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.

fmvsm_l_mol_unc0.5_1		97.99 4	98.12 1	97.58 54	98.16 114	93.34 73	96.88 235	98.28 52	97.29 4	99.72 1	99.45 1	94.43 14	99.79 47	99.20 12	99.66 10	99.62 27

fmvsm_l_conf0.5_n_9		97.59 14	97.79 7	96.97 88	98.28 96	91.49 147	97.61 141	98.71 13	97.10 6	99.70 2	98.93 25	90.95 78	99.77 54	99.35 6	99.53 34	99.65 21

fmvsm_s_conf0.5_n_9		97.33 28	97.57 16	96.62 103	98.43 84	90.32 209	97.80 105	98.53 29	97.24 5	99.62 3	99.14 3	88.65 111	99.80 41	99.54 1	99.15 95	99.74 10

fmvsm_s_conf0.5_n_10		97.29 32	97.40 27	96.97 88	98.24 102	91.96 129	97.89 89	98.72 12	96.77 8	99.46 4	99.06 13	87.78 130	99.84 27	99.40 4	99.27 76	99.12 95

fmvsm_s_conf0.5_n_11		97.30 30	97.59 15	96.43 121	98.42 85	91.37 154	98.04 64	98.00 119	97.30 3	99.45 5	99.21 2	89.28 99	99.80 41	99.27 10	99.35 70	98.12 232

fmvsm_l_conf0.5_n_3		97.64 11	97.60 14	97.79 35	98.14 116	93.94 58	97.93 84	98.65 23	96.70 9	99.38 6	99.07 12	89.92 93	99.81 36	99.16 15	99.43 54	99.61 31

fmvsm_s_conf0.5_n_2		96.62 71	96.82 56	96.02 156	97.98 128	90.43 200	97.50 156	98.59 26	96.59 11	99.31 7	99.08 9	84.47 214	99.75 60	99.37 5	98.45 134	97.88 253

fmvsm_l_conf0.5_n		97.65 10	97.75 9	97.34 63	98.21 108	92.75 95	97.83 99	98.73 10	95.04 48	99.30 8	98.84 39	93.34 27	99.78 51	99.32 7	99.13 98	99.50 53

test_fmvsm_n_1920		97.55 17	97.89 5	96.53 107	98.41 87	91.73 133	98.01 67	99.02 1	96.37 14	99.30 8	98.92 26	92.39 46	99.79 47	99.16 15	99.46 47	98.08 240

fmvsm_s_conf0.5_n_3		97.15 37	97.36 29	96.52 109	97.98 128	91.19 164	97.84 96	98.65 23	97.08 7	99.25 10	99.10 7	87.88 128	99.79 47	99.32 7	99.18 91	98.59 181

fmvsm_l_conf0.5_n_a		97.63 12	97.76 8	97.26 70	98.25 101	92.59 103	97.81 104	98.68 18	94.93 51	99.24 11	98.87 34	93.52 24	99.79 47	99.32 7	99.21 84	99.40 67

fmvsm_s_conf0.5_n_6		97.08 40	97.17 31	96.81 91	97.28 172	91.73 133	97.75 111	98.50 30	94.86 55	99.22 12	98.78 43	89.75 96	99.76 56	99.10 18	99.29 74	98.94 126

fmvsm_s_conf0.5_n_8		97.32 29	97.48 24	96.85 90	98.28 96	91.07 172	97.76 109	98.62 25	97.53 2	99.20 13	99.12 6	88.24 119	99.81 36	99.41 3	99.17 92	99.67 16

SED-MVS		98.05 3	97.99 3	98.24 12	99.42 10	95.30 19	98.25 40	98.27 56	95.13 43	99.19 14	98.89 31	95.54 5	99.85 22	97.52 43	99.66 10	99.56 41

test_241102_ONE					99.42 10	95.30 19		98.27 56	95.09 46	99.19 14	98.81 40	95.54 5	99.65 81

fmvsm_s_conf0.1_n_2		96.33 85	96.44 80	96.00 160	97.30 170	90.37 206	97.53 153	97.92 129	96.52 12	99.14 16	99.08 9	83.21 238	99.74 61	99.22 11	98.06 153	97.88 253

fmvsm_s_conf0.5_n_4		96.75 63	97.07 35	95.79 180	97.76 144	89.57 241	97.66 130	98.66 21	95.36 33	99.03 17	98.90 28	88.39 116	99.73 63	99.17 14	98.66 122	98.08 240

SD-MVS		97.41 24	97.53 19	97.06 84	98.57 79	94.46 40	97.92 85	98.14 85	94.82 60	99.01 18	98.55 52	94.18 16	97.41 417	96.94 60	99.64 15	99.32 75
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
test0726					99.45 6	95.36 15	98.31 32	98.29 50	94.92 53	98.99 19	98.92 26	95.08 9

TestfortrainingZip a		97.79 8	97.62 13	98.28 10	99.56 1	95.15 25	98.69 11	98.35 41	95.63 26	98.95 20	98.95 21	93.45 25	99.88 4	96.63 71	98.41 137	99.82 1

IU-MVS					99.42 10	95.39 13		97.94 126	90.40 275	98.94 21				97.41 50	99.66 10	99.74 10

fmvsm_s_conf0.1_n_a		96.40 80	96.47 74	96.16 144	95.48 330	90.69 191	97.91 86	98.33 45	94.07 95	98.93 22	99.14 3	87.44 144	99.61 93	98.63 27	98.32 140	98.18 225

DVP-MVS++		98.06 2	97.99 3	98.28 10	98.67 68	95.39 13	99.29 1	98.28 52	94.78 64	98.93 22	98.87 34	96.04 2	99.86 11	97.45 47	99.58 26	99.59 33

test_241102_TWO								98.27 56	95.13 43	98.93 22	98.89 31	94.99 12	99.85 22	97.52 43	99.65 14	99.74 10

test_fmvsmconf_n		97.49 22	97.56 17	97.29 66	97.44 167	92.37 110	97.91 86	98.88 4	95.83 20	98.92 25	99.05 15	91.45 63	99.80 41	99.12 17	99.46 47	99.69 15

fmvsm_s_conf0.5_n_a		96.75 63	96.93 47	96.20 142	97.64 153	90.72 190	98.00 68	98.73 10	94.55 76	98.91 26	99.08 9	88.22 120	99.63 90	98.91 22	98.37 138	98.25 220

fmvsm_s_conf0.5_n_5		97.00 46	96.97 44	97.09 81	97.58 163	92.56 104	97.68 126	98.47 34	94.02 97	98.90 27	98.89 31	88.94 105	99.78 51	99.18 13	99.03 107	98.93 130

PC_three_1452									90.77 251	98.89 28	98.28 87	96.24 1	98.35 295	95.76 108	99.58 26	99.59 33

SMA-MVS		97.35 26	97.03 41	98.30 9	99.06 45	95.42 12	97.94 82	98.18 78	90.57 268	98.85 29	98.94 24	93.33 28	99.83 32	96.72 68	99.68 4	99.63 26
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
fmvsm_s_conf0.1_n		96.58 74	96.77 61	96.01 159	96.67 235	90.25 211	97.91 86	98.38 37	94.48 80	98.84 30	99.14 3	88.06 122	99.62 92	98.82 24	98.60 126	98.15 229

fmvsm_s_conf0.5_n		96.85 55	97.13 32	96.04 153	98.07 123	90.28 210	97.97 78	98.76 9	94.93 51	98.84 30	99.06 13	88.80 108	99.65 81	99.06 19	98.63 124	98.18 225

aaatest				98.00 25	99.56 1	94.50 37	98.69 11	98.70 16	93.45 125	98.73 32	98.53 54		99.86 11	97.40 51	99.58 26	99.65 21

MED-MVS		98.08 1	98.08 2	98.06 21	99.56 1	94.50 37	98.69 11	98.70 16	95.63 26	98.73 32	98.95 21	95.46 7	99.86 11	97.40 51	99.63 17	99.82 1

DVP-MVS		97.91 5	97.81 6	98.22 15	99.45 6	95.36 15	98.21 48	97.85 139	94.92 53	98.73 32	98.87 34	95.08 9	99.84 27	97.52 43	99.67 6	99.48 57
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									94.78 64	98.73 32	98.87 34	95.87 4	99.84 27	97.45 47	99.72 2	99.77 4

DPE-MVS		97.86 6	97.65 11	98.47 5	99.17 39	95.78 8	97.21 202	98.35 41	95.16 41	98.71 36	98.80 41	95.05 11	99.89 3	96.70 70	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
lecture		97.58 16	97.63 12	97.43 60	99.37 19	92.93 89	98.86 7	98.85 5	95.27 37	98.65 37	98.90 28	91.97 54	99.80 41	97.63 39	99.21 84	99.57 37

TSAR-MVS + MP.		97.42 23	97.33 30	97.69 47	99.25 33	94.24 47	98.07 61	97.85 139	93.72 109	98.57 38	98.35 73	93.69 21	99.40 136	97.06 58	99.46 47	99.44 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSP-MVS		97.59 14	97.54 18	97.73 43	99.40 14	93.77 63	98.53 19	98.29 50	95.55 30	98.56 39	97.81 141	93.90 18	99.65 81	96.62 72	99.21 84	99.77 4
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
FOURS1					99.55 4	93.34 73	99.29 1	98.35 41	94.98 49	98.49 40

test_one_0601					99.32 27	95.20 22		98.25 62	95.13 43	98.48 41	98.87 34	95.16 8

fmvsm_s_conf0.5_n_7		96.45 78	96.80 58	95.37 216	97.29 171	88.38 298	97.23 199	98.47 34	95.14 42	98.43 42	99.09 8	87.58 136	99.72 67	98.80 26	99.21 84	98.02 244

test_fmvsmconf0.1_n		97.09 39	97.06 36	97.19 75	95.67 321	92.21 117	97.95 81	98.27 56	95.78 24	98.40 43	99.00 17	89.99 91	99.78 51	99.06 19	99.41 60	99.59 33

APDe-MVS		97.82 7	97.73 10	98.08 20	99.15 40	94.82 31	98.81 8	98.30 48	94.76 67	98.30 44	98.90 28	93.77 20	99.68 77	97.93 30	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.39 25	97.13 32	98.17 17	99.02 49	95.28 21	98.23 44	98.27 56	92.37 179	98.27 45	98.65 48	93.33 28	99.72 67	96.49 77	99.52 36	99.51 50

BridgeMVS		96.84 57	96.89 49	96.68 95	97.63 155	92.22 116	98.17 54	97.82 146	94.44 82	98.23 46	97.36 188	90.97 77	99.22 155	97.74 33	99.66 10	98.61 179

TestfortrainingZip				98.34 8	98.54 80	96.25 4	98.69 11	97.85 139	94.15 92	98.17 47	97.94 114	94.00 17	99.63 90		97.45 176	99.15 89

aaEdge-Enhanced		97.54 18	97.39 28	98.00 25	99.21 37	94.50 37	97.75 111	98.34 44	94.23 90	98.15 48	98.53 54	93.32 30	99.84 27	97.40 51	99.58 26	99.65 21

SteuartSystems-ACMMP		97.62 13	97.53 19	97.87 29	98.39 90	94.25 46	98.43 27	98.27 56	95.34 35	98.11 49	98.56 50	94.53 13	99.71 69	96.57 75	99.62 20	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
test_vis1_n_1920		94.17 176	94.58 150	92.91 368	97.42 168	82.02 440	97.83 99	97.85 139	94.68 70	98.10 50	98.49 59	70.15 425	99.32 144	97.91 31	98.82 114	97.40 283

test_part2					99.28 31	95.74 9				98.10 50

APD-MVS		96.95 48	96.60 67	98.01 23	99.03 48	94.93 30	97.72 119	98.10 93	91.50 216	98.01 52	98.32 81	92.33 47	99.58 101	94.85 145	99.51 39	99.53 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test-260524					99.31 29	95.74 9		98.19 75		97.99 53		93.53 23	99.87 8	98.08 29	99.63 17

reproduce_model		97.51 21	97.51 21	97.50 56	98.99 53	93.01 85	97.79 107	98.21 68	95.73 25	97.99 53	99.03 16	92.63 41	99.82 34	97.80 32	99.42 57	99.67 16

patch_mono-2		96.83 58	97.44 25	95.01 237	99.05 46	85.39 392	96.98 222	98.77 8	94.70 69	97.99 53	98.66 46	93.61 22	99.91 1	97.67 38	99.50 41	99.72 14

DeepPCF-MVS	93.97 1	96.61 72	97.09 34	95.15 228	98.09 119	86.63 358	96.00 328	98.15 83	95.43 31	97.95 56	98.56 50	93.40 26	99.36 140	96.77 65	99.48 45	99.45 60

ACMMP_NAP		97.20 34	96.86 50	98.23 13	99.09 41	95.16 24	97.60 142	98.19 75	92.82 161	97.93 57	98.74 45	91.60 61	99.86 11	96.26 82	99.52 36	99.67 16

reproduce-ours		97.53 19	97.51 21	97.60 52	98.97 54	93.31 76	97.71 122	98.20 70	95.80 22	97.88 58	98.98 19	92.91 33	99.81 36	97.68 34	99.43 54	99.67 16

our_new_method		97.53 19	97.51 21	97.60 52	98.97 54	93.31 76	97.71 122	98.20 70	95.80 22	97.88 58	98.98 19	92.91 33	99.81 36	97.68 34	99.43 54	99.67 16

9.14			96.75 62		98.93 57		97.73 116	98.23 67	91.28 228	97.88 58	98.44 65	93.00 32	99.65 81	95.76 108	99.47 46

CNVR-MVS		97.68 9	97.44 25	98.37 7	98.90 60	95.86 7	97.27 193	98.08 95	95.81 21	97.87 61	98.31 82	94.26 15	99.68 77	97.02 59	99.49 44	99.57 37

test_vis1_n		92.37 260	92.26 244	92.72 376	94.75 380	82.64 430	98.02 66	96.80 307	91.18 235	97.77 62	97.93 115	58.02 484	98.29 302	97.63 39	98.21 145	97.23 292

test_cas_vis1_n_1920		94.48 169	94.55 154	94.28 291	96.78 225	86.45 364	97.63 137	97.64 166	93.32 131	97.68 63	98.36 72	73.75 393	99.08 180	96.73 67	99.05 104	97.31 288

test_fmvsmconf0.01_n		96.15 89	95.85 92	97.03 85	92.66 447	91.83 132	97.97 78	97.84 144	95.57 29	97.53 64	99.00 17	84.20 221	99.76 56	98.82 24	99.08 102	99.48 57

MM		97.29 32	96.98 43	98.23 13	98.01 126	95.03 29	98.07 61	95.76 368	97.78 1	97.52 65	98.80 41	88.09 121	99.86 11	99.44 2	99.37 68	99.80 3

VNet		95.89 99	95.45 103	97.21 73	98.07 123	92.94 88	97.50 156	98.15 83	93.87 104	97.52 65	97.61 168	85.29 197	99.53 115	95.81 107	95.27 260	99.16 87

SR-MVS		97.01 45	96.86 50	97.47 58	99.09 41	93.27 78	97.98 72	98.07 100	93.75 108	97.45 67	98.48 62	91.43 65	99.59 98	96.22 85	99.27 76	99.54 46

APD-MVS_3200maxsize		96.81 59	96.71 64	97.12 78	99.01 52	92.31 113	97.98 72	98.06 103	93.11 142	97.44 68	98.55 52	90.93 79	99.55 111	96.06 95	99.25 81	99.51 50

TSAR-MVS + GP.		96.69 68	96.49 72	97.27 69	98.31 94	93.39 69	96.79 248	96.72 310	94.17 91	97.44 68	97.66 160	92.76 36	99.33 142	96.86 64	97.76 165	99.08 101

SR-MVS-dyc-post		96.88 52	96.80 58	97.11 80	99.02 49	92.34 111	97.98 72	98.03 112	93.52 122	97.43 70	98.51 57	91.40 66	99.56 109	96.05 96	99.26 79	99.43 64

RE-MVS-def			96.72 63		99.02 49	92.34 111	97.98 72	98.03 112	93.52 122	97.43 70	98.51 57	90.71 83		96.05 96	99.26 79	99.43 64

dcpmvs_2		96.37 82	97.05 39	94.31 289	98.96 56	84.11 413	97.56 147	97.51 197	93.92 102	97.43 70	98.52 56	92.75 37	99.32 144	97.32 56	99.50 41	99.51 50

MVSMamba_PlusPlus		96.51 75	96.48 73	96.59 104	98.07 123	91.97 127	98.14 55	97.79 148	90.43 273	97.34 73	97.52 178	91.29 69	99.19 158	98.12 28	99.64 15	98.60 180

旧先验2							95.94 331		81.66 464	97.34 73			98.82 212	92.26 213

MSLP-MVS++		96.94 49	97.06 36	96.59 104	98.72 65	91.86 131	97.67 127	98.49 31	94.66 72	97.24 75	98.41 68	92.31 49	98.94 198	96.61 73	99.46 47	98.96 119

