.67 435	99.04 299	99.35 358	92.35 366	99.77 257	98.50 223	97.94 312	99.34 278

ttmdpeth		97.80 318	97.63 309	98.29 354	98.77 414	97.38 329	99.64 96	99.36 305	98.78 99	96.30 453	99.58 280	92.34 367	99.39 349	98.36 242	95.58 398	98.10 451

OPM-MVS		98.19 251	98.10 249	98.45 336	98.88 393	97.07 346	99.28 326	99.38 294	98.57 118	99.22 259	99.81 135	92.12 368	99.66 302	98.08 271	97.54 334	98.61 401
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ET-MVSNet_ETH3D		96.49 393	95.64 407	99.05 239	99.53 221	98.82 232	98.84 431	97.51 480	97.63 269	84.77 489	99.21 389	92.09 369	98.91 445	98.98 140	92.21 451	99.41 265

sd_testset		98.75 208	98.57 216	99.29 209	99.81 57	98.26 282	99.56 152	99.62 51	98.78 99	99.64 145	99.88 58	92.02 370	99.88 168	99.54 51	98.26 294	99.72 138

AUN-MVS		96.88 385	96.31 391	98.59 311	99.48 251	97.04 351	99.27 331	99.22 368	97.44 295	98.51 379	99.41 338	91.97 371	99.66 302	97.71 309	83.83 476	99.07 307

ACMP	97.20 11	98.06 268	97.94 270	98.45 336	99.37 283	97.01 355	99.44 254	99.49 193	97.54 282	98.45 385	99.79 170	91.95 372	99.72 277	97.91 283	97.49 342	98.62 392
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211		98.30 243	97.98 264	99.26 215	99.57 205	98.16 286	99.41 271	98.55 455	96.03 411	99.19 269	99.74 201	91.87 373	99.92 123	99.16 118	98.29 293	99.70 152

KD-MVS_self_test		95.00 427	94.34 430	96.96 438	97.07 468	95.39 428	99.56 152	99.44 260	95.11 423	97.13 442	97.32 478	91.86 374	97.27 480	90.35 470	81.23 484	98.23 445

tpm		97.67 343	97.55 314	98.03 375	99.02 372	95.01 438	99.43 260	98.54 456	96.44 382	99.12 280	99.34 362	91.83 375	99.60 320	97.75 304	96.46 372	99.48 244

thres100view900		97.76 322	97.45 330	98.69 304	99.72 111	97.86 310	99.59 126	98.74 439	97.93 229	99.26 252	98.62 437	91.75 376	99.83 221	93.22 452	98.18 302	98.37 437

thres600view7		97.86 303	97.51 321	98.92 258	99.72 111	97.95 304	99.59 126	98.74 439	97.94 228	99.27 247	98.62 437	91.75 376	99.86 182	93.73 446	98.19 301	98.96 322

LTVRE_ROB	97.16 12	98.02 278	97.90 273	98.40 344	99.23 322	96.80 373	99.70 59	99.60 67	97.12 324	98.18 406	99.70 218	91.73 378	99.72 277	98.39 237	97.45 344	98.68 362
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
OurMVSNet-221017-0		97.88 299	97.77 290	98.19 364	98.71 422	96.53 384	99.88 4	99.00 400	97.79 249	98.78 344	99.94 6	91.68 379	99.35 361	97.21 356	96.99 363	98.69 357

tfpn200view9		97.72 332	97.38 343	98.72 299	99.69 127	97.96 301	99.50 204	98.73 445	97.83 243	99.17 274	98.45 444	91.67 380	99.83 221	93.22 452	98.18 302	98.37 437

thres400		97.77 321	97.38 343	98.92 258	99.69 127	97.96 301	99.50 204	98.73 445	97.83 243	99.17 274	98.45 444	91.67 380	99.83 221	93.22 452	98.18 302	98.96 322

thisisatest0515		98.14 257	97.79 285	99.19 224	99.50 242	98.50 268	98.61 453	96.82 485	96.95 342	99.54 175	99.43 332	91.66 382	99.86 182	98.08 271	99.51 174	99.22 291

thres200		97.61 348	97.28 359	98.62 309	99.64 165	98.03 295	99.26 340	98.74 439	97.68 264	99.09 288	98.32 450	91.66 382	99.81 235	92.88 457	98.22 297	98.03 456

new_pmnet		96.38 396	96.03 398	97.41 425	98.13 449	95.16 435	99.05 391	99.20 373	93.94 441	97.39 434	98.79 432	91.61 384	99.04 419	90.43 469	95.77 391	98.05 455

pmmvs5		97.52 354	97.30 356	98.16 366	98.57 438	96.73 374	99.27 331	98.90 417	96.14 404	98.37 390	99.53 300	91.54 385	99.14 400	97.51 330	95.87 389	98.63 390

