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_conf0.5_n_9		97.59 13	97.79 6	96.97 86	98.28 94	91.49 144	97.61 138	98.71 13	97.10 5	99.70 1	98.93 22	90.95 76	99.77 52	99.35 6	99.53 33	99.65 20

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 101	98.43 82	90.32 201	97.80 104	98.53 30	97.24 4	99.62 2	99.14 2	88.65 109	99.80 40	99.54 1	99.15 95	99.74 9

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 86	98.24 100	91.96 126	97.89 88	98.72 12	96.77 7	99.46 3	99.06 12	87.78 127	99.84 26	99.40 4	99.27 75	99.12 92

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 119	98.42 83	91.37 151	98.04 63	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 69	98.12 214

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 34	98.14 113	93.94 56	97.93 83	98.65 24	96.70 8	99.38 5	99.07 11	89.92 91	99.81 35	99.16 14	99.43 53	99.61 30

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 151	97.98 126	90.43 194	97.50 153	98.59 27	96.59 10	99.31 6	99.08 8	84.47 198	99.75 58	99.37 5	98.45 133	97.88 235

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 61	98.21 106	92.75 92	97.83 98	98.73 10	95.04 45	99.30 7	98.84 36	93.34 24	99.78 49	99.32 7	99.13 98	99.50 52

test_fmvsm_n_1920		97.55 16	97.89 3	96.53 105	98.41 85	91.73 130	98.01 66	99.02 1	96.37 13	99.30 7	98.92 23	92.39 44	99.79 46	99.16 14	99.46 46	98.08 222

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 107	97.98 126	91.19 161	97.84 95	98.65 24	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 90	98.59 165

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 68	98.25 99	92.59 100	97.81 103	98.68 19	94.93 48	99.24 10	98.87 31	93.52 22	99.79 46	99.32 7	99.21 83	99.40 66

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 89	97.28 170	91.73 130	97.75 110	98.50 31	94.86 52	99.22 11	98.78 40	89.75 94	99.76 54	99.10 17	99.29 73	98.94 120

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 88	98.28 94	91.07 169	97.76 108	98.62 26	97.53 2	99.20 12	99.12 5	88.24 117	99.81 35	99.41 3	99.17 91	99.67 15

SED-MVS		98.05 2	97.99 1	98.24 11	99.42 10	95.30 18	98.25 40	98.27 55	95.13 40	99.19 13	98.89 28	95.54 5	99.85 21	97.52 42	99.66 10	99.56 40

test_241102_ONE					99.42 10	95.30 18		98.27 55	95.09 43	99.19 13	98.81 37	95.54 5	99.65 79

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 155	97.30 168	90.37 200	97.53 150	97.92 127	96.52 11	99.14 15	99.08 8	83.21 220	99.74 59	99.22 11	98.06 150	97.88 235

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 172	97.76 142	89.57 230	97.66 128	98.66 22	95.36 30	99.03 16	98.90 25	88.39 114	99.73 61	99.17 13	98.66 121	98.08 222

SD-MVS		97.41 23	97.53 18	97.06 82	98.57 78	94.46 38	97.92 84	98.14 83	94.82 57	99.01 17	98.55 49	94.18 16	97.41 385	96.94 58	99.64 14	99.32 74
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 14	98.31 32	98.29 50	94.92 50	98.99 18	98.92 23	95.08 10

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 257	98.94 19				97.41 49	99.66 10	99.74 9

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 142	95.48 310	90.69 185	97.91 85	98.33 45	94.07 91	98.93 20	99.14 2	87.44 140	99.61 90	98.63 26	98.32 138	98.18 207

DVP-MVS++		98.06 1	97.99 1	98.28 10	98.67 67	95.39 12	99.29 1	98.28 52	94.78 61	98.93 20	98.87 31	96.04 2	99.86 9	97.45 46	99.58 23	99.59 32

test_241102_TWO								98.27 55	95.13 40	98.93 20	98.89 28	94.99 13	99.85 21	97.52 42	99.65 13	99.74 9

test_fmvsmconf_n		97.49 21	97.56 16	97.29 64	97.44 165	92.37 107	97.91 85	98.88 4	95.83 19	98.92 23	99.05 14	91.45 61	99.80 40	99.12 16	99.46 46	99.69 14

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 140	97.64 151	90.72 184	98.00 67	98.73 10	94.55 73	98.91 24	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 202

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 79	97.58 161	92.56 101	97.68 124	98.47 35	94.02 93	98.90 25	98.89 28	88.94 103	99.78 49	99.18 12	99.03 107	98.93 124

PC_three_1452									90.77 234	98.89 26	98.28 86	96.24 1	98.35 276	95.76 106	99.58 23	99.59 32

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 44	95.42 11	97.94 81	98.18 76	90.57 250	98.85 27	98.94 21	93.33 25	99.83 31	96.72 66	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 73	96.77 60	96.01 154	96.67 227	90.25 203	97.91 85	98.38 38	94.48 77	98.84 28	99.14 2	88.06 120	99.62 89	98.82 23	98.60 125	98.15 211

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 149	98.07 120	90.28 202	97.97 77	98.76 9	94.93 48	98.84 28	99.06 12	88.80 106	99.65 79	99.06 18	98.63 123	98.18 207

MED-MVS test				98.00 23	99.56 1	94.50 35	98.69 11	98.70 16	93.45 118	98.73 30	98.53 51		99.86 9	97.40 50	99.58 23	99.65 20

MED-MVS		97.91 4	97.88 4	98.00 23	99.56 1	94.50 35	98.69 11	98.70 16	94.23 87	98.73 30	98.53 51	95.46 7	99.86 9	97.40 50	99.58 23	99.65 20

TestfortrainingZip a		97.92 3	97.70 10	98.58 3	99.56 1	96.08 5	98.69 11	98.70 16	93.45 118	98.73 30	98.53 51	95.46 7	99.86 9	96.63 69	99.58 23	99.80 1

DVP-MVS		97.91 4	97.81 5	98.22 14	99.45 6	95.36 14	98.21 47	97.85 137	94.92 50	98.73 30	98.87 31	95.08 10	99.84 26	97.52 42	99.67 6	99.48 56
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 61	98.73 30	98.87 31	95.87 4	99.84 26	97.45 46	99.72 2	99.77 3

DPE-MVS		97.86 6	97.65 11	98.47 6	99.17 38	95.78 8	97.21 193	98.35 42	95.16 38	98.71 35	98.80 38	95.05 12	99.89 3	96.70 68	99.73 1	99.73 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
lecture		97.58 15	97.63 12	97.43 58	99.37 19	92.93 86	98.86 7	98.85 5	95.27 34	98.65 36	98.90 25	91.97 52	99.80 40	97.63 38	99.21 83	99.57 36

TSAR-MVS + MP.		97.42 22	97.33 29	97.69 46	99.25 32	94.24 45	98.07 60	97.85 137	93.72 103	98.57 37	98.35 72	93.69 20	99.40 133	97.06 56	99.46 46	99.44 61
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 13	97.54 17	97.73 42	99.40 14	93.77 61	98.53 19	98.29 50	95.55 27	98.56 38	97.81 131	93.90 17	99.65 79	96.62 70	99.21 83	99.77 3
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 71	99.29 1	98.35 42	94.98 46	98.49 39

test_one_0601					99.32 27	95.20 21		98.25 61	95.13 40	98.48 40	98.87 31	95.16 9

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 202	97.29 169	88.38 274	97.23 190	98.47 35	95.14 39	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 83	98.02 226