HFP-MVS		97.14 38	96.92 48	97.83 31	99.42 10	94.12 52	98.52 20	98.32 46	93.21 133	97.18 76	98.29 85	92.08 51	99.83 32	95.63 116	99.59 22	99.54 46

MGCNet		96.74 65	96.31 82	98.02 22	96.87 207	94.65 33	97.58 143	94.39 439	96.47 13	97.16 77	98.39 69	87.53 139	99.87 8	98.97 21	99.41 60	99.55 44

ACMMPR		97.07 42	96.84 52	97.79 35	99.44 9	93.88 59	98.52 20	98.31 47	93.21 133	97.15 78	98.33 79	91.35 67	99.86 11	95.63 116	99.59 22	99.62 27

region2R		97.07 42	96.84 52	97.77 39	99.46 5	93.79 61	98.52 20	98.24 64	93.19 136	97.14 79	98.34 76	91.59 62	99.87 8	95.46 125	99.59 22	99.64 25

PGM-MVS		96.81 59	96.53 70	97.65 48	99.35 25	93.53 67	97.65 131	98.98 2	92.22 186	97.14 79	98.44 65	91.17 73	99.85 22	94.35 172	99.46 47	99.57 37

PHI-MVS		96.77 61	96.46 77	97.71 46	98.40 88	94.07 54	98.21 48	98.45 36	89.86 285	97.11 81	98.01 107	92.52 44	99.69 75	96.03 99	99.53 34	99.36 73

NCCC		97.30 30	97.03 41	98.11 19	98.77 63	95.06 28	97.34 182	98.04 110	95.96 16	97.09 82	97.88 128	93.18 31	99.71 69	95.84 106	99.17 92	99.56 41

CS-MVS		96.86 53	97.06 36	96.26 137	98.16 114	91.16 169	99.09 3	97.87 134	95.30 36	97.06 83	98.03 104	91.72 56	98.71 246	97.10 57	99.17 92	98.90 135

ZD-MVS					99.05 46	94.59 35		98.08 95	89.22 310	97.03 84	98.10 96	92.52 44	99.65 81	94.58 165	99.31 73

testdata				95.46 213	98.18 113	88.90 277		97.66 162	82.73 454	97.03 84	98.07 99	90.06 89	98.85 208	89.67 281	98.98 109	98.64 177

SPE-MVS-test		96.89 51	97.04 40	96.45 120	98.29 95	91.66 140	99.03 4	97.85 139	95.84 19	96.90 86	97.97 112	91.24 70	98.75 235	96.92 61	99.33 71	98.94 126

mvsany_test1		93.93 195	93.98 173	93.78 324	94.94 370	86.80 351	94.62 399	92.55 474	88.77 332	96.85 87	98.49 59	88.98 103	98.08 327	95.03 135	95.62 250	96.46 318

GDP-MVS		95.62 108	95.13 119	97.09 81	96.79 220	93.26 79	97.89 89	97.83 145	93.58 114	96.80 88	97.82 139	83.06 245	99.16 165	94.40 169	97.95 159	98.87 146

test_fmvs1		93.21 223	93.53 188	92.25 391	96.55 253	81.20 447	97.40 176	96.96 289	90.68 256	96.80 88	98.04 102	69.25 434	98.40 287	97.58 42	98.50 129	97.16 295

test_fmvs1_n		92.73 249	92.88 217	92.29 388	96.08 304	81.05 448	97.98 72	97.08 270	90.72 254	96.79 90	98.18 92	63.07 473	98.45 284	97.62 41	98.42 136	97.36 284

HPM-MVS_fast		96.51 75	96.27 84	97.22 72	99.32 27	92.74 96	98.74 10	98.06 103	90.57 268	96.77 91	98.35 73	90.21 88	99.53 115	94.80 152	99.63 17	99.38 71

h-mvs33		94.15 179	93.52 190	96.04 153	97.81 141	90.22 212	97.62 140	97.58 178	95.19 39	96.74 92	97.45 181	83.67 229	99.61 93	95.85 104	79.73 453	98.29 217

hse-mvs2		93.45 216	92.99 210	94.81 251	97.02 194	88.59 288	96.69 262	96.47 328	95.19 39	96.74 92	96.16 269	83.67 229	98.48 282	95.85 104	79.13 457	97.35 286

GST-MVS		96.85 55	96.52 71	97.82 32	99.36 23	94.14 51	98.29 34	98.13 86	92.72 164	96.70 94	98.06 100	91.35 67	99.86 11	94.83 148	99.28 75	99.47 59

xiu_mvs_v1_base_debu		95.01 142	94.76 140	95.75 186	96.58 246	91.71 136	96.25 307	97.35 235	92.99 146	96.70 94	96.63 242	82.67 256	99.44 132	96.22 85	97.46 172	96.11 330

xiu_mvs_v1_base		95.01 142	94.76 140	95.75 186	96.58 246	91.71 136	96.25 307	97.35 235	92.99 146	96.70 94	96.63 242	82.67 256	99.44 132	96.22 85	97.46 172	96.11 330

xiu_mvs_v1_base_debi		95.01 142	94.76 140	95.75 186	96.58 246	91.71 136	96.25 307	97.35 235	92.99 146	96.70 94	96.63 242	82.67 256	99.44 132	96.22 85	97.46 172	96.11 330

CDPH-MVS		95.97 95	95.38 109	97.77 39	98.93 57	94.44 41	96.35 295	97.88 132	86.98 383	96.65 98	97.89 123	91.99 53	99.47 128	92.26 213	99.46 47	99.39 69

PRO-TEST		95.74 103	95.69 94	95.91 165	96.68 234	90.34 208	97.49 164	97.61 173	93.99 99	96.64 99	97.00 218	88.00 125	98.54 275	95.58 122	98.18 147	98.84 152

EC-MVSNet		96.42 79	96.47 74	96.26 137	97.01 195	91.52 146	98.89 5	97.75 151	94.42 83	96.64 99	97.68 157	89.32 98	98.60 268	97.45 47	99.11 101	98.67 176

UA-Net		95.95 96	95.53 99	97.20 74	97.67 149	92.98 87	97.65 131	98.13 86	94.81 62	96.61 101	98.35 73	88.87 106	99.51 120	90.36 267	97.35 180	99.11 97

HPM-MVS++		97.34 27	96.97 44	98.47 5	99.08 43	96.16 5	97.55 152	97.97 123	95.59 28	96.61 101	97.89 123	92.57 43	99.84 27	95.95 101	99.51 39	99.40 67

XVS		97.18 35	96.96 46	97.81 33	99.38 17	94.03 56	98.59 17	98.20 70	94.85 56	96.59 103	98.29 85	91.70 58	99.80 41	95.66 111	99.40 62	99.62 27

X-MVStestdata		91.71 287	89.67 357	97.81 33	99.38 17	94.03 56	98.59 17	98.20 70	94.85 56	96.59 103	32.69 553	91.70 58	99.80 41	95.66 111	99.40 62	99.62 27

DeepC-MVS_fast	93.89 2	96.93 50	96.64 66	97.78 37	98.64 74	94.30 43	97.41 172	98.04 110	94.81 62	96.59 103	98.37 71	91.24 70	99.64 89	95.16 132	99.52 36	99.42 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NormalMVS		96.36 83	96.11 87	97.12 78	99.37 19	92.90 90	97.99 69	97.63 168	95.92 17	96.57 106	97.93 115	85.34 195	99.50 123	94.99 137	99.21 84	98.97 116

SymmetryMVS		95.94 97	95.54 98	97.15 76	97.85 138	92.90 90	97.99 69	96.91 297	95.92 17	96.57 106	97.93 115	85.34 195	99.50 123	94.99 137	96.39 232	99.05 106

diffmvs_AUTHOR		95.33 118	95.27 114	95.50 208	96.37 274	89.08 268	96.08 321	97.38 230	93.09 144	96.53 108	97.74 150	86.45 164	98.68 250	96.32 80	97.48 171	98.75 167

PS-MVSNAJ		95.37 116	95.33 111	95.49 209	97.35 169	90.66 193	95.31 371	97.48 203	93.85 105	96.51 109	95.70 296	88.65 111	99.65 81	94.80 152	98.27 143	96.17 324

EI-MVSNet-Vis-set		96.51 75	96.47 74	96.63 100	98.24 102	91.20 163	96.89 233	97.73 154	94.74 68	96.49 110	98.49 59	90.88 81	99.58 101	96.44 78	98.32 140	99.13 92

ETV-MVS		96.02 92	95.89 91	96.40 124	97.16 178	92.44 108	97.47 166	97.77 150	94.55 76	96.48 111	94.51 353	91.23 72	98.92 201	95.65 114	98.19 146	97.82 261

alignmvs		95.87 101	95.23 115	97.78 37	97.56 165	95.19 23	97.86 92	97.17 259	94.39 86	96.47 112	96.40 256	85.89 176	99.20 157	96.21 89	95.11 265	98.95 123

KinetiMVS		95.26 122	94.75 143	96.79 92	96.99 197	92.05 123	97.82 101	97.78 149	94.77 66	96.46 113	97.70 154	80.62 301	99.34 141	92.37 212	98.28 142	98.97 116

xiu_mvs_v2_base		95.32 119	95.29 112	95.40 215	97.22 174	90.50 196	95.44 364	97.44 218	93.70 111	96.46 113	96.18 266	88.59 115	99.53 115	94.79 155	97.81 162	96.17 324

CP-MVS		97.02 44	96.81 57	97.64 50	99.33 26	93.54 66	98.80 9	98.28 52	92.99 146	96.45 115	98.30 84	91.90 55	99.85 22	95.61 118	99.68 4	99.54 46

HPM-MVS		96.69 68	96.45 78	97.40 61	99.36 23	93.11 83	98.87 6	98.06 103	91.17 236	96.40 116	97.99 110	90.99 76	99.58 101	95.61 118	99.61 21	99.49 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ZNCC-MVS		96.96 47	96.67 65	97.85 30	99.37 19	94.12 52	98.49 24	98.18 78	92.64 169	96.39 117	98.18 92	91.61 60	99.88 4	95.59 121	99.55 31	99.57 37

balanced_ft_v1		95.56 112	95.40 107	96.07 150	97.16 178	90.36 207	98.23 44	97.31 240	92.89 158	96.36 118	97.11 206	83.28 236	99.26 151	97.40 51	98.80 116	98.58 182

BP-MVS1		95.89 99	95.49 100	97.08 83	96.67 235	93.20 80	98.08 59	96.32 336	94.56 75	96.32 119	97.84 135	84.07 224	99.15 167	96.75 66	98.78 117	98.90 135

diffmvs		95.25 124	95.13 119	95.63 194	96.43 268	89.34 255	95.99 329	97.35 235	92.83 160	96.31 120	97.37 187	86.44 165	98.67 253	96.26 82	97.19 190	98.87 146
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LFMVS		93.60 206	92.63 229	96.52 109	98.13 118	91.27 158	97.94 82	93.39 462	90.57 268	96.29 121	98.31 82	69.00 436	99.16 165	94.18 174	95.87 242	99.12 95

sasdasda		96.02 92	95.45 103	97.75 41	97.59 159	95.15 25	98.28 35	97.60 174	94.52 78	96.27 122	96.12 271	87.65 133	99.18 161	96.20 90	94.82 269	98.91 132

canonicalmvs		96.02 92	95.45 103	97.75 41	97.59 159	95.15 25	98.28 35	97.60 174	94.52 78	96.27 122	96.12 271	87.65 133	99.18 161	96.20 90	94.82 269	98.91 132

MVSFormer		95.37 116	95.16 117	95.99 161	96.34 276	91.21 161	98.22 46	97.57 181	91.42 220	96.22 124	97.32 189	86.20 171	97.92 359	94.07 175	99.05 104	98.85 148

lupinMVS		94.99 146	94.56 151	96.29 135	96.34 276	91.21 161	95.83 338	96.27 343	88.93 323	96.22 124	96.88 224	86.20 171	98.85 208	95.27 128	99.05 104	98.82 155

MGCFI-Net		95.94 97	95.40 107	97.56 55	97.59 159	94.62 34	98.21 48	97.57 181	94.41 84	96.17 126	96.16 269	87.54 138	99.17 163	96.19 92	94.73 274	98.91 132

EI-MVSNet-UG-set		96.34 84	96.30 83	96.47 117	98.20 109	90.93 179	96.86 237	97.72 156	94.67 71	96.16 127	98.46 63	90.43 86	99.58 101	96.23 84	97.96 158	98.90 135

MTAPA		97.08 40	96.78 60	97.97 28	99.37 19	94.42 42	97.24 195	98.08 95	95.07 47	96.11 128	98.59 49	90.88 81	99.90 2	96.18 94	99.50 41	99.58 36

test_fmvsmvis_n_1920		96.70 66	96.84 52	96.31 131	96.62 237	91.73 133	97.98 72	98.30 48	96.19 15	96.10 129	98.95 21	89.42 97	99.76 56	98.90 23	99.08 102	97.43 281

MCST-MVS		97.18 35	96.84 52	98.20 16	99.30 30	95.35 17	97.12 209	98.07 100	93.54 119	96.08 130	97.69 156	93.86 19	99.71 69	96.50 76	99.39 64	99.55 44

TEST9					98.70 66	94.19 48	96.41 286	98.02 115	88.17 348	96.03 131	97.56 175	92.74 38	99.59 98

train_agg		96.30 86	95.83 93	97.72 44	98.70 66	94.19 48	96.41 286	98.02 115	88.58 335	96.03 131	97.56 175	92.73 39	99.59 98	95.04 134	99.37 68	99.39 69

test_prior2							96.35 295		92.80 162	96.03 131	97.59 171	92.01 52		95.01 136	99.38 65

jason		94.84 154	94.39 161	96.18 143	95.52 328	90.93 179	96.09 320	96.52 325	89.28 308	96.01 134	97.32 189	84.70 210	98.77 223	95.15 133	98.91 113	98.85 148
jason: jason.
onestephybrid01		95.12 134	95.01 126	95.46 213	96.39 273	88.92 275	96.28 305	97.27 246	92.67 165	96.00 135	97.73 153	86.28 167	98.66 256	95.58 122	96.85 203	98.79 158

test_8					98.67 68	94.06 55	96.37 294	98.01 118	88.58 335	95.98 136	97.55 177	92.73 39	99.58 101

mPP-MVS		96.86 53	96.60 67	97.64 50	99.40 14	93.44 68	98.50 23	98.09 94	93.27 132	95.95 137	98.33 79	91.04 75	99.88 4	95.20 130	99.57 30	99.60 32

LuminaMVS		94.89 150	94.35 163	96.53 107	95.48 330	92.80 94	96.88 235	96.18 353	92.85 159	95.92 138	96.87 226	81.44 283	98.83 211	96.43 79	97.10 193	97.94 249

DELS-MVS		96.61 72	96.38 81	97.30 65	97.79 142	93.19 81	95.96 330	98.18 78	95.23 38	95.87 139	97.65 161	91.45 63	99.70 74	95.87 102	99.44 53	99.00 113
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
VDD-MVS		93.82 199	93.08 208	96.02 156	97.88 137	89.96 225	97.72 119	95.85 364	92.43 177	95.86 140	98.44 65	68.42 443	99.39 137	96.31 81	94.85 267	98.71 173

MVS_111021_HR		96.68 70	96.58 69	96.99 86	98.46 81	92.31 113	96.20 313	98.90 3	94.30 89	95.86 140	97.74 150	92.33 47	99.38 139	96.04 98	99.42 57	99.28 78

MVS_111021_LR		96.24 88	96.19 86	96.39 126	98.23 107	91.35 156	96.24 310	98.79 7	93.99 99	95.80 142	97.65 161	89.92 93	99.24 153	95.87 102	99.20 89	98.58 182

VDDNet		93.05 232	92.07 247	96.02 156	96.84 211	90.39 202	98.08 59	95.85 364	86.22 399	95.79 143	98.46 63	67.59 446	99.19 158	94.92 140	94.85 267	98.47 196

新几何1				97.32 64	98.60 75	93.59 65		97.75 151	81.58 465	95.75 144	97.85 133	90.04 90	99.67 79	86.50 363	99.13 98	98.69 174

guyue		95.17 133	94.96 129	95.82 175	96.97 199	89.65 236	97.56 147	95.58 380	94.82 60	95.72 145	97.42 184	82.90 250	98.84 210	96.71 69	96.93 198	98.96 119

test_yl		94.78 158	94.23 166	96.43 121	97.74 145	91.22 159	96.85 238	97.10 267	91.23 233	95.71 146	96.93 219	84.30 218	99.31 146	93.10 199	95.12 263	98.75 167

DCV-MVSNet		94.78 158	94.23 166	96.43 121	97.74 145	91.22 159	96.85 238	97.10 267	91.23 233	95.71 146	96.93 219	84.30 218	99.31 146	93.10 199	95.12 263	98.75 167

