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.

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 11	98.69 61	98.20 3	99.93 1	99.98 2	96.82 23	100.00 1	99.75 25	100.00 1	99.99 23

patch_mono-2		98.24 52	99.12 5	95.59 207	99.67 77	86.91 323	99.95 45	98.89 45	97.60 16	99.90 2	99.76 62	96.54 28	99.98 43	99.94 11	99.82 76	99.88 81

NCCC		99.37 2	99.25 2	99.71 13	99.96 8	99.15 20	99.97 21	98.62 73	98.02 8	99.90 2	99.95 3	97.33 17	100.00 1	99.54 34	100.00 1	100.00 1

TSAR-MVS + MP.		98.93 14	98.77 16	99.41 37	99.74 69	98.67 46	99.77 131	98.38 144	96.73 45	99.88 4	99.74 73	94.89 59	99.59 139	99.80 22	99.98 32	99.97 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test0726					99.93 24	99.29 14	99.96 28	98.42 129	97.28 25	99.86 5	99.94 4	97.22 19

xiu_mvs_v2_base		98.23 53	97.97 55	99.02 67	98.69 137	98.66 48	99.52 182	98.08 185	97.05 33	99.86 5	99.86 26	90.65 157	99.71 128	99.39 43	98.63 128	98.69 203

test_vis1_n_1920		95.44 154	95.31 145	95.82 203	98.50 147	88.74 302	99.98 11	97.30 257	97.84 11	99.85 7	99.19 130	66.82 336	99.97 53	98.82 67	99.46 102	98.76 199

PS-MVSNAJ		98.44 38	98.20 42	99.16 52	98.80 132	98.92 27	99.54 180	98.17 174	97.34 23	99.85 7	99.85 30	91.20 145	99.89 87	99.41 41	99.67 85	98.69 203

旧先验2							99.46 193		94.21 120	99.85 7			99.95 64	96.96 141

IU-MVS					99.93 24	99.31 9		98.41 133	97.71 13	99.84 10				100.00 1	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 11	99.93 24	99.29 14	99.95 45	98.32 155	97.28 25	99.83 11	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 80
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_THIRD									96.48 51	99.83 11	99.91 14	97.87 6	100.00 1	99.92 12	100.00 1	100.00 1

SF-MVS		98.67 24	98.40 29	99.50 29	99.77 65	98.67 46	99.90 79	98.21 169	93.53 148	99.81 13	99.89 19	94.70 62	99.86 98	99.84 19	99.93 60	99.96 61

SD-MVS		98.92 15	98.70 17	99.56 24	99.70 76	98.73 43	99.94 61	98.34 152	96.38 56	99.81 13	99.76 62	94.59 63	99.98 43	99.84 19	99.96 46	99.97 55
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
test_fmvsm_n_1920		98.44 38	98.61 21	97.92 128	99.27 100	95.18 172	100.00 1	98.90 43	98.05 7	99.80 15	99.73 75	92.64 118	99.99 36	99.58 33	99.51 98	98.59 205

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 9	99.95 45	98.43 118	96.48 51	99.80 15	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

PC_three_1452									96.96 36	99.80 15	99.79 54	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 11	99.96 28	98.43 118	97.27 27	99.80 15	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 118	97.27 27	99.80 15	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 11		98.43 118	97.26 29	99.80 15	99.88 21	96.71 24	100.00 1

MSLP-MVS++		99.13 8	99.01 11	99.49 31	99.94 13	98.46 58	99.98 11	98.86 49	97.10 32	99.80 15	99.94 4	95.92 36	100.00 1	99.51 35	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 47	98.72 136	97.71 76	99.98 11	98.44 110	96.85 38	99.80 15	99.91 14	97.57 8	99.85 99	99.44 39	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
testdata				98.42 108	99.47 91	95.33 164		98.56 81	93.78 141	99.79 23	99.85 30	93.64 93	99.94 72	94.97 168	99.94 54	100.00 1

9.14			98.38 31		99.87 51		99.91 74	98.33 153	93.22 157	99.78 24	99.89 19	94.57 64	99.85 99	99.84 19	99.97 42

SMA-MVS		98.76 21	98.48 26	99.62 19	99.87 51	98.87 31	99.86 104	98.38 144	93.19 158	99.77 25	99.94 4	95.54 42	100.00 1	99.74 27	99.99 21	100.00 1
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
CDPH-MVS		98.65 25	98.36 35	99.49 31	99.94 13	98.73 43	99.87 91	98.33 153	93.97 133	99.76 26	99.87 24	94.99 57	99.75 122	98.55 83	100.00 1	99.98 48

test_one_0601					99.94 13	99.30 11		98.41 133	96.63 48	99.75 27	99.93 11	97.49 10

APD-MVS		98.62 26	98.35 36	99.41 37	99.90 42	98.51 56	99.87 91	98.36 148	94.08 125	99.74 28	99.73 75	94.08 80	99.74 124	99.42 40	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1		95.35 156	95.68 137	94.36 256	98.99 113	84.98 332	99.96 28	96.65 317	97.60 16	99.73 29	98.96 151	71.58 316	99.93 79	98.31 92	99.37 108	98.17 210

test_prior2							99.95 45		95.78 69	99.73 29	99.76 62	96.00 33		99.78 24	100.00 1

TEST9					99.92 31	98.92 27	99.96 28	98.43 118	93.90 138	99.71 31	99.86 26	95.88 37	99.85 99

train_agg		98.88 17	98.65 18	99.59 22	99.92 31	98.92 27	99.96 28	98.43 118	94.35 112	99.71 31	99.86 26	95.94 34	99.85 99	99.69 32	99.98 32	99.99 23

test_8					99.92 31	98.88 30	99.96 28	98.43 118	94.35 112	99.69 33	99.85 30	95.94 34	99.85 99

CS-MVS		97.79 71	97.91 61	97.43 154	99.10 106	94.42 188	99.99 4	97.10 276	95.07 86	99.68 34	99.75 67	92.95 109	98.34 212	98.38 88	99.14 117	99.54 137

test_fmvs1_n		94.25 187	94.36 167	93.92 271	97.68 198	83.70 338	99.90 79	96.57 320	97.40 22	99.67 35	98.88 162	61.82 352	99.92 80	98.23 94	99.13 118	98.14 213

test12				99.43 34	99.74 69	98.56 54		98.40 137		99.65 36		94.76 60	99.75 122		99.98 32	99.99 23

DPE-MVS		99.26 6	99.10 8	99.74 10	99.89 45	99.24 18	99.87 91	98.44 110	97.48 21	99.64 37	99.94 4	96.68 26	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
agg_prior					99.93 24	98.77 39		98.43 118		99.63 38			99.85 99

EC-MVSNet		97.38 88	97.24 81	97.80 133	97.41 209	95.64 153	99.99 4	97.06 281	94.59 102	99.63 38	99.32 118	89.20 179	98.14 226	98.76 71	99.23 114	99.62 119

xiu_mvs_v1_base_debu		97.43 81	97.06 86	98.55 95	97.74 190	98.14 61	99.31 211	97.86 206	96.43 53	99.62 40	99.69 84	85.56 210	99.68 132	99.05 51	98.31 135	97.83 216

CS-MVS-test		97.88 63	97.94 59	97.70 142	99.28 99	95.20 171	99.98 11	97.15 271	95.53 77	99.62 40	99.79 54	92.08 134	98.38 208	98.75 72	99.28 112	99.52 141

xiu_mvs_v1_base		97.43 81	97.06 86	98.55 95	97.74 190	98.14 61	99.31 211	97.86 206	96.43 53	99.62 40	99.69 84	85.56 210	99.68 132	99.05 51	98.31 135	97.83 216

xiu_mvs_v1_base_debi		97.43 81	97.06 86	98.55 95	97.74 190	98.14 61	99.31 211	97.86 206	96.43 53	99.62 40	99.69 84	85.56 210	99.68 132	99.05 51	98.31 135	97.83 216

原ACMM1				98.96 72	99.73 72	96.99 106		98.51 96	94.06 128	99.62 40	99.85 30	94.97 58	99.96 57	95.11 164	99.95 49	99.92 77

PHI-MVS		98.41 41	98.21 41	99.03 65	99.86 53	97.10 102	99.98 11	98.80 55	90.78 239	99.62 40	99.78 58	95.30 47	100.00 1	99.80 22	99.93 60	99.99 23

mvsany_test1		97.82 68	97.90 62	97.55 147	98.77 134	93.04 222	99.80 125	97.93 197	96.95 37	99.61 46	99.68 88	90.92 152	99.83 108	99.18 47	98.29 138	99.80 91

test_cas_vis1_n_1920		96.59 117	96.23 111	97.65 143	98.22 162	94.23 192	99.99 4	97.25 262	97.77 12	99.58 47	99.08 136	77.10 278	99.97 53	97.64 123	99.45 103	98.74 201

DPM-MVS		98.83 19	98.46 27	99.97 1	99.33 97	99.92 1	99.96 28	98.44 110	97.96 9	99.55 48	99.94 4	97.18 21	100.00 1	93.81 199	99.94 54	99.98 48

新几何1				99.42 36	99.75 68	98.27 60		98.63 72	92.69 175	99.55 48	99.82 46	94.40 67	100.00 1	91.21 234	99.94 54	99.99 23

test_vis1_n		93.61 202	93.03 203	95.35 214	95.86 262	86.94 321	99.87 91	96.36 327	96.85 38	99.54 50	98.79 171	52.41 365	99.83 108	98.64 79	98.97 121	99.29 172

ACMMP_NAP		98.49 34	98.14 46	99.54 26	99.66 78	98.62 52	99.85 107	98.37 147	94.68 100	99.53 51	99.83 43	92.87 111	100.00 1	98.66 78	99.84 71	99.99 23

PMMVS		96.76 108	96.76 97	96.76 176	98.28 158	92.10 243	99.91 74	97.98 192	94.12 123	99.53 51	99.39 114	86.93 199	98.73 178	96.95 142	97.73 150	99.45 151

FOURS1					99.92 31	97.66 80	99.95 45	98.36 148	95.58 75	99.52 53

MSP-MVS		99.09 9	99.12 5	98.98 70	99.93 24	97.24 95	99.95 45	98.42 129	97.50 20	99.52 53	99.88 21	97.43 16	99.71 128	99.50 36	99.98 32	100.00 1
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
test_part2					99.89 45	99.25 17				99.49 55

APDe-MVS		99.06 11	98.91 14	99.51 28	99.94 13	98.76 42	99.91 74	98.39 140	97.20 31	99.46 56	99.85 30	95.53 44	99.79 113	99.86 18	100.00 1	99.99 23

region2R		98.54 30	98.37 33	99.05 63	99.96 8	97.18 98	99.96 28	98.55 87	94.87 93	99.45 57	99.85 30	94.07 81	100.00 1	98.67 76	100.00 1	99.98 48

HPM-MVS++		99.07 10	98.88 15	99.63 16	99.90 42	99.02 24	99.95 45	98.56 81	97.56 19	99.44 58	99.85 30	95.38 46	100.00 1	99.31 44	99.99 21	99.87 83

MVSFormer		96.94 100	96.60 101	97.95 126	97.28 219	97.70 78	99.55 178	97.27 260	91.17 228	99.43 59	99.54 102	90.92 152	96.89 293	94.67 180	99.62 88	99.25 175

lupinMVS		97.85 65	97.60 70	98.62 88	97.28 219	97.70 78	99.99 4	97.55 230	95.50 79	99.43 59	99.67 89	90.92 152	98.71 181	98.40 87	99.62 88	99.45 151