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 73	95.67 301	92.21 114	97.95 80	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 59	99.59 32

APDe-MVS		97.82 7	97.73 9	98.08 19	99.15 39	94.82 29	98.81 8	98.30 48	94.76 64	98.30 43	98.90 25	93.77 19	99.68 75	97.93 29	99.69 3	99.75 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.39 24	97.13 31	98.17 16	99.02 48	95.28 20	98.23 44	98.27 55	92.37 166	98.27 44	98.65 45	93.33 25	99.72 65	96.49 75	99.52 35	99.51 49

balanced_conf03		96.84 56	96.89 48	96.68 93	97.63 153	92.22 113	98.17 53	97.82 143	94.44 79	98.23 45	97.36 173	90.97 75	99.22 151	97.74 32	99.66 10	98.61 162

ME-MVS		97.54 17	97.39 27	98.00 23	99.21 36	94.50 35	97.75 110	98.34 44	94.23 87	98.15 46	98.53 51	93.32 27	99.84 26	97.40 50	99.58 23	99.65 20

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 28	98.39 88	94.25 44	98.43 27	98.27 55	95.34 32	98.11 47	98.56 47	94.53 14	99.71 67	96.57 73	99.62 17	99.65 20
Skip Steuart: Steuart Systems R&D Blog.
test_vis1_n_1920		94.17 161	94.58 136	92.91 336	97.42 166	82.02 406	97.83 98	97.85 137	94.68 67	98.10 48	98.49 58	70.15 396	99.32 141	97.91 30	98.82 114	97.40 264

test_part2					99.28 30	95.74 9				98.10 48

APD-MVS		96.95 47	96.60 66	98.01 21	99.03 47	94.93 28	97.72 118	98.10 91	91.50 200	98.01 50	98.32 80	92.33 45	99.58 98	94.85 133	99.51 38	99.53 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
reproduce_model		97.51 20	97.51 20	97.50 54	98.99 52	93.01 82	97.79 106	98.21 67	95.73 24	97.99 51	99.03 15	92.63 39	99.82 33	97.80 31	99.42 56	99.67 15

patch_mono-2		96.83 57	97.44 24	95.01 219	99.05 45	85.39 358	96.98 213	98.77 8	94.70 66	97.99 51	98.66 43	93.61 21	99.91 1	97.67 37	99.50 40	99.72 13

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 210	98.09 116	86.63 325	96.00 310	98.15 81	95.43 28	97.95 53	98.56 47	93.40 23	99.36 137	96.77 63	99.48 44	99.45 59

ACMMP_NAP		97.20 33	96.86 49	98.23 12	99.09 40	95.16 23	97.60 139	98.19 74	92.82 154	97.93 54	98.74 42	91.60 59	99.86 9	96.26 80	99.52 35	99.67 15

reproduce-ours		97.53 18	97.51 20	97.60 51	98.97 53	93.31 73	97.71 120	98.20 69	95.80 21	97.88 55	98.98 18	92.91 30	99.81 35	97.68 33	99.43 53	99.67 15

our_new_method		97.53 18	97.51 20	97.60 51	98.97 53	93.31 73	97.71 120	98.20 69	95.80 21	97.88 55	98.98 18	92.91 30	99.81 35	97.68 33	99.43 53	99.67 15

9.14			96.75 61		98.93 56		97.73 115	98.23 66	91.28 211	97.88 55	98.44 64	93.00 29	99.65 79	95.76 106	99.47 45

CNVR-MVS		97.68 8	97.44 24	98.37 8	98.90 59	95.86 7	97.27 184	98.08 93	95.81 20	97.87 58	98.31 81	94.26 15	99.68 75	97.02 57	99.49 43	99.57 36

test_vis1_n		92.37 244	92.26 228	92.72 344	94.75 360	82.64 396	98.02 65	96.80 287	91.18 218	97.77 59	97.93 111	58.02 449	98.29 281	97.63 38	98.21 143	97.23 273

test_cas_vis1_n_1920		94.48 154	94.55 140	94.28 267	96.78 218	86.45 330	97.63 135	97.64 164	93.32 125	97.68 60	98.36 71	73.75 372	99.08 177	96.73 65	99.05 104	97.31 269

test_fmvsmconf0.01_n		96.15 88	95.85 92	97.03 83	92.66 424	91.83 129	97.97 77	97.84 141	95.57 26	97.53 61	99.00 16	84.20 204	99.76 54	98.82 23	99.08 102	99.48 56

MM		97.29 31	96.98 42	98.23 12	98.01 123	95.03 27	98.07 60	95.76 341	97.78 1	97.52 62	98.80 38	88.09 119	99.86 9	99.44 2	99.37 67	99.80 1

VNet		95.89 98	95.45 101	97.21 71	98.07 120	92.94 85	97.50 153	98.15 81	93.87 99	97.52 62	97.61 154	85.29 182	99.53 112	95.81 105	95.27 241	99.16 85

SR-MVS		97.01 44	96.86 49	97.47 56	99.09 40	93.27 75	97.98 71	98.07 98	93.75 102	97.45 64	98.48 61	91.43 63	99.59 95	96.22 83	99.27 75	99.54 45

APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 76	99.01 51	92.31 110	97.98 71	98.06 101	93.11 136	97.44 65	98.55 49	90.93 77	99.55 108	96.06 93	99.25 80	99.51 49

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 67	98.31 92	93.39 67	96.79 237	96.72 290	94.17 89	97.44 65	97.66 147	92.76 34	99.33 139	96.86 62	97.76 162	99.08 98

SR-MVS-dyc-post		96.88 51	96.80 57	97.11 78	99.02 48	92.34 108	97.98 71	98.03 110	93.52 115	97.43 67	98.51 56	91.40 64	99.56 106	96.05 94	99.26 78	99.43 63

RE-MVS-def			96.72 62		99.02 48	92.34 108	97.98 71	98.03 110	93.52 115	97.43 67	98.51 56	90.71 81		96.05 94	99.26 78	99.43 63

dcpmvs_2		96.37 81	97.05 38	94.31 265	98.96 55	84.11 379	97.56 144	97.51 187	93.92 97	97.43 67	98.52 55	92.75 35	99.32 141	97.32 54	99.50 40	99.51 49

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 102	98.07 120	91.97 124	98.14 54	97.79 145	90.43 255	97.34 70	97.52 163	91.29 67	99.19 154	98.12 28	99.64 14	98.60 163

旧先验2							95.94 313		81.66 429	97.34 70			98.82 209	92.26 197

MSLP-MVS++		96.94 48	97.06 35	96.59 102	98.72 64	91.86 128	97.67 125	98.49 32	94.66 69	97.24 72	98.41 67	92.31 47	98.94 195	96.61 71	99.46 46	98.96 114

HFP-MVS		97.14 37	96.92 47	97.83 30	99.42 10	94.12 50	98.52 20	98.32 46	93.21 127	97.18 73	98.29 84	92.08 49	99.83 31	95.63 113	99.59 19	99.54 45

MGCNet		96.74 64	96.31 81	98.02 20	96.87 202	94.65 31	97.58 140	94.39 407	96.47 12	97.16 74	98.39 68	87.53 136	99.87 7	98.97 20	99.41 59	99.55 43