AstraMVS		94.82 156	94.64 146	95.34 219	96.36 275	88.09 315	97.58 143	94.56 431	94.98 49	95.70 148	97.92 118	81.93 276	98.93 199	96.87 63	95.88 241	98.99 115

agg_prior					98.67 68	93.79 61		98.00 119		95.68 149			99.57 108

MG-MVS		95.61 109	95.38 109	96.31 131	98.42 85	90.53 195	96.04 324	97.48 203	93.47 124	95.67 150	98.10 96	89.17 101	99.25 152	91.27 242	98.77 118	99.13 92

viewmamba		95.18 132	95.15 118	95.26 223	96.31 278	88.25 305	96.29 303	97.27 246	93.61 113	95.65 151	97.91 120	86.79 156	98.64 260	95.69 110	96.82 205	98.88 143

baseline		95.58 110	95.42 106	96.08 148	96.78 225	90.41 201	97.16 206	97.45 214	93.69 112	95.65 151	97.85 133	87.29 148	98.68 250	95.66 111	97.25 187	99.13 92

MVS_Test		94.89 150	94.62 147	95.68 192	96.83 214	89.55 244	96.70 260	97.17 259	91.17 236	95.60 153	96.11 275	87.87 129	98.76 229	93.01 206	97.17 191	98.72 171

hybridnocas07		94.93 147	94.78 139	95.37 216	96.27 280	88.62 286	96.10 319	97.26 248	92.35 180	95.58 154	97.48 179	85.60 190	98.65 258	95.47 124	96.90 201	98.85 148

DPM-MVS		95.69 104	94.92 130	98.01 23	98.08 122	95.71 11	95.27 374	97.62 172	90.43 273	95.55 155	97.07 209	91.72 56	99.50 123	89.62 283	98.94 111	98.82 155

MP-MVS-pluss		96.70 66	96.27 84	97.98 27	99.23 36	94.71 32	96.96 224	98.06 103	90.67 257	95.55 155	98.78 43	91.07 74	99.86 11	96.58 74	99.55 31	99.38 71
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 61	96.45 78	97.72 44	99.39 16	93.80 60	98.41 28	98.06 103	93.37 128	95.54 157	98.34 76	90.59 85	99.88 4	94.83 148	99.54 33	99.49 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test12				97.65 48	98.46 81	94.26 45		97.66 162		95.52 158		90.89 80	99.46 129		99.25 81	99.22 83

viewmanbaseed2359cas		95.24 125	95.02 125	95.91 165	96.87 207	89.98 222	96.82 243	97.49 200	92.26 184	95.47 159	97.82 139	86.47 163	98.69 248	94.80 152	97.20 189	99.06 105

casdiffmvs		95.64 107	95.49 100	96.08 148	96.76 231	90.45 198	97.29 188	97.44 218	94.00 98	95.46 160	97.98 111	87.52 141	98.73 239	95.64 115	97.33 181	99.08 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybrid		94.76 160	94.60 148	95.27 221	96.24 282	88.36 299	96.05 323	97.25 251	91.40 222	95.40 161	97.59 171	85.48 193	98.63 263	95.23 129	96.71 213	98.83 154

E3new		95.28 120	95.11 122	95.80 177	97.03 192	89.76 231	96.78 252	97.54 194	92.06 197	95.40 161	97.75 147	87.49 142	98.76 229	94.85 145	97.10 193	98.88 143

viewcassd2359sk11		95.26 122	95.09 123	95.80 177	96.95 201	89.72 233	96.80 247	97.56 189	92.21 188	95.37 163	97.80 143	87.17 151	98.77 223	94.82 150	97.10 193	98.90 135

viewmacassd2359aftdt		95.07 137	94.80 138	95.87 169	96.53 256	89.84 228	96.90 231	97.48 203	92.44 176	95.36 164	97.89 123	85.23 198	98.68 250	94.40 169	97.00 197	99.09 99

E2		95.20 128	95.00 127	95.79 180	96.79 220	89.66 234	96.82 243	97.58 178	92.35 180	95.28 165	97.83 137	86.68 158	98.76 229	94.79 155	96.92 199	98.95 123

E3		95.20 128	95.00 127	95.79 180	96.77 227	89.66 234	96.82 243	97.58 178	92.35 180	95.28 165	97.83 137	86.69 157	98.76 229	94.79 155	96.92 199	98.95 123

test222					98.24 102	92.21 117	95.33 369	97.60 174	79.22 478	95.25 167	97.84 135	88.80 108			99.15 95	98.72 171

Casviewmamba		95.67 106	95.55 97	96.03 155	96.95 201	90.12 214	97.72 119	97.55 193	94.10 94	95.23 168	98.18 92	87.32 147	98.80 217	95.40 126	97.52 170	99.19 84

test2506		91.60 296	90.78 301	94.04 304	97.66 151	83.81 416	98.27 37	75.53 520	93.43 126	95.23 168	98.21 89	67.21 449	99.07 184	93.01 206	98.49 130	99.25 81

原ACMM1				96.38 127	98.59 76	91.09 171		97.89 130	87.41 375	95.22 170	97.68 157	90.25 87	99.54 113	87.95 320	99.12 100	98.49 193

CPTT-MVS		95.57 111	95.19 116	96.70 94	99.27 32	91.48 149	98.33 31	98.11 91	87.79 363	95.17 171	98.03 104	87.09 152	99.61 93	93.51 190	99.42 57	99.02 107

casdiffmvs_mvg		95.81 102	95.57 96	96.51 113	96.87 207	91.49 147	97.50 156	97.56 189	93.99 99	95.13 172	97.92 118	87.89 127	98.78 219	95.97 100	97.33 181	99.26 80
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DP-MVS Recon		95.68 105	95.12 121	97.37 62	99.19 38	94.19 48	97.03 213	98.08 95	88.35 344	95.09 173	97.65 161	89.97 92	99.48 127	92.08 224	98.59 127	98.44 201

E5new		95.04 138	94.88 132	95.52 202	96.62 237	89.02 270	97.29 188	97.57 181	92.54 170	95.04 174	97.89 123	85.65 185	98.77 223	94.92 140	96.44 227	98.78 159

E6new		95.04 138	94.88 132	95.52 202	96.60 242	89.02 270	97.29 188	97.57 181	92.54 170	95.04 174	97.90 121	85.66 183	98.77 223	94.92 140	96.44 227	98.78 159

E6		95.04 138	94.88 132	95.52 202	96.60 242	89.02 270	97.29 188	97.57 181	92.54 170	95.04 174	97.90 121	85.66 183	98.77 223	94.92 140	96.44 227	98.78 159

E5		95.04 138	94.88 132	95.52 202	96.62 237	89.02 270	97.29 188	97.57 181	92.54 170	95.04 174	97.89 123	85.65 185	98.77 223	94.92 140	96.44 227	98.78 159

E4		95.09 135	94.86 136	95.77 183	96.58 246	89.56 242	96.85 238	97.56 189	92.50 174	95.03 178	97.86 131	86.03 174	98.78 219	94.71 158	96.65 217	98.96 119

dtuplus		94.16 178	93.98 173	94.70 260	96.18 291	86.85 350	96.04 324	97.07 273	89.75 292	95.02 179	97.79 145	84.94 207	98.62 266	92.62 211	96.43 231	98.62 178

viewmambaseed2359dif		94.28 172	94.14 168	94.71 259	96.21 283	86.97 347	95.93 332	97.11 266	89.00 318	95.00 180	97.70 154	86.02 175	98.59 272	93.71 186	96.59 219	98.57 184

RRT-MVS		94.51 167	94.35 163	94.98 241	96.40 269	86.55 361	97.56 147	97.41 224	93.19 136	94.93 181	97.04 211	79.12 330	99.30 148	96.19 92	97.32 183	99.09 99

Vis-MVSNet		95.23 126	94.81 137	96.51 113	97.18 177	91.58 144	98.26 39	98.12 88	94.38 87	94.90 182	98.15 95	82.28 266	98.92 201	91.45 239	98.58 128	99.01 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		96.39 81	96.02 88	97.50 56	97.62 156	93.38 70	97.02 215	97.96 124	95.42 32	94.86 183	97.81 141	87.38 146	99.82 34	96.88 62	99.20 89	99.29 76

Elysia		94.00 189	93.12 206	96.64 96	96.08 304	92.72 98	97.50 156	97.63 168	91.15 238	94.82 184	97.12 204	74.98 380	99.06 186	90.78 252	98.02 154	98.12 232

StellarMVS		94.00 189	93.12 206	96.64 96	96.08 304	92.72 98	97.50 156	97.63 168	91.15 238	94.82 184	97.12 204	74.98 380	99.06 186	90.78 252	98.02 154	98.12 232

API-MVS		94.84 154	94.49 157	95.90 167	97.90 136	92.00 126	97.80 105	97.48 203	89.19 311	94.81 186	96.71 231	88.84 107	99.17 163	88.91 305	98.76 119	96.53 313

hybridcas		95.46 114	95.29 112	95.96 163	96.83 214	90.08 216	97.63 137	97.49 200	93.76 107	94.79 187	98.04 102	86.87 154	98.72 244	94.71 158	97.53 169	99.08 101

mvsmamba		94.57 164	94.14 168	95.87 169	97.03 192	89.93 226	97.84 96	95.85 364	91.34 224	94.79 187	96.80 227	80.67 299	98.81 214	94.85 145	98.12 151	98.85 148

OMC-MVS		95.09 135	94.70 144	96.25 140	98.46 81	91.28 157	96.43 282	97.57 181	92.04 198	94.77 189	97.96 113	87.01 153	99.09 178	91.31 241	96.77 207	98.36 208

ECVR-MVS		93.19 225	92.73 225	94.57 271	97.66 151	85.41 390	98.21 48	88.23 500	93.43 126	94.70 190	98.21 89	72.57 402	99.07 184	93.05 203	98.49 130	99.25 81

viewdifsd2359ckpt13		94.87 152	94.52 155	95.90 167	96.88 206	90.19 213	96.92 228	97.36 233	91.26 229	94.65 191	97.46 180	85.79 180	98.64 260	93.64 187	96.76 208	98.88 143

WTY-MVS		94.71 163	94.02 171	96.79 92	97.71 147	92.05 123	96.59 275	97.35 235	90.61 263	94.64 192	96.93 219	86.41 166	99.39 137	91.20 244	94.71 275	98.94 126

test1111		93.19 225	92.82 219	94.30 290	97.58 163	84.56 407	98.21 48	89.02 498	93.53 120	94.58 193	98.21 89	72.69 401	99.05 189	93.06 202	98.48 132	99.28 78

ACMMP		96.27 87	95.93 89	97.28 68	99.24 34	92.62 101	98.25 40	98.81 6	92.99 146	94.56 194	98.39 69	88.96 104	99.85 22	94.57 166	97.63 166	99.36 73
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
viewdifsd2359ckpt07		94.76 160	94.68 145	95.01 237	96.76 231	87.41 333	96.38 292	97.43 221	92.65 167	94.52 195	97.75 147	85.55 191	98.81 214	94.36 171	96.69 214	98.82 155

Effi-MVS+		94.93 147	94.45 159	96.36 129	96.61 240	91.47 150	96.41 286	97.41 224	91.02 244	94.50 196	95.92 280	87.53 139	98.78 219	93.89 181	96.81 206	98.84 152

sss		94.51 167	93.80 177	96.64 96	97.07 184	91.97 127	96.32 300	98.06 103	88.94 322	94.50 196	96.78 228	84.60 211	99.27 150	91.90 225	96.02 236	98.68 175

mmtdpeth		89.70 376	88.96 374	91.90 400	95.84 316	84.42 408	97.46 168	95.53 387	90.27 276	94.46 198	90.50 458	69.74 431	98.95 196	97.39 55	69.48 496	92.34 470

PVSNet_BlendedMVS		94.06 185	93.92 175	94.47 277	98.27 98	89.46 250	96.73 256	98.36 38	90.17 278	94.36 199	95.24 319	88.02 123	99.58 101	93.44 192	90.72 346	94.36 432

PVSNet_Blended		94.87 152	94.56 151	95.81 176	98.27 98	89.46 250	95.47 362	98.36 38	88.84 326	94.36 199	96.09 276	88.02 123	99.58 101	93.44 192	98.18 147	98.40 204

viewdifsd2359ckpt09		94.81 157	94.37 162	96.12 147	96.91 203	90.75 189	96.94 225	97.31 240	90.51 271	94.31 201	97.38 186	85.70 182	98.71 246	93.54 188	96.75 209	98.90 135

PMMVS		92.86 243	92.34 241	94.42 281	94.92 371	86.73 354	94.53 403	96.38 334	84.78 422	94.27 202	95.12 324	83.13 242	98.40 287	91.47 238	96.49 224	98.12 232

EPP-MVSNet		95.22 127	95.04 124	95.76 184	97.49 166	89.56 242	98.67 15	97.00 287	90.69 255	94.24 203	97.62 167	89.79 95	98.81 214	93.39 195	96.49 224	98.92 131

viewmsd2359difaftdt		93.46 213	93.23 203	94.17 295	96.12 299	85.42 388	96.43 282	97.08 270	92.91 154	94.21 204	98.00 108	80.82 297	98.74 237	94.41 168	89.05 364	98.34 214

viewdifsd2359ckpt11		93.46 213	93.22 204	94.17 295	96.11 301	85.42 388	96.43 282	97.07 273	92.91 154	94.20 205	98.00 108	80.82 297	98.73 239	94.42 167	89.04 366	98.34 214

FA-MVS(test-final)		93.52 211	92.92 215	95.31 220	96.77 227	88.54 291	94.82 395	96.21 350	89.61 297	94.20 205	95.25 318	83.24 237	99.14 170	90.01 271	96.16 235	98.25 220

PVSNet_Blended_VisFu		95.27 121	94.91 131	96.38 127	98.20 109	90.86 182	97.27 193	98.25 62	90.21 277	94.18 207	97.27 195	87.48 143	99.73 63	93.53 189	97.77 164	98.55 185

SSM_0404		94.73 162	94.31 165	95.98 162	97.05 189	90.90 181	97.01 218	97.29 242	91.24 230	94.17 208	97.60 169	85.03 202	98.76 229	92.14 218	97.30 184	98.29 217

FE-MVS		92.05 276	91.05 289	95.08 232	96.83 214	87.93 319	93.91 432	95.70 371	86.30 396	94.15 209	94.97 327	76.59 364	99.21 156	84.10 398	96.86 202	98.09 239

thisisatest0530		93.03 233	92.21 245	95.49 209	97.07 184	89.11 267	97.49 164	92.19 479	90.16 279	94.09 210	96.41 255	76.43 368	99.05 189	90.38 266	95.68 248	98.31 216

XVG-OURS-SEG-HR		93.86 198	93.55 186	94.81 251	97.06 187	88.53 293	95.28 372	97.45 214	91.68 208	94.08 211	97.68 157	82.41 264	98.90 204	93.84 183	92.47 315	96.98 298

XVG-OURS		93.72 203	93.35 199	94.80 254	97.07 184	88.61 287	94.79 396	97.46 209	91.97 201	93.99 212	97.86 131	81.74 279	98.88 205	92.64 210	92.67 314	96.92 303

IS-MVSNet		94.90 149	94.52 155	96.05 152	97.67 149	90.56 194	98.44 26	96.22 348	93.21 133	93.99 212	97.74 150	85.55 191	98.45 284	89.98 272	97.86 160	99.14 91

CSCG		96.05 91	95.91 90	96.46 119	99.24 34	90.47 197	98.30 33	98.57 28	89.01 317	93.97 214	97.57 173	92.62 42	99.76 56	94.66 160	99.27 76	99.15 89

casdiffseed414692147		94.55 165	94.02 171	96.15 145	96.61 240	90.79 185	97.42 170	97.39 226	92.18 193	93.95 215	97.64 164	84.37 217	98.66 256	90.68 257	95.91 240	99.00 113

EIA-MVS		95.53 113	95.47 102	95.71 191	97.06 187	89.63 237	97.82 101	97.87 134	93.57 115	93.92 216	95.04 325	90.61 84	98.95 196	94.62 162	98.68 121	98.54 186

tttt0517		92.96 236	92.33 242	94.87 248	97.11 182	87.16 343	97.97 78	92.09 480	90.63 261	93.88 217	97.01 217	76.50 365	99.06 186	90.29 269	95.45 257	98.38 206

HyFIR lowres test		93.66 205	92.92 215	95.87 169	98.24 102	89.88 227	94.58 401	98.49 31	85.06 417	93.78 218	95.78 291	82.86 251	98.67 253	91.77 230	95.71 247	99.07 104