blended_shiyan6		95.54 412	94.78 419	97.84 399	96.60 473	95.89 408	98.85 428	99.28 350	92.17 465	98.43 386	97.95 464	91.44 386	99.02 425	97.30 350	80.97 486	98.60 404

blended_shiyan8		95.56 411	94.79 418	97.87 392	96.60 473	95.90 407	98.85 428	99.27 357	92.19 462	98.47 383	97.94 465	91.43 387	99.11 409	97.26 353	81.09 485	98.60 404

test_fmvs1		98.88 179	98.79 182	99.16 227	99.69 127	97.61 322	99.55 167	99.49 193	99.32 30	99.98 13	99.91 26	91.41 388	99.96 41	99.82 29	99.92 38	99.90 27

tttt0517		98.42 230	98.14 244	99.28 213	99.66 149	98.38 278	99.74 48	96.85 484	97.68 264	99.79 76	99.74 201	91.39 389	99.89 163	98.83 173	99.56 170	99.57 215

UWE-MVS-28		97.36 367	97.24 363	97.75 409	98.84 402	94.44 451	99.24 347	97.58 479	97.98 225	99.00 306	99.00 412	91.35 390	99.53 329	93.75 445	98.39 282	99.27 287

tpm2		97.44 364	97.34 350	97.74 411	99.15 349	94.36 454	99.45 247	98.94 406	93.45 451	98.90 322	99.44 330	91.35 390	99.59 321	97.31 347	98.07 308	99.29 282

MVS-HIRNet		95.75 408	95.16 413	97.51 422	99.30 302	93.69 462	98.88 425	95.78 491	85.09 488	98.78 344	92.65 491	91.29 392	99.37 354	94.85 432	99.85 93	99.46 255

thisisatest0530		98.35 239	98.03 259	99.31 201	99.63 169	98.56 257	99.54 172	96.75 486	97.53 283	99.73 97	99.65 250	91.25 393	99.89 163	98.62 202	99.56 170	99.48 244

wanda-best-256-512		95.43 415	94.66 421	97.77 407	96.45 475	95.68 414	98.48 464	99.28 350	92.18 463	98.36 391	97.68 468	91.20 394	99.03 421	97.31 347	80.97 486	98.60 404

FE-blended-shiyan7		95.43 415	94.66 421	97.77 407	96.45 475	95.68 414	98.48 464	99.28 350	92.18 463	98.36 391	97.68 468	91.20 394	99.03 421	97.31 347	80.97 486	98.60 404

usedtu_blend_shiyan5		95.04 425	94.10 432	97.86 395	96.45 475	95.92 405	99.29 320	99.22 368	86.17 486	98.36 391	97.68 468	91.20 394	99.07 414	97.53 327	80.97 486	98.60 404

testgi		97.65 345	97.50 322	98.13 370	99.36 286	96.45 387	99.42 267	99.48 205	97.76 253	97.87 422	99.45 329	91.09 397	98.81 450	94.53 435	98.52 277	99.13 296

ITE_SJBPF				98.08 373	99.29 306	96.37 389		98.92 410	98.34 144	98.83 336	99.75 195	91.09 397	99.62 318	95.82 409	97.40 350	98.25 443

DeepMVS_CX				93.34 461	99.29 306	82.27 490		99.22 368	85.15 487	96.33 452	99.05 404	90.97 399	99.73 273	93.57 448	97.77 321	98.01 457

ACMH	97.28 8	98.10 261	97.99 263	98.44 339	99.41 269	96.96 361	99.60 115	99.56 89	98.09 198	98.15 408	99.91 26	90.87 400	99.70 290	98.88 157	97.45 344	98.67 370
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		98.04 274	98.11 248	97.83 402	99.74 100	93.82 458	99.58 136	95.40 493	99.12 46	99.65 140	99.93 10	90.73 401	99.84 199	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 274	98.05 257	98.00 380	99.74 100	94.37 453	99.59 126	94.98 494	99.13 41	99.66 130	99.93 10	90.67 402	99.84 199	99.40 71	99.38 183	99.80 88

SixPastTwentyTwo		97.50 357	97.33 353	98.03 375	98.65 429	96.23 396	99.77 35	98.68 448	97.14 321	97.90 420	99.93 10	90.45 403	99.18 395	97.00 370	96.43 373	98.67 370

MIMVSNet		97.73 330	97.45 330	98.57 315	99.45 260	97.50 325	99.02 399	98.98 402	96.11 406	99.41 206	99.14 395	90.28 404	98.74 453	95.74 412	98.93 244	99.47 250