ACMMPR		97.07 41	96.84 51	97.79 34	99.44 9	93.88 57	98.52 20	98.31 47	93.21 127	97.15 75	98.33 78	91.35 65	99.86 9	95.63 113	99.59 19	99.62 27

region2R		97.07 41	96.84 51	97.77 38	99.46 5	93.79 59	98.52 20	98.24 63	93.19 130	97.14 76	98.34 75	91.59 60	99.87 7	95.46 119	99.59 19	99.64 25

PGM-MVS		96.81 58	96.53 69	97.65 47	99.35 25	93.53 65	97.65 129	98.98 2	92.22 172	97.14 76	98.44 64	91.17 71	99.85 21	94.35 157	99.46 46	99.57 36

PHI-MVS		96.77 60	96.46 76	97.71 45	98.40 86	94.07 52	98.21 47	98.45 37	89.86 268	97.11 78	98.01 104	92.52 42	99.69 73	96.03 97	99.53 33	99.36 72

NCCC		97.30 29	97.03 40	98.11 18	98.77 62	95.06 26	97.34 177	98.04 108	95.96 15	97.09 79	97.88 119	93.18 28	99.71 67	95.84 104	99.17 91	99.56 40

CS-MVS		96.86 52	97.06 35	96.26 135	98.16 112	91.16 166	99.09 3	97.87 132	95.30 33	97.06 80	98.03 101	91.72 54	98.71 235	97.10 55	99.17 91	98.90 129

ZD-MVS					99.05 45	94.59 33		98.08 93	89.22 289	97.03 81	98.10 94	92.52 42	99.65 79	94.58 150	99.31 72

testdata				95.46 200	98.18 111	88.90 260		97.66 160	82.73 421	97.03 81	98.07 97	90.06 87	98.85 205	89.67 263	98.98 109	98.64 161

SPE-MVS-test		96.89 50	97.04 39	96.45 118	98.29 93	91.66 137	99.03 4	97.85 137	95.84 18	96.90 83	97.97 109	91.24 68	98.75 225	96.92 59	99.33 70	98.94 120

mvsany_test1		93.93 179	93.98 158	93.78 299	94.94 350	86.80 318	94.62 372	92.55 440	88.77 311	96.85 84	98.49 58	88.98 101	98.08 303	95.03 127	95.62 231	96.46 295

GDP-MVS		95.62 105	95.13 114	97.09 79	96.79 213	93.26 76	97.89 88	97.83 142	93.58 107	96.80 85	97.82 129	83.06 227	99.16 161	94.40 154	97.95 156	98.87 138

test_fmvs1		93.21 207	93.53 172	92.25 359	96.55 239	81.20 413	97.40 171	96.96 269	90.68 239	96.80 85	98.04 100	69.25 404	98.40 268	97.58 41	98.50 128	97.16 275

test_fmvs1_n		92.73 233	92.88 201	92.29 356	96.08 285	81.05 414	97.98 71	97.08 251	90.72 237	96.79 87	98.18 91	63.07 439	98.45 265	97.62 40	98.42 135	97.36 265

HPM-MVS_fast		96.51 74	96.27 83	97.22 70	99.32 27	92.74 93	98.74 10	98.06 101	90.57 250	96.77 88	98.35 72	90.21 86	99.53 112	94.80 139	99.63 16	99.38 70

h-mvs33		94.15 163	93.52 174	96.04 149	97.81 139	90.22 204	97.62 137	97.58 175	95.19 36	96.74 89	97.45 165	83.67 212	99.61 90	95.85 102	79.73 428	98.29 200

hse-mvs2		93.45 200	92.99 194	94.81 233	97.02 190	88.59 266	96.69 250	96.47 308	95.19 36	96.74 89	96.16 251	83.67 212	98.48 264	95.85 102	79.13 432	97.35 267

GST-MVS		96.85 54	96.52 70	97.82 31	99.36 23	94.14 49	98.29 34	98.13 84	92.72 157	96.70 91	98.06 98	91.35 65	99.86 9	94.83 135	99.28 74	99.47 58

xiu_mvs_v1_base_debu		95.01 129	94.76 127	95.75 177	96.58 233	91.71 133	96.25 293	97.35 223	92.99 140	96.70 91	96.63 225	82.67 238	99.44 129	96.22 83	97.46 167	96.11 307

xiu_mvs_v1_base		95.01 129	94.76 127	95.75 177	96.58 233	91.71 133	96.25 293	97.35 223	92.99 140	96.70 91	96.63 225	82.67 238	99.44 129	96.22 83	97.46 167	96.11 307

xiu_mvs_v1_base_debi		95.01 129	94.76 127	95.75 177	96.58 233	91.71 133	96.25 293	97.35 223	92.99 140	96.70 91	96.63 225	82.67 238	99.44 129	96.22 83	97.46 167	96.11 307

CDPH-MVS		95.97 94	95.38 106	97.77 38	98.93 56	94.44 39	96.35 283	97.88 130	86.98 360	96.65 95	97.89 116	91.99 51	99.47 125	92.26 197	99.46 46	99.39 68

EC-MVSNet		96.42 78	96.47 73	96.26 135	97.01 191	91.52 143	98.89 5	97.75 149	94.42 80	96.64 96	97.68 144	89.32 96	98.60 251	97.45 46	99.11 101	98.67 160

UA-Net		95.95 95	95.53 97	97.20 72	97.67 147	92.98 84	97.65 129	98.13 84	94.81 59	96.61 97	98.35 72	88.87 104	99.51 117	90.36 249	97.35 174	99.11 94

HPM-MVS++		97.34 26	96.97 43	98.47 6	99.08 42	96.16 4	97.55 149	97.97 121	95.59 25	96.61 97	97.89 116	92.57 41	99.84 26	95.95 99	99.51 38	99.40 66

XVS		97.18 34	96.96 45	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	98.29 84	91.70 56	99.80 40	95.66 108	99.40 61	99.62 27

X-MVStestdata		91.71 270	89.67 336	97.81 32	99.38 17	94.03 54	98.59 17	98.20 69	94.85 53	96.59 99	32.69 476	91.70 56	99.80 40	95.66 108	99.40 61	99.62 27

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 36	98.64 73	94.30 41	97.41 167	98.04 108	94.81 59	96.59 99	98.37 70	91.24 68	99.64 87	95.16 124	99.52 35	99.42 65
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 82	96.11 86	97.12 76	99.37 19	92.90 87	97.99 68	97.63 166	95.92 16	96.57 102	97.93 111	85.34 180	99.50 120	94.99 129	99.21 83	98.97 111

SymmetryMVS		95.94 96	95.54 96	97.15 74	97.85 136	92.90 87	97.99 68	96.91 277	95.92 16	96.57 102	97.93 111	85.34 180	99.50 120	94.99 129	96.39 215	99.05 102

diffmvs_AUTHOR		95.33 113	95.27 110	95.50 195	96.37 259	89.08 256	96.08 305	97.38 218	93.09 138	96.53 104	97.74 138	86.45 157	98.68 239	96.32 78	97.48 166	98.75 151

PS-MVSNAJ		95.37 111	95.33 108	95.49 196	97.35 167	90.66 187	95.31 350	97.48 192	93.85 100	96.51 105	95.70 278	88.65 109	99.65 79	94.80 139	98.27 141	96.17 301