XVS		98.70 23	98.55 23	99.15 54	99.94 13	97.50 87	99.94 61	98.42 129	96.22 61	99.41 61	99.78 58	94.34 72	99.96 57	98.92 60	99.95 49	99.99 23

X-MVStestdata		93.83 192	92.06 224	99.15 54	99.94 13	97.50 87	99.94 61	98.42 129	96.22 61	99.41 61	41.37 385	94.34 72	99.96 57	98.92 60	99.95 49	99.99 23

SR-MVS-dyc-post		98.31 45	98.17 44	98.71 82	99.79 62	96.37 126	99.76 136	98.31 157	94.43 107	99.40 63	99.75 67	93.28 101	99.78 115	98.90 63	99.92 63	99.97 55

RE-MVS-def			98.13 47		99.79 62	96.37 126	99.76 136	98.31 157	94.43 107	99.40 63	99.75 67	92.95 109		98.90 63	99.92 63	99.97 55

APD-MVS_3200maxsize		98.25 51	98.08 51	98.78 79	99.81 60	96.60 118	99.82 119	98.30 160	93.95 135	99.37 65	99.77 60	92.84 112	99.76 121	98.95 57	99.92 63	99.97 55

PGM-MVS		98.34 44	98.13 47	98.99 69	99.92 31	97.00 105	99.75 139	99.50 17	93.90 138	99.37 65	99.76 62	93.24 103	100.00 1	97.75 122	99.96 46	99.98 48

SR-MVS		98.46 36	98.30 39	98.93 74	99.88 49	97.04 103	99.84 111	98.35 150	94.92 91	99.32 67	99.80 51	93.35 96	99.78 115	99.30 45	99.95 49	99.96 61

ZD-MVS					99.92 31	98.57 53		98.52 93	92.34 194	99.31 68	99.83 43	95.06 52	99.80 111	99.70 31	99.97 42

HFP-MVS		98.56 29	98.37 33	99.14 56	99.96 8	97.43 91	99.95 45	98.61 74	94.77 95	99.31 68	99.85 30	94.22 76	100.00 1	98.70 74	99.98 32	99.98 48

ACMMPR		98.50 33	98.32 37	99.05 63	99.96 8	97.18 98	99.95 45	98.60 75	94.77 95	99.31 68	99.84 41	93.73 90	100.00 1	98.70 74	99.98 32	99.98 48

ETV-MVS		97.92 62	97.80 65	98.25 115	98.14 169	96.48 120	99.98 11	97.63 219	95.61 74	99.29 71	99.46 108	92.55 122	98.82 171	99.02 56	98.54 129	99.46 149

test222					99.55 85	97.41 93	99.34 207	98.55 87	91.86 207	99.27 72	99.83 43	93.84 88			99.95 49	99.99 23

CANet_DTU		96.76 108	96.15 113	98.60 90	98.78 133	97.53 83	99.84 111	97.63 219	97.25 30	99.20 73	99.64 93	81.36 243	99.98 43	92.77 219	98.89 122	98.28 209

EPNet		98.49 34	98.40 29	98.77 80	99.62 80	96.80 113	99.90 79	99.51 16	97.60 16	99.20 73	99.36 117	93.71 91	99.91 81	97.99 107	98.71 127	99.61 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	95.94 2	97.71 75	98.98 12	93.92 271	99.63 79	81.76 350	99.96 28	98.56 81	99.47 1	99.19 75	99.99 1	94.16 79	100.00 1	99.92 12	99.93 60	100.00 1

VNet		97.21 93	96.57 103	99.13 60	98.97 115	97.82 74	99.03 245	99.21 28	94.31 115	99.18 76	98.88 162	86.26 206	99.89 87	98.93 59	94.32 208	99.69 105

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 21	98.64 69	98.47 2	99.13 77	99.92 13	96.38 30	100.00 1	99.74 27	100.00 1	100.00 1

DeepC-MVS_fast	96.59 1	98.81 20	98.54 24	99.62 19	99.90 42	98.85 33	99.24 220	98.47 103	98.14 5	99.08 78	99.91 14	93.09 106	100.00 1	99.04 54	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
114514_t		97.41 86	96.83 94	99.14 56	99.51 89	97.83 73	99.89 86	98.27 164	88.48 279	99.06 79	99.66 91	90.30 162	99.64 138	96.32 150	99.97 42	99.96 61

PVSNet	91.05 13	97.13 94	96.69 99	98.45 105	99.52 87	95.81 144	99.95 45	99.65 11	94.73 97	99.04 80	99.21 129	84.48 220	99.95 64	94.92 170	98.74 126	99.58 131

CHOSEN 280x420		99.01 13	99.03 10	98.95 73	99.38 95	98.87 31	98.46 290	99.42 21	97.03 34	99.02 81	99.09 135	99.35 1	98.21 224	99.73 29	99.78 79	99.77 96

MG-MVS		98.91 16	98.65 18	99.68 14	99.94 13	99.07 23	99.64 164	99.44 19	97.33 24	99.00 82	99.72 78	94.03 82	99.98 43	98.73 73	100.00 1	100.00 1

diffmvs		97.00 98	96.64 100	98.09 122	97.64 199	96.17 136	99.81 121	97.19 265	94.67 101	98.95 83	99.28 119	86.43 203	98.76 176	98.37 89	97.42 158	99.33 166
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS_fast		97.80 70	97.50 73	98.68 84	99.79 62	96.42 122	99.88 88	98.16 178	91.75 212	98.94 84	99.54 102	91.82 140	99.65 137	97.62 125	99.99 21	99.99 23

dcpmvs_2		97.42 85	98.09 50	95.42 212	99.58 84	87.24 319	99.23 221	96.95 293	94.28 117	98.93 85	99.73 75	94.39 70	99.16 160	99.89 16	99.82 76	99.86 85

CP-MVS		98.45 37	98.32 37	98.87 76	99.96 8	96.62 117	99.97 21	98.39 140	94.43 107	98.90 86	99.87 24	94.30 74	100.00 1	99.04 54	99.99 21	99.99 23

MVS_Test		96.46 121	95.74 134	98.61 89	98.18 166	97.23 96	99.31 211	97.15 271	91.07 232	98.84 87	97.05 235	88.17 188	98.97 165	94.39 184	97.50 155	99.61 122

API-MVS		97.86 64	97.66 67	98.47 103	99.52 87	95.41 161	99.47 191	98.87 48	91.68 213	98.84 87	99.85 30	92.34 128	99.99 36	98.44 86	99.96 46	100.00 1

GST-MVS		98.27 48	97.97 55	99.17 50	99.92 31	97.57 82	99.93 67	98.39 140	94.04 131	98.80 89	99.74 73	92.98 108	100.00 1	98.16 97	99.76 80	99.93 72

MVS_111021_LR		98.42 40	98.38 31	98.53 100	99.39 94	95.79 145	99.87 91	99.86 2	96.70 46	98.78 90	99.79 54	92.03 135	99.90 83	99.17 48	99.86 70	99.88 81

h-mvs33		94.92 164	94.36 167	96.59 182	98.85 129	91.29 264	98.93 254	98.94 38	95.90 66	98.77 91	98.42 195	90.89 155	99.77 118	97.80 115	70.76 354	98.72 202

hse-mvs2		94.38 181	94.08 174	95.31 217	98.27 159	90.02 288	99.29 216	98.56 81	95.90 66	98.77 91	98.00 204	90.89 155	98.26 222	97.80 115	69.20 360	97.64 221

TSAR-MVS + GP.		98.60 27	98.51 25	98.86 77	99.73 72	96.63 116	99.97 21	97.92 200	98.07 6	98.76 93	99.55 100	95.00 56	99.94 72	99.91 15	97.68 152	99.99 23

sss		97.57 78	97.03 90	99.18 47	98.37 153	98.04 66	99.73 147	99.38 22	93.46 150	98.76 93	99.06 138	91.21 144	99.89 87	96.33 149	97.01 169	99.62 119

MVS_0304		98.87 18	98.61 21	99.67 15	99.18 101	99.13 21	99.87 91	99.65 11	98.17 4	98.75 95	99.75 67	92.76 115	99.94 72	99.88 17	99.44 104	99.94 70

CostFormer		96.10 133	95.88 131	96.78 175	97.03 225	92.55 235	97.08 327	97.83 209	90.04 251	98.72 96	94.89 313	95.01 55	98.29 216	96.54 148	95.77 191	99.50 145

tpmrst		96.27 132	95.98 119	97.13 166	97.96 176	93.15 218	96.34 339	98.17 174	92.07 200	98.71 97	95.12 304	93.91 85	98.73 178	94.91 172	96.62 174	99.50 145

MVS_111021_HR		98.72 22	98.62 20	99.01 68	99.36 96	97.18 98	99.93 67	99.90 1	96.81 43	98.67 98	99.77 60	93.92 84	99.89 87	99.27 46	99.94 54	99.96 61

MAR-MVS		97.43 81	97.19 83	98.15 120	99.47 91	94.79 182	99.05 242	98.76 56	92.65 178	98.66 99	99.82 46	88.52 186	99.98 43	98.12 99	99.63 87	99.67 108
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
Effi-MVS+		96.30 129	95.69 135	98.16 117	97.85 183	96.26 129	97.41 319	97.21 264	90.37 244	98.65 100	98.58 182	86.61 202	98.70 182	97.11 135	97.37 160	99.52 141

HPM-MVS		97.96 59	97.72 66	98.68 84	99.84 56	96.39 125	99.90 79	98.17 174	92.61 180	98.62 101	99.57 99	91.87 138	99.67 135	98.87 65	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		98.39 43	98.20 42	98.97 71	99.97 3	96.92 109	99.95 45	98.38 144	95.04 87	98.61 102	99.80 51	93.39 95	100.00 1	98.64 79	100.00 1	99.98 48

jason		97.24 91	96.86 93	98.38 111	95.73 269	97.32 94	99.97 21	97.40 248	95.34 82	98.60 103	99.54 102	87.70 190	98.56 189	97.94 110	99.47 100	99.25 175
jason: jason.
CANet		98.27 48	97.82 64	99.63 16	99.72 74	99.10 22	99.98 11	98.51 96	97.00 35	98.52 104	99.71 80	87.80 189	99.95 64	99.75 25	99.38 107	99.83 87

EI-MVSNet-Vis-set		98.27 48	98.11 49	98.75 81	99.83 57	96.59 119	99.40 197	98.51 96	95.29 83	98.51 105	99.76 62	93.60 94	99.71 128	98.53 84	99.52 96	99.95 68

ZNCC-MVS		98.31 45	98.03 52	99.17 50	99.88 49	97.59 81	99.94 61	98.44 110	94.31 115	98.50 106	99.82 46	93.06 107	99.99 36	98.30 93	99.99 21	99.93 72

LFMVS		94.75 170	93.56 189	98.30 113	99.03 109	95.70 151	98.74 273	97.98 192	87.81 289	98.47 107	99.39 114	67.43 334	99.53 140	98.01 105	95.20 202	99.67 108

tpm2		95.47 153	95.18 150	96.35 191	96.91 231	91.70 257	96.96 330	97.93 197	88.04 286	98.44 108	95.40 290	93.32 98	97.97 235	94.00 191	95.61 195	99.38 158

alignmvs		97.81 69	97.33 79	99.25 42	98.77 134	98.66 48	99.99 4	98.44 110	94.40 111	98.41 109	99.47 106	93.65 92	99.42 152	98.57 82	94.26 209	99.67 108