GBi-Net		97.68 340	97.48 324	98.29 354	99.51 230	97.26 335	99.43 260	99.48 205	96.49 376	99.07 291	99.32 370	90.26 405	98.98 432	97.10 364	96.65 367	98.62 392

test1		97.68 340	97.48 324	98.29 354	99.51 230	97.26 335	99.43 260	99.48 205	96.49 376	99.07 291	99.32 370	90.26 405	98.98 432	97.10 364	96.65 367	98.62 392

FMVSNet2		97.72 332	97.36 345	98.80 291	99.51 230	98.84 226	99.45 247	99.42 273	96.49 376	98.86 334	99.29 375	90.26 405	98.98 432	96.44 396	96.56 370	98.58 411

gbinet_0.2-2-1-0.02		95.40 418	94.58 425	97.85 396	96.11 480	95.97 402	98.56 460	99.26 359	92.12 467	98.47 383	97.49 474	90.23 408	99.00 429	97.71 309	81.25 483	98.58 411

Anonymous20240529		98.09 262	97.68 302	99.34 193	99.66 149	98.44 274	99.40 279	99.43 271	93.67 445	99.22 259	99.89 45	90.23 408	99.93 108	99.26 103	98.33 286	99.66 170

ACMH+	97.24 10	97.92 294	97.78 288	98.32 351	99.46 254	96.68 379	99.56 152	99.54 108	98.41 136	97.79 426	99.87 72	90.18 410	99.66 302	98.05 275	97.18 359	98.62 392

LF4IMVS		97.52 354	97.46 329	97.70 413	98.98 381	95.55 419	99.29 320	98.82 427	98.07 203	98.66 359	99.64 256	89.97 411	99.61 319	97.01 369	96.68 366	97.94 464

MVStest1		96.08 403	95.48 408	97.89 391	98.93 386	96.70 375	99.56 152	99.35 312	92.69 459	91.81 484	99.46 327	89.90 412	98.96 441	95.00 430	92.61 449	98.00 460

GA-MVS		97.85 304	97.47 327	99.00 245	99.38 280	97.99 298	98.57 456	99.15 379	97.04 335	98.90 322	99.30 373	89.83 413	99.38 351	96.70 387	98.33 286	99.62 192

PVSNet_0	94.43 19	96.09 402	95.47 409	97.94 386	99.31 301	94.34 455	97.81 483	99.70 18	97.12 324	97.46 430	98.75 434	89.71 414	99.79 248	97.69 313	81.69 482	99.68 161

Anonymous20240521		96.20 399	95.89 402	97.13 432	97.72 456	94.96 440	99.79 31	99.29 348	93.01 455	97.20 440	99.03 408	89.69 415	98.36 461	91.16 467	96.13 380	98.07 453

XVG-ACMP-BASELINE		97.83 311	97.71 299	98.20 363	99.11 353	96.33 391	99.41 271	99.52 133	98.06 207	99.05 298	99.50 311	89.64 416	99.73 273	97.73 306	97.38 351	98.53 417

gg-mvs-nofinetune		96.17 400	95.32 412	98.73 297	98.79 406	98.14 288	99.38 288	94.09 497	91.07 473	98.07 413	91.04 495	89.62 417	99.35 361	96.75 384	99.09 231	98.68 362

GG-mvs-BLEND				98.45 336	98.55 439	98.16 286	99.43 260	93.68 498		97.23 437	98.46 443	89.30 418	99.22 387	95.43 421	98.22 297	97.98 462

reproduce_monomvs		97.89 298	97.87 278	97.96 385	99.51 230	95.45 425	99.60 115	99.25 362	99.17 36	98.85 335	99.49 314	89.29 419	99.64 311	99.35 76	96.31 377	98.78 332

USDC		97.34 369	97.20 364	97.75 409	99.07 363	95.20 432	98.51 463	99.04 395	97.99 224	98.31 396	99.86 81	89.02 420	99.55 327	95.67 416	97.36 352	98.49 422

MS-PatchMatch		97.24 376	97.32 354	96.99 436	98.45 443	93.51 466	98.82 434	99.32 335	97.41 299	98.13 409	99.30 373	88.99 421	99.56 325	95.68 415	99.80 125	97.90 467

VPNet		97.84 308	97.44 335	99.01 243	99.21 327	98.94 199	99.48 229	99.57 84	98.38 138	99.28 241	99.73 207	88.89 422	99.39 349	99.19 109	93.27 440	98.71 348

WBMVS		97.74 328	97.50 322	98.46 334	99.24 320	97.43 327	99.21 356	99.42 273	97.45 292	98.96 313	99.41 338	88.83 423	99.23 381	98.94 148	96.02 382	98.71 348

UWE-MVS		97.58 350	97.29 358	98.48 328	99.09 359	96.25 395	99.01 404	96.61 489	97.86 236	99.19 269	99.01 411	88.72 424	99.90 148	97.38 344	98.69 265	99.28 283