CHOSEN 1792x2688		94.15 179	93.51 191	96.06 151	98.27 98	89.38 253	95.18 383	98.48 33	85.60 407	93.76 219	97.11 206	83.15 241	99.61 93	91.33 240	98.72 120	99.19 84

mamba_0408		93.70 204	92.99 210	95.83 174	96.79 220	90.38 203	88.69 496	97.07 273	90.96 246	93.68 220	97.31 191	84.97 205	98.76 229	90.95 248	96.51 220	98.35 210

SSM_04072		93.51 212	92.99 210	95.05 233	96.79 220	90.38 203	88.69 496	97.07 273	90.96 246	93.68 220	97.31 191	84.97 205	96.42 449	90.95 248	96.51 220	98.35 210

SSM_0407		94.54 166	94.12 170	95.80 177	96.79 220	90.38 203	96.79 248	97.29 242	91.24 230	93.68 220	97.60 169	85.03 202	98.67 253	92.14 218	96.51 220	98.35 210

Anonymous202405211		92.07 275	90.83 300	95.76 184	98.19 111	88.75 281	97.58 143	95.00 410	86.00 402	93.64 223	97.45 181	66.24 458	99.53 115	90.68 257	92.71 312	99.01 110

IMVS_0403		93.98 191	93.79 178	94.55 272	96.19 287	86.16 373	96.35 295	97.24 253	91.54 211	93.59 224	97.04 211	85.86 177	98.73 239	90.68 257	95.59 251	98.76 163

CDS-MVSNet		94.14 182	93.54 187	95.93 164	96.18 291	91.46 151	96.33 299	97.04 282	88.97 321	93.56 225	96.51 250	87.55 137	97.89 363	89.80 277	95.95 238	98.44 201
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MDTV_nov1_ep13_2view						70.35 500	93.10 456		83.88 434	93.55 226		82.47 263		86.25 366		98.38 206

Anonymous20240529		91.98 278	90.73 306	95.73 189	98.14 116	89.40 252	97.99 69	97.72 156	79.63 476	93.54 227	97.41 185	69.94 427	99.56 109	91.04 247	91.11 339	98.22 222

CANet_DTU		94.37 170	93.65 183	96.55 106	96.46 266	92.13 121	96.21 311	96.67 317	94.38 87	93.53 228	97.03 216	79.34 326	99.71 69	90.76 254	98.45 134	97.82 261

icg_test_0407_2		93.58 207	93.46 193	93.94 314	96.19 287	86.16 373	93.73 438	97.24 253	91.54 211	93.50 229	97.04 211	85.64 188	96.91 438	90.68 257	95.59 251	98.76 163

IMVS_0407		93.94 193	93.75 179	94.49 276	96.19 287	86.16 373	96.35 295	97.24 253	91.54 211	93.50 229	97.04 211	85.64 188	98.54 275	90.68 257	95.59 251	98.76 163

tpmrst		91.44 308	91.32 276	91.79 406	95.15 359	79.20 474	93.42 449	95.37 391	88.55 338	93.49 231	93.67 400	82.49 262	98.27 305	90.41 265	89.34 360	97.90 251

TAMVS		94.01 188	93.46 193	95.64 193	96.16 294	90.45 198	96.71 259	96.89 300	89.27 309	93.46 232	96.92 222	87.29 148	97.94 356	88.70 311	95.74 245	98.53 187

thisisatest0515		92.29 265	91.30 278	95.25 224	96.60 242	88.90 277	94.36 414	92.32 477	87.92 355	93.43 233	94.57 349	77.28 359	99.00 193	89.42 288	95.86 243	97.86 257

DeepC-MVS	93.07 3	96.06 90	95.66 95	97.29 66	97.96 130	93.17 82	97.30 187	98.06 103	93.92 102	93.38 234	98.66 46	86.83 155	99.73 63	95.60 120	99.22 83	98.96 119
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		92.49 254	91.60 266	95.18 227	97.91 135	89.47 248	97.65 131	94.66 426	92.18 193	93.33 235	94.91 331	78.06 352	99.10 175	81.61 424	94.06 294	96.98 298

thres100view900		92.43 256	91.58 267	94.98 241	97.92 134	89.37 254	97.71 122	94.66 426	92.20 189	93.31 236	94.90 332	78.06 352	99.08 180	81.40 428	94.08 290	96.48 316

thres200		92.23 269	91.39 273	94.75 258	97.61 157	89.03 269	96.60 274	95.09 407	92.08 196	93.28 237	94.00 386	78.39 346	99.04 192	81.26 434	94.18 286	96.19 323

tfpn200view9		92.38 259	91.52 270	94.95 245	97.85 138	89.29 258	97.41 172	94.88 418	92.19 191	93.27 238	94.46 358	78.17 348	99.08 180	81.40 428	94.08 290	96.48 316

thres400		92.42 257	91.52 270	95.12 231	97.85 138	89.29 258	97.41 172	94.88 418	92.19 191	93.27 238	94.46 358	78.17 348	99.08 180	81.40 428	94.08 290	96.98 298

testing3-2		92.10 274	92.05 248	92.27 389	97.71 147	79.56 468	97.42 170	94.41 438	93.53 120	93.22 240	95.49 307	69.16 435	99.11 173	93.25 196	94.22 283	98.13 230

ab-mvs		93.57 209	92.55 233	96.64 96	97.28 172	91.96 129	95.40 365	97.45 214	89.81 289	93.22 240	96.28 262	79.62 323	99.46 129	90.74 255	93.11 306	98.50 191

Vis-MVSNet (Re-imp)		94.15 179	93.88 176	94.95 245	97.61 157	87.92 320	98.10 57	95.80 367	92.22 186	93.02 242	97.45 181	84.53 213	97.91 362	88.24 315	97.97 157	99.02 107

114514_t		93.95 192	93.06 209	96.63 100	99.07 44	91.61 141	97.46 168	97.96 124	77.99 484	93.00 243	97.57 173	86.14 173	99.33 142	89.22 295	99.15 95	98.94 126

UGNet		94.04 187	93.28 201	96.31 131	96.85 210	91.19 164	97.88 91	97.68 161	94.40 85	93.00 243	96.18 266	73.39 397	99.61 93	91.72 231	98.46 133	98.13 230
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
HY-MVS	89.66 9	93.87 197	92.95 214	96.63 100	97.10 183	92.49 107	95.64 353	96.64 318	89.05 316	93.00 243	95.79 290	85.77 181	99.45 131	89.16 299	94.35 278	97.96 247

PVSNet	86.66 18	92.24 268	91.74 263	93.73 325	97.77 143	83.69 420	92.88 459	96.72 310	87.91 356	93.00 243	94.86 334	78.51 343	99.05 189	86.53 361	97.45 176	98.47 196

MAR-MVS		94.22 174	93.46 193	96.51 113	98.00 127	92.19 120	97.67 127	97.47 207	88.13 352	93.00 243	95.84 284	84.86 209	99.51 120	87.99 319	98.17 149	97.83 260
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
PAPM_NR		95.01 142	94.59 149	96.26 137	98.89 61	90.68 192	97.24 195	97.73 154	91.80 203	92.93 248	96.62 245	89.13 102	99.14 170	89.21 296	97.78 163	98.97 116

MDTV_nov1_ep13			90.76 302		95.22 353	80.33 457	93.03 457	95.28 397	88.14 351	92.84 249	93.83 390	81.34 284	98.08 327	82.86 410	94.34 279

CostFormer		91.18 326	90.70 308	92.62 380	94.84 376	81.76 442	94.09 425	94.43 436	84.15 429	92.72 250	93.77 394	79.43 325	98.20 310	90.70 256	92.18 321	97.90 251

FBQ-MVS		91.77 285	90.62 312	95.21 225	96.84 211	88.89 279	96.90 231	95.31 396	90.60 265	92.64 251	92.29 440	69.43 432	98.48 282	87.33 349	94.21 284	98.27 219

EPNet		95.20 128	94.56 151	97.14 77	92.80 444	92.68 100	97.85 95	94.87 421	96.64 10	92.46 252	97.80 143	86.23 168	99.65 81	93.72 185	98.62 125	99.10 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		90.82 340	89.77 353	93.95 312	94.45 393	87.19 341	90.23 487	95.68 375	86.89 385	92.40 253	92.36 436	80.91 293	97.05 431	81.09 435	93.95 295	97.60 274

RPMNet		88.98 382	87.05 396	94.77 256	94.45 393	87.19 341	90.23 487	98.03 112	77.87 486	92.40 253	87.55 487	80.17 311	99.51 120	68.84 494	93.95 295	97.60 274

EPMVS		90.70 345	89.81 351	93.37 351	94.73 382	84.21 411	93.67 442	88.02 501	89.50 301	92.38 255	93.49 408	77.82 356	97.78 374	86.03 373	92.68 313	98.11 238

baseline1		92.82 246	91.90 256	95.55 200	97.20 176	90.77 187	97.19 203	94.58 430	92.20 189	92.36 256	96.34 259	84.16 222	98.21 309	89.20 297	83.90 432	97.68 268

PatchT		88.87 386	87.42 390	93.22 357	94.08 404	85.10 398	89.51 492	94.64 428	81.92 461	92.36 256	88.15 480	80.05 313	97.01 434	72.43 483	93.65 301	97.54 277

UWE-MVS		89.91 367	89.48 363	91.21 420	95.88 310	78.23 480	94.91 392	90.26 494	89.11 313	92.35 258	94.52 352	68.76 438	97.96 350	83.95 402	95.59 251	97.42 282

ETVMVS		90.52 351	89.14 372	94.67 262	96.81 219	87.85 325	95.91 334	93.97 453	89.71 293	92.34 259	92.48 431	65.41 464	97.96 350	81.37 431	94.27 282	98.21 223

PAPR		94.18 175	93.42 198	96.48 116	97.64 153	91.42 153	95.55 357	97.71 160	88.99 319	92.34 259	95.82 286	89.19 100	99.11 173	86.14 369	97.38 178	98.90 135

SCA		91.84 283	91.18 285	93.83 320	95.59 324	84.95 403	94.72 397	95.58 380	90.82 249	92.25 261	93.69 397	75.80 372	98.10 322	86.20 367	95.98 237	98.45 198

CVMVSNet		91.23 321	91.75 261	89.67 447	95.77 317	74.69 491	96.44 280	94.88 418	85.81 404	92.18 262	97.64 164	79.07 331	95.58 466	88.06 318	95.86 243	98.74 170

AUN-MVS		91.76 286	90.75 304	94.81 251	97.00 196	88.57 289	96.65 266	96.49 327	89.63 296	92.15 263	96.12 271	78.66 341	98.50 279	90.83 250	79.18 456	97.36 284

AdaColmap		94.34 171	93.68 182	96.31 131	98.59 76	91.68 139	96.59 275	97.81 147	89.87 284	92.15 263	97.06 210	83.62 231	99.54 113	89.34 290	98.07 152	97.70 267

GeoE		93.89 196	93.28 201	95.72 190	96.96 200	89.75 232	98.24 43	96.92 296	89.47 302	92.12 265	97.21 199	84.42 215	98.39 292	87.71 329	96.50 223	99.01 110

PatchmatchNet		91.91 280	91.35 274	93.59 339	95.38 337	84.11 413	93.15 454	95.39 389	89.54 299	92.10 266	93.68 399	82.82 253	98.13 317	84.81 389	95.32 259	98.52 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		93.24 222	92.48 238	95.51 206	95.70 319	92.39 109	97.86 92	98.66 21	92.30 183	92.09 267	95.37 311	80.49 304	98.40 287	93.95 178	85.86 398	95.75 347

tpm		90.25 358	89.74 356	91.76 409	93.92 407	79.73 466	93.98 426	93.54 460	88.28 345	91.99 268	93.25 418	77.51 358	97.44 414	87.30 351	87.94 377	98.12 232

myMVS_eth3d28		91.52 304	90.97 292	93.17 359	96.91 203	83.24 424	95.61 354	94.96 414	92.24 185	91.98 269	93.28 417	69.31 433	98.40 287	88.71 310	95.68 248	97.88 253

UBG		91.55 301	90.76 302	93.94 314	96.52 259	85.06 399	95.22 378	94.54 432	90.47 272	91.98 269	92.71 424	72.02 406	98.74 237	88.10 317	95.26 261	98.01 245

CNLPA		94.28 172	93.53 188	96.52 109	98.38 91	92.55 105	96.59 275	96.88 301	90.13 281	91.91 271	97.24 197	85.21 199	99.09 178	87.64 338	97.83 161	97.92 250

testing91		91.90 281	91.02 290	94.53 274	96.54 254	86.55 361	95.86 336	95.64 377	91.77 205	91.89 272	93.47 410	69.94 427	98.86 206	90.23 270	93.86 297	98.18 225

BH-RMVSNet		92.72 250	91.97 253	94.97 243	97.16 178	87.99 318	96.15 317	95.60 378	90.62 262	91.87 273	97.15 203	78.41 345	98.57 273	83.16 407	97.60 167	98.36 208

PatchMatch-RL		92.90 240	92.02 251	95.56 198	98.19 111	90.80 184	95.27 374	97.18 257	87.96 354	91.86 274	95.68 297	80.44 305	98.99 194	84.01 400	97.54 168	96.89 304

SDMVSNet		94.17 176	93.61 184	95.86 172	98.09 119	91.37 154	97.35 181	98.20 70	93.18 138	91.79 275	97.28 193	79.13 329	98.93 199	94.61 163	92.84 309	97.28 289

sd_testset		93.10 229	92.45 239	95.05 233	98.09 119	89.21 262	96.89 233	97.64 166	93.18 138	91.79 275	97.28 193	75.35 377	98.65 258	88.99 302	92.84 309	97.28 289

testing99		91.62 295	90.72 307	94.32 287	96.48 263	86.11 378	95.81 340	94.76 423	91.55 210	91.75 277	93.44 412	68.55 441	98.82 212	90.43 264	93.69 299	98.04 243

testing222		90.31 355	88.96 374	94.35 283	96.54 254	87.29 335	95.50 360	93.84 457	90.97 245	91.75 277	92.96 421	62.18 479	98.00 341	82.86 410	94.08 290	97.76 264

OPM-MVS		93.28 221	92.76 221	94.82 249	94.63 386	90.77 187	96.65 266	97.18 257	93.72 109	91.68 279	97.26 196	79.33 327	98.63 263	92.13 221	92.28 317	95.07 388
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tpm2		89.96 366	89.21 369	92.23 392	94.91 373	81.25 445	93.78 436	94.42 437	80.62 472	91.56 280	93.44 412	76.44 367	97.94 356	85.60 379	92.08 325	97.49 278

TAPA-MVS	90.10 7	92.30 264	91.22 283	95.56 198	98.33 93	89.60 239	96.79 248	97.65 164	81.83 462	91.52 281	97.23 198	87.94 126	98.91 203	71.31 487	98.37 138	98.17 228
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvs2		89.77 374	89.93 346	89.31 454	93.68 416	76.37 486	97.64 135	95.90 361	89.84 288	91.49 282	96.26 264	58.77 482	97.10 428	94.65 161	91.13 338	94.46 428

TR-MVS		91.48 307	90.59 316	94.16 298	96.40 269	87.33 334	95.67 348	95.34 395	87.68 369	91.46 283	95.52 306	76.77 363	98.35 295	82.85 412	93.61 303	96.79 307

RPSCF		90.75 342	90.86 296	90.42 437	96.84 211	76.29 487	95.61 354	96.34 335	83.89 433	91.38 284	97.87 129	76.45 366	98.78 219	87.16 355	92.23 318	96.20 322

dtuonly		90.88 338	91.13 286	90.13 441	92.98 439	75.01 490	92.74 465	95.54 383	87.69 368	91.37 285	96.61 247	79.65 322	98.15 315	87.44 346	96.21 234	97.23 292

PLC	91.00 6	94.11 183	93.43 196	96.13 146	98.58 78	91.15 170	96.69 262	97.39 226	87.29 378	91.37 285	96.71 231	88.39 116	99.52 119	87.33 349	97.13 192	97.73 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		93.12 228	92.72 226	94.34 285	96.71 233	87.27 337	90.29 486	97.72 156	86.61 391	91.34 287	95.29 313	84.29 220	98.41 286	93.25 196	98.94 111	97.35 286

HQP_MVS		93.78 201	93.43 196	94.82 249	96.21 283	89.99 220	97.74 114	97.51 197	94.85 56	91.34 287	96.64 238	81.32 285	98.60 268	93.02 204	92.23 318	95.86 335

plane_prior3						90.00 218			94.46 81	91.34 287

Fast-Effi-MVS+		93.46 213	92.75 223	95.59 197	96.77 227	90.03 217	96.81 246	97.13 261	88.19 347	91.30 290	94.27 371	86.21 170	98.63 263	87.66 337	96.46 226	98.12 232

EI-MVSNet		93.03 233	92.88 217	93.48 347	95.77 317	86.98 346	96.44 280	97.12 262	90.66 259	91.30 290	97.64 164	86.56 160	98.05 334	89.91 274	90.55 348	95.41 362