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 98	98.24 100	91.20 160	96.89 223	97.73 152	94.74 65	96.49 106	98.49 58	90.88 79	99.58 98	96.44 76	98.32 138	99.13 89

ETV-MVS		96.02 91	95.89 91	96.40 122	97.16 176	92.44 105	97.47 162	97.77 148	94.55 73	96.48 107	94.51 335	91.23 70	98.92 198	95.65 111	98.19 144	97.82 243

alignmvs		95.87 100	95.23 111	97.78 36	97.56 163	95.19 22	97.86 91	97.17 242	94.39 83	96.47 108	96.40 238	85.89 167	99.20 153	96.21 87	95.11 246	98.95 117

KinetiMVS		95.26 116	94.75 130	96.79 90	96.99 193	92.05 120	97.82 100	97.78 146	94.77 63	96.46 109	97.70 141	80.62 281	99.34 138	92.37 196	98.28 140	98.97 111

xiu_mvs_v2_base		95.32 114	95.29 109	95.40 201	97.22 172	90.50 190	95.44 343	97.44 207	93.70 105	96.46 109	96.18 248	88.59 113	99.53 112	94.79 142	97.81 159	96.17 301

CP-MVS		97.02 43	96.81 56	97.64 49	99.33 26	93.54 64	98.80 9	98.28 52	92.99 140	96.45 111	98.30 83	91.90 53	99.85 21	95.61 115	99.68 4	99.54 45

HPM-MVS		96.69 67	96.45 77	97.40 59	99.36 23	93.11 80	98.87 6	98.06 101	91.17 219	96.40 112	97.99 107	90.99 74	99.58 98	95.61 115	99.61 18	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ZNCC-MVS		96.96 46	96.67 64	97.85 29	99.37 19	94.12 50	98.49 24	98.18 76	92.64 161	96.39 113	98.18 91	91.61 58	99.88 4	95.59 118	99.55 30	99.57 36

BP-MVS1		95.89 98	95.49 98	97.08 81	96.67 227	93.20 77	98.08 58	96.32 315	94.56 72	96.32 114	97.84 125	84.07 207	99.15 163	96.75 64	98.78 116	98.90 129

diffmvs		95.25 118	95.13 114	95.63 185	96.43 254	89.34 243	95.99 311	97.35 223	92.83 153	96.31 115	97.37 172	86.44 158	98.67 242	96.26 80	97.19 184	98.87 138
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		93.60 190	92.63 213	96.52 107	98.13 115	91.27 155	97.94 81	93.39 428	90.57 250	96.29 116	98.31 81	69.00 406	99.16 161	94.18 159	95.87 223	99.12 92

sasdasda		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 253	87.65 130	99.18 157	96.20 88	94.82 250	98.91 126

canonicalmvs		96.02 91	95.45 101	97.75 40	97.59 157	95.15 24	98.28 35	97.60 171	94.52 75	96.27 117	96.12 253	87.65 130	99.18 157	96.20 88	94.82 250	98.91 126

MVSFormer		95.37 111	95.16 113	95.99 156	96.34 261	91.21 158	98.22 45	97.57 178	91.42 204	96.22 119	97.32 174	86.20 163	97.92 335	94.07 160	99.05 104	98.85 140

lupinMVS		94.99 133	94.56 137	96.29 133	96.34 261	91.21 158	95.83 320	96.27 319	88.93 302	96.22 119	96.88 207	86.20 163	98.85 205	95.27 121	99.05 104	98.82 144

MGCFI-Net		95.94 96	95.40 105	97.56 53	97.59 157	94.62 32	98.21 47	97.57 178	94.41 81	96.17 121	96.16 251	87.54 135	99.17 159	96.19 90	94.73 255	98.91 126

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 115	98.20 107	90.93 174	96.86 226	97.72 154	94.67 68	96.16 122	98.46 62	90.43 84	99.58 98	96.23 82	97.96 155	98.90 129

MTAPA		97.08 39	96.78 59	97.97 27	99.37 19	94.42 40	97.24 186	98.08 93	95.07 44	96.11 123	98.59 46	90.88 79	99.90 2	96.18 92	99.50 40	99.58 35

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 129	96.62 229	91.73 130	97.98 71	98.30 48	96.19 14	96.10 124	98.95 20	89.42 95	99.76 54	98.90 22	99.08 102	97.43 262

MCST-MVS		97.18 34	96.84 51	98.20 15	99.30 29	95.35 16	97.12 200	98.07 98	93.54 112	96.08 125	97.69 143	93.86 18	99.71 67	96.50 74	99.39 63	99.55 43

TEST9					98.70 65	94.19 46	96.41 274	98.02 113	88.17 327	96.03 126	97.56 160	92.74 36	99.59 95

train_agg		96.30 85	95.83 93	97.72 43	98.70 65	94.19 46	96.41 274	98.02 113	88.58 314	96.03 126	97.56 160	92.73 37	99.59 95	95.04 126	99.37 67	99.39 68

test_prior2							96.35 283		92.80 155	96.03 126	97.59 157	92.01 50		95.01 128	99.38 64

jason		94.84 140	94.39 147	96.18 141	95.52 308	90.93 174	96.09 304	96.52 305	89.28 287	96.01 129	97.32 174	84.70 194	98.77 218	95.15 125	98.91 113	98.85 140
jason: jason.
test_8					98.67 67	94.06 53	96.37 282	98.01 116	88.58 314	95.98 130	97.55 162	92.73 37	99.58 98

mPP-MVS		96.86 52	96.60 66	97.64 49	99.40 14	93.44 66	98.50 23	98.09 92	93.27 126	95.95 131	98.33 78	91.04 73	99.88 4	95.20 122	99.57 29	99.60 31

LuminaMVS		94.89 136	94.35 149	96.53 105	95.48 310	92.80 91	96.88 225	96.18 326	92.85 152	95.92 132	96.87 209	81.44 265	98.83 208	96.43 77	97.10 187	97.94 231

DELS-MVS		96.61 71	96.38 80	97.30 63	97.79 140	93.19 78	95.96 312	98.18 76	95.23 35	95.87 133	97.65 148	91.45 61	99.70 72	95.87 100	99.44 52	99.00 109
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		93.82 183	93.08 192	96.02 151	97.88 135	89.96 215	97.72 118	95.85 337	92.43 164	95.86 134	98.44 64	68.42 413	99.39 134	96.31 79	94.85 248	98.71 157

MVS_111021_HR		96.68 69	96.58 68	96.99 84	98.46 79	92.31 110	96.20 298	98.90 3	94.30 86	95.86 134	97.74 138	92.33 45	99.38 136	96.04 96	99.42 56	99.28 77

MVS_111021_LR		96.24 87	96.19 85	96.39 124	98.23 105	91.35 153	96.24 296	98.79 7	93.99 95	95.80 136	97.65 148	89.92 91	99.24 149	95.87 100	99.20 88	98.58 166

VDDNet		93.05 216	92.07 231	96.02 151	96.84 206	90.39 196	98.08 58	95.85 337	86.22 375	95.79 137	98.46 62	67.59 416	99.19 154	94.92 132	94.85 248	98.47 179