K. test v3		97.10 380	96.79 380	98.01 378	98.72 420	96.33 391	99.87 8	97.05 482	97.59 273	96.16 455	99.80 153	88.71 425	99.04 419	96.69 388	96.55 371	98.65 381

lessismore_v0				97.79 406	98.69 426	95.44 427		94.75 495		95.71 459	99.87 72	88.69 426	99.32 366	95.89 408	94.93 414	98.62 392

tt0805		97.97 288	97.77 290	98.57 315	99.59 197	96.61 382	99.45 247	99.08 388	98.21 169	98.88 325	99.80 153	88.66 427	99.70 290	98.58 211	97.72 322	99.39 269

UBG		97.85 304	97.48 324	98.95 252	99.25 318	97.64 320	99.24 347	98.74 439	97.90 232	98.64 366	98.20 455	88.65 428	99.81 235	98.27 250	98.40 281	99.42 262

TDRefinement		95.42 417	94.57 426	97.97 383	89.83 499	96.11 400	99.48 229	98.75 436	96.74 355	96.68 449	99.88 58	88.65 428	99.71 283	98.37 240	82.74 480	98.09 452

TESTMET0.1,1		97.55 351	97.27 362	98.40 344	98.93 386	96.53 384	98.67 447	97.61 477	96.96 340	98.64 366	99.28 377	88.63 430	99.45 336	97.30 350	99.38 183	99.21 292

test_0402		96.64 390	96.24 392	97.85 396	98.85 400	96.43 388	99.44 254	99.26 359	93.52 448	96.98 445	99.52 304	88.52 431	99.20 394	92.58 462	97.50 339	97.93 465

UnsupCasMVSNet_eth		96.44 394	96.12 395	97.40 426	98.65 429	95.65 416	99.36 296	99.51 156	97.13 322	96.04 457	98.99 414	88.40 432	98.17 464	96.71 386	90.27 461	98.40 434

MDA-MVSNet-bldmvs		94.96 428	93.98 435	97.92 388	98.24 447	97.27 333	99.15 368	99.33 325	93.80 444	80.09 496	99.03 408	88.31 433	97.86 472	93.49 449	94.36 423	98.62 392

test-mter		97.49 362	97.13 369	98.55 321	98.79 406	97.10 342	98.67 447	97.75 472	96.65 362	98.61 372	98.85 426	88.23 434	99.45 336	97.25 354	99.38 183	99.10 297

TinyColmap		97.12 379	96.89 378	97.83 402	99.07 363	95.52 422	98.57 456	98.74 439	97.58 275	97.81 425	99.79 170	88.16 435	99.56 325	95.10 427	97.21 357	98.39 435

pmmvs-eth3d		95.34 420	94.73 420	97.15 430	95.53 485	95.94 404	99.35 301	99.10 385	95.13 421	93.55 476	97.54 473	88.15 436	97.91 470	94.58 434	89.69 466	97.61 471

SSC-MVS3.2		97.34 369	97.15 366	97.93 387	99.02 372	95.76 413	99.48 229	99.58 77	97.62 271	99.09 288	99.53 300	87.95 437	99.27 374	96.42 397	95.66 396	98.75 340

KD-MVS_2432*1600		94.62 432	93.72 439	97.31 427	97.19 466	95.82 411	98.34 471	99.20 373	95.00 428	97.57 428	98.35 448	87.95 437	98.10 465	92.87 458	77.00 493	98.01 457

miper_refine_blended		94.62 432	93.72 439	97.31 427	97.19 466	95.82 411	98.34 471	99.20 373	95.00 428	97.57 428	98.35 448	87.95 437	98.10 465	92.87 458	77.00 493	98.01 457

new-patchmatchnet		94.48 435	94.08 434	95.67 453	95.08 488	92.41 472	99.18 363	99.28 350	94.55 438	93.49 477	97.37 477	87.86 440	97.01 483	91.57 465	88.36 468	97.61 471

test2506		96.81 387	96.65 383	97.29 429	99.74 100	92.21 474	99.60 115	85.06 506	99.13 41	99.77 85	99.93 10	87.82 441	99.85 190	99.38 74	99.38 183	99.80 88

FMVSNet5		96.43 395	96.19 394	97.15 430	99.11 353	95.89 408	99.32 309	99.52 133	94.47 439	98.34 395	99.07 401	87.54 442	97.07 481	92.61 461	95.72 394	98.47 425

test_vis1_n_1920		98.63 220	98.40 228	99.31 201	99.86 25	97.94 306	99.67 76	99.62 51	99.43 19	99.99 2	99.91 26	87.29 443	100.00 1	99.92 24	99.92 38	99.98 2