UA-Net		96.54 118	95.96 123	98.27 114	98.23 161	95.71 150	98.00 312	98.45 106	93.72 144	98.41 109	99.27 122	88.71 185	99.66 136	91.19 235	97.69 151	99.44 153

DP-MVS Recon		98.41 41	98.02 53	99.56 24	99.97 3	98.70 45	99.92 70	98.44 110	92.06 202	98.40 111	99.84 41	95.68 40	100.00 1	98.19 95	99.71 83	99.97 55

CPTT-MVS		97.64 77	97.32 80	98.58 93	99.97 3	95.77 146	99.96 28	98.35 150	89.90 252	98.36 112	99.79 54	91.18 148	99.99 36	98.37 89	99.99 21	99.99 23

PAPM		98.60 27	98.42 28	99.14 56	96.05 256	98.96 25	99.90 79	99.35 24	96.68 47	98.35 113	99.66 91	96.45 29	98.51 192	99.45 38	99.89 66	99.96 61

HY-MVS	92.50 7	97.79 71	97.17 85	99.63 16	98.98 114	99.32 8	97.49 318	99.52 14	95.69 72	98.32 114	97.41 222	93.32 98	99.77 118	98.08 103	95.75 193	99.81 89

EI-MVSNet-UG-set		98.14 55	97.99 54	98.60 90	99.80 61	96.27 128	99.36 206	98.50 101	95.21 85	98.30 115	99.75 67	93.29 100	99.73 127	98.37 89	99.30 111	99.81 89

PVSNet_BlendedMVS		96.05 135	95.82 133	96.72 178	99.59 81	96.99 106	99.95 45	99.10 29	94.06 128	98.27 116	95.80 271	89.00 181	99.95 64	99.12 49	87.53 264	93.24 323

PVSNet_Blended		97.94 60	97.64 68	98.83 78	99.59 81	96.99 106	100.00 1	99.10 29	95.38 80	98.27 116	99.08 136	89.00 181	99.95 64	99.12 49	99.25 113	99.57 132

MP-MVS		98.23 53	97.97 55	99.03 65	99.94 13	97.17 101	99.95 45	98.39 140	94.70 99	98.26 118	99.81 50	91.84 139	100.00 1	98.85 66	99.97 42	99.93 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
WTY-MVS		98.10 57	97.60 70	99.60 21	98.92 121	99.28 16	99.89 86	99.52 14	95.58 75	98.24 119	99.39 114	93.33 97	99.74 124	97.98 109	95.58 196	99.78 95

DELS-MVS		98.54 30	98.22 40	99.50 29	99.15 105	98.65 50	100.00 1	98.58 77	97.70 14	98.21 120	99.24 127	92.58 121	99.94 72	98.63 81	99.94 54	99.92 77
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
MDTV_nov1_ep13_2view						96.26 129	96.11 344		91.89 206	98.06 121		94.40 67		94.30 187		99.67 108

PAPR		98.52 32	98.16 45	99.58 23	99.97 3	98.77 39	99.95 45	98.43 118	95.35 81	98.03 122	99.75 67	94.03 82	99.98 43	98.11 100	99.83 72	99.99 23

MDTV_nov1_ep13			95.69 135		97.90 179	94.15 193	95.98 347	98.44 110	93.12 160	97.98 123	95.74 273	95.10 50	98.58 188	90.02 259	96.92 171

test2506		97.53 79	97.19 83	98.58 93	98.66 139	96.90 110	98.81 268	99.77 5	94.93 89	97.95 124	98.96 151	92.51 123	99.20 156	94.93 169	98.15 140	99.64 114

GG-mvs-BLEND				98.54 98	98.21 163	98.01 67	93.87 357	98.52 93		97.92 125	97.92 210	99.02 2	97.94 240	98.17 96	99.58 93	99.67 108

EIA-MVS		97.53 79	97.46 74	97.76 139	98.04 173	94.84 179	99.98 11	97.61 224	94.41 110	97.90 126	99.59 96	92.40 126	98.87 169	98.04 104	99.13 118	99.59 125

test_yl		97.83 66	97.37 77	99.21 44	99.18 101	97.98 69	99.64 164	99.27 26	91.43 221	97.88 127	98.99 145	95.84 38	99.84 106	98.82 67	95.32 200	99.79 92

DCV-MVSNet		97.83 66	97.37 77	99.21 44	99.18 101	97.98 69	99.64 164	99.27 26	91.43 221	97.88 127	98.99 145	95.84 38	99.84 106	98.82 67	95.32 200	99.79 92

canonicalmvs		97.09 97	96.32 109	99.39 39	98.93 119	98.95 26	99.72 150	97.35 251	94.45 105	97.88 127	99.42 110	86.71 200	99.52 141	98.48 85	93.97 213	99.72 102

VDDNet		93.12 213	91.91 228	96.76 176	96.67 246	92.65 233	98.69 279	98.21 169	82.81 339	97.75 130	99.28 119	61.57 353	99.48 149	98.09 102	94.09 211	98.15 211

EPMVS		96.53 119	96.01 116	98.09 122	98.43 150	96.12 139	96.36 338	99.43 20	93.53 148	97.64 131	95.04 306	94.41 66	98.38 208	91.13 236	98.11 143	99.75 98

JIA-IIPM		91.76 246	90.70 246	94.94 228	96.11 254	87.51 317	93.16 360	98.13 182	75.79 359	97.58 132	77.68 373	92.84 112	97.97 235	88.47 275	96.54 175	99.33 166

EPNet_dtu		95.71 146	95.39 142	96.66 180	98.92 121	93.41 214	99.57 174	98.90 43	96.19 63	97.52 133	98.56 184	92.65 117	97.36 257	77.89 343	98.33 134	99.20 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		98.12 56	97.93 60	98.70 83	99.94 13	96.13 137	99.82 119	98.43 118	94.56 103	97.52 133	99.70 82	94.40 67	99.98 43	97.00 139	99.98 32	99.99 23

FE-MVS		95.70 148	95.01 156	97.79 135	98.21 163	94.57 184	95.03 352	98.69 61	88.90 270	97.50 135	96.19 262	92.60 120	99.49 148	89.99 260	97.94 149	99.31 168

thisisatest0515		97.41 86	97.02 91	98.59 92	97.71 197	97.52 84	99.97 21	98.54 90	91.83 208	97.45 136	99.04 139	97.50 9	99.10 162	94.75 177	96.37 180	99.16 180

OMC-MVS		97.28 89	97.23 82	97.41 155	99.76 66	93.36 217	99.65 160	97.95 195	96.03 65	97.41 137	99.70 82	89.61 170	99.51 142	96.73 146	98.25 139	99.38 158

gg-mvs-nofinetune		93.51 204	91.86 230	98.47 103	97.72 195	97.96 71	92.62 361	98.51 96	74.70 363	97.33 138	69.59 376	98.91 3	97.79 244	97.77 120	99.56 94	99.67 108

PatchT		90.38 271	88.75 286	95.25 219	95.99 258	90.16 284	91.22 368	97.54 232	76.80 355	97.26 139	86.01 367	91.88 137	96.07 327	66.16 368	95.91 188	99.51 143

PLC	95.54 3	97.93 61	97.89 63	98.05 124	99.82 58	94.77 183	99.92 70	98.46 105	93.93 136	97.20 140	99.27 122	95.44 45	99.97 53	97.41 127	99.51 98	99.41 156
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		98.29 47	97.96 58	99.30 41	99.85 54	97.93 72	99.39 201	98.28 162	95.76 70	97.18 141	99.88 21	92.74 116	100.00 1	98.67 76	99.88 68	99.99 23

PatchmatchNet		95.94 139	95.45 140	97.39 157	97.83 184	94.41 189	96.05 345	98.40 137	92.86 164	97.09 142	95.28 301	94.21 78	98.07 231	89.26 266	98.11 143	99.70 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		97.10 95	96.72 98	98.22 116	97.60 201	96.70 114	99.92 70	98.54 90	91.11 231	97.07 143	98.97 149	97.47 12	99.03 163	93.73 204	96.09 183	98.92 190

test_fmvsmvis_n_1920		97.67 76	97.59 72	97.91 130	97.02 226	95.34 163	99.95 45	98.45 106	97.87 10	97.02 144	99.59 96	89.64 169	99.98 43	99.41 41	99.34 110	98.42 206

CR-MVSNet		93.45 207	92.62 211	95.94 199	96.29 249	92.66 231	92.01 364	96.23 329	92.62 179	96.94 145	93.31 337	91.04 149	96.03 328	79.23 336	95.96 186	99.13 184

RPMNet		89.76 285	87.28 300	97.19 165	96.29 249	92.66 231	92.01 364	98.31 157	70.19 369	96.94 145	85.87 368	87.25 195	99.78 115	62.69 371	95.96 186	99.13 184

baseline		96.43 122	95.98 119	97.76 139	97.34 213	95.17 173	99.51 184	97.17 268	93.92 137	96.90 147	99.28 119	85.37 214	98.64 186	97.50 126	96.86 173	99.46 149

ECVR-MVS		95.66 149	95.05 154	97.51 150	98.66 139	93.71 205	98.85 265	98.45 106	94.93 89	96.86 148	98.96 151	75.22 299	99.20 156	95.34 161	98.15 140	99.64 114

Vis-MVSNet		95.72 144	95.15 151	97.45 152	97.62 200	94.28 191	99.28 217	98.24 166	94.27 119	96.84 149	98.94 158	79.39 262	98.76 176	93.25 209	98.49 130	99.30 170
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
VDD-MVS		93.77 196	92.94 204	96.27 193	98.55 143	90.22 283	98.77 272	97.79 211	90.85 237	96.82 150	99.42 110	61.18 355	99.77 118	98.95 57	94.13 210	98.82 196

UGNet		95.33 157	94.57 164	97.62 146	98.55 143	94.85 178	98.67 281	99.32 25	95.75 71	96.80 151	96.27 260	72.18 313	99.96 57	94.58 182	99.05 120	98.04 214
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
AdaColmap		97.23 92	96.80 96	98.51 101	99.99 1	95.60 155	99.09 231	98.84 52	93.32 154	96.74 152	99.72 78	86.04 207	100.00 1	98.01 105	99.43 106	99.94 70

tpm		93.70 200	93.41 195	94.58 243	95.36 280	87.41 318	97.01 328	96.90 300	90.85 237	96.72 153	94.14 329	90.40 161	96.84 296	90.75 247	88.54 247	99.51 143

test1111		95.57 151	94.98 157	97.37 158	98.56 141	93.37 216	98.86 263	98.45 106	94.95 88	96.63 154	98.95 156	75.21 300	99.11 161	95.02 167	98.14 142	99.64 114

tttt0517		96.85 103	96.49 105	97.92 128	97.48 207	95.89 143	99.85 107	98.54 90	90.72 240	96.63 154	98.93 160	97.47 12	99.02 164	93.03 216	95.76 192	98.85 194

casdiffmvs		96.42 124	95.97 122	97.77 138	97.30 217	94.98 175	99.84 111	97.09 278	93.75 143	96.58 156	99.26 125	85.07 216	98.78 174	97.77 120	97.04 167	99.54 137
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		97.76 73	97.38 76	98.92 75	99.53 86	96.84 111	99.87 91	98.14 181	93.78 141	96.55 157	99.69 84	92.28 129	99.98 43	97.13 134	99.44 104	99.93 72