MVSTER		93.20 224	92.81 220	94.37 282	96.56 251	89.59 240	97.06 212	97.12 262	91.24 230	91.30 290	95.96 278	82.02 272	98.05 334	93.48 191	90.55 348	95.47 357

ADS-MVSNet2		89.45 378	88.59 380	92.03 396	95.86 311	82.26 438	90.93 482	94.32 444	83.23 447	91.28 293	91.81 448	79.01 336	95.99 455	79.52 445	91.39 334	97.84 258

ADS-MVSNet		89.89 369	88.68 379	93.53 343	95.86 311	84.89 404	90.93 482	95.07 408	83.23 447	91.28 293	91.81 448	79.01 336	97.85 365	79.52 445	91.39 334	97.84 258

testing11		91.68 290	90.75 304	94.47 277	96.53 256	86.56 360	95.76 344	94.51 434	91.10 242	91.24 295	93.59 405	68.59 440	98.86 206	91.10 245	94.29 281	98.00 246

nrg030		94.05 186	93.31 200	96.27 136	95.22 353	94.59 35	98.34 30	97.46 209	92.93 153	91.21 296	96.64 238	87.23 150	98.22 308	94.99 137	85.80 399	95.98 334

Effi-MVS+-dtu		93.08 230	93.21 205	92.68 379	96.02 308	83.25 423	97.14 208	96.72 310	93.85 105	91.20 297	93.44 412	83.08 243	98.30 301	91.69 234	95.73 246	96.50 315

VPNet		92.23 269	91.31 277	94.99 239	95.56 326	90.96 175	97.22 201	97.86 138	92.96 152	90.96 298	96.62 245	75.06 378	98.20 310	91.90 225	83.65 434	95.80 341

JIA-IIPM		88.26 393	87.04 397	91.91 399	93.52 423	81.42 444	89.38 493	94.38 440	80.84 469	90.93 299	80.74 511	79.22 328	97.92 359	82.76 414	91.62 329	96.38 319

MonoMVSNet		91.92 279	91.77 259	92.37 383	92.94 440	83.11 426	97.09 211	95.55 382	92.91 154	90.85 300	94.55 350	81.27 287	96.52 447	93.01 206	87.76 379	97.47 280

WB-MVSnew		89.88 370	89.56 360	90.82 429	94.57 390	83.06 427	95.65 352	92.85 469	87.86 359	90.83 301	94.10 380	79.66 321	96.88 439	76.34 463	94.19 285	92.54 466

test-LLR		91.42 309	91.19 284	92.12 394	94.59 387	80.66 451	94.29 419	92.98 467	91.11 240	90.76 302	92.37 433	79.02 334	98.07 331	88.81 307	96.74 210	97.63 269

test-mter		90.19 362	89.54 361	92.12 394	94.59 387	80.66 451	94.29 419	92.98 467	87.68 369	90.76 302	92.37 433	67.67 445	98.07 331	88.81 307	96.74 210	97.63 269

ACMM	89.79 8	92.96 236	92.50 237	94.35 283	96.30 279	88.71 282	97.58 143	97.36 233	91.40 222	90.53 304	96.65 237	79.77 318	98.75 235	91.24 243	91.64 328	95.59 353
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
F-COLMAP		93.58 207	92.98 213	95.37 216	98.40 88	88.98 274	97.18 204	97.29 242	87.75 366	90.49 305	97.10 208	85.21 199	99.50 123	86.70 360	96.72 212	97.63 269

TESTMET0.1,1		90.06 364	89.42 364	91.97 397	94.41 395	80.62 453	94.29 419	91.97 482	87.28 379	90.44 306	92.47 432	68.79 437	97.67 384	88.50 314	96.60 218	97.61 273

FIs		94.09 184	93.70 181	95.27 221	95.70 319	92.03 125	98.10 57	98.68 18	93.36 130	90.39 307	96.70 233	87.63 135	97.94 356	92.25 215	90.50 350	95.84 338

GA-MVS		91.38 311	90.31 325	94.59 266	94.65 385	87.62 330	94.34 415	96.19 352	90.73 253	90.35 308	93.83 390	71.84 408	97.96 350	87.22 352	93.61 303	98.21 223

LS3D		93.57 209	92.61 231	96.47 117	97.59 159	91.61 141	97.67 127	97.72 156	85.17 415	90.29 309	98.34 76	84.60 211	99.73 63	83.85 405	98.27 143	98.06 242

FC-MVSNet-test		93.94 193	93.57 185	95.04 235	95.48 330	91.45 152	98.12 56	98.71 13	93.37 128	90.23 310	96.70 233	87.66 132	97.85 365	91.49 237	90.39 351	95.83 339

HQP-NCC					95.86 311		96.65 266		93.55 116	90.14 311

ACMP_Plane					95.86 311		96.65 266		93.55 116	90.14 311

HQP4-MVS										90.14 311			98.50 279			95.78 343

HQP-MVS		93.19 225	92.74 224	94.54 273	95.86 311	89.33 256	96.65 266	97.39 226	93.55 116	90.14 311	95.87 282	80.95 291	98.50 279	92.13 221	92.10 323	95.78 343

UniMVSNet_NR-MVSNet		93.37 218	92.67 227	95.47 212	95.34 342	92.83 92	97.17 205	98.58 27	92.98 151	90.13 315	95.80 287	88.37 118	97.85 365	91.71 232	83.93 429	95.73 349

DU-MVS		92.90 240	92.04 249	95.49 209	94.95 368	92.83 92	97.16 206	98.24 64	93.02 145	90.13 315	95.71 294	83.47 232	97.85 365	91.71 232	83.93 429	95.78 343

LPG-MVS_test		92.94 238	92.56 232	94.10 300	96.16 294	88.26 303	97.65 131	97.46 209	91.29 225	90.12 317	97.16 201	79.05 332	98.73 239	92.25 215	91.89 326	95.31 372

LGP-MVS_train				94.10 300	96.16 294	88.26 303		97.46 209	91.29 225	90.12 317	97.16 201	79.05 332	98.73 239	92.25 215	91.89 326	95.31 372

UniMVSNet (Re)		93.31 220	92.55 233	95.61 196	95.39 336	93.34 73	97.39 177	98.71 13	93.14 141	90.10 319	94.83 336	87.71 131	98.03 338	91.67 235	83.99 428	95.46 358

mvs_anonymous		93.82 199	93.74 180	94.06 302	96.44 267	85.41 390	95.81 340	97.05 280	89.85 287	90.09 320	96.36 258	87.44 144	97.75 379	93.97 177	96.69 214	99.02 107

test_djsdf		93.07 231	92.76 221	94.00 306	93.49 425	88.70 283	98.22 46	97.57 181	91.42 220	90.08 321	95.55 304	82.85 252	97.92 359	94.07 175	91.58 330	95.40 365

dp		88.90 385	88.26 385	90.81 430	94.58 389	76.62 485	92.85 461	94.93 415	85.12 416	90.07 322	93.07 419	75.81 371	98.12 320	80.53 439	87.42 384	97.71 266

PS-MVSNAJss		93.74 202	93.51 191	94.44 279	93.91 408	89.28 260	97.75 111	97.56 189	92.50 174	89.94 323	96.54 249	88.65 111	98.18 313	93.83 184	90.90 344	95.86 335

UniMVSNet_ETH3D		91.34 316	90.22 333	94.68 261	94.86 375	87.86 323	97.23 199	97.46 209	87.99 353	89.90 324	96.92 222	66.35 456	98.23 307	90.30 268	90.99 342	97.96 247

CLD-MVS		92.98 235	92.53 235	94.32 287	96.12 299	89.20 263	95.28 372	97.47 207	92.66 166	89.90 324	95.62 300	80.58 302	98.40 287	92.73 209	92.40 316	95.38 367
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
gg-mvs-nofinetune		87.82 396	85.61 410	94.44 279	94.46 392	89.27 261	91.21 480	84.61 511	80.88 468	89.89 326	74.98 517	71.50 411	97.53 406	85.75 378	97.21 188	96.51 314

1112_ss		93.37 218	92.42 240	96.21 141	97.05 189	90.99 173	96.31 301	96.72 310	86.87 386	89.83 327	96.69 235	86.51 162	99.14 170	88.12 316	93.67 300	98.50 191

BH-untuned		92.94 238	92.62 230	93.92 318	97.22 174	86.16 373	96.40 290	96.25 347	90.06 282	89.79 328	96.17 268	83.19 239	98.35 295	87.19 353	97.27 186	97.24 291

VortexMVS		92.88 242	92.64 228	93.58 340	96.58 246	87.53 332	96.93 227	97.28 245	92.78 163	89.75 329	94.99 326	82.73 255	97.76 377	94.60 164	88.16 375	95.46 358

V42		91.58 299	90.87 295	93.73 325	94.05 405	88.50 294	97.32 185	96.97 288	88.80 331	89.71 330	94.33 366	82.54 260	98.05 334	89.01 301	85.07 411	94.64 425

Baseline_NR-MVSNet		91.20 323	90.62 312	92.95 367	93.83 411	88.03 316	97.01 218	95.12 406	88.42 342	89.70 331	95.13 323	83.47 232	97.44 414	89.66 282	83.24 437	93.37 453

v144192		91.06 329	90.28 327	93.39 350	93.66 417	87.23 340	96.83 242	97.07 273	87.43 374	89.69 332	94.28 370	81.48 282	98.00 341	87.18 354	84.92 415	94.93 396

v1144		91.37 313	90.60 315	93.68 332	93.89 409	88.23 306	96.84 241	97.03 284	88.37 343	89.69 332	94.39 360	82.04 271	97.98 343	87.80 324	85.37 404	94.84 405

Test_1112_low_res		92.84 245	91.84 258	95.85 173	97.04 191	89.97 224	95.53 359	96.64 318	85.38 410	89.65 334	95.18 320	85.86 177	99.10 175	87.70 330	93.58 305	98.49 193

nomal-1		91.63 293	90.62 312	94.66 263	96.07 307	87.86 323	95.58 356	94.63 429	89.80 290	89.61 335	92.66 425	72.05 405	98.29 302	90.61 263	94.55 277	97.82 261

v1192		91.07 328	90.23 331	93.58 340	93.70 414	87.82 326	96.73 256	97.07 273	87.77 364	89.58 336	94.32 368	80.90 295	97.97 346	86.52 362	85.48 402	94.95 392

v1240		90.70 345	89.85 349	93.23 356	93.51 424	86.80 351	96.61 272	97.02 286	87.16 381	89.58 336	94.31 369	79.55 324	97.98 343	85.52 380	85.44 403	94.90 399

TranMVSNet+NR-MVSNet		92.50 252	91.63 265	95.14 229	94.76 379	92.07 122	97.53 153	98.11 91	92.90 157	89.56 338	96.12 271	83.16 240	97.60 394	89.30 291	83.20 438	95.75 347

v2v482		91.59 297	90.85 298	93.80 322	93.87 410	88.17 312	96.94 225	96.88 301	89.54 299	89.53 339	94.90 332	81.70 280	98.02 339	89.25 294	85.04 413	95.20 380

v1921920		90.85 339	90.03 342	93.29 354	93.55 421	86.96 349	96.74 255	97.04 282	87.36 376	89.52 340	94.34 365	80.23 310	97.97 346	86.27 365	85.21 408	94.94 394

IterMVS-LS		92.29 265	91.94 254	93.34 352	96.25 281	86.97 347	96.57 278	97.05 280	90.67 257	89.50 341	94.80 338	86.59 159	97.64 389	89.91 274	86.11 397	95.40 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cascas		91.20 323	90.08 337	94.58 270	94.97 366	89.16 266	93.65 444	97.59 177	79.90 475	89.40 342	92.92 422	75.36 376	98.36 294	92.14 218	94.75 272	96.23 320

XVG-ACMP-BASELINE		90.93 336	90.21 334	93.09 362	94.31 399	85.89 379	95.33 369	97.26 248	91.06 243	89.38 343	95.44 310	68.61 439	98.60 268	89.46 286	91.05 340	94.79 416

GBi-Net		91.35 314	90.27 328	94.59 266	96.51 260	91.18 166	97.50 156	96.93 292	88.82 328	89.35 344	94.51 353	73.87 389	97.29 424	86.12 370	88.82 367	95.31 372

test1		91.35 314	90.27 328	94.59 266	96.51 260	91.18 166	97.50 156	96.93 292	88.82 328	89.35 344	94.51 353	73.87 389	97.29 424	86.12 370	88.82 367	95.31 372

FMVSNet3		91.78 284	90.69 309	95.03 236	96.53 256	92.27 115	97.02 215	96.93 292	89.79 291	89.35 344	94.65 346	77.01 360	97.47 411	86.12 370	88.82 367	95.35 369

WR-MVS		92.34 261	91.53 269	94.77 256	95.13 361	90.83 183	96.40 290	97.98 122	91.88 202	89.29 347	95.54 305	82.50 261	97.80 372	89.79 278	85.27 407	95.69 350

DP-MVS		92.76 248	91.51 272	96.52 109	98.77 63	90.99 173	97.38 179	96.08 356	82.38 458	89.29 347	97.87 129	83.77 227	99.69 75	81.37 431	96.69 214	98.89 141

BH-w/o		92.14 273	91.75 261	93.31 353	96.99 197	85.73 383	95.67 348	95.69 373	88.73 333	89.26 349	94.82 337	82.97 248	98.07 331	85.26 385	96.32 233	96.13 329

3Dnovator	91.36 5	95.19 131	94.44 160	97.44 59	96.56 251	93.36 72	98.65 16	98.36 38	94.12 93	89.25 350	98.06 100	82.20 268	99.77 54	93.41 194	99.32 72	99.18 86

usedtu_dtu_shiyan1		91.65 291	90.67 310	94.60 264	93.65 419	90.95 176	94.86 393	97.12 262	89.69 294	89.21 351	93.62 402	81.17 288	97.67 384	87.54 341	89.14 362	95.17 385

FE-MVSNET3		91.65 291	90.67 310	94.60 264	93.65 419	90.95 176	94.86 393	97.12 262	89.69 294	89.21 351	93.62 402	81.17 288	97.67 384	87.54 341	89.14 362	95.17 385

tt0805		91.09 327	90.07 340	94.16 298	95.61 323	88.31 300	97.56 147	96.51 326	89.56 298	89.17 353	95.64 299	67.08 453	98.38 293	91.07 246	88.44 373	95.80 341

miper_enhance_ethall		91.54 303	91.01 291	93.15 360	95.35 341	87.07 345	93.97 427	96.90 298	86.79 387	89.17 353	93.43 415	86.55 161	97.64 389	89.97 273	86.93 388	94.74 421

Fast-Effi-MVS+-dtu		92.29 265	91.99 252	93.21 358	95.27 349	85.52 386	97.03 213	96.63 321	92.09 195	89.11 355	95.14 322	80.33 308	98.08 327	87.54 341	94.74 273	96.03 333

WBMVS		90.69 347	89.99 344	92.81 373	96.48 263	85.00 400	95.21 380	96.30 338	89.46 303	89.04 356	94.05 384	72.45 404	97.82 369	89.46 286	87.41 385	95.61 352

XXY-MVS		92.16 271	91.23 282	94.95 245	94.75 380	90.94 178	97.47 166	97.43 221	89.14 312	88.90 357	96.43 254	79.71 319	98.24 306	89.56 284	87.68 380	95.67 351

PCF-MVS	89.48 11	91.56 300	89.95 345	96.36 129	96.60 242	92.52 106	92.51 469	97.26 248	79.41 477	88.90 357	96.56 248	84.04 225	99.55 111	77.01 462	97.30 184	97.01 297
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_ehance_all_eth		91.59 297	91.13 286	92.97 366	95.55 327	86.57 359	94.47 408	96.88 301	87.77 364	88.88 359	94.01 385	86.22 169	97.54 404	89.49 285	86.93 388	94.79 416

SSC-MVS3.2		89.74 375	89.26 368	91.19 423	95.16 356	80.29 459	94.53 403	97.03 284	91.79 204	88.86 360	94.10 380	69.94 427	97.82 369	85.29 383	86.66 393	95.45 360

jajsoiax		92.42 257	91.89 257	94.03 305	93.33 433	88.50 294	97.73 116	97.53 195	92.00 200	88.85 361	96.50 251	75.62 375	98.11 321	93.88 182	91.56 331	95.48 355

eth_miper_zixun_eth		91.02 331	90.59 316	92.34 386	95.33 345	84.35 409	94.10 424	96.90 298	88.56 337	88.84 362	94.33 366	84.08 223	97.60 394	88.77 309	84.37 425	95.06 389

c3_l		91.38 311	90.89 294	92.88 370	95.58 325	86.30 367	94.68 398	96.84 305	88.17 348	88.83 363	94.23 374	85.65 185	97.47 411	89.36 289	84.63 417	94.89 400

mvs_tets		92.31 263	91.76 260	93.94 314	93.41 430	88.29 301	97.63 137	97.53 195	92.04 198	88.76 364	96.45 253	74.62 385	98.09 326	93.91 180	91.48 332	95.45 360

v148		90.99 332	90.38 322	92.81 373	93.83 411	85.80 380	96.78 252	96.68 315	89.45 304	88.75 365	93.93 389	82.96 249	97.82 369	87.83 322	83.25 436	94.80 414