0.4-1-1-0.1		95.23 423	94.22 431	98.26 360	97.39 459	95.86 410	97.59 487	97.62 475	93.85 443	94.97 467	97.03 480	87.20 444	99.87 175	98.47 227	83.84 475	99.05 309

mvs5depth		96.66 389	96.22 393	97.97 383	97.00 469	96.28 393	98.66 450	99.03 397	96.61 367	96.93 447	99.79 170	87.20 444	99.47 332	96.65 392	94.13 427	98.16 448

0.4-1-1-0.2		94.94 430	93.92 437	97.99 381	96.84 471	95.13 436	96.64 491	97.62 475	93.45 451	94.92 468	96.56 483	87.14 446	99.86 182	98.43 234	83.69 478	98.98 318

blend_shiyan4		95.25 422	94.39 429	97.84 399	96.70 472	95.92 405	98.84 431	99.28 350	92.21 461	98.16 407	97.84 466	87.10 447	99.07 414	97.53 327	81.87 481	98.54 415

pmmvs6		96.53 392	96.09 397	97.82 404	98.69 426	95.47 423	99.37 290	99.47 227	93.46 450	97.41 431	99.78 177	87.06 448	99.33 364	96.92 379	92.70 448	98.65 381

myMVS_eth3d28		97.69 337	97.34 350	98.73 297	99.27 311	97.52 324	99.33 306	98.78 434	98.03 219	98.82 338	98.49 442	86.64 449	99.46 334	98.44 231	98.24 296	99.23 290

testing3-2		97.84 308	97.70 300	98.24 361	99.53 221	95.37 429	99.55 167	98.67 450	98.46 129	99.27 247	99.34 362	86.58 450	99.83 221	99.32 84	98.63 267	99.52 227

mmtdpeth		96.95 383	96.71 382	97.67 414	99.33 293	94.90 441	99.89 2	99.28 350	98.15 177	99.72 102	98.57 440	86.56 451	99.90 148	99.82 29	89.02 467	98.20 446

FE-MVSNET		94.07 439	93.36 444	96.22 450	94.05 492	94.71 445	99.56 152	98.36 459	93.15 454	93.76 475	97.55 472	86.47 452	96.49 487	87.48 481	89.83 465	97.48 476

pmmvs3		94.09 438	93.25 445	96.60 446	94.76 491	94.49 450	98.92 421	98.18 467	89.66 474	96.48 451	98.06 462	86.28 453	97.33 479	89.68 472	87.20 471	97.97 463

FE-MVSNET2		95.10 424	94.44 428	97.08 435	95.08 488	95.97 402	99.51 193	99.37 303	95.02 427	94.10 471	97.57 471	86.18 454	97.66 477	93.28 451	89.86 464	97.61 471

IB-MVS	95.67 18	96.22 397	95.44 411	98.57 315	99.21 327	96.70 375	98.65 451	97.74 474	96.71 357	97.27 436	98.54 441	86.03 455	99.92 123	98.47 227	86.30 472	99.10 297
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
tmp_tt		82.80 458	81.52 461	86.66 476	66.61 506	68.44 505	92.79 495	97.92 469	68.96 494	80.04 497	99.85 88	85.77 456	96.15 489	97.86 288	43.89 499	95.39 489

CMPMVS	69.68 23	94.13 437	94.90 417	91.84 466	97.24 464	80.01 496	98.52 462	99.48 205	89.01 478	91.99 483	99.67 243	85.67 457	99.13 403	95.44 420	97.03 362	96.39 484
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testing11		97.50 357	97.10 370	98.71 302	99.20 329	96.91 367	99.29 320	98.82 427	97.89 233	98.21 404	98.40 446	85.63 458	99.83 221	98.45 230	98.04 309	99.37 273

0.3-1-1-0.015		94.79 431	93.69 442	98.10 372	96.99 470	95.46 424	97.02 489	97.61 477	93.53 447	94.03 473	96.54 484	85.60 459	99.86 182	98.43 234	83.45 479	98.99 317

APD_test1		95.87 405	96.49 387	94.00 458	99.53 221	84.01 487	99.54 172	99.32 335	95.91 413	97.99 415	99.85 88	85.49 460	99.88 168	91.96 463	98.84 256	98.12 450

testing91		97.44 364	97.02 373	98.71 302	99.18 335	96.89 369	99.19 361	99.04 395	97.78 251	98.31 396	98.29 451	85.41 461	99.85 190	98.01 277	97.95 311	99.39 269

test_fmvs1_n		98.41 232	98.14 244	99.21 222	99.82 53	97.71 318	99.74 48	99.49 193	99.32 30	99.99 2	99.95 3	85.32 462	99.97 29	99.82 29	99.84 101	99.96 7