新几何1				97.32 62	98.60 74	93.59 63		97.75 149	81.58 430	95.75 138	97.85 123	90.04 88	99.67 77	86.50 331	99.13 98	98.69 158

guyue		95.17 126	94.96 122	95.82 168	96.97 195	89.65 225	97.56 144	95.58 353	94.82 57	95.72 139	97.42 169	82.90 232	98.84 207	96.71 67	96.93 191	98.96 114

test_yl		94.78 144	94.23 152	96.43 119	97.74 143	91.22 156	96.85 227	97.10 248	91.23 216	95.71 140	96.93 202	84.30 201	99.31 143	93.10 184	95.12 244	98.75 151

DCV-MVSNet		94.78 144	94.23 152	96.43 119	97.74 143	91.22 156	96.85 227	97.10 248	91.23 216	95.71 140	96.93 202	84.30 201	99.31 143	93.10 184	95.12 244	98.75 151

AstraMVS		94.82 142	94.64 133	95.34 204	96.36 260	88.09 286	97.58 140	94.56 400	94.98 46	95.70 142	97.92 114	81.93 258	98.93 196	96.87 61	95.88 222	98.99 110

agg_prior					98.67 67	93.79 59		98.00 117		95.68 143			99.57 105

MG-MVS		95.61 106	95.38 106	96.31 129	98.42 83	90.53 189	96.04 307	97.48 192	93.47 117	95.67 144	98.10 94	89.17 99	99.25 148	91.27 226	98.77 117	99.13 89

baseline		95.58 107	95.42 104	96.08 145	96.78 218	90.41 195	97.16 197	97.45 203	93.69 106	95.65 145	97.85 123	87.29 143	98.68 239	95.66 108	97.25 181	99.13 89

MVS_Test		94.89 136	94.62 134	95.68 183	96.83 208	89.55 232	96.70 248	97.17 242	91.17 219	95.60 146	96.11 257	87.87 126	98.76 220	93.01 191	97.17 185	98.72 155

DPM-MVS		95.69 102	94.92 123	98.01 21	98.08 119	95.71 10	95.27 353	97.62 170	90.43 255	95.55 147	97.07 193	91.72 54	99.50 120	89.62 265	98.94 111	98.82 144

MP-MVS-pluss		96.70 65	96.27 83	97.98 26	99.23 35	94.71 30	96.96 215	98.06 101	90.67 240	95.55 147	98.78 40	91.07 72	99.86 9	96.58 72	99.55 30	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 60	96.45 77	97.72 43	99.39 16	93.80 58	98.41 28	98.06 101	93.37 122	95.54 149	98.34 75	90.59 83	99.88 4	94.83 135	99.54 32	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test12				97.65 47	98.46 79	94.26 43		97.66 160		95.52 150		90.89 78	99.46 126		99.25 80	99.22 82

viewmanbaseed2359cas		95.24 119	95.02 119	95.91 159	96.87 202	89.98 212	96.82 231	97.49 190	92.26 170	95.47 151	97.82 129	86.47 156	98.69 237	94.80 139	97.20 183	99.06 101

casdiffmvs		95.64 104	95.49 98	96.08 145	96.76 224	90.45 192	97.29 183	97.44 207	94.00 94	95.46 152	97.98 108	87.52 138	98.73 229	95.64 112	97.33 175	99.08 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		95.26 116	95.09 117	95.80 170	96.95 197	89.72 222	96.80 236	97.56 182	92.21 174	95.37 153	97.80 133	87.17 146	98.77 218	94.82 137	97.10 187	98.90 129

viewmacassd2359aftdt		95.07 128	94.80 126	95.87 162	96.53 242	89.84 218	96.90 222	97.48 192	92.44 163	95.36 154	97.89 116	85.23 183	98.68 239	94.40 154	97.00 190	99.09 96

E2		95.20 122	95.00 120	95.79 172	96.79 213	89.66 223	96.82 231	97.58 175	92.35 167	95.28 155	97.83 127	86.68 151	98.76 220	94.79 142	96.92 192	98.95 117

E3		95.20 122	95.00 120	95.79 172	96.77 220	89.66 223	96.82 231	97.58 175	92.35 167	95.28 155	97.83 127	86.69 150	98.76 220	94.79 142	96.92 192	98.95 117

test222					98.24 100	92.21 114	95.33 348	97.60 171	79.22 443	95.25 157	97.84 125	88.80 106			99.15 95	98.72 155

test2506		91.60 276	90.78 284	94.04 279	97.66 149	83.81 382	98.27 37	75.53 477	93.43 120	95.23 158	98.21 88	67.21 419	99.07 181	93.01 191	98.49 129	99.25 80

原ACMM1				96.38 125	98.59 75	91.09 168		97.89 128	87.41 352	95.22 159	97.68 144	90.25 85	99.54 110	87.95 299	99.12 100	98.49 176

CPTT-MVS		95.57 108	95.19 112	96.70 92	99.27 31	91.48 146	98.33 31	98.11 89	87.79 341	95.17 160	98.03 101	87.09 147	99.61 90	93.51 175	99.42 56	99.02 103

casdiffmvs_mvg		95.81 101	95.57 95	96.51 111	96.87 202	91.49 144	97.50 153	97.56 182	93.99 95	95.13 161	97.92 114	87.89 124	98.78 215	95.97 98	97.33 175	99.26 79
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		95.68 103	95.12 116	97.37 60	99.19 37	94.19 46	97.03 204	98.08 93	88.35 323	95.09 162	97.65 148	89.97 90	99.48 124	92.08 208	98.59 126	98.44 184

viewmambaseed2359dif		94.28 157	94.14 154	94.71 241	96.21 265	86.97 315	95.93 314	97.11 247	89.00 297	95.00 163	97.70 141	86.02 166	98.59 255	93.71 171	96.59 207	98.57 167

RRT-MVS		94.51 152	94.35 149	94.98 223	96.40 255	86.55 328	97.56 144	97.41 213	93.19 130	94.93 164	97.04 195	79.12 309	99.30 145	96.19 90	97.32 177	99.09 96

Vis-MVSNet		95.23 120	94.81 125	96.51 111	97.18 175	91.58 141	98.26 39	98.12 86	94.38 84	94.90 165	98.15 93	82.28 248	98.92 198	91.45 223	98.58 127	99.01 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		96.39 80	96.02 88	97.50 54	97.62 154	93.38 68	97.02 206	97.96 122	95.42 29	94.86 166	97.81 131	87.38 142	99.82 33	96.88 60	99.20 88	99.29 75

Elysia		94.00 173	93.12 190	96.64 94	96.08 285	92.72 95	97.50 153	97.63 166	91.15 221	94.82 167	97.12 189	74.98 359	99.06 183	90.78 236	98.02 151	98.12 214

StellarMVS		94.00 173	93.12 190	96.64 94	96.08 285	92.72 95	97.50 153	97.63 166	91.15 221	94.82 167	97.12 189	74.98 359	99.06 183	90.78 236	98.02 151	98.12 214

API-MVS		94.84 140	94.49 143	95.90 160	97.90 134	92.00 123	97.80 104	97.48 192	89.19 290	94.81 169	96.71 214	88.84 105	99.17 159	88.91 285	98.76 118	96.53 290

mvsmamba		94.57 150	94.14 154	95.87 162	97.03 189	89.93 216	97.84 95	95.85 337	91.34 207	94.79 170	96.80 210	80.67 279	98.81 211	94.85 133	98.12 148	98.85 140