PatchMatch-RL		96.04 136	95.40 141	97.95 126	99.59 81	95.22 170	99.52 182	99.07 32	93.96 134	96.49 158	98.35 196	82.28 234	99.82 110	90.15 258	99.22 115	98.81 197

MP-MVS-pluss		98.07 58	97.64 68	99.38 40	99.74 69	98.41 59	99.74 142	98.18 173	93.35 152	96.45 159	99.85 30	92.64 118	99.97 53	98.91 62	99.89 66	99.77 96
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ADS-MVSNet2		93.80 195	93.88 180	93.55 285	97.87 181	85.94 326	94.24 353	96.84 305	90.07 249	96.43 160	94.48 324	90.29 163	95.37 337	87.44 285	97.23 161	99.36 161

ADS-MVSNet		94.79 167	94.02 175	97.11 168	97.87 181	93.79 202	94.24 353	98.16 178	90.07 249	96.43 160	94.48 324	90.29 163	98.19 225	87.44 285	97.23 161	99.36 161

ACMMP		97.74 74	97.44 75	98.66 86	99.92 31	96.13 137	99.18 225	99.45 18	94.84 94	96.41 162	99.71 80	91.40 142	99.99 36	97.99 107	98.03 147	99.87 83
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
PVSNet_Blended_VisFu		97.27 90	96.81 95	98.66 86	98.81 131	96.67 115	99.92 70	98.64 69	94.51 104	96.38 163	98.49 188	89.05 180	99.88 93	97.10 136	98.34 133	99.43 154

AUN-MVS		93.28 208	92.60 212	95.34 215	98.29 156	90.09 286	99.31 211	98.56 81	91.80 211	96.35 164	98.00 204	89.38 173	98.28 218	92.46 220	69.22 359	97.64 221

FA-MVS(test-final)		95.86 140	95.09 153	98.15 120	97.74 190	95.62 154	96.31 340	98.17 174	91.42 223	96.26 165	96.13 265	90.56 159	99.47 150	92.18 224	97.07 165	99.35 163

thres200		96.96 99	96.21 112	99.22 43	98.97 115	98.84 34	99.85 107	99.71 6	93.17 159	96.26 165	98.88 162	89.87 167	99.51 142	94.26 188	94.91 203	99.31 168

HyFIR lowres test		96.66 115	96.43 107	97.36 160	99.05 108	93.91 201	99.70 152	99.80 3	90.54 241	96.26 165	98.08 201	92.15 132	98.23 223	96.84 145	95.46 197	99.93 72

SCA		94.69 171	93.81 182	97.33 162	97.10 222	94.44 186	98.86 263	98.32 155	93.30 155	96.17 168	95.59 280	76.48 286	97.95 238	91.06 238	97.43 156	99.59 125

casdiffmvs_mvg		96.43 122	95.94 126	97.89 132	97.44 208	95.47 157	99.86 104	97.29 258	93.35 152	96.03 169	99.19 130	85.39 213	98.72 180	97.89 114	97.04 167	99.49 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tfpn200view9		96.79 106	95.99 117	99.19 46	98.94 117	98.82 35	99.78 128	99.71 6	92.86 164	96.02 170	98.87 165	89.33 174	99.50 144	93.84 196	94.57 204	99.27 173

thres400		96.78 107	95.99 117	99.16 52	98.94 117	98.82 35	99.78 128	99.71 6	92.86 164	96.02 170	98.87 165	89.33 174	99.50 144	93.84 196	94.57 204	99.16 180

dp		95.05 161	94.43 166	96.91 171	97.99 175	92.73 229	96.29 341	97.98 192	89.70 255	95.93 172	94.67 319	93.83 89	98.45 197	86.91 297	96.53 176	99.54 137

thres100view900		96.74 110	95.92 129	99.18 47	98.90 126	98.77 39	99.74 142	99.71 6	92.59 182	95.84 173	98.86 167	89.25 176	99.50 144	93.84 196	94.57 204	99.27 173

thres600view7		96.69 113	95.87 132	99.14 56	98.90 126	98.78 38	99.74 142	99.71 6	92.59 182	95.84 173	98.86 167	89.25 176	99.50 144	93.44 208	94.50 207	99.16 180

EPP-MVSNet		96.69 113	96.60 101	96.96 170	97.74 190	93.05 221	99.37 204	98.56 81	88.75 273	95.83 175	99.01 142	96.01 32	98.56 189	96.92 143	97.20 163	99.25 175

TESTMET0.1,1		96.74 110	96.26 110	98.16 117	97.36 212	96.48 120	99.96 28	98.29 161	91.93 205	95.77 176	98.07 202	95.54 42	98.29 216	90.55 250	98.89 122	99.70 103

F-COLMAP		96.93 101	96.95 92	96.87 173	99.71 75	91.74 253	99.85 107	97.95 195	93.11 161	95.72 177	99.16 133	92.35 127	99.94 72	95.32 162	99.35 109	98.92 190

test-LLR		96.47 120	96.04 115	97.78 136	97.02 226	95.44 158	99.96 28	98.21 169	94.07 126	95.55 178	96.38 256	93.90 86	98.27 220	90.42 253	98.83 124	99.64 114

test-mter		96.39 125	95.93 127	97.78 136	97.02 226	95.44 158	99.96 28	98.21 169	91.81 210	95.55 178	96.38 256	95.17 48	98.27 220	90.42 253	98.83 124	99.64 114

IS-MVSNet		96.29 130	95.90 130	97.45 152	98.13 170	94.80 181	99.08 233	97.61 224	92.02 204	95.54 180	98.96 151	90.64 158	98.08 229	93.73 204	97.41 159	99.47 148

CHOSEN 1792x2688		96.81 105	96.53 104	97.64 144	98.91 125	93.07 219	99.65 160	99.80 3	95.64 73	95.39 181	98.86 167	84.35 223	99.90 83	96.98 140	99.16 116	99.95 68

CDS-MVSNet		96.34 126	96.07 114	97.13 166	97.37 211	94.96 176	99.53 181	97.91 201	91.55 216	95.37 182	98.32 197	95.05 53	97.13 275	93.80 200	95.75 193	99.30 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		94.53 178	95.30 146	92.22 304	97.77 188	82.54 343	99.59 170	97.06 281	94.92 91	95.29 183	95.37 294	85.81 208	97.89 241	94.80 175	97.07 165	96.23 234

CSCG		97.10 95	97.04 89	97.27 164	99.89 45	91.92 248	99.90 79	99.07 32	88.67 275	95.26 184	99.82 46	93.17 105	99.98 43	98.15 98	99.47 100	99.90 79

Vis-MVSNet (Re-imp)		96.32 127	95.98 119	97.35 161	97.93 178	94.82 180	99.47 191	98.15 180	91.83 208	95.09 185	99.11 134	91.37 143	97.47 255	93.47 207	97.43 156	99.74 99

TAMVS		95.85 141	95.58 138	96.65 181	97.07 223	93.50 210	99.17 226	97.82 210	91.39 225	95.02 186	98.01 203	92.20 130	97.30 264	93.75 203	95.83 190	99.14 183

XVG-OURS-SEG-HR		94.79 167	94.70 163	95.08 223	98.05 172	89.19 297	99.08 233	97.54 232	93.66 145	94.87 187	99.58 98	78.78 268	99.79 113	97.31 129	93.40 217	96.25 232

XVG-OURS		94.82 165	94.74 162	95.06 224	98.00 174	89.19 297	99.08 233	97.55 230	94.10 124	94.71 188	99.62 94	80.51 254	99.74 124	96.04 154	93.06 222	96.25 232

ab-mvs		94.69 171	93.42 193	98.51 101	98.07 171	96.26 129	96.49 336	98.68 63	90.31 246	94.54 189	97.00 237	76.30 288	99.71 128	95.98 155	93.38 218	99.56 133

TAPA-MVS	92.12 8	94.42 180	93.60 186	96.90 172	99.33 97	91.78 252	99.78 128	98.00 189	89.89 253	94.52 190	99.47 106	91.97 136	99.18 158	69.90 360	99.52 96	99.73 100
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TR-MVS		94.54 176	93.56 189	97.49 151	97.96 176	94.34 190	98.71 276	97.51 237	90.30 247	94.51 191	98.69 174	75.56 294	98.77 175	92.82 218	95.99 185	99.35 163

Fast-Effi-MVS+		95.02 162	94.19 171	97.52 149	97.88 180	94.55 185	99.97 21	97.08 279	88.85 272	94.47 192	97.96 209	84.59 219	98.41 200	89.84 262	97.10 164	99.59 125

DeepC-MVS	94.51 4	96.92 102	96.40 108	98.45 105	99.16 104	95.90 142	99.66 158	98.06 186	96.37 59	94.37 193	99.49 105	83.29 230	99.90 83	97.63 124	99.61 91	99.55 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		91.80 243	92.79 209	88.83 331	98.15 168	69.87 367	98.11 308	96.60 319	83.93 331	94.33 194	99.27 122	79.60 261	99.46 151	91.99 225	93.16 220	97.18 228

BH-RMVSNet		95.18 158	94.31 170	97.80 133	98.17 167	95.23 169	99.76 136	97.53 234	92.52 187	94.27 195	99.25 126	76.84 282	98.80 172	90.89 244	99.54 95	99.35 163

CVMVSNet		94.68 173	94.94 158	93.89 274	96.80 239	86.92 322	99.06 238	98.98 36	94.45 105	94.23 196	99.02 140	85.60 209	95.31 339	90.91 243	95.39 199	99.43 154

baseline1		95.78 143	94.86 159	98.54 98	98.47 149	98.07 64	99.06 238	97.99 190	92.68 176	94.13 197	98.62 179	93.28 101	98.69 183	93.79 201	85.76 273	98.84 195

Anonymous202405211		93.10 214	91.99 226	96.40 188	99.10 106	89.65 294	98.88 259	97.93 197	83.71 333	94.00 198	98.75 173	68.79 326	99.88 93	95.08 166	91.71 223	99.68 106

cascas		94.64 174	93.61 184	97.74 141	97.82 185	96.26 129	99.96 28	97.78 212	85.76 314	94.00 198	97.54 218	76.95 281	99.21 155	97.23 132	95.43 198	97.76 220

Anonymous20240529		92.10 236	90.65 247	96.47 183	98.82 130	90.61 275	98.72 275	98.67 66	75.54 360	93.90 200	98.58 182	66.23 338	99.90 83	94.70 179	90.67 226	98.90 193

LS3D		95.84 142	95.11 152	98.02 125	99.85 54	95.10 174	98.74 273	98.50 101	87.22 296	93.66 201	99.86 26	87.45 193	99.95 64	90.94 242	99.81 78	99.02 188

GeoE		94.36 184	93.48 191	96.99 169	97.29 218	93.54 209	99.96 28	96.72 314	88.35 282	93.43 202	98.94 158	82.05 235	98.05 232	88.12 280	96.48 178	99.37 160

HQP-NCC					95.78 263		99.87 91		96.82 40	93.37 203

ACMP_Plane					95.78 263		99.87 91		96.82 40	93.37 203

HQP4-MVS										93.37 203			98.39 204			94.53 239

HQP-MVS		94.61 175	94.50 165	94.92 229	95.78 263	91.85 249	99.87 91	97.89 202	96.82 40	93.37 203	98.65 176	80.65 252	98.39 204	97.92 111	89.60 228	94.53 239