MIMVSNet1		95.51 413	95.04 416	96.92 441	97.38 460	95.60 417	99.52 183	99.50 180	93.65 446	96.97 446	99.17 391	85.28 463	96.56 486	88.36 477	95.55 400	98.60 404

testing99		97.36 367	96.94 376	98.63 308	99.18 335	96.70 375	99.30 315	98.93 407	97.71 259	98.23 401	98.26 453	84.92 464	99.84 199	98.04 276	97.85 318	99.35 275

LFMVS		97.90 297	97.35 347	99.54 126	99.52 227	99.01 179	99.39 283	98.24 463	97.10 328	99.65 140	99.79 170	84.79 465	99.91 135	99.28 97	98.38 283	99.69 155

ETVMVS		97.50 357	96.90 377	99.29 209	99.23 322	98.78 238	99.32 309	98.90 417	97.52 285	98.56 376	98.09 461	84.72 466	99.69 296	97.86 288	97.88 315	99.39 269

test_fmvs2		97.25 374	97.30 356	97.09 434	99.43 262	93.31 467	99.73 52	98.87 422	98.83 89	99.28 241	99.80 153	84.45 467	99.66 302	97.88 285	97.45 344	98.30 439

EGC-MVSNET		82.80 458	77.86 464	97.62 416	97.91 450	96.12 399	99.33 306	99.28 350	8.40 503	25.05 504	99.27 380	84.11 468	99.33 364	89.20 473	98.22 297	97.42 477

FMVSNet1		96.84 386	96.36 390	98.29 354	99.32 300	97.26 335	99.43 260	99.48 205	95.11 423	98.55 377	99.32 370	83.95 469	98.98 432	95.81 410	96.26 378	98.62 392

testing3		97.28 372	96.76 381	98.82 286	99.37 283	98.07 294	99.45 247	99.36 305	97.56 278	97.89 421	98.95 419	83.70 470	98.82 449	96.03 405	98.56 274	99.58 212

tt0320		95.71 410	95.07 414	97.62 416	99.05 368	95.02 437	99.25 342	99.52 133	86.81 482	97.97 417	99.72 211	83.58 471	99.15 398	96.38 400	93.35 437	98.68 362

myMVS_eth3d		96.89 384	96.37 389	98.43 341	99.00 375	97.16 339	99.29 320	99.39 286	97.06 332	97.41 431	98.15 456	83.46 472	98.68 455	95.27 425	98.34 284	99.45 258

VDD-MVS		97.73 330	97.35 347	98.88 273	99.47 252	97.12 341	99.34 304	98.85 424	98.19 172	99.67 125	99.85 88	82.98 473	99.92 123	99.49 61	98.32 290	99.60 197

EG-PatchMatch MVS		95.97 404	95.69 405	96.81 443	97.78 453	92.79 470	99.16 365	98.93 407	96.16 401	94.08 472	99.22 386	82.72 474	99.47 332	95.67 416	97.50 339	98.17 447

VDDNet		97.55 351	97.02 373	99.16 227	99.49 244	98.12 291	99.38 288	99.30 344	95.35 419	99.68 119	99.90 36	82.62 475	99.93 108	99.31 86	98.13 306	99.42 262

UniMVSNet_ETH3D		97.32 371	96.81 379	98.87 277	99.40 274	97.46 326	99.51 193	99.53 124	95.86 414	98.54 378	99.77 186	82.44 476	99.66 302	98.68 195	97.52 336	99.50 240

dongtai		93.26 442	92.93 446	94.25 457	99.39 277	85.68 485	97.68 485	93.27 499	92.87 457	96.85 448	99.39 346	82.33 477	97.48 478	76.78 492	97.80 319	99.58 212

testing222		97.16 377	96.50 386	99.16 227	99.16 345	98.47 273	99.27 331	98.66 451	97.71 259	98.23 401	98.15 456	82.28 478	99.84 199	97.36 345	97.66 324	99.18 293

OpenMVS_ROB	92.34 20	94.38 436	93.70 441	96.41 448	97.38 460	93.17 468	99.06 389	98.75 436	86.58 484	94.84 469	98.26 453	81.53 479	99.32 366	89.01 474	97.87 316	96.76 480

kuosan		90.92 451	90.11 455	93.34 461	98.78 409	85.59 486	98.15 480	93.16 501	89.37 477	92.07 482	98.38 447	81.48 480	95.19 491	62.54 499	97.04 361	99.25 288

sc_t1		95.75 408	95.05 415	97.87 392	98.83 403	94.61 448	99.21 356	99.45 251	87.45 481	97.97 417	99.85 88	81.19 481	99.43 345	98.27 250	93.20 441	99.57 215