OMC-MVS		95.09 127	94.70 131	96.25 138	98.46 79	91.28 154	96.43 270	97.57 178	92.04 182	94.77 171	97.96 110	87.01 148	99.09 174	91.31 225	96.77 197	98.36 191

ECVR-MVS		93.19 209	92.73 209	94.57 249	97.66 149	85.41 356	98.21 47	88.23 461	93.43 120	94.70 172	98.21 88	72.57 376	99.07 181	93.05 188	98.49 129	99.25 80

viewdifsd2359ckpt13		94.87 138	94.52 141	95.90 160	96.88 201	90.19 205	96.92 219	97.36 221	91.26 212	94.65 173	97.46 164	85.79 171	98.64 246	93.64 172	96.76 198	98.88 137

WTY-MVS		94.71 148	94.02 157	96.79 90	97.71 145	92.05 120	96.59 263	97.35 223	90.61 246	94.64 174	96.93 202	86.41 159	99.39 134	91.20 228	94.71 256	98.94 120

test1111		93.19 209	92.82 203	94.30 266	97.58 161	84.56 373	98.21 47	89.02 459	93.53 113	94.58 175	98.21 88	72.69 375	99.05 186	93.06 187	98.48 131	99.28 77

ACMMP		96.27 86	95.93 89	97.28 66	99.24 33	92.62 98	98.25 40	98.81 6	92.99 140	94.56 176	98.39 68	88.96 102	99.85 21	94.57 151	97.63 163	99.36 72
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		94.76 146	94.68 132	95.01 219	96.76 224	87.41 301	96.38 280	97.43 210	92.65 159	94.52 177	97.75 136	85.55 177	98.81 211	94.36 156	96.69 203	98.82 144

mamv4		94.66 149	96.10 87	90.37 405	98.01 123	73.41 456	96.82 231	97.78 146	89.95 266	94.52 177	97.43 168	92.91 30	99.09 174	98.28 27	99.16 94	98.60 163

Effi-MVS+		94.93 134	94.45 145	96.36 127	96.61 230	91.47 147	96.41 274	97.41 213	91.02 227	94.50 179	95.92 262	87.53 136	98.78 215	93.89 166	96.81 196	98.84 143

sss		94.51 152	93.80 161	96.64 94	97.07 181	91.97 124	96.32 288	98.06 101	88.94 301	94.50 179	96.78 211	84.60 195	99.27 147	91.90 209	96.02 218	98.68 159

mmtdpeth		89.70 355	88.96 353	91.90 368	95.84 296	84.42 374	97.46 164	95.53 358	90.27 258	94.46 181	90.50 432	69.74 402	98.95 193	97.39 53	69.48 458	92.34 434

PVSNet_BlendedMVS		94.06 169	93.92 159	94.47 254	98.27 96	89.46 238	96.73 244	98.36 39	90.17 260	94.36 182	95.24 301	88.02 121	99.58 98	93.44 177	90.72 325	94.36 400

PVSNet_Blended		94.87 138	94.56 137	95.81 169	98.27 96	89.46 238	95.47 342	98.36 39	88.84 305	94.36 182	96.09 258	88.02 121	99.58 98	93.44 177	98.18 145	98.40 187

viewdifsd2359ckpt09		94.81 143	94.37 148	96.12 144	96.91 198	90.75 183	96.94 216	97.31 228	90.51 253	94.31 184	97.38 171	85.70 173	98.71 235	93.54 173	96.75 199	98.90 129

PMMVS		92.86 227	92.34 225	94.42 258	94.92 351	86.73 321	94.53 376	96.38 313	84.78 398	94.27 185	95.12 306	83.13 224	98.40 268	91.47 222	96.49 212	98.12 214

EPP-MVSNet		95.22 121	95.04 118	95.76 175	97.49 164	89.56 231	98.67 15	97.00 267	90.69 238	94.24 186	97.62 153	89.79 93	98.81 211	93.39 180	96.49 212	98.92 125

viewmsd2359difaftdt		93.46 197	93.23 187	94.17 270	96.12 280	85.42 354	96.43 270	97.08 251	92.91 148	94.21 187	98.00 105	80.82 277	98.74 227	94.41 153	89.05 341	98.34 197

viewdifsd2359ckpt11		93.46 197	93.22 188	94.17 270	96.11 282	85.42 354	96.43 270	97.07 254	92.91 148	94.20 188	98.00 105	80.82 277	98.73 229	94.42 152	89.04 343	98.34 197

FA-MVS(test-final)		93.52 195	92.92 199	95.31 205	96.77 220	88.54 269	94.82 368	96.21 324	89.61 276	94.20 188	95.25 300	83.24 219	99.14 166	90.01 253	96.16 217	98.25 202

PVSNet_Blended_VisFu		95.27 115	94.91 124	96.38 125	98.20 107	90.86 177	97.27 184	98.25 61	90.21 259	94.18 190	97.27 180	87.48 139	99.73 61	93.53 174	97.77 161	98.55 168

SSM_0404		94.73 147	94.31 151	95.98 157	97.05 186	90.90 176	97.01 209	97.29 229	91.24 213	94.17 191	97.60 155	85.03 187	98.76 220	92.14 202	97.30 178	98.29 200

FE-MVS		92.05 260	91.05 272	95.08 214	96.83 208	87.93 289	93.91 403	95.70 344	86.30 372	94.15 192	94.97 309	76.59 343	99.21 152	84.10 366	96.86 194	98.09 221

thisisatest0530		93.03 217	92.21 229	95.49 196	97.07 181	89.11 255	97.49 161	92.19 442	90.16 261	94.09 193	96.41 237	76.43 347	99.05 186	90.38 248	95.68 229	98.31 199

XVG-OURS-SEG-HR		93.86 182	93.55 170	94.81 233	97.06 184	88.53 270	95.28 351	97.45 203	91.68 192	94.08 194	97.68 144	82.41 246	98.90 201	93.84 168	92.47 294	96.98 278

XVG-OURS		93.72 187	93.35 183	94.80 236	97.07 181	88.61 265	94.79 369	97.46 198	91.97 185	93.99 195	97.86 122	81.74 261	98.88 202	92.64 195	92.67 293	96.92 282

IS-MVSNet		94.90 135	94.52 141	96.05 148	97.67 147	90.56 188	98.44 26	96.22 322	93.21 127	93.99 195	97.74 138	85.55 177	98.45 265	89.98 254	97.86 157	99.14 88

CSCG		96.05 90	95.91 90	96.46 117	99.24 33	90.47 191	98.30 33	98.57 29	89.01 296	93.97 197	97.57 158	92.62 40	99.76 54	94.66 145	99.27 75	99.15 87

EIA-MVS		95.53 109	95.47 100	95.71 182	97.06 184	89.63 226	97.82 100	97.87 132	93.57 108	93.92 198	95.04 307	90.61 82	98.95 193	94.62 147	98.68 120	98.54 169

tttt0517		92.96 220	92.33 226	94.87 230	97.11 179	87.16 311	97.97 77	92.09 443	90.63 244	93.88 199	97.01 201	76.50 344	99.06 183	90.29 251	95.45 238	98.38 189

HyFIR lowres test		93.66 189	92.92 199	95.87 162	98.24 100	89.88 217	94.58 374	98.49 32	85.06 393	93.78 200	95.78 273	82.86 233	98.67 242	91.77 214	95.71 228	99.07 100