HQP_MVS		94.49 179	94.36 167	94.87 230	95.71 272	91.74 253	99.84 111	97.87 204	96.38 56	93.01 207	98.59 180	80.47 256	98.37 210	97.79 118	89.55 231	94.52 241

plane_prior3						91.64 259			96.63 48	93.01 207

GA-MVS		93.83 192	92.84 206	96.80 174	95.73 269	93.57 207	99.88 88	97.24 263	92.57 184	92.92 209	96.66 248	78.73 269	97.67 249	87.75 283	94.06 212	99.17 179

tpm cat1		93.51 204	92.52 217	96.47 183	97.77 188	91.47 263	96.13 343	98.06 186	80.98 346	92.91 210	93.78 332	89.66 168	98.87 169	87.03 293	96.39 179	99.09 186

1112_ss		96.01 137	95.20 149	98.42 108	97.80 186	96.41 123	99.65 160	96.66 316	92.71 173	92.88 211	99.40 112	92.16 131	99.30 153	91.92 227	93.66 214	99.55 134

Test_1112_low_res		95.72 144	94.83 160	98.42 108	97.79 187	96.41 123	99.65 160	96.65 317	92.70 174	92.86 212	96.13 265	92.15 132	99.30 153	91.88 228	93.64 215	99.55 134

IB-MVS	92.85 6	94.99 163	93.94 178	98.16 117	97.72 195	95.69 152	99.99 4	98.81 53	94.28 117	92.70 213	96.90 239	95.08 51	99.17 159	96.07 153	73.88 349	99.60 124
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
iter_conf_final		96.01 137	95.93 127	96.28 192	98.38 152	97.03 104	99.87 91	97.03 284	94.05 130	92.61 214	97.98 207	98.01 5	97.34 259	97.02 138	88.39 250	94.47 244

Fast-Effi-MVS+-dtu		93.72 199	93.86 181	93.29 289	97.06 224	86.16 324	99.80 125	96.83 306	92.66 177	92.58 215	97.83 213	81.39 242	97.67 249	89.75 263	96.87 172	96.05 236

SDMVSNet		94.80 166	93.96 177	97.33 162	98.92 121	95.42 160	99.59 170	98.99 35	92.41 191	92.55 216	97.85 211	75.81 293	98.93 168	97.90 113	91.62 224	97.64 221

sd_testset		93.55 203	92.83 207	95.74 205	98.92 121	90.89 270	98.24 301	98.85 51	92.41 191	92.55 216	97.85 211	71.07 321	98.68 184	93.93 193	91.62 224	97.64 221

iter_conf05		96.07 134	95.95 125	96.44 187	98.43 150	97.52 84	99.91 74	96.85 304	94.16 121	92.49 218	97.98 207	98.20 4	97.34 259	97.26 131	88.29 251	94.45 250

dmvs_re		93.20 210	93.15 201	93.34 287	96.54 247	83.81 337	98.71 276	98.51 96	91.39 225	92.37 219	98.56 184	78.66 270	97.83 243	93.89 194	89.74 227	98.38 207

tpmvs		94.28 186	93.57 188	96.40 188	98.55 143	91.50 262	95.70 351	98.55 87	87.47 291	92.15 220	94.26 328	91.42 141	98.95 167	88.15 278	95.85 189	98.76 199

BH-w/o		95.71 146	95.38 143	96.68 179	98.49 148	92.28 239	99.84 111	97.50 238	92.12 199	92.06 221	98.79 171	84.69 218	98.67 185	95.29 163	99.66 86	99.09 186

VPA-MVSNet		92.70 223	91.55 235	96.16 195	95.09 282	96.20 134	98.88 259	99.00 34	91.02 234	91.82 222	95.29 300	76.05 292	97.96 237	95.62 160	81.19 307	94.30 261

baseline2		96.71 112	96.49 105	97.37 158	95.63 276	95.96 141	99.74 142	98.88 47	92.94 163	91.61 223	98.97 149	97.72 7	98.62 187	94.83 174	98.08 146	97.53 226

OPM-MVS		93.21 209	92.80 208	94.44 252	93.12 318	90.85 271	99.77 131	97.61 224	96.19 63	91.56 224	98.65 176	75.16 301	98.47 193	93.78 202	89.39 234	93.99 292
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		93.73 198	93.40 196	94.74 235	96.80 239	92.69 230	99.06 238	97.67 217	88.96 267	91.39 225	99.02 140	88.75 184	97.30 264	91.07 237	87.85 258	94.22 266

MVSTER		95.53 152	95.22 148	96.45 185	98.56 141	97.72 75	99.91 74	97.67 217	92.38 193	91.39 225	97.14 229	97.24 18	97.30 264	94.80 175	87.85 258	94.34 260

mvsmamba		94.10 188	93.72 183	95.25 219	93.57 307	94.13 194	99.67 157	96.45 325	93.63 147	91.34 227	97.77 214	86.29 205	97.22 270	96.65 147	88.10 255	94.40 252

test_fmvs2		89.47 289	89.70 266	88.77 334	94.54 292	75.74 362	99.83 117	94.70 358	94.71 98	91.08 228	96.82 247	54.46 362	97.78 246	92.87 217	88.27 252	92.80 331

BH-untuned		95.18 158	94.83 160	96.22 194	98.36 154	91.22 265	99.80 125	97.32 255	90.91 235	91.08 228	98.67 175	83.51 227	98.54 191	94.23 189	99.61 91	98.92 190

CLD-MVS		94.06 190	93.90 179	94.55 245	96.02 257	90.69 272	99.98 11	97.72 213	96.62 50	91.05 230	98.85 170	77.21 277	98.47 193	98.11 100	89.51 233	94.48 243
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		96.60 116	95.56 139	99.72 12	96.85 236	99.22 19	98.31 298	98.94 38	91.57 215	90.90 231	99.61 95	86.66 201	99.96 57	97.36 128	99.88 68	99.99 23

MSDG		94.37 182	93.36 197	97.40 156	98.88 128	93.95 200	99.37 204	97.38 249	85.75 316	90.80 232	99.17 132	84.11 225	99.88 93	86.35 298	98.43 132	98.36 208

VPNet		91.81 240	90.46 249	95.85 202	94.74 288	95.54 156	98.98 248	98.59 76	92.14 198	90.77 233	97.44 221	68.73 328	97.54 253	94.89 173	77.89 332	94.46 245

MIMVSNet		90.30 274	88.67 287	95.17 222	96.45 248	91.64 259	92.39 362	97.15 271	85.99 311	90.50 234	93.19 339	66.95 335	94.86 345	82.01 325	93.43 216	99.01 189

mvs_anonymous		95.65 150	95.03 155	97.53 148	98.19 165	95.74 148	99.33 208	97.49 239	90.87 236	90.47 235	97.10 231	88.23 187	97.16 272	95.92 156	97.66 153	99.68 106

bld_raw_dy_0_64		92.74 221	92.03 225	94.87 230	93.09 320	93.46 211	99.12 228	95.41 346	92.84 167	90.44 236	97.54 218	78.08 275	97.04 283	93.94 192	87.77 260	94.11 281

Patchmatch-test		92.65 226	91.50 236	96.10 197	96.85 236	90.49 278	91.50 366	97.19 265	82.76 340	90.23 237	95.59 280	95.02 54	98.00 234	77.41 345	96.98 170	99.82 88

LPG-MVS_test		92.96 216	92.71 210	93.71 279	95.43 278	88.67 304	99.75 139	97.62 221	92.81 168	90.05 238	98.49 188	75.24 297	98.40 202	95.84 158	89.12 235	94.07 284

LGP-MVS_train				93.71 279	95.43 278	88.67 304		97.62 221	92.81 168	90.05 238	98.49 188	75.24 297	98.40 202	95.84 158	89.12 235	94.07 284

DP-MVS		94.54 176	93.42 193	97.91 130	99.46 93	94.04 196	98.93 254	97.48 240	81.15 345	90.04 240	99.55 100	87.02 198	99.95 64	88.97 268	98.11 143	99.73 100

test_djsdf		92.83 219	92.29 220	94.47 250	91.90 339	92.46 236	99.55 178	97.27 260	91.17 228	89.96 241	96.07 268	81.10 245	96.89 293	94.67 180	88.91 237	94.05 286

ACMM	91.95 10	92.88 218	92.52 217	93.98 270	95.75 268	89.08 300	99.77 131	97.52 236	93.00 162	89.95 242	97.99 206	76.17 290	98.46 196	93.63 206	88.87 239	94.39 254
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
1314		96.84 104	95.96 123	99.48 33	96.74 243	98.52 55	98.31 298	98.86 49	95.82 68	89.91 243	98.98 147	87.49 192	99.96 57	97.80 115	99.73 82	99.96 61

XVG-ACMP-BASELINE		91.22 254	90.75 245	92.63 301	93.73 305	85.61 327	98.52 289	97.44 242	92.77 171	89.90 244	96.85 243	66.64 337	98.39 204	92.29 222	88.61 244	93.89 300

miper_enhance_ethall		94.36 184	93.98 176	95.49 208	98.68 138	95.24 168	99.73 147	97.29 258	93.28 156	89.86 245	95.97 269	94.37 71	97.05 281	92.20 223	84.45 285	94.19 269

nrg030		93.51 204	92.53 216	96.45 185	94.36 294	97.20 97	99.81 121	97.16 270	91.60 214	89.86 245	97.46 220	86.37 204	97.68 248	95.88 157	80.31 319	94.46 245

V42		91.28 251	90.12 261	94.74 235	93.42 312	93.46 211	99.68 155	97.02 285	87.36 293	89.85 247	95.05 305	81.31 244	97.34 259	87.34 288	80.07 321	93.40 318

v144192		90.79 262	89.52 271	94.59 242	93.11 319	92.77 225	99.56 176	96.99 288	86.38 307	89.82 248	94.95 312	80.50 255	97.10 278	83.98 313	80.41 317	93.90 299

GBi-Net		90.88 259	89.82 264	94.08 263	97.53 203	91.97 244	98.43 292	96.95 293	87.05 297	89.68 249	94.72 315	71.34 317	96.11 323	87.01 294	85.65 274	94.17 270

test1		90.88 259	89.82 264	94.08 263	97.53 203	91.97 244	98.43 292	96.95 293	87.05 297	89.68 249	94.72 315	71.34 317	96.11 323	87.01 294	85.65 274	94.17 270

FMVSNet3		92.69 224	91.58 233	95.99 198	98.29 156	97.42 92	99.26 219	97.62 221	89.80 254	89.68 249	95.32 296	81.62 241	96.27 318	87.01 294	85.65 274	94.29 262

IterMVS-LS		92.69 224	92.11 222	94.43 254	96.80 239	92.74 227	99.45 194	96.89 301	88.98 265	89.65 252	95.38 293	88.77 183	96.34 315	90.98 241	82.04 301	94.22 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		91.09 255	89.83 263	94.87 230	93.25 315	93.69 206	99.62 167	96.98 290	86.83 303	89.64 253	94.99 310	80.94 247	97.05 281	85.08 307	81.16 308	93.87 302

v1921920		90.46 269	89.12 278	94.50 248	92.96 324	92.46 236	99.49 188	96.98 290	86.10 310	89.61 254	95.30 297	78.55 272	97.03 286	82.17 324	80.89 315	94.01 289

v1192		90.62 267	89.25 276	94.72 237	93.13 316	93.07 219	99.50 186	97.02 285	86.33 308	89.56 255	95.01 307	79.22 264	97.09 280	82.34 323	81.16 308	94.01 289