FMVSNet2		91.31 317	90.08 337	94.99 239	96.51 260	92.21 117	97.41 172	96.95 290	88.82 328	88.62 366	94.75 340	73.87 389	97.42 416	85.20 386	88.55 372	95.35 369

PAPM		91.52 304	90.30 326	95.20 226	95.30 348	89.83 229	93.38 450	96.85 304	86.26 398	88.59 367	95.80 287	84.88 208	98.15 315	75.67 468	95.93 239	97.63 269

cl22		91.21 322	90.56 318	93.14 361	96.09 303	86.80 351	94.41 412	96.58 324	87.80 362	88.58 368	93.99 387	80.85 296	97.62 392	89.87 276	86.93 388	94.99 391

3Dnovator+	91.43 4	95.40 115	94.48 158	98.16 18	96.90 205	95.34 18	98.48 25	97.87 134	94.65 73	88.53 369	98.02 106	83.69 228	99.71 69	93.18 198	98.96 110	99.44 62

dmvs_re		90.21 360	89.50 362	92.35 384	95.47 334	85.15 396	95.70 347	94.37 441	90.94 248	88.42 370	93.57 406	74.63 384	95.67 463	82.80 413	89.57 358	96.22 321

anonymousdsp		92.16 271	91.55 268	93.97 310	92.58 449	89.55 244	97.51 155	97.42 223	89.42 305	88.40 371	94.84 335	80.66 300	97.88 364	91.87 227	91.28 336	94.48 427

reproduce_monomvs		91.30 318	91.10 288	91.92 398	96.82 217	82.48 434	97.01 218	97.49 200	94.64 74	88.35 372	95.27 316	70.53 420	98.10 322	95.20 130	84.60 419	95.19 383

WR-MVS_H		92.00 277	91.35 274	93.95 312	95.09 363	89.47 248	98.04 64	98.68 18	91.46 218	88.34 373	94.68 343	85.86 177	97.56 397	85.77 377	84.24 426	94.82 411

v8		91.29 320	90.53 319	93.57 342	94.15 401	88.12 314	97.34 182	97.06 279	88.99 319	88.32 374	94.26 373	83.08 243	98.01 340	87.62 339	83.92 431	94.57 426

ACMP	89.59 10	92.62 251	92.14 246	94.05 303	96.40 269	88.20 310	97.36 180	97.25 251	91.52 215	88.30 375	96.64 238	78.46 344	98.72 244	91.86 228	91.48 332	95.23 379
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		91.04 330	90.23 331	93.49 346	94.12 402	88.16 313	97.32 185	97.08 270	88.26 346	88.29 376	94.22 376	82.17 269	97.97 346	86.45 364	84.12 427	94.33 433

QAPM		93.45 216	92.27 243	96.98 87	96.77 227	92.62 101	98.39 29	98.12 88	84.50 425	88.27 377	97.77 146	82.39 265	99.81 36	85.40 382	98.81 115	98.51 190

Anonymous20231211		90.63 348	89.42 364	94.27 292	98.24 102	89.19 265	98.05 63	97.89 130	79.95 474	88.25 378	94.96 328	72.56 403	98.13 317	89.70 280	85.14 409	95.49 354

CP-MVSNet		91.89 282	91.24 281	93.82 321	95.05 364	88.57 289	97.82 101	98.19 75	91.70 207	88.21 379	95.76 292	81.96 273	97.52 408	87.86 321	84.65 416	95.37 368

DIV-MVS_self_test		90.97 334	90.33 323	92.88 370	95.36 340	86.19 372	94.46 410	96.63 321	87.82 360	88.18 380	94.23 374	82.99 246	97.53 406	87.72 327	85.57 401	94.93 396

IMVS_0404		92.44 255	91.92 255	94.00 306	96.19 287	86.16 373	93.84 435	97.24 253	91.54 211	88.17 381	97.04 211	76.96 362	97.09 429	90.68 257	95.59 251	98.76 163

cl____		90.96 335	90.32 324	92.89 369	95.37 339	86.21 370	94.46 410	96.64 318	87.82 360	88.15 382	94.18 377	82.98 247	97.54 404	87.70 330	85.59 400	94.92 398

tpmvs		89.83 373	89.15 371	91.89 401	94.92 371	80.30 458	93.11 455	95.46 388	86.28 397	88.08 383	92.65 426	80.44 305	98.52 278	81.47 427	89.92 354	96.84 305

PS-CasMVS		91.55 301	90.84 299	93.69 329	94.96 367	88.28 302	97.84 96	98.24 64	91.46 218	88.04 384	95.80 287	79.67 320	97.48 410	87.02 357	84.54 422	95.31 372

MIMVSNet		88.50 390	86.76 400	93.72 327	94.84 376	87.77 327	91.39 476	94.05 450	86.41 394	87.99 385	92.59 429	63.27 472	95.82 460	77.44 456	92.84 309	97.57 276

GG-mvs-BLEND				93.62 337	93.69 415	89.20 263	92.39 471	83.33 514		87.98 386	89.84 466	71.00 416	96.87 440	82.08 421	95.40 258	94.80 414

miper_lstm_enhance		90.50 353	90.06 341	91.83 403	95.33 345	83.74 417	93.86 433	96.70 314	87.56 372	87.79 387	93.81 393	83.45 234	96.92 437	87.39 347	84.62 418	94.82 411

PEN-MVS		91.20 323	90.44 320	93.48 347	94.49 391	87.91 322	97.76 109	98.18 78	91.29 225	87.78 388	95.74 293	80.35 307	97.33 422	85.46 381	82.96 439	95.19 383

ITE_SJBPF				92.43 382	95.34 342	85.37 393		95.92 359	91.47 217	87.75 389	96.39 257	71.00 416	97.96 350	82.36 419	89.86 355	93.97 443

v7n		90.76 341	89.86 348	93.45 349	93.54 422	87.60 331	97.70 125	97.37 231	88.85 325	87.65 390	94.08 383	81.08 290	98.10 322	84.68 391	83.79 433	94.66 424

Patchmtry		88.64 389	87.25 392	92.78 375	94.09 403	86.64 355	89.82 491	95.68 375	80.81 470	87.63 391	92.36 436	80.91 293	97.03 432	78.86 451	85.12 410	94.67 423

testing3		87.67 398	86.88 399	90.05 442	96.14 297	80.71 450	97.10 210	92.85 469	90.15 280	87.54 392	94.55 350	55.70 489	94.10 483	73.77 478	94.10 289	95.35 369

pmmvs4		90.93 336	89.85 349	94.17 295	93.34 432	90.79 185	94.60 400	96.02 357	84.62 423	87.45 393	95.15 321	81.88 277	97.45 413	87.70 330	87.87 378	94.27 437

tpm cat1		88.36 391	87.21 394	91.81 405	95.13 361	80.55 454	92.58 468	95.70 371	74.97 490	87.45 393	91.96 446	78.01 354	98.17 314	80.39 440	88.74 370	96.72 309

FMVSNet1		89.88 370	88.31 383	94.59 266	95.41 335	91.18 166	97.50 156	96.93 292	86.62 390	87.41 395	94.51 353	65.94 461	97.29 424	83.04 409	87.43 383	95.31 372

IterMVS-SCA-FT		90.31 355	89.81 351	91.82 404	95.52 328	84.20 412	94.30 418	96.15 354	90.61 263	87.39 396	94.27 371	75.80 372	96.44 448	87.34 348	86.88 392	94.82 411

MVS		91.71 287	90.44 320	95.51 206	95.20 355	91.59 143	96.04 324	97.45 214	73.44 494	87.36 397	95.60 301	85.42 194	99.10 175	85.97 374	97.46 172	95.83 339

EU-MVSNet		88.72 388	88.90 376	88.20 459	93.15 436	74.21 493	96.63 271	94.22 446	85.18 414	87.32 398	95.97 277	76.16 369	94.98 474	85.27 384	86.17 395	95.41 362

IterMVS		90.15 363	89.67 357	91.61 411	95.48 330	83.72 418	94.33 416	96.12 355	89.99 283	87.31 399	94.15 379	75.78 374	96.27 453	86.97 358	86.89 391	94.83 406
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UWE-MVS-28		86.81 415	86.41 402	88.02 461	92.87 441	74.60 492	95.38 367	86.70 507	88.17 348	87.28 400	94.67 345	70.83 418	93.30 493	67.45 495	94.31 280	96.17 324

pmmvs5		89.86 372	88.87 377	92.82 372	92.86 442	86.23 369	96.26 306	95.39 389	84.24 428	87.12 401	94.51 353	74.27 387	97.36 421	87.61 340	87.57 381	94.86 401

DTE-MVSNet		90.56 349	89.75 355	93.01 364	93.95 406	87.25 338	97.64 135	97.65 164	90.74 252	87.12 401	95.68 297	79.97 315	97.00 435	83.33 406	81.66 445	94.78 418

mvs5depth		86.53 416	85.08 421	90.87 427	88.74 486	82.52 433	91.91 473	94.23 445	86.35 395	87.11 403	93.70 396	66.52 454	97.76 377	81.37 431	75.80 469	92.31 472

Patchmatch-test		89.42 379	87.99 386	93.70 328	95.27 349	85.11 397	88.98 494	94.37 441	81.11 466	87.10 404	93.69 397	82.28 266	97.50 409	74.37 474	94.76 271	98.48 195

IB-MVS	87.33 17	89.91 367	88.28 384	94.79 255	95.26 352	87.70 328	95.12 387	93.95 454	89.35 307	87.03 405	92.49 430	70.74 419	99.19 158	89.18 298	81.37 446	97.49 278
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
EPNet_dtu		91.71 287	91.28 279	92.99 365	93.76 413	83.71 419	96.69 262	95.28 397	93.15 140	87.02 406	95.95 279	83.37 235	97.38 420	79.46 448	96.84 204	97.88 253
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Syy-MVS		87.13 408	87.02 398	87.47 463	95.16 356	73.21 496	95.00 389	93.93 455	88.55 338	86.96 407	91.99 444	75.90 370	94.00 485	61.59 506	94.11 287	95.20 380

myMVS_eth3d		87.18 407	86.38 403	89.58 448	95.16 356	79.53 469	95.00 389	93.93 455	88.55 338	86.96 407	91.99 444	56.23 488	94.00 485	75.47 470	94.11 287	95.20 380

baseline2		91.63 293	90.86 296	93.94 314	94.33 397	86.32 366	95.92 333	91.64 484	89.37 306	86.94 409	94.69 342	81.62 281	98.69 248	88.64 312	94.57 276	96.81 306

MSDG		91.42 309	90.24 330	94.96 244	97.15 181	88.91 276	93.69 441	96.32 336	85.72 406	86.93 410	96.47 252	80.24 309	98.98 195	80.57 438	95.05 266	96.98 298

test0.0.03 1		89.37 380	88.70 378	91.41 416	92.47 451	85.63 384	95.22 378	92.70 472	91.11 240	86.91 411	93.65 401	79.02 334	93.19 496	78.00 455	89.18 361	95.41 362

COLMAP_ROB	87.81 15	90.40 354	89.28 367	93.79 323	97.95 131	87.13 344	96.92 228	95.89 363	82.83 450	86.88 412	97.18 200	73.77 392	99.29 149	78.44 453	93.62 302	94.95 392
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
D2MVS		91.30 318	90.95 293	92.35 384	94.71 383	85.52 386	96.18 315	98.21 68	88.89 324	86.60 413	93.82 392	79.92 316	97.95 354	89.29 292	90.95 343	93.56 448

SD_0403		90.01 365	90.02 343	89.96 444	95.65 322	76.76 483	95.76 344	96.46 329	90.58 267	86.59 414	96.29 261	82.12 270	94.78 476	73.00 482	93.76 298	98.35 210

OurMVSNet-221017-0		90.51 352	90.19 335	91.44 415	93.41 430	81.25 445	96.98 222	96.28 342	91.68 208	86.55 415	96.30 260	74.20 388	97.98 343	88.96 304	87.40 386	95.09 387

sc_t1		86.48 418	84.10 436	93.63 336	93.45 428	85.76 382	96.79 248	94.71 424	73.06 495	86.45 416	94.35 363	55.13 490	97.95 354	84.38 396	78.55 460	97.18 294

MS-PatchMatch		90.27 357	89.77 353	91.78 407	94.33 397	84.72 406	95.55 357	96.73 309	86.17 400	86.36 417	95.28 315	71.28 413	97.80 372	84.09 399	98.14 150	92.81 459

blended_shiyan8		87.58 400	85.55 411	93.66 334	88.76 485	88.54 291	95.21 380	96.29 341	82.81 451	86.25 418	87.73 484	73.70 394	97.58 396	87.81 323	71.42 488	94.85 404

1314		92.81 247	92.03 250	95.14 229	95.33 345	89.52 247	96.04 324	97.44 218	87.72 367	86.25 418	95.33 312	83.84 226	98.79 218	89.26 293	97.05 196	97.11 296

blend_shiyan4		86.87 412	84.61 430	93.67 333	88.87 481	88.70 283	95.17 384	96.30 338	82.80 452	86.16 420	87.11 490	65.12 469	97.55 399	87.73 325	72.21 485	94.75 420

tfpnnormal		89.70 376	88.40 382	93.60 338	95.15 359	90.10 215	97.56 147	98.16 82	87.28 379	86.16 420	94.63 347	77.57 357	98.05 334	74.48 472	84.59 420	92.65 463

gbinet_0.2-2-1-0.02		87.30 403	85.16 419	93.69 329	88.70 488	88.81 280	95.14 385	96.20 351	83.03 449	86.14 422	87.06 491	71.26 414	97.40 418	87.46 345	71.49 487	94.86 401

pm-mvs1		90.72 344	89.65 359	93.96 311	94.29 400	89.63 237	97.79 107	96.82 306	89.07 314	86.12 423	95.48 309	78.61 342	97.78 374	86.97 358	81.67 444	94.46 428

blended_shiyan6		87.55 401	85.52 412	93.64 335	88.78 483	88.50 294	95.23 377	96.30 338	82.80 452	86.09 424	87.70 485	73.69 395	97.56 397	87.70 330	71.36 489	94.86 401

0.4-1-1-0.1		86.83 413	84.27 433	94.50 275	91.39 462	88.23 306	92.62 467	92.27 478	84.04 431	86.01 425	83.30 504	65.29 466	98.31 299	89.08 300	74.45 475	96.96 302

wanda-best-256-512		87.29 404	85.21 417	93.53 343	88.54 489	88.21 308	94.51 406	96.27 343	82.69 455	85.92 426	86.89 493	73.04 398	97.55 399	87.68 334	71.36 489	94.83 406

FE-blended-shiyan7		87.29 404	85.21 417	93.53 343	88.54 489	88.21 308	94.51 406	96.27 343	82.69 455	85.92 426	86.89 493	73.03 399	97.55 399	87.68 334	71.36 489	94.83 406

usedtu_blend_shiyan5		87.06 410	84.84 425	93.69 329	88.54 489	88.70 283	95.83 338	95.54 383	78.74 480	85.92 426	86.89 493	73.03 399	97.55 399	87.73 325	71.36 489	94.83 406

OpenMVS	89.19 12	92.86 243	91.68 264	96.40 124	95.34 342	92.73 97	98.27 37	98.12 88	84.86 420	85.78 429	97.75 147	78.89 339	99.74 61	87.50 344	98.65 123	96.73 308

LTVRE_ROB	88.41 13	90.99 332	89.92 347	94.19 294	96.18 291	89.55 244	96.31 301	97.09 269	87.88 357	85.67 430	95.91 281	78.79 340	98.57 273	81.50 425	89.98 353	94.44 430
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
testgi		87.97 394	87.21 394	90.24 439	92.86 442	80.76 449	96.67 265	94.97 412	91.74 206	85.52 431	95.83 285	62.66 477	94.47 479	76.25 464	88.36 374	95.48 355

AllTest		90.23 359	88.98 373	93.98 308	97.94 132	86.64 355	96.51 279	95.54 383	85.38 410	85.49 432	96.77 229	70.28 422	99.15 167	80.02 442	92.87 307	96.15 327

TestCases				93.98 308	97.94 132	86.64 355		95.54 383	85.38 410	85.49 432	96.77 229	70.28 422	99.15 167	80.02 442	92.87 307	96.15 327

DSMNet-mixed		86.34 422	86.12 407	87.00 469	89.88 474	70.43 499	94.93 391	90.08 495	77.97 485	85.42 434	92.78 423	74.44 386	93.96 487	74.43 473	95.14 262	96.62 312

ppachtmachnet_test		88.35 392	87.29 391	91.53 412	92.45 452	83.57 421	93.75 437	95.97 358	84.28 426	85.32 435	94.18 377	79.00 338	96.93 436	75.71 467	84.99 414	94.10 438