CHOSEN 1792x2688		94.15 163	93.51 175	96.06 147	98.27 96	89.38 241	95.18 360	98.48 34	85.60 383	93.76 201	97.11 191	83.15 223	99.61 90	91.33 224	98.72 119	99.19 83

mamba_0408		93.70 188	92.99 194	95.83 167	96.79 213	90.38 197	88.69 459	97.07 254	90.96 229	93.68 202	97.31 176	84.97 190	98.76 220	90.95 232	96.51 208	98.35 193

SSM_04072		93.51 196	92.99 194	95.05 215	96.79 213	90.38 197	88.69 459	97.07 254	90.96 229	93.68 202	97.31 176	84.97 190	96.42 416	90.95 232	96.51 208	98.35 193

SSM_0407		94.54 151	94.12 156	95.80 170	96.79 213	90.38 197	96.79 237	97.29 229	91.24 213	93.68 202	97.60 155	85.03 187	98.67 242	92.14 202	96.51 208	98.35 193

Anonymous202405211		92.07 259	90.83 283	95.76 175	98.19 109	88.75 262	97.58 140	95.00 380	86.00 378	93.64 205	97.45 165	66.24 428	99.53 112	90.68 241	92.71 291	99.01 106

IMVS_0403		93.98 175	93.79 162	94.55 250	96.19 269	86.16 339	96.35 283	97.24 236	91.54 195	93.59 206	97.04 195	85.86 168	98.73 229	90.68 241	95.59 232	98.76 147

CDS-MVSNet		94.14 166	93.54 171	95.93 158	96.18 273	91.46 148	96.33 287	97.04 262	88.97 300	93.56 207	96.51 232	87.55 134	97.89 339	89.80 259	95.95 220	98.44 184
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MDTV_nov1_ep13_2view						70.35 460	93.10 426		83.88 408	93.55 208		82.47 245		86.25 334		98.38 189

Anonymous20240529		91.98 262	90.73 289	95.73 180	98.14 113	89.40 240	97.99 68	97.72 154	79.63 441	93.54 209	97.41 170	69.94 398	99.56 106	91.04 231	91.11 318	98.22 204

CANet_DTU		94.37 155	93.65 167	96.55 104	96.46 252	92.13 118	96.21 297	96.67 297	94.38 84	93.53 210	97.03 200	79.34 305	99.71 67	90.76 238	98.45 133	97.82 243

icg_test_0407_2		93.58 191	93.46 177	93.94 289	96.19 269	86.16 339	93.73 409	97.24 236	91.54 195	93.50 211	97.04 195	85.64 175	96.91 405	90.68 241	95.59 232	98.76 147

IMVS_0407		93.94 177	93.75 163	94.49 253	96.19 269	86.16 339	96.35 283	97.24 236	91.54 195	93.50 211	97.04 195	85.64 175	98.54 258	90.68 241	95.59 232	98.76 147

tpmrst		91.44 288	91.32 260	91.79 374	95.15 339	79.20 439	93.42 419	95.37 362	88.55 317	93.49 213	93.67 382	82.49 244	98.27 282	90.41 247	89.34 339	97.90 233

TAMVS		94.01 172	93.46 177	95.64 184	96.16 275	90.45 192	96.71 247	96.89 280	89.27 288	93.46 214	96.92 205	87.29 143	97.94 332	88.70 290	95.74 226	98.53 170

thisisatest0515		92.29 249	91.30 262	95.25 207	96.60 231	88.90 260	94.36 385	92.32 441	87.92 334	93.43 215	94.57 331	77.28 338	99.00 190	89.42 270	95.86 224	97.86 239

DeepC-MVS	93.07 3	96.06 89	95.66 94	97.29 64	97.96 128	93.17 79	97.30 182	98.06 101	93.92 97	93.38 216	98.66 43	86.83 149	99.73 61	95.60 117	99.22 82	98.96 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		92.49 238	91.60 250	95.18 209	97.91 133	89.47 236	97.65 129	94.66 396	92.18 179	93.33 217	94.91 313	78.06 331	99.10 171	81.61 389	94.06 273	96.98 278

thres100view900		92.43 240	91.58 251	94.98 223	97.92 132	89.37 242	97.71 120	94.66 396	92.20 175	93.31 218	94.90 314	78.06 331	99.08 177	81.40 393	94.08 269	96.48 293

thres200		92.23 253	91.39 257	94.75 240	97.61 155	89.03 257	96.60 262	95.09 377	92.08 181	93.28 219	94.00 368	78.39 325	99.04 189	81.26 399	94.18 265	96.19 300

tfpn200view9		92.38 243	91.52 254	94.95 227	97.85 136	89.29 246	97.41 167	94.88 388	92.19 177	93.27 220	94.46 340	78.17 327	99.08 177	81.40 393	94.08 269	96.48 293

thres400		92.42 241	91.52 254	95.12 213	97.85 136	89.29 246	97.41 167	94.88 388	92.19 177	93.27 220	94.46 340	78.17 327	99.08 177	81.40 393	94.08 269	96.98 278

testing3-2		92.10 258	92.05 232	92.27 357	97.71 145	79.56 433	97.42 166	94.41 406	93.53 113	93.22 222	95.49 289	69.16 405	99.11 169	93.25 181	94.22 263	98.13 212

ab-mvs		93.57 193	92.55 217	96.64 94	97.28 170	91.96 126	95.40 344	97.45 203	89.81 272	93.22 222	96.28 244	79.62 302	99.46 126	90.74 239	93.11 285	98.50 174

Vis-MVSNet (Re-imp)		94.15 163	93.88 160	94.95 227	97.61 155	87.92 290	98.10 56	95.80 340	92.22 172	93.02 224	97.45 165	84.53 197	97.91 338	88.24 294	97.97 154	99.02 103

114514_t		93.95 176	93.06 193	96.63 98	99.07 43	91.61 138	97.46 164	97.96 122	77.99 447	93.00 225	97.57 158	86.14 165	99.33 139	89.22 277	99.15 95	98.94 120

UGNet		94.04 171	93.28 185	96.31 129	96.85 205	91.19 161	97.88 90	97.68 159	94.40 82	93.00 225	96.18 248	73.39 374	99.61 90	91.72 215	98.46 132	98.13 212
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	93.87 181	92.95 198	96.63 98	97.10 180	92.49 104	95.64 334	96.64 298	89.05 295	93.00 225	95.79 272	85.77 172	99.45 128	89.16 281	94.35 258	97.96 229

PVSNet	86.66 18	92.24 252	91.74 247	93.73 300	97.77 141	83.69 386	92.88 429	96.72 290	87.91 335	93.00 225	94.86 316	78.51 322	99.05 186	86.53 329	97.45 171	98.47 179

MAR-MVS		94.22 159	93.46 177	96.51 111	98.00 125	92.19 117	97.67 125	97.47 196	88.13 331	93.00 225	95.84 266	84.86 193	99.51 117	87.99 298	98.17 146	97.83 242
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		95.01 129	94.59 135	96.26 135	98.89 60	90.68 186	97.24 186	97.73 152	91.80 187	92.93 230	96.62 228	89.13 100	99.14 166	89.21 278	97.78 160	98.97 111