PCF-MVS	94.20 5	95.18 158	94.10 173	98.43 107	98.55 143	95.99 140	97.91 314	97.31 256	90.35 245	89.48 256	99.22 128	85.19 215	99.89 87	90.40 255	98.47 131	99.41 156
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	91.47 12	96.28 131	95.34 144	99.08 62	96.82 238	97.47 90	99.45 194	98.81 53	95.52 78	89.39 257	99.00 144	81.97 236	99.95 64	97.27 130	99.83 72	99.84 86

v1240		90.20 277	88.79 285	94.44 252	93.05 322	92.27 240	99.38 202	96.92 299	85.89 312	89.36 258	94.87 314	77.89 276	97.03 286	80.66 331	81.08 311	94.01 289

FIs		94.10 188	93.43 192	96.11 196	94.70 289	96.82 112	99.58 172	98.93 42	92.54 185	89.34 259	97.31 225	87.62 191	97.10 278	94.22 190	86.58 269	94.40 252

ITE_SJBPF				92.38 302	95.69 274	85.14 330		95.71 339	92.81 168	89.33 260	98.11 200	70.23 323	98.42 199	85.91 302	88.16 254	93.59 315

v2v482		91.30 249	90.07 262	95.01 225	93.13 316	93.79 202	99.77 131	97.02 285	88.05 285	89.25 261	95.37 294	80.73 250	97.15 273	87.28 289	80.04 322	94.09 283

UniMVSNet (Re)		93.07 215	92.13 221	95.88 200	94.84 286	96.24 133	99.88 88	98.98 36	92.49 189	89.25 261	95.40 290	87.09 197	97.14 274	93.13 214	78.16 330	94.26 263

tt0805		91.28 251	90.18 258	94.60 241	96.26 251	87.55 316	98.39 296	98.72 58	89.00 264	89.22 263	98.47 192	62.98 349	98.96 166	90.57 249	88.00 257	97.28 227

UniMVSNet_NR-MVSNet		92.95 217	92.11 222	95.49 208	94.61 291	95.28 166	99.83 117	99.08 31	91.49 217	89.21 264	96.86 242	87.14 196	96.73 301	93.20 210	77.52 335	94.46 245

DU-MVS		92.46 229	91.45 238	95.49 208	94.05 299	95.28 166	99.81 121	98.74 57	92.25 197	89.21 264	96.64 250	81.66 239	96.73 301	93.20 210	77.52 335	94.46 245

eth_miper_zixun_eth		92.41 230	91.93 227	93.84 275	97.28 219	90.68 273	98.83 266	96.97 292	88.57 278	89.19 266	95.73 275	89.24 178	96.69 303	89.97 261	81.55 304	94.15 276

cl22		93.77 196	93.25 200	95.33 216	99.49 90	94.43 187	99.61 168	98.09 183	90.38 243	89.16 267	95.61 278	90.56 159	97.34 259	91.93 226	84.45 285	94.21 268

Baseline_NR-MVSNet		90.33 273	89.51 272	92.81 299	92.84 325	89.95 290	99.77 131	93.94 363	84.69 328	89.04 268	95.66 277	81.66 239	96.52 308	90.99 240	76.98 341	91.97 342

FC-MVSNet-test		93.81 194	93.15 201	95.80 204	94.30 296	96.20 134	99.42 196	98.89 45	92.33 195	89.03 269	97.27 227	87.39 194	96.83 297	93.20 210	86.48 270	94.36 256

QAPM		95.40 155	94.17 172	99.10 61	96.92 230	97.71 76	99.40 197	98.68 63	89.31 258	88.94 270	98.89 161	82.48 233	99.96 57	93.12 215	99.83 72	99.62 119

RRT_MVS		93.14 212	92.92 205	93.78 276	93.31 314	90.04 287	99.66 158	97.69 215	92.53 186	88.91 271	97.76 215	84.36 221	96.93 291	95.10 165	86.99 267	94.37 255

miper_ehance_all_eth		93.16 211	92.60 212	94.82 234	97.57 202	93.56 208	99.50 186	97.07 280	88.75 273	88.85 272	95.52 284	90.97 151	96.74 300	90.77 246	84.45 285	94.17 270

AllTest		92.48 228	91.64 231	95.00 226	99.01 110	88.43 308	98.94 253	96.82 308	86.50 305	88.71 273	98.47 192	74.73 303	99.88 93	85.39 304	96.18 181	96.71 230

TestCases				95.00 226	99.01 110	88.43 308		96.82 308	86.50 305	88.71 273	98.47 192	74.73 303	99.88 93	85.39 304	96.18 181	96.71 230

c3_l		92.53 227	91.87 229	94.52 246	97.40 210	92.99 223	99.40 197	96.93 298	87.86 287	88.69 275	95.44 288	89.95 166	96.44 311	90.45 252	80.69 316	94.14 279

pmmvs4		92.10 236	91.07 243	95.18 221	92.82 327	94.96 176	99.48 190	96.83 306	87.45 292	88.66 276	96.56 254	83.78 226	96.83 297	89.29 265	84.77 283	93.75 308

PS-MVSNAJss		93.64 201	93.31 198	94.61 240	92.11 336	92.19 241	99.12 228	97.38 249	92.51 188	88.45 277	96.99 238	91.20 145	97.29 267	94.36 185	87.71 261	94.36 256

UniMVSNet_ETH3D		90.06 281	88.58 288	94.49 249	94.67 290	88.09 313	97.81 316	97.57 229	83.91 332	88.44 278	97.41 222	57.44 359	97.62 251	91.41 232	88.59 246	97.77 219

TranMVSNet+NR-MVSNet		91.68 247	90.61 248	94.87 230	93.69 306	93.98 199	99.69 153	98.65 67	91.03 233	88.44 278	96.83 246	80.05 259	96.18 321	90.26 257	76.89 343	94.45 250

FMVSNet2		91.02 256	89.56 269	95.41 213	97.53 203	95.74 148	98.98 248	97.41 247	87.05 297	88.43 280	95.00 309	71.34 317	96.24 320	85.12 306	85.21 279	94.25 265

COLMAP_ROB	90.47 14	92.18 235	91.49 237	94.25 259	99.00 112	88.04 314	98.42 295	96.70 315	82.30 342	88.43 280	99.01 142	76.97 280	99.85 99	86.11 301	96.50 177	94.86 238
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator+	91.53 11	96.31 128	95.24 147	99.52 27	96.88 235	98.64 51	99.72 150	98.24 166	95.27 84	88.42 282	98.98 147	82.76 232	99.94 72	97.10 136	99.83 72	99.96 61

v148		90.70 263	89.63 267	93.92 271	92.97 323	90.97 267	99.75 139	96.89 301	87.51 290	88.27 283	95.01 307	81.67 238	97.04 283	87.40 287	77.17 340	93.75 308

DSMNet-mixed		88.28 298	88.24 293	88.42 336	89.64 357	75.38 364	98.06 310	89.86 376	85.59 318	88.20 284	92.14 347	76.15 291	91.95 364	78.46 341	96.05 184	97.92 215

WR-MVS		92.31 232	91.25 240	95.48 211	94.45 293	95.29 165	99.60 169	98.68 63	90.10 248	88.07 285	96.89 240	80.68 251	96.80 299	93.14 213	79.67 323	94.36 256

test0.0.03 1		93.86 191	93.61 184	94.64 239	95.02 285	92.18 242	99.93 67	98.58 77	94.07 126	87.96 286	98.50 187	93.90 86	94.96 343	81.33 328	93.17 219	96.78 229

XXY-MVS		91.82 239	90.46 249	95.88 200	93.91 302	95.40 162	98.87 262	97.69 215	88.63 277	87.87 287	97.08 232	74.38 306	97.89 241	91.66 230	84.07 289	94.35 259

Patchmtry		89.70 286	88.49 289	93.33 288	96.24 252	89.94 292	91.37 367	96.23 329	78.22 353	87.69 288	93.31 337	91.04 149	96.03 328	80.18 335	82.10 300	94.02 287

DIV-MVS_self_test		92.32 231	91.60 232	94.47 250	97.31 216	92.74 227	99.58 172	96.75 312	86.99 300	87.64 289	95.54 282	89.55 171	96.50 309	88.58 272	82.44 298	94.17 270

D2MVS		92.76 220	92.59 215	93.27 290	95.13 281	89.54 296	99.69 153	99.38 22	92.26 196	87.59 290	94.61 321	85.05 217	97.79 244	91.59 231	88.01 256	92.47 336

cl____		92.31 232	91.58 233	94.52 246	97.33 215	92.77 225	99.57 174	96.78 311	86.97 301	87.56 291	95.51 285	89.43 172	96.62 305	88.60 271	82.44 298	94.16 275

v8		90.54 268	89.17 277	94.66 238	93.43 311	93.40 215	99.20 223	96.94 297	85.76 314	87.56 291	94.51 322	81.96 237	97.19 271	84.94 308	78.25 329	93.38 320

miper_lstm_enhance		91.81 240	91.39 239	93.06 296	97.34 213	89.18 299	99.38 202	96.79 310	86.70 304	87.47 293	95.22 302	90.00 165	95.86 332	88.26 276	81.37 306	94.15 276

anonymousdsp		91.79 245	90.92 244	94.41 255	90.76 350	92.93 224	98.93 254	97.17 268	89.08 260	87.46 294	95.30 297	78.43 274	96.92 292	92.38 221	88.73 242	93.39 319

jajsoiax		91.92 238	91.18 241	94.15 260	91.35 345	90.95 268	99.00 247	97.42 245	92.61 180	87.38 295	97.08 232	72.46 312	97.36 257	94.53 183	88.77 241	94.13 280

mvs_tets		91.81 240	91.08 242	94.00 268	91.63 343	90.58 276	98.67 281	97.43 243	92.43 190	87.37 296	97.05 235	71.76 314	97.32 263	94.75 177	88.68 243	94.11 281

v10		90.25 276	88.82 284	94.57 244	93.53 309	93.43 213	99.08 233	96.87 303	85.00 323	87.34 297	94.51 322	80.93 248	97.02 288	82.85 320	79.23 324	93.26 322

pmmvs5		90.17 279	89.09 279	93.40 286	92.10 337	89.77 293	99.74 142	95.58 343	85.88 313	87.24 298	95.74 273	73.41 310	96.48 310	88.54 273	83.56 292	93.95 295

ACMP	92.05 9	92.74 221	92.42 219	93.73 277	95.91 261	88.72 303	99.81 121	97.53 234	94.13 122	87.00 299	98.23 198	74.07 307	98.47 193	96.22 152	88.86 240	93.99 292
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS-HIRNet		86.22 307	83.19 320	95.31 217	96.71 245	90.29 282	92.12 363	97.33 254	62.85 370	86.82 300	70.37 375	69.37 325	97.49 254	75.12 352	97.99 148	98.15 211

Anonymous20231211		89.86 283	88.44 290	94.13 262	98.93 119	90.68 273	98.54 287	98.26 165	76.28 356	86.73 301	95.54 282	70.60 322	97.56 252	90.82 245	80.27 320	94.15 276

v7n		89.65 287	88.29 292	93.72 278	92.22 334	90.56 277	99.07 237	97.10 276	85.42 321	86.73 301	94.72 315	80.06 258	97.13 275	81.14 329	78.12 331	93.49 316