0.4-1-1-0.2		86.27 424	83.62 438	94.20 293	90.38 469	87.69 329	91.04 481	92.52 475	83.43 445	85.22 436	81.49 509	65.31 465	98.29 302	88.90 306	74.30 477	96.64 311

CL-MVSNet_self_test		86.31 423	85.15 420	89.80 446	88.83 482	81.74 443	93.93 430	96.22 348	86.67 389	85.03 437	90.80 457	78.09 351	94.50 477	74.92 471	71.86 486	93.15 455

our_test_3		88.78 387	87.98 387	91.20 422	92.45 452	82.53 432	93.61 446	95.69 373	85.77 405	84.88 438	93.71 395	79.99 314	96.78 444	79.47 447	86.24 394	94.28 436

MVP-Stereo		90.74 343	90.08 337	92.71 377	93.19 435	88.20 310	95.86 336	96.27 343	86.07 401	84.86 439	94.76 339	77.84 355	97.75 379	83.88 404	98.01 156	92.17 476
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	87.92 14	90.20 361	89.18 370	93.25 355	96.48 263	86.45 364	96.99 221	96.68 315	88.83 327	84.79 440	96.22 265	70.16 424	98.53 277	84.42 395	88.04 376	94.77 419

0.3-1-1-0.015		86.11 428	83.37 439	94.34 285	90.58 468	88.02 317	91.64 475	92.45 476	83.56 442	84.46 441	81.84 507	62.73 476	98.31 299	88.98 303	74.09 478	96.70 310

NR-MVSNet		92.34 261	91.27 280	95.53 201	94.95 368	93.05 84	97.39 177	98.07 100	92.65 167	84.46 441	95.71 294	85.00 204	97.77 376	89.71 279	83.52 435	95.78 343

LF4IMVS		87.94 395	87.25 392	89.98 443	92.38 455	80.05 464	94.38 413	95.25 400	87.59 371	84.34 443	94.74 341	64.31 470	97.66 388	84.83 388	87.45 382	92.23 473

LCM-MVSNet-Re		92.50 252	92.52 236	92.44 381	96.82 217	81.89 441	96.92 228	93.71 459	92.41 178	84.30 444	94.60 348	85.08 201	97.03 432	91.51 236	97.36 179	98.40 204

TransMVSNet (Re)		88.94 383	87.56 389	93.08 363	94.35 396	88.45 297	97.73 116	95.23 401	87.47 373	84.26 445	95.29 313	79.86 317	97.33 422	79.44 449	74.44 476	93.45 452

Anonymous20231206		87.09 409	86.14 406	89.93 445	91.22 464	80.35 456	96.11 318	95.35 392	83.57 441	84.16 446	93.02 420	73.54 396	95.61 464	72.16 484	86.14 396	93.84 445

SixPastTwentyTwo		89.15 381	88.54 381	90.98 425	93.49 425	80.28 460	96.70 260	94.70 425	90.78 250	84.15 447	95.57 302	71.78 409	97.71 382	84.63 392	85.07 411	94.94 394

test_fmvs3		83.21 447	83.02 442	83.78 475	86.77 500	68.34 504	96.76 254	94.91 416	86.49 392	84.14 448	89.48 469	36.04 507	91.73 501	91.86 228	80.77 449	91.26 487

TDRefinement		86.53 416	84.76 427	91.85 402	82.23 512	84.25 410	96.38 292	95.35 392	84.97 419	84.09 449	94.94 329	65.76 462	98.34 298	84.60 393	74.52 474	92.97 456

KD-MVS_self_test		85.95 430	84.95 423	88.96 456	89.55 477	79.11 475	95.13 386	96.42 331	85.91 403	84.07 450	90.48 459	70.03 426	94.82 475	80.04 441	72.94 482	92.94 457

pmmvs6		87.81 397	86.19 405	92.69 378	91.32 463	86.30 367	97.34 182	96.41 332	80.59 473	84.05 451	94.37 362	67.37 448	97.67 384	84.75 390	79.51 455	94.09 440

ACMH	87.59 16	90.53 350	89.42 364	93.87 319	96.21 283	87.92 320	97.24 195	96.94 291	88.45 341	83.91 452	96.27 263	71.92 407	98.62 266	84.43 394	89.43 359	95.05 390
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		87.29 404	85.79 408	91.78 407	94.80 378	87.28 336	95.49 361	95.28 397	84.09 430	83.85 453	91.82 447	62.95 474	94.17 482	78.48 452	85.34 406	93.91 444

USDC		88.94 383	87.83 388	92.27 389	94.66 384	84.96 402	93.86 433	95.90 361	87.34 377	83.40 454	95.56 303	67.43 447	98.19 312	82.64 417	89.67 357	93.66 447

ttmdpeth		85.91 431	84.76 427	89.36 452	89.14 478	80.25 461	95.66 351	93.16 466	83.77 436	83.39 455	95.26 317	66.24 458	95.26 473	80.65 437	75.57 470	92.57 464

Anonymous20240521		86.42 420	85.44 413	89.34 453	90.33 470	79.79 465	96.73 256	95.92 359	83.71 438	83.25 456	91.36 454	63.92 471	96.01 454	78.39 454	85.36 405	92.22 474

KD-MVS_2432*1600		84.81 441	82.64 444	91.31 418	91.07 465	85.34 394	91.22 478	95.75 369	85.56 408	83.09 457	90.21 462	67.21 449	95.89 456	77.18 460	62.48 508	92.69 461

miper_refine_blended		84.81 441	82.64 444	91.31 418	91.07 465	85.34 394	91.22 478	95.75 369	85.56 408	83.09 457	90.21 462	67.21 449	95.89 456	77.18 460	62.48 508	92.69 461

PVSNet_0	82.17 19	85.46 436	83.64 437	90.92 426	95.27 349	79.49 471	90.55 485	95.60 378	83.76 437	83.00 459	89.95 464	71.09 415	97.97 346	82.75 415	60.79 510	95.31 372

tt0320		85.39 437	83.12 440	92.19 393	93.44 429	85.79 381	96.19 314	94.87 421	71.19 498	82.92 460	91.76 450	58.43 483	96.81 442	81.03 436	78.26 461	93.98 442

mvsany_test3		83.59 445	82.44 447	87.03 468	83.80 505	73.82 494	93.70 439	90.92 492	86.42 393	82.51 461	90.26 461	46.76 499	95.71 461	90.82 251	76.76 466	91.57 481

ArgMatch-Sym		83.08 450	81.73 453	87.11 466	91.53 460	76.72 484	92.86 460	91.54 485	83.66 439	82.34 462	93.45 411	44.99 501	92.15 499	81.78 423	73.46 481	92.47 469

test_0402		86.46 419	84.79 426	91.45 414	95.02 365	85.55 385	96.29 303	94.89 417	80.90 467	82.21 463	93.97 388	68.21 444	97.29 424	62.98 504	88.68 371	91.51 482

Patchmatch-RL test		87.38 402	86.24 404	90.81 430	88.74 486	78.40 479	88.12 503	93.17 464	87.11 382	82.17 464	89.29 470	81.95 274	95.60 465	88.64 312	77.02 464	98.41 203

tt0320-xc		84.83 440	82.33 448	92.31 387	93.66 417	86.20 371	96.17 316	94.06 449	71.26 497	82.04 465	92.22 441	55.07 491	96.72 445	81.49 426	75.04 473	94.02 441

ArgMatch-SfM		83.09 449	81.67 454	87.34 465	91.48 461	76.29 487	92.76 463	91.31 488	84.26 427	81.99 466	93.35 416	45.52 500	92.98 497	81.83 422	72.49 484	92.76 460

TinyColmap		86.82 414	85.35 416	91.21 420	94.91 373	82.99 428	93.94 429	94.02 452	83.58 440	81.56 467	94.68 343	62.34 478	98.13 317	75.78 466	87.35 387	92.52 467

test20.03		86.14 427	85.40 415	88.35 457	90.12 471	80.06 463	95.90 335	95.20 402	88.59 334	81.29 468	93.62 402	71.43 412	92.65 498	71.26 488	81.17 447	92.34 470

dtuonlycased		85.91 431	85.69 409	86.60 470	92.42 454	76.96 482	93.66 443	94.49 435	86.68 388	80.87 469	92.00 443	71.52 410	93.23 495	79.58 444	79.97 451	89.60 494

N_pmnet		78.73 460	78.71 460	78.79 485	92.80 444	46.50 535	94.14 423	43.71 537	78.61 481	80.83 470	91.66 451	74.94 382	96.36 450	67.24 496	84.45 423	93.50 450

MVS-HIRNet		82.47 452	81.21 455	86.26 472	95.38 337	69.21 502	88.96 495	89.49 496	66.28 503	80.79 471	74.08 519	68.48 442	97.39 419	71.93 485	95.47 256	92.18 475

PM-MVS		83.48 446	81.86 452	88.31 458	87.83 494	77.59 481	93.43 448	91.75 483	86.91 384	80.63 472	89.91 465	44.42 503	95.84 459	85.17 387	76.73 467	91.50 484

ambc				86.56 471	83.60 507	70.00 501	85.69 508	94.97 412		80.60 473	88.45 476	37.42 506	96.84 441	82.69 416	75.44 472	92.86 458

MIMVSNet1		84.93 439	83.05 441	90.56 435	89.56 476	84.84 405	95.40 365	95.35 392	83.91 432	80.38 474	92.21 442	57.23 485	93.34 492	70.69 490	82.75 442	93.50 450

lessismore_v0				90.45 436	91.96 458	79.09 476		87.19 505		80.32 475	94.39 360	66.31 457	97.55 399	84.00 401	76.84 465	94.70 422

K. test v3		87.64 399	86.75 401	90.32 438	93.02 438	79.48 472	96.61 272	92.08 481	90.66 259	80.25 476	94.09 382	67.21 449	96.65 446	85.96 375	80.83 448	94.83 406

OpenMVS_ROB	81.14 20	84.42 443	82.28 449	90.83 428	90.06 472	84.05 415	95.73 346	94.04 451	73.89 493	80.17 477	91.53 452	59.15 481	97.64 389	66.92 498	89.05 364	90.80 489

EG-PatchMatch MVS		87.02 411	85.44 413	91.76 409	92.67 446	85.00 400	96.08 321	96.45 330	83.41 446	79.52 478	93.49 408	57.10 486	97.72 381	79.34 450	90.87 345	92.56 465

pmmvs-eth3d		86.22 425	84.45 431	91.53 412	88.34 492	87.25 338	94.47 408	95.01 409	83.47 443	79.51 479	89.61 468	69.75 430	95.71 461	83.13 408	76.73 467	91.64 479

FE-MVSNET2		86.36 421	84.68 429	91.39 417	87.67 495	86.47 363	96.21 311	96.41 332	87.87 358	79.31 480	89.64 467	65.29 466	95.58 466	82.42 418	77.28 463	92.14 477

test_vis1_rt		86.16 426	85.06 422	89.46 450	93.47 427	80.46 455	96.41 286	86.61 508	85.22 413	79.15 481	88.64 475	52.41 494	97.06 430	93.08 201	90.57 347	90.87 488

FE-MVSNET		83.85 444	81.97 450	89.51 449	87.19 498	83.19 425	95.21 380	93.17 464	83.45 444	78.90 482	89.05 472	65.46 463	93.84 489	69.71 493	75.56 471	91.51 482

pmmvs3		79.97 458	77.50 462	87.39 464	82.80 511	79.38 473	92.70 466	90.75 493	70.69 499	78.66 483	87.47 488	51.34 495	93.40 491	73.39 480	69.65 495	89.38 495

UnsupCasMVSNet_eth		85.99 429	84.45 431	90.62 434	89.97 473	82.40 437	93.62 445	97.37 231	89.86 285	78.59 484	92.37 433	65.25 468	95.35 472	82.27 420	70.75 493	94.10 438

dmvs_testset		81.38 455	82.60 446	77.73 486	91.74 459	51.49 526	93.03 457	84.21 513	89.07 314	78.28 485	91.25 455	76.97 361	88.53 508	56.57 514	82.24 443	93.16 454

test_f		80.57 456	79.62 458	83.41 477	83.38 509	67.80 506	93.57 447	93.72 458	80.80 471	77.91 486	87.63 486	33.40 508	92.08 500	87.14 356	79.04 458	90.34 491

new-patchmatchnet		83.18 448	81.87 451	87.11 466	86.88 499	75.99 489	93.70 439	95.18 403	85.02 418	77.30 487	88.40 477	65.99 460	93.88 488	74.19 476	70.18 494	91.47 485

usedtu_dtu_shiyan2		80.00 457	76.91 463	89.27 455	82.13 513	79.69 467	95.45 363	94.20 447	72.95 496	75.80 488	87.75 483	44.44 502	94.30 481	70.64 491	68.81 499	93.84 445

UnsupCasMVSNet_bld		82.13 454	79.46 459	90.14 440	88.00 493	82.47 435	90.89 484	96.62 323	78.94 479	75.61 489	84.40 502	56.63 487	96.31 452	77.30 459	66.77 502	91.63 480

ET-MVSNet_ETH3D		91.49 306	90.11 336	95.63 194	96.40 269	91.57 145	95.34 368	93.48 461	90.60 265	75.58 490	95.49 307	80.08 312	96.79 443	94.25 173	89.76 356	98.52 188

new_pmnet		82.89 451	81.12 456	88.18 460	89.63 475	80.18 462	91.77 474	92.57 473	76.79 488	75.56 491	88.23 479	61.22 480	94.48 478	71.43 486	82.92 440	89.87 492

dongtai		69.99 471	69.33 470	71.98 499	88.78 483	61.64 516	89.86 490	59.93 529	75.67 489	74.96 492	85.45 499	50.19 496	81.66 520	43.86 522	55.27 514	72.63 519

APD_test1		79.31 459	77.70 461	84.14 474	89.11 480	69.07 503	92.36 472	91.50 486	69.07 500	73.87 493	92.63 428	39.93 505	94.32 480	70.54 492	80.25 450	89.02 496

CMPMVS	62.92 21	85.62 435	84.92 424	87.74 462	89.14 478	73.12 497	94.17 422	96.80 307	73.98 491	73.65 494	94.93 330	66.36 455	97.61 393	83.95 402	91.28 336	92.48 468
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		82.38 453	80.04 457	89.37 451	87.63 496	82.83 429	95.03 388	93.37 463	73.90 492	73.50 495	94.35 363	62.89 475	93.25 494	73.80 477	65.92 504	92.04 478

MASt3R-SfM		71.17 468	70.37 467	73.55 497	74.50 525	51.20 527	82.17 514	80.88 518	64.49 508	72.54 496	91.37 453	25.17 516	81.85 519	75.86 465	66.37 503	87.59 498

WB-MVS		76.77 461	76.63 464	77.18 487	85.32 502	56.82 523	94.53 403	89.39 497	82.66 457	71.35 497	89.18 471	75.03 379	88.88 506	35.42 527	66.79 501	85.84 502

SSC-MVS		76.05 462	75.83 465	76.72 491	84.77 503	56.22 524	94.32 417	88.96 499	81.82 463	70.52 498	88.91 473	74.79 383	88.71 507	33.69 529	64.71 505	85.23 505

YYNet1		85.87 433	84.23 434	90.78 433	92.38 455	82.46 436	93.17 452	95.14 405	82.12 460	67.69 499	92.36 436	78.16 350	95.50 470	77.31 458	79.73 453	94.39 431

kuosan		65.27 479	64.66 479	67.11 505	83.80 505	61.32 517	88.53 499	60.77 528	68.22 501	67.67 500	80.52 512	49.12 497	70.76 530	29.67 531	53.64 516	69.26 521

MDA-MVSNet_test_wron		85.87 433	84.23 434	90.80 432	92.38 455	82.57 431	93.17 452	95.15 404	82.15 459	67.65 501	92.33 439	78.20 347	95.51 469	77.33 457	79.74 452	94.31 435

DeepMVS_CX				74.68 496	90.84 467	64.34 513		81.61 516	65.34 505	67.47 502	88.01 482	48.60 498	80.13 523	62.33 505	73.68 480	79.58 513

LCM-MVSNet		72.55 464	69.39 469	82.03 479	70.81 534	65.42 511	90.12 489	94.36 443	55.02 516	65.88 503	81.72 508	24.16 517	89.96 502	74.32 475	68.10 500	90.71 490

test_method		66.11 478	64.89 478	69.79 501	72.62 532	35.23 541	65.19 530	92.83 471	20.35 536	65.20 504	88.08 481	43.14 504	82.70 518	73.12 481	63.46 506	91.45 486

MDA-MVSNet-bldmvs		85.00 438	82.95 443	91.17 424	93.13 437	83.33 422	94.56 402	95.00 410	84.57 424	65.13 505	92.65 426	70.45 421	95.85 458	73.57 479	77.49 462	94.33 433