tt0320-xc		95.31 421	94.59 424	97.45 424	98.92 388	94.73 443	99.20 359	99.31 339	86.74 483	97.23 437	99.72 211	81.14 482	98.95 442	97.08 367	91.98 452	98.67 370

test_method		91.10 449	91.36 450	90.31 471	95.85 481	73.72 504	94.89 492	99.25 362	68.39 495	95.82 458	99.02 410	80.50 483	98.95 442	93.64 447	94.89 416	98.25 443

test_vis1_n		97.92 294	97.44 335	99.34 193	99.53 221	98.08 293	99.74 48	99.49 193	99.15 38	100.00 1	99.94 6	79.51 484	99.98 20	99.88 26	99.76 140	99.97 4

test_vis1_rt		95.81 407	95.65 406	96.32 449	99.67 137	91.35 477	99.49 221	96.74 487	98.25 161	95.24 460	98.10 460	74.96 485	99.90 148	99.53 53	98.85 255	97.70 470

UnsupCasMVSNet_bld		93.53 441	92.51 447	96.58 447	97.38 460	93.82 458	98.24 476	99.48 205	91.10 472	93.10 478	96.66 482	74.89 486	98.37 460	94.03 443	87.71 470	97.56 474

usedtu_dtu_shiyan2		91.34 448	89.96 456	95.47 454	93.61 494	90.81 478	99.15 368	98.68 448	86.37 485	95.19 463	98.27 452	72.64 487	97.05 482	85.40 489	80.32 490	98.54 415

Gipuma		90.99 450	90.15 454	93.51 460	98.73 418	90.12 480	93.98 493	99.45 251	79.32 491	92.28 481	94.91 488	69.61 488	97.98 469	87.42 482	95.67 395	92.45 491
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mvsany_test3		93.77 440	93.45 443	94.74 456	95.78 482	88.01 482	99.64 96	98.25 462	98.28 151	94.31 470	97.97 463	68.89 489	98.51 459	97.50 331	90.37 460	97.71 468

PM-MVS		92.96 444	92.23 448	95.14 455	95.61 483	89.98 481	99.37 290	98.21 465	94.80 433	95.04 466	97.69 467	65.06 490	97.90 471	94.30 437	89.98 463	97.54 475

EMVS		80.02 461	79.22 463	82.43 481	91.19 496	76.40 499	97.55 488	92.49 504	66.36 498	83.01 492	91.27 494	64.63 491	85.79 500	65.82 498	60.65 497	85.08 496

E-PMN		80.61 460	79.88 462	82.81 479	90.75 497	76.38 500	97.69 484	95.76 492	66.44 497	83.52 490	92.25 492	62.54 492	87.16 499	68.53 497	61.40 496	84.89 497

testf1		90.42 452	90.68 452	89.65 474	97.78 453	73.97 502	99.13 372	98.81 429	89.62 475	91.80 485	98.93 421	62.23 493	98.80 451	86.61 486	91.17 455	96.19 485

APD_test2		90.42 452	90.68 452	89.65 474	97.78 453	73.97 502	99.13 372	98.81 429	89.62 475	91.80 485	98.93 421	62.23 493	98.80 451	86.61 486	91.17 455	96.19 485

ambc				93.06 464	92.68 495	82.36 489	98.47 466	98.73 445		95.09 465	97.41 475	55.55 495	99.10 412	96.42 397	91.32 454	97.71 468

test_f		91.90 447	91.26 451	93.84 459	95.52 486	85.92 484	99.69 63	98.53 457	95.31 420	93.87 474	96.37 486	55.33 496	98.27 462	95.70 413	90.98 458	97.32 478

test_fmvs3		92.10 446	91.77 449	93.08 463	96.19 478	86.25 483	99.82 16	98.62 453	96.65 362	95.19 463	96.90 481	55.05 497	95.93 490	96.63 393	90.92 459	97.06 479

FPMVS		84.93 457	85.65 458	82.75 480	86.77 501	63.39 506	98.35 470	98.92 410	74.11 492	83.39 491	98.98 416	50.85 498	92.40 495	84.54 490	94.97 412	92.46 490

PMMVS2		86.87 455	85.37 459	91.35 469	90.21 498	83.80 488	98.89 424	97.45 481	83.13 490	91.67 487	95.03 487	48.49 499	94.70 493	85.86 488	77.62 492	95.54 488

LCM-MVSNet		86.80 456	85.22 460	91.53 468	87.81 500	80.96 494	98.23 478	98.99 401	71.05 493	90.13 488	96.51 485	48.45 500	96.88 484	90.51 468	85.30 473	96.76 480

test_vis3_rt		87.04 454	85.81 457	90.73 470	93.99 493	81.96 491	99.76 38	90.23 505	92.81 458	81.35 493	91.56 493	40.06 501	99.07 414	94.27 439	88.23 469	91.15 493