IterMVS-SCA-FT		90.85 261	90.16 260	92.93 297	96.72 244	89.96 289	98.89 257	96.99 288	88.95 268	86.63 303	95.67 276	76.48 286	95.00 342	87.04 292	84.04 291	93.84 304

EU-MVSNet		90.14 280	90.34 253	89.54 326	92.55 330	81.06 354	98.69 279	98.04 188	91.41 224	86.59 304	96.84 245	80.83 249	93.31 359	86.20 299	81.91 302	94.26 263

OpenMVS	90.15 15	94.77 169	93.59 187	98.33 112	96.07 255	97.48 89	99.56 176	98.57 79	90.46 242	86.51 305	98.95 156	78.57 271	99.94 72	93.86 195	99.74 81	97.57 225

IterMVS		90.91 258	90.17 259	93.12 293	96.78 242	90.42 281	98.89 257	97.05 283	89.03 262	86.49 306	95.42 289	76.59 285	95.02 341	87.22 290	84.09 288	93.93 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS_H		91.30 249	90.35 252	94.15 260	94.17 298	92.62 234	99.17 226	98.94 38	88.87 271	86.48 307	94.46 326	84.36 221	96.61 306	88.19 277	78.51 328	93.21 324

MS-PatchMatch		90.65 264	90.30 254	91.71 310	94.22 297	85.50 329	98.24 301	97.70 214	88.67 275	86.42 308	96.37 258	67.82 332	98.03 233	83.62 316	99.62 88	91.60 344

CP-MVSNet		91.23 253	90.22 256	94.26 258	93.96 301	92.39 238	99.09 231	98.57 79	88.95 268	86.42 308	96.57 253	79.19 265	96.37 313	90.29 256	78.95 325	94.02 287

LF4IMVS		89.25 293	88.85 283	90.45 320	92.81 328	81.19 353	98.12 307	94.79 355	91.44 220	86.29 310	97.11 230	65.30 343	98.11 228	88.53 274	85.25 278	92.07 339

PVSNet_0	88.03 19	91.80 243	90.27 255	96.38 190	98.27 159	90.46 279	99.94 61	99.61 13	93.99 132	86.26 311	97.39 224	71.13 320	99.89 87	98.77 70	67.05 364	98.79 198

PS-CasMVS		90.63 266	89.51 272	93.99 269	93.83 303	91.70 257	98.98 248	98.52 93	88.48 279	86.15 312	96.53 255	75.46 295	96.31 317	88.83 269	78.86 327	93.95 295

FMVSNet1		88.50 296	86.64 302	94.08 263	95.62 277	91.97 244	98.43 292	96.95 293	83.00 337	86.08 313	94.72 315	59.09 357	96.11 323	81.82 327	84.07 289	94.17 270

PEN-MVS		90.19 278	89.06 280	93.57 284	93.06 321	90.90 269	99.06 238	98.47 103	88.11 284	85.91 314	96.30 259	76.67 283	95.94 331	87.07 291	76.91 342	93.89 300

ppachtmachnet_test		89.58 288	88.35 291	93.25 291	92.40 332	90.44 280	99.33 208	96.73 313	85.49 319	85.90 315	95.77 272	81.09 246	96.00 330	76.00 351	82.49 297	93.30 321

OurMVSNet-221017-0		89.81 284	89.48 274	90.83 316	91.64 342	81.21 352	98.17 306	95.38 348	91.48 218	85.65 316	97.31 225	72.66 311	97.29 267	88.15 278	84.83 282	93.97 294

our_test_3		90.39 270	89.48 274	93.12 293	92.40 332	89.57 295	99.33 208	96.35 328	87.84 288	85.30 317	94.99 310	84.14 224	96.09 326	80.38 332	84.56 284	93.71 313

testgi		89.01 294	88.04 295	91.90 308	93.49 310	84.89 333	99.73 147	95.66 341	93.89 140	85.14 318	98.17 199	59.68 356	94.66 347	77.73 344	88.88 238	96.16 235

DTE-MVSNet		89.40 290	88.24 293	92.88 298	92.66 329	89.95 290	99.10 230	98.22 168	87.29 294	85.12 319	96.22 261	76.27 289	95.30 340	83.56 317	75.74 346	93.41 317

FMVSNet5		88.32 297	87.47 299	90.88 314	96.90 234	88.39 310	97.28 321	95.68 340	82.60 341	84.67 320	92.40 345	79.83 260	91.16 366	76.39 350	81.51 305	93.09 325

tfpnnormal		89.29 292	87.61 298	94.34 257	94.35 295	94.13 194	98.95 252	98.94 38	83.94 330	84.47 321	95.51 285	74.84 302	97.39 256	77.05 348	80.41 317	91.48 346

MVP-Stereo		90.93 257	90.45 251	92.37 303	91.25 347	88.76 301	98.05 311	96.17 331	87.27 295	84.04 322	95.30 297	78.46 273	97.27 269	83.78 315	99.70 84	91.09 347
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LTVRE_ROB	88.28 18	90.29 275	89.05 281	94.02 266	95.08 283	90.15 285	97.19 323	97.43 243	84.91 326	83.99 323	97.06 234	74.00 308	98.28 218	84.08 311	87.71 261	93.62 314
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
pm-mvs1		89.36 291	87.81 297	94.01 267	93.40 313	91.93 247	98.62 284	96.48 324	86.25 309	83.86 324	96.14 264	73.68 309	97.04 283	86.16 300	75.73 347	93.04 327

USDC		90.00 282	88.96 282	93.10 295	94.81 287	88.16 312	98.71 276	95.54 344	93.66 145	83.75 325	97.20 228	65.58 340	98.31 215	83.96 314	87.49 265	92.85 330

CL-MVSNet_self_test		84.50 318	83.15 321	88.53 335	86.00 365	81.79 349	98.82 267	97.35 251	85.12 322	83.62 326	90.91 352	76.66 284	91.40 365	69.53 361	60.36 372	92.40 337

ACMH+	89.98 16	90.35 272	89.54 270	92.78 300	95.99 258	86.12 325	98.81 268	97.18 267	89.38 257	83.14 327	97.76 215	68.42 330	98.43 198	89.11 267	86.05 272	93.78 307

Anonymous20231206		86.32 306	85.42 309	89.02 330	89.11 359	80.53 358	99.05 242	95.28 349	85.43 320	82.82 328	93.92 330	74.40 305	93.44 358	66.99 365	81.83 303	93.08 326

KD-MVS_self_test		83.59 324	82.06 324	88.20 337	86.93 363	80.70 356	97.21 322	96.38 326	82.87 338	82.49 329	88.97 356	67.63 333	92.32 362	73.75 354	62.30 371	91.58 345

SixPastTwentyTwo		88.73 295	88.01 296	90.88 314	91.85 340	82.24 345	98.22 304	95.18 353	88.97 266	82.26 330	96.89 240	71.75 315	96.67 304	84.00 312	82.98 293	93.72 312

KD-MVS_2432*1600		88.00 300	86.10 304	93.70 281	96.91 231	94.04 196	97.17 324	97.12 274	84.93 324	81.96 331	92.41 343	92.48 124	94.51 348	79.23 336	52.68 375	92.56 333

miper_refine_blended		88.00 300	86.10 304	93.70 281	96.91 231	94.04 196	97.17 324	97.12 274	84.93 324	81.96 331	92.41 343	92.48 124	94.51 348	79.23 336	52.68 375	92.56 333

TinyColmap		87.87 302	86.51 303	91.94 307	95.05 284	85.57 328	97.65 317	94.08 361	84.40 329	81.82 333	96.85 243	62.14 351	98.33 213	80.25 334	86.37 271	91.91 343

ACMH	89.72 17	90.64 265	89.63 267	93.66 283	95.64 275	88.64 306	98.55 285	97.45 241	89.03 262	81.62 334	97.61 217	69.75 324	98.41 200	89.37 264	87.62 263	93.92 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		85.15 314	83.81 316	89.16 329	88.32 360	82.69 341	98.80 270	95.74 338	79.72 349	81.53 335	90.99 350	65.38 342	94.16 350	72.69 355	81.11 310	90.63 352

pmmvs6		85.69 308	83.84 315	91.26 313	90.00 356	84.41 335	97.82 315	96.15 332	75.86 358	81.29 336	95.39 292	61.21 354	96.87 295	83.52 318	73.29 350	92.50 335

TransMVSNet (Re)		87.25 303	85.28 310	93.16 292	93.56 308	91.03 266	98.54 287	94.05 362	83.69 334	81.09 337	96.16 263	75.32 296	96.40 312	76.69 349	68.41 361	92.06 340

test_method		80.79 329	79.70 333	84.08 344	92.83 326	67.06 369	99.51 184	95.42 345	54.34 374	81.07 338	93.53 334	44.48 370	92.22 363	78.90 340	77.23 339	92.94 328

NR-MVSNet		91.56 248	90.22 256	95.60 206	94.05 299	95.76 147	98.25 300	98.70 60	91.16 230	80.78 339	96.64 250	83.23 231	96.57 307	91.41 232	77.73 334	94.46 245

LCM-MVSNet-Re		92.31 232	92.60 212	91.43 311	97.53 203	79.27 360	99.02 246	91.83 372	92.07 200	80.31 340	94.38 327	83.50 228	95.48 335	97.22 133	97.58 154	99.54 137

TDRefinement		84.76 315	82.56 323	91.38 312	74.58 379	84.80 334	97.36 320	94.56 359	84.73 327	80.21 341	96.12 267	63.56 347	98.39 204	87.92 281	63.97 368	90.95 350

N_pmnet		80.06 332	80.78 330	77.89 351	91.94 338	45.28 386	98.80 270	56.82 389	78.10 354	80.08 342	93.33 335	77.03 279	95.76 333	68.14 364	82.81 294	92.64 332

test_fmvs3		79.99 333	80.17 332	79.45 350	84.02 369	62.83 370	99.05 242	93.49 367	88.29 283	80.06 343	86.65 365	28.09 377	88.00 371	88.63 270	73.27 351	87.54 367

test_0402		85.58 309	83.94 314	90.50 318	93.81 304	85.04 331	98.55 285	95.20 352	76.01 357	79.72 344	95.13 303	64.15 346	96.26 319	66.04 369	86.88 268	90.21 355

test20.03		84.72 317	83.99 312	86.91 339	88.19 362	80.62 357	98.88 259	95.94 335	88.36 281	78.87 345	94.62 320	68.75 327	89.11 370	66.52 367	75.82 345	91.00 348

pmmvs3		80.27 331	77.77 336	87.76 338	80.32 374	82.43 344	98.23 303	91.97 371	72.74 367	78.75 346	87.97 361	57.30 360	90.99 367	70.31 359	62.37 370	89.87 357

dmvs_testset		83.79 322	86.07 306	76.94 352	92.14 335	48.60 384	96.75 333	90.27 375	89.48 256	78.65 347	98.55 186	79.25 263	86.65 375	66.85 366	82.69 295	95.57 237

MIMVSNet1		82.58 325	80.51 331	88.78 332	86.68 364	84.20 336	96.65 334	95.41 346	78.75 352	78.59 348	92.44 342	51.88 366	89.76 369	65.26 370	78.95 325	92.38 338