RoMa-SfM		70.64 469	67.48 473	80.09 480	84.70 504	66.61 507	88.62 498	73.09 524	65.10 506	64.98 506	88.91 473	22.38 520	87.00 511	63.51 503	56.06 513	86.67 500

DenseAffine		72.53 465	69.17 471	82.59 478	87.49 497	70.91 498	88.38 500	81.13 517	67.58 502	64.27 507	87.44 489	23.61 519	88.47 510	66.10 499	56.56 512	88.38 497

PMMVS2		70.19 470	66.92 474	80.01 481	76.35 522	65.67 509	86.22 507	87.58 503	64.83 507	62.38 508	80.29 513	26.78 513	88.49 509	63.79 502	54.07 515	85.88 501

testf1		69.31 472	66.76 475	76.94 489	78.61 520	61.93 514	88.27 501	86.11 509	55.62 514	59.69 509	85.31 500	20.19 523	89.32 503	57.62 511	69.44 497	79.58 513

APD_test2		69.31 472	66.76 475	76.94 489	78.61 520	61.93 514	88.27 501	86.11 509	55.62 514	59.69 509	85.31 500	20.19 523	89.32 503	57.62 511	69.44 497	79.58 513

DKM		67.96 475	64.19 480	79.27 483	83.41 508	64.35 512	86.88 506	68.11 526	63.15 509	59.36 511	86.08 497	16.45 532	86.15 513	64.54 501	49.73 517	87.32 499

RoMa-HiRes		64.40 480	60.91 483	74.89 495	78.66 519	58.85 521	85.22 510	58.46 531	58.65 512	59.29 512	86.60 496	16.97 529	83.91 516	59.14 509	45.20 522	81.91 512

test_vis3_rt		72.73 463	70.55 466	79.27 483	80.02 517	68.13 505	93.92 431	74.30 523	76.90 487	58.99 513	73.58 520	20.29 522	95.37 471	84.16 397	72.80 483	74.31 516

FPMVS		71.27 467	69.85 468	75.50 493	74.64 524	59.03 520	91.30 477	91.50 486	58.80 511	57.92 514	88.28 478	29.98 511	85.53 514	53.43 517	82.84 441	81.95 511

Gipuma		67.86 476	65.41 477	75.18 494	92.66 447	73.45 495	66.50 529	94.52 433	53.33 519	57.80 515	66.07 525	30.81 509	89.20 505	48.15 520	78.88 459	62.90 528
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_clip		37.19 502	40.69 505	26.70 527	52.35 551	23.34 559	43.13 542	10.51 562	12.50 551	56.71 516	80.13 514	19.51 525	16.50 558	43.87 521	47.47 518	40.26 536

DKM-HiRes		64.02 481	59.97 484	76.17 492	79.46 518	59.20 519	84.48 511	58.37 532	58.52 513	56.03 517	83.71 503	13.19 540	83.72 517	60.49 508	45.50 521	85.59 503

LoFTR		72.43 466	68.71 472	83.60 476	85.67 501	65.61 510	88.04 504	87.40 504	66.11 504	55.94 518	85.54 498	25.43 514	95.55 468	60.87 507	63.38 507	89.63 493

MatchFormer		67.84 477	63.81 481	79.93 482	83.26 510	60.99 518	87.61 505	84.49 512	54.89 517	51.76 519	81.06 510	22.08 521	94.10 483	50.36 519	58.82 511	84.72 506

PDCNetPlus		61.05 483	58.26 486	69.44 502	75.52 523	55.68 525	81.49 515	51.76 534	62.45 510	51.54 520	82.02 506	23.69 518	78.90 524	65.91 500	29.91 539	73.74 517

tmp_tt		51.94 491	53.82 489	46.29 513	33.73 561	45.30 537	78.32 517	67.24 527	18.02 538	50.93 521	87.05 492	52.99 493	53.11 534	70.76 489	25.29 545	40.46 535

VLMVS_CLIP		39.93 501	41.64 501	34.80 520	33.81 560	19.16 561	46.81 537	59.30 530	16.50 539	47.57 522	67.74 524	14.11 537	49.88 535	42.98 523	45.94 520	35.36 538

PMatch-SfM		57.38 486	52.53 491	71.95 500	68.62 535	49.38 528	77.61 518	45.82 535	52.41 520	46.59 523	82.04 505	4.86 557	81.03 521	58.34 510	36.49 532	85.43 504

ELoFTR		60.03 484	55.86 487	72.52 498	67.65 536	48.49 530	76.21 519	75.14 522	53.94 518	45.93 524	79.98 515	9.14 542	85.06 515	55.39 515	39.36 530	84.02 508

PMatch-Up-SfM		52.53 489	47.58 494	67.36 504	63.24 539	43.29 538	72.10 521	34.71 547	47.03 521	43.51 525	79.07 516	3.90 560	75.83 525	54.68 516	30.02 538	82.95 509

ANet_high		63.94 482	59.58 485	77.02 488	61.24 541	66.06 508	85.66 509	87.93 502	78.53 482	42.94 526	71.04 521	25.42 515	80.71 522	52.60 518	30.83 536	84.28 507

E-PMN		53.28 487	52.56 490	55.43 508	74.43 526	47.13 534	83.63 513	76.30 519	42.23 523	42.59 527	62.22 529	28.57 512	74.40 527	31.53 530	31.51 534	44.78 532

SP-DiffGlue		43.94 496	43.32 497	45.79 516	47.79 557	33.03 542	63.37 531	42.65 540	25.71 530	41.26 528	69.27 522	18.83 527	38.88 542	34.96 528	46.05 519	65.47 527

EMVS		52.08 490	51.31 492	54.39 510	72.62 532	45.39 536	83.84 512	75.51 521	41.13 524	40.77 529	59.65 531	30.08 510	73.60 528	28.31 532	29.90 540	44.18 533

MVE	50.73 23	53.25 488	48.81 493	66.58 506	65.34 537	57.50 522	72.49 520	70.94 525	40.15 525	39.28 530	63.51 526	6.89 546	73.48 529	38.29 525	42.38 527	68.76 522
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ALIKED-LG		47.63 492	45.22 495	54.88 509	81.48 514	48.47 531	71.83 522	45.44 536	32.66 527	37.07 531	63.26 528	19.21 526	63.71 531	15.49 541	40.53 528	52.46 529

ALIKED-NN		46.19 494	43.87 496	53.16 512	80.39 516	47.77 532	69.82 528	43.65 538	27.89 528	36.60 532	63.35 527	17.30 528	61.29 533	15.84 540	39.98 529	50.41 531

PMVS	53.92 22	58.58 485	55.40 488	68.12 503	51.00 555	48.64 529	78.86 516	87.10 506	46.77 522	35.84 533	74.28 518	8.76 543	86.34 512	42.07 524	73.91 479	69.38 520
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GLUNet-SfM		46.44 493	41.21 503	62.14 507	51.92 552	38.44 540	58.72 532	57.51 533	34.08 526	34.61 534	67.84 523	11.40 541	74.90 526	35.48 526	19.30 551	73.08 518

ALIKED-MNN		45.42 495	42.62 498	53.80 511	80.52 515	47.58 533	70.83 525	43.05 539	27.21 529	34.32 535	61.10 530	14.85 536	62.94 532	14.90 542	36.82 531	50.89 530

SP-SuperGlue		43.33 498	42.50 499	45.81 515	73.95 529	31.24 545	71.34 523	41.17 541	23.96 531	33.42 536	56.47 533	16.72 531	39.64 540	21.11 536	44.32 524	66.57 524

SP-LightGlue		43.37 497	42.49 500	46.03 514	74.26 527	31.37 544	71.24 524	40.98 542	23.86 532	33.18 537	56.34 535	16.78 530	39.73 539	21.09 537	44.68 523	66.97 523

SP-NN		42.37 499	41.40 502	45.29 518	72.86 531	30.45 547	70.32 527	39.16 545	22.21 533	31.32 538	56.73 532	15.45 534	39.53 541	20.27 538	44.25 525	65.88 526

XFeat-NN		33.93 504	33.70 507	34.60 521	41.69 559	24.48 557	51.85 535	36.02 546	19.55 537	31.20 539	56.38 534	13.46 539	40.91 537	22.51 535	30.65 537	38.42 537

VLMVS		20.83 518	22.16 521	16.83 538	23.35 562	13.77 565	21.05 552	12.13 561	1.76 558	31.04 540	45.78 539	15.59 533	13.56 559	13.60 543	35.16 533	23.18 539

SP-MNN		42.11 500	40.98 504	45.49 517	72.87 530	30.19 549	70.72 526	39.96 543	20.98 534	30.21 541	55.72 537	15.26 535	40.07 538	19.70 539	43.42 526	66.21 525

XFeat-MNN		35.01 503	34.34 506	37.02 519	42.54 558	25.71 556	54.01 534	39.41 544	20.70 535	30.13 542	55.85 536	14.08 538	44.62 536	22.90 534	29.45 543	40.75 534

MVS_baseline		12.31 524	14.46 527	5.86 539	16.09 563	0.78 568	6.53 553	1.85 566	0.36 560	23.99 543	49.92 538	2.55 563	0.00 562	8.94 544	19.86 549	16.82 552

SIFT-NN		28.47 505	28.54 509	28.27 522	64.38 538	31.62 543	48.50 536	24.78 548	14.32 540	19.55 544	40.46 540	7.22 544	31.96 544	6.20 547	31.47 535	21.24 540

SIFT-MNN		27.50 506	27.40 510	27.80 523	61.71 540	30.57 546	46.59 538	24.66 549	14.04 541	17.35 545	39.90 541	6.52 547	31.80 545	6.13 548	29.65 541	21.04 541

SIFT-NN-NCMNet		27.16 507	27.05 511	27.51 524	59.97 543	30.42 548	46.49 539	24.52 550	13.94 543	17.23 546	39.47 542	6.39 548	31.40 546	5.94 549	29.49 542	20.72 543

SIFT-NN-CMatch		25.59 509	25.23 513	26.67 528	56.47 547	28.89 552	42.75 543	22.52 553	13.89 544	16.98 547	39.39 544	6.26 550	30.38 548	5.77 551	22.99 547	20.75 542

SIFT-NN-PointCN		23.81 514	23.84 517	23.73 533	52.41 550	22.80 560	42.30 545	20.98 555	13.02 550	15.14 548	37.74 549	6.20 551	28.40 553	5.52 553	21.24 548	19.98 545

SIFT-ConvMatch		24.62 512	24.14 516	26.03 529	58.66 544	29.15 551	40.80 546	21.31 554	13.69 545	13.51 549	38.52 545	5.65 553	30.22 550	5.51 554	19.65 550	18.73 548

SIFT-NN-UMatch		25.24 510	25.01 514	25.92 530	54.55 549	27.33 553	44.97 540	22.85 551	13.97 542	13.40 550	39.41 543	6.28 549	30.23 549	5.83 550	23.82 546	20.21 544

SIFT-CM-Cal		23.18 516	22.70 519	24.60 532	57.42 545	26.79 554	37.63 548	18.36 557	13.35 548	12.57 551	37.37 550	5.54 554	28.79 552	5.17 557	16.92 555	18.23 549

SIFT-UMatch		24.03 513	23.67 518	25.10 531	57.10 546	26.49 555	42.43 544	20.05 556	13.49 547	12.40 552	38.51 546	5.45 555	30.07 551	5.56 552	18.08 552	18.74 547

SIFT-NCM-Cal		25.87 508	25.57 512	26.75 525	60.60 542	29.37 550	44.96 541	22.64 552	13.57 546	11.67 553	37.90 547	5.81 552	31.26 547	5.32 555	27.70 544	19.63 546

SIFT-UM-Cal		22.52 517	22.27 520	23.27 534	56.41 548	23.87 558	39.94 547	16.81 559	13.33 549	10.54 554	37.90 547	5.16 556	28.36 554	5.23 556	15.12 556	17.57 550

wuyk23d		25.11 511	24.57 515	26.74 526	73.98 528	39.89 539	57.88 533	9.80 564	12.27 552	10.39 555	6.97 559	7.03 545	36.44 543	25.43 533	17.39 553	3.89 557

SIFT-PCN-Cal		20.26 520	20.34 523	20.01 536	51.70 553	17.74 563	35.64 550	16.15 560	11.90 554	10.28 556	33.69 551	4.55 558	25.68 555	4.57 558	14.59 557	16.60 553

SIFT-PointCN		20.70 519	20.89 522	20.14 535	51.62 554	18.11 562	37.52 549	17.71 558	12.03 553	10.05 557	33.23 552	4.33 559	25.40 556	4.55 559	16.94 554	16.90 551

SIFT-NCMNet		17.70 521	17.74 524	17.60 537	49.47 556	16.50 564	30.22 551	10.39 563	11.77 555	8.79 558	29.74 554	3.61 562	22.42 557	3.97 560	11.69 558	13.89 554

testmvs		13.36 522	16.33 525	4.48 541	5.04 564	2.26 567	93.18 451	3.28 565	2.70 556	8.24 559	21.66 555	2.29 564	2.19 560	7.58 545	2.96 559	9.00 556

test123		13.04 523	15.66 526	5.18 540	4.51 565	3.45 566	92.50 470	1.81 567	2.50 557	7.58 560	20.15 556	3.67 561	2.18 561	7.13 546	1.07 560	9.90 555

EGC-MVSNET		68.77 474	63.01 482	86.07 473	92.49 450	82.24 439	93.96 428	90.96 491	0.71 559	2.62 561	90.89 456	53.66 492	93.46 490	57.25 513	84.55 421	82.51 510

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

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

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

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

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

cdsmvs_eth3d_5k		23.24 515	30.99 508	0.00 542	0.00 566	0.00 569	0.00 554	97.63 168	0.00 561	0.00 562	96.88 224	84.38 216	0.00 562	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		7.39 526	9.85 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	88.65 111	0.00 562	0.00 561	0.00 561	0.00 558

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

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

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

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

ab-mvs-re		8.06 525	10.74 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	96.69 235	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

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

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet2					0.00 566	79.04 477	92.75 464	94.19 448	78.18 483
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														67.11 497	84.43 424	93.53 449
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													96.32 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.53 469								75.56 469

MSC_two_6792asdad				98.86 1	98.67 68	96.94 1		97.93 127					99.86 11	97.68 34	99.67 6	99.77 4

No_MVS				98.86 1	98.67 68	96.94 1		97.93 127					99.86 11	97.68 34	99.67 6	99.77 4

eth-test2					0.00 566

eth-test					0.00 566

OPU-MVS				98.55 3	98.82 62	96.86 3	98.25 40				98.26 88	96.04 2	99.24 153	95.36 127	99.59 22	99.56 41

save fliter					98.91 59	94.28 44	97.02 215	98.02 115	95.35 34

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 11	97.52 43	99.67 6	99.75 8

GSMVS																98.45 198

sam_mvs1												82.76 254				98.45 198

sam_mvs												81.94 275

MTGPA								98.08 95

test_post1							92.81 462				16.58 558	80.53 303	97.68 383	86.20 367

test_post											17.58 557	81.76 278	98.08 327

patchmatchnet-post											90.45 460	82.65 259	98.10 322

MTMP							97.86 92	82.03 515

gm-plane-assit					93.22 434	78.89 478			84.82 421		93.52 407		98.64 260	87.72 327

test9_res														94.81 151	99.38 65	99.45 60

agg_prior2														93.94 179	99.38 65	99.50 53

test_prior4						93.66 64	96.42 285

test_prior				97.23 71	98.67 68	92.99 86		98.00 119					99.41 135			99.29 76

新几何2							95.79 342

旧先验1					98.38 91	93.38 70		97.75 151			98.09 98	92.30 50			99.01 108	99.16 87

无先验							95.79 342	97.87 134	83.87 435				99.65 81	87.68 334		98.89 141

原ACMM2							95.67 348

testdata2													99.67 79	85.96 375

segment_acmp												92.89 35

testdata1							95.26 376		93.10 143

plane_prior7					96.21 283	89.98 222

plane_prior6					96.10 302	90.00 218						81.32 285

plane_prior5								97.51 197					98.60 268	93.02 204	92.23 318	95.86 335

plane_prior4											96.64 238

plane_prior2							97.74 114		94.85 56

plane_prior1					96.14 297

plane_prior						89.99 220	97.24 195		94.06 96						92.16 322

n2								0.00 568

nn								0.00 568

door-mid								91.06 490

test11								97.88 132

door								91.13 489

HQP5-MVS						89.33 256

BP-MVS														92.13 221

HQP3-MVS								97.39 226							92.10 323

HQP2-MVS												80.95 291

NP-MVS					95.99 309	89.81 230					95.87 282

ACMMP++_ref															90.30 352

ACMMP++															91.02 341

Test By Simon												88.73 110

High-resolution multi-view benchmark