ANet_high		77.30 462	74.86 466	84.62 478	75.88 504	77.61 498	97.63 486	93.15 502	88.81 479	64.27 499	89.29 496	36.51 502	83.93 501	75.89 494	52.31 498	92.33 492

test123		39.01 467	42.50 469	28.53 484	39.17 507	20.91 509	98.75 441	19.17 509	19.83 502	38.57 501	66.67 499	33.16 503	15.42 503	37.50 502	29.66 501	49.26 498

testmvs		39.17 466	43.78 468	25.37 485	36.04 508	16.84 510	98.36 469	26.56 507	20.06 501	38.51 502	67.32 498	29.64 504	15.30 504	37.59 501	39.90 500	43.98 499

wuyk23d		40.18 465	41.29 470	36.84 483	86.18 502	49.12 508	79.73 496	22.81 508	27.64 500	25.46 503	28.45 503	21.98 505	48.89 502	55.80 500	23.56 502	12.51 500

PMVS	70.75 22	75.98 464	74.97 465	79.01 482	70.98 505	55.18 507	93.37 494	98.21 465	65.08 499	61.78 500	93.83 490	21.74 506	92.53 494	78.59 491	91.12 457	89.34 495
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	76.82 21	76.91 463	74.31 467	84.70 477	85.38 503	76.05 501	96.88 490	93.17 500	67.39 496	71.28 498	89.01 497	21.66 507	87.69 498	71.74 496	72.29 495	90.35 494
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
mmdepth		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.13 471	0.17 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	1.57 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.30 469	11.06 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	99.58 280	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.02 472	0.03 475	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.27 505	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

MED-MVS test				99.87 22	99.88 13	99.81 33	99.69 63	99.87 6	99.34 28	99.90 34	99.83 109		99.95 76	98.83 173	99.89 67	99.83 64

WAC-MVS						97.16 339								95.47 419

FOURS1					99.91 1	99.93 1	99.87 8	99.56 89	99.10 48	99.81 69

MSC_two_6792asdad				99.87 22	99.51 230	99.76 49		99.33 325					99.96 41	98.87 160	99.84 101	99.89 30

No_MVS				99.87 22	99.51 230	99.76 49		99.33 325					99.96 41	98.87 160	99.84 101	99.89 30

eth-test2					0.00 509

eth-test					0.00 509

IU-MVS					99.84 38	99.88 10		99.32 335	98.30 150	99.84 55				98.86 165	99.85 93	99.89 30

save fliter					99.76 82	99.59 89	99.14 371	99.40 283	99.00 67

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 144	99.51 156					99.96 41	98.93 151	99.86 86	99.88 36

GSMVS																99.52 227

test_part2					99.81 57	99.83 22				99.77 85

MTGPA								99.47 227

MTMP							99.54 172	98.88 420

gm-plane-assit					98.54 440	92.96 469			94.65 436		99.15 394		99.64 311	97.56 324

test9_res														97.49 332	99.72 148	99.75 113

agg_prior2														97.21 356	99.73 147	99.75 113

agg_prior					99.67 137	99.62 83		99.40 283		98.87 328			99.91 135

test_prior4						99.56 95	98.99 407

test_prior				99.68 90	99.67 137	99.48 112		99.56 89					99.83 221			99.74 118

旧先验2							98.96 414		96.70 358	99.47 187			99.94 91	98.19 256

新几何2							99.01 404

无先验							98.99 407	99.51 156	96.89 346				99.93 108	97.53 327		99.72 138

原ACMM2							98.95 417

testdata2													99.95 76	96.67 389

testdata1							98.85 428		98.32 148

plane_prior7					99.29 306	97.03 354

plane_prior5								99.47 227					99.69 296	97.78 298	97.63 325	98.67 370

plane_prior4											99.61 271

plane_prior3						97.00 356			98.69 108	99.11 282

plane_prior2							99.39 283		98.97 76

plane_prior1					99.26 314

plane_prior						96.97 359	99.21 356		98.45 131						97.60 328

n2								0.00 510

nn								0.00 510

door-mid								98.05 468

test11								99.35 312

door								97.92 469

HQP5-MVS						96.83 370

HQP-NCC					99.19 332		98.98 410		98.24 163	98.66 359

ACMP_Plane					99.19 332		98.98 410		98.24 163	98.66 359

BP-MVS														97.19 360

HQP4-MVS										98.66 359			99.64 311			98.64 383

HQP3-MVS								99.39 286							97.58 330

NP-MVS					99.23 322	96.92 366					99.40 342

ACMMP++_ref															97.19 358

ACMMP++															97.43 348

High-resolution multi-view benchmark