DeepMVS_CX				82.92 347	95.98 260	58.66 377		96.01 334	92.72 172	78.34 349	95.51 285	58.29 358	98.08 229	82.57 321	85.29 277	92.03 341

test_vis1_rt		86.87 305	86.05 307	89.34 327	96.12 253	78.07 361	99.87 91	83.54 383	92.03 203	78.21 350	89.51 354	45.80 369	99.91 81	96.25 151	93.11 221	90.03 356

mvsany_test3		82.12 326	81.14 328	85.06 343	81.87 372	70.41 366	97.09 326	92.14 370	91.27 227	77.84 351	88.73 357	39.31 372	95.49 334	90.75 247	71.24 353	89.29 363

Patchmatch-RL test		86.90 304	85.98 308	89.67 325	84.45 367	75.59 363	89.71 371	92.43 369	86.89 302	77.83 352	90.94 351	94.22 76	93.63 356	87.75 283	69.61 356	99.79 92

APD_test1		81.15 328	80.92 329	81.86 348	92.45 331	59.76 376	96.04 346	93.61 366	73.29 366	77.06 353	96.64 250	44.28 371	96.16 322	72.35 356	82.52 296	89.67 359

lessismore_v0				90.53 317	90.58 351	80.90 355		95.80 337		77.01 354	95.84 270	66.15 339	96.95 289	83.03 319	75.05 348	93.74 311

K. test v3		88.05 299	87.24 301	90.47 319	91.82 341	82.23 346	98.96 251	97.42 245	89.05 261	76.93 355	95.60 279	68.49 329	95.42 336	85.87 303	81.01 313	93.75 308

ambc				83.23 346	77.17 377	62.61 371	87.38 373	94.55 360		76.72 356	86.65 365	30.16 374	96.36 314	84.85 309	69.86 355	90.73 351

PM-MVS		80.47 330	78.88 335	85.26 342	83.79 370	72.22 365	95.89 349	91.08 373	85.71 317	76.56 357	88.30 358	36.64 373	93.90 353	82.39 322	69.57 357	89.66 360

OpenMVS_ROB	79.82 20	83.77 323	81.68 326	90.03 323	88.30 361	82.82 340	98.46 290	95.22 351	73.92 365	76.00 358	91.29 349	55.00 361	96.94 290	68.40 363	88.51 248	90.34 353

UnsupCasMVSNet_eth		85.52 310	83.99 312	90.10 322	89.36 358	83.51 339	96.65 334	97.99 190	89.14 259	75.89 359	93.83 331	63.25 348	93.92 352	81.92 326	67.90 363	92.88 329

new_pmnet		84.49 319	82.92 322	89.21 328	90.03 355	82.60 342	96.89 332	95.62 342	80.59 347	75.77 360	89.17 355	65.04 344	94.79 346	72.12 357	81.02 312	90.23 354

EG-PatchMatch MVS		85.35 313	83.81 316	89.99 324	90.39 352	81.89 348	98.21 305	96.09 333	81.78 344	74.73 361	93.72 333	51.56 367	97.12 277	79.16 339	88.61 244	90.96 349

test_f		78.40 335	77.59 337	80.81 349	80.82 373	62.48 373	96.96 330	93.08 368	83.44 335	74.57 362	84.57 369	27.95 378	92.63 361	84.15 310	72.79 352	87.32 368

pmmvs-eth3d		84.03 321	81.97 325	90.20 321	84.15 368	87.09 320	98.10 309	94.73 357	83.05 336	74.10 363	87.77 362	65.56 341	94.01 351	81.08 330	69.24 358	89.49 361

new-patchmatchnet		81.19 327	79.34 334	86.76 340	82.86 371	80.36 359	97.92 313	95.27 350	82.09 343	72.02 364	86.87 364	62.81 350	90.74 368	71.10 358	63.08 369	89.19 364

ET-MVSNet_ETH3D		94.37 182	93.28 199	97.64 144	98.30 155	97.99 68	99.99 4	97.61 224	94.35 112	71.57 365	99.45 109	96.23 31	95.34 338	96.91 144	85.14 280	99.59 125

UnsupCasMVSNet_bld		79.97 334	77.03 338	88.78 332	85.62 366	81.98 347	93.66 358	97.35 251	75.51 361	70.79 366	83.05 370	48.70 368	94.91 344	78.31 342	60.29 373	89.46 362

CMPMVS	61.59 21	84.75 316	85.14 311	83.57 345	90.32 353	62.54 372	96.98 329	97.59 228	74.33 364	69.95 367	96.66 248	64.17 345	98.32 214	87.88 282	88.41 249	89.84 358
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testmvs		40.60 350	44.45 353	29.05 367	19.49 391	14.11 392	99.68 155	18.47 390	20.74 383	64.59 368	98.48 191	10.95 388	17.09 387	56.66 377	11.01 383	55.94 380

LCM-MVSNet		67.77 341	64.73 344	76.87 353	62.95 385	56.25 379	89.37 372	93.74 365	44.53 377	61.99 369	80.74 371	20.42 384	86.53 376	69.37 362	59.50 374	87.84 365

PMMVS2		67.15 342	64.15 345	76.14 354	70.56 382	62.07 374	93.89 356	87.52 380	58.09 371	60.02 370	78.32 372	22.38 381	84.54 377	59.56 373	47.03 377	81.80 370

testf1		68.38 339	66.92 340	72.78 357	78.80 375	50.36 381	90.95 369	87.35 381	55.47 372	58.95 371	88.14 359	20.64 382	87.60 372	57.28 375	64.69 366	80.39 371

APD_test2		68.38 339	66.92 340	72.78 357	78.80 375	50.36 381	90.95 369	87.35 381	55.47 372	58.95 371	88.14 359	20.64 382	87.60 372	57.28 375	64.69 366	80.39 371

Gipuma		66.95 343	65.00 343	72.79 356	91.52 344	67.96 368	66.16 378	95.15 354	47.89 376	58.54 373	67.99 378	29.74 375	87.54 374	50.20 378	77.83 333	62.87 378
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		85.50 312	83.33 318	92.00 306	90.89 349	88.38 311	99.22 222	96.55 321	79.60 351	57.26 374	92.72 340	79.09 267	93.78 355	77.25 346	77.37 338	93.84 304

MDA-MVSNet_test_wron		85.51 311	83.32 319	92.10 305	90.96 348	88.58 307	99.20 223	96.52 322	79.70 350	57.12 375	92.69 341	79.11 266	93.86 354	77.10 347	77.46 337	93.86 303

MDA-MVSNet-bldmvs		84.09 320	81.52 327	91.81 309	91.32 346	88.00 315	98.67 281	95.92 336	80.22 348	55.60 376	93.32 336	68.29 331	93.60 357	73.76 353	76.61 344	93.82 306

FPMVS		68.72 338	68.72 339	68.71 360	65.95 383	44.27 388	95.97 348	94.74 356	51.13 375	53.26 377	90.50 353	25.11 380	83.00 378	60.80 372	80.97 314	78.87 373

test123		37.68 351	39.14 354	33.31 366	19.94 390	24.83 391	98.36 297	9.75 391	15.53 384	51.31 378	87.14 363	19.62 385	17.74 386	47.10 379	3.47 385	57.36 379

test_vis3_rt		68.82 337	66.69 342	75.21 355	76.24 378	60.41 375	96.44 337	68.71 388	75.13 362	50.54 379	69.52 377	16.42 387	96.32 316	80.27 333	66.92 365	68.89 375

tmp_tt		65.23 344	62.94 347	72.13 359	44.90 388	50.03 383	81.05 375	89.42 379	38.45 378	48.51 380	99.90 18	54.09 363	78.70 380	91.84 229	18.26 382	87.64 366

E-PMN		52.30 347	52.18 349	52.67 364	71.51 380	45.40 385	93.62 359	76.60 386	36.01 380	43.50 381	64.13 380	27.11 379	67.31 383	31.06 383	26.06 379	45.30 382

EMVS		51.44 349	51.22 351	52.11 365	70.71 381	44.97 387	94.04 355	75.66 387	35.34 382	42.40 382	61.56 383	28.93 376	65.87 384	27.64 384	24.73 380	45.49 381

MVE	53.74 22	51.54 348	47.86 352	62.60 362	59.56 386	50.93 380	79.41 376	77.69 385	35.69 381	36.27 383	61.76 382	5.79 391	69.63 381	37.97 382	36.61 378	67.24 376
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 345	52.24 348	67.66 361	49.27 387	56.82 378	83.94 374	82.02 384	70.47 368	33.28 384	64.54 379	17.23 386	69.16 382	45.59 380	23.85 381	77.02 374

PMVS	49.05 23	53.75 346	51.34 350	60.97 363	40.80 389	34.68 389	74.82 377	89.62 378	37.55 379	28.67 385	72.12 374	7.09 389	81.63 379	43.17 381	68.21 362	66.59 377
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 353	20.84 356	18.99 368	65.34 384	27.73 390	50.43 379	7.67 392	9.50 385	8.01 386	6.34 386	6.13 390	26.24 385	23.40 385	10.69 384	2.99 383

EGC-MVSNET		69.38 336	63.76 346	86.26 341	90.32 353	81.66 351	96.24 342	93.85 364	0.99 386	3.22 387	92.33 346	52.44 364	92.92 360	59.53 374	84.90 281	84.21 369

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.02 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		23.43 352	31.24 355	0.00 369	0.00 392	0.00 393	0.00 380	98.09 183	0.00 387	0.00 388	99.67 89	83.37 229	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		7.60 355	10.13 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	91.20 145	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		8.28 354	11.04 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	99.40 112	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 388	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 133					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 133					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 392

eth-test					0.00 392

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 28				99.80 51	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 58	98.79 37	99.96 28	98.40 137	97.66 15

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 45	98.43 118					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 125

sam_mvs1												94.72 61				99.59 125

sam_mvs												94.25 75

MTGPA								98.28 162

test_post1							95.78 350				59.23 384	93.20 104	97.74 247	91.06 238

test_post											63.35 381	94.43 65	98.13 227

patchmatchnet-post											91.70 348	95.12 49	97.95 238

MTMP							99.87 91	96.49 323

gm-plane-assit					96.97 229	93.76 204			91.47 219		98.96 151		98.79 173	94.92 170

test9_res														99.71 30	99.99 21	100.00 1

agg_prior2														99.48 37	100.00 1	100.00 1

test_prior4						98.05 65	99.94 61

test_prior				99.43 34	99.94 13	98.49 57		98.65 67					99.80 111			99.99 23

新几何2							99.40 197

旧先验1					99.76 66	97.52 84		98.64 69			99.85 30	95.63 41			99.94 54	99.99 23

无先验							99.49 188	98.71 59	93.46 150				100.00 1	94.36 185		99.99 23

原ACMM2							99.90 79

testdata2													99.99 36	90.54 251

segment_acmp												96.68 26

testdata1							99.28 217		96.35 60

plane_prior7					95.71 272	91.59 261

plane_prior6					95.76 267	91.72 256						80.47 256

plane_prior5								97.87 204					98.37 210	97.79 118	89.55 231	94.52 241

plane_prior4											98.59 180

plane_prior2							99.84 111		96.38 56

plane_prior1					95.73 269

plane_prior						91.74 253	99.86 104		96.76 44						89.59 230

n2								0.00 393

nn								0.00 393

door-mid								89.69 377

test11								98.44 110

door								90.31 374

HQP5-MVS						91.85 249

BP-MVS														97.92 111

HQP3-MVS								97.89 202							89.60 228

HQP2-MVS												80.65 252

NP-MVS					95.77 266	91.79 251					98.65 176

ACMMP++_ref															87.04 266

ACMMP++															88.23 253

Test By Simon												92.82 114

High-resolution multi-view benchmark