MDTV_nov1_ep13			90.76 285		95.22 333	80.33 423	93.03 427	95.28 367	88.14 330	92.84 231	93.83 372	81.34 266	98.08 303	82.86 378	94.34 259

CostFormer		91.18 306	90.70 291	92.62 348	94.84 356	81.76 408	94.09 396	94.43 404	84.15 404	92.72 232	93.77 376	79.43 304	98.20 287	90.70 240	92.18 300	97.90 233

EPNet		95.20 122	94.56 137	97.14 75	92.80 421	92.68 97	97.85 94	94.87 391	96.64 9	92.46 233	97.80 133	86.23 160	99.65 79	93.72 170	98.62 124	99.10 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		90.82 319	89.77 332	93.95 287	94.45 373	87.19 309	90.23 450	95.68 348	86.89 362	92.40 234	92.36 413	80.91 273	97.05 398	81.09 400	93.95 274	97.60 255

RPMNet		88.98 361	87.05 375	94.77 238	94.45 373	87.19 309	90.23 450	98.03 110	77.87 449	92.40 234	87.55 456	80.17 291	99.51 117	68.84 456	93.95 274	97.60 255

EPMVS		90.70 324	89.81 330	93.37 319	94.73 362	84.21 377	93.67 413	88.02 462	89.50 280	92.38 236	93.49 388	77.82 335	97.78 350	86.03 341	92.68 292	98.11 220

baseline1		92.82 230	91.90 240	95.55 191	97.20 174	90.77 181	97.19 194	94.58 399	92.20 175	92.36 237	96.34 241	84.16 205	98.21 286	89.20 279	83.90 408	97.68 249

PatchT		88.87 365	87.42 369	93.22 325	94.08 384	85.10 364	89.51 455	94.64 398	81.92 426	92.36 237	88.15 452	80.05 293	97.01 401	72.43 446	93.65 280	97.54 258

UWE-MVS		89.91 346	89.48 342	91.21 387	95.88 290	78.23 444	94.91 367	90.26 455	89.11 292	92.35 239	94.52 334	68.76 408	97.96 326	83.95 370	95.59 232	97.42 263

ETVMVS		90.52 330	89.14 351	94.67 243	96.81 212	87.85 294	95.91 316	93.97 419	89.71 274	92.34 240	92.48 408	65.41 434	97.96 326	81.37 396	94.27 262	98.21 205

PAPR		94.18 160	93.42 182	96.48 114	97.64 151	91.42 150	95.55 337	97.71 158	88.99 298	92.34 240	95.82 268	89.19 98	99.11 169	86.14 337	97.38 172	98.90 129

SCA		91.84 267	91.18 269	93.83 295	95.59 304	84.95 369	94.72 370	95.58 353	90.82 232	92.25 242	93.69 379	75.80 351	98.10 298	86.20 335	95.98 219	98.45 181

CVMVSNet		91.23 301	91.75 245	89.67 414	95.77 297	74.69 451	96.44 268	94.88 388	85.81 380	92.18 243	97.64 151	79.07 310	95.58 432	88.06 297	95.86 224	98.74 154

AUN-MVS		91.76 269	90.75 287	94.81 233	97.00 192	88.57 267	96.65 254	96.49 307	89.63 275	92.15 244	96.12 253	78.66 320	98.50 261	90.83 234	79.18 431	97.36 265

AdaColmap		94.34 156	93.68 166	96.31 129	98.59 75	91.68 136	96.59 263	97.81 144	89.87 267	92.15 244	97.06 194	83.62 214	99.54 110	89.34 272	98.07 149	97.70 248

GeoE		93.89 180	93.28 185	95.72 181	96.96 196	89.75 221	98.24 43	96.92 276	89.47 281	92.12 246	97.21 184	84.42 199	98.39 273	87.71 305	96.50 211	99.01 106

PatchmatchNet		91.91 264	91.35 258	93.59 309	95.38 317	84.11 379	93.15 424	95.39 360	89.54 278	92.10 247	93.68 381	82.82 235	98.13 293	84.81 357	95.32 240	98.52 171
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		93.24 206	92.48 222	95.51 193	95.70 299	92.39 106	97.86 91	98.66 22	92.30 169	92.09 248	95.37 293	80.49 284	98.40 268	93.95 163	85.86 375	95.75 324

tpm		90.25 337	89.74 335	91.76 377	93.92 387	79.73 432	93.98 397	93.54 426	88.28 324	91.99 249	93.25 396	77.51 337	97.44 382	87.30 319	87.94 354	98.12 214

myMVS_eth3d28		91.52 284	90.97 275	93.17 327	96.91 198	83.24 390	95.61 335	94.96 384	92.24 171	91.98 250	93.28 395	69.31 403	98.40 268	88.71 289	95.68 229	97.88 235

UBG		91.55 281	90.76 285	93.94 289	96.52 245	85.06 365	95.22 356	94.54 401	90.47 254	91.98 250	92.71 402	72.02 379	98.74 227	88.10 296	95.26 242	98.01 227

CNLPA		94.28 157	93.53 172	96.52 107	98.38 89	92.55 102	96.59 263	96.88 281	90.13 263	91.91 252	97.24 182	85.21 184	99.09 174	87.64 311	97.83 158	97.92 232

testing91		91.90 265	91.02 273	94.53 252	96.54 240	86.55 328	95.86 318	95.64 350	91.77 189	91.89 253	93.47 390	69.94 398	98.86 203	90.23 252	93.86 276	98.18 207

BH-RMVSNet		92.72 234	91.97 237	94.97 225	97.16 176	87.99 288	96.15 302	95.60 351	90.62 245	91.87 254	97.15 188	78.41 324	98.57 256	83.16 375	97.60 164	98.36 191

PatchMatch-RL		92.90 224	92.02 235	95.56 189	98.19 109	90.80 179	95.27 353	97.18 240	87.96 333	91.86 255	95.68 279	80.44 285	98.99 191	84.01 368	97.54 165	96.89 283

SDMVSNet		94.17 161	93.61 168	95.86 165	98.09 116	91.37 151	97.35 176	98.20 69	93.18 132	91.79 256	97.28 178	79.13 308	98.93 196	94.61 148	92.84 288	97.28 270

sd_testset		93.10 213	92.45 223	95.05 215	98.09 116	89.21 250	96.89 223	97.64 164	93.18 132	91.79 256	97.28 178	75.35 356	98.65 245	88.99 283	92.84 288	97.28 270

testing99		91.62 275	90.72 290	94.32 263	96.48 249	86.11 344	95.81 321	94.76 393	91.55 194	91.75 258	93.44 391	68.55 411	98.82 209	90.43 246	93.69 278	98.04 225

testing222		90.31 334	88.96 353	94.35 260	96.54 240	87.29 303	95.50 340	93.84 423	90.97 228	91.75 258	92.96 399	62.18 444	98.00 317	82.86 378	94.08 269	97.76 245

OPM-MVS		93.28 205	92.76 205	94.82 231	94.63 366	90.77 181	96.65 254	97.18 240	93.72 103	91.68 260	97.26 181	79.33 306	98.63 248	92.13 205	92.28 296	95.07 363
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tpm2		89.96 345	89.21 348	92.23 360	94.91 353	81.25 411	93.78 407	94.42 405	80.62 437	91.56 261	93.44 391	76.44 346	97.94 332	85.60 347	92.08 304	97.49 259

TAPA-MVS	90.10 7	92.30 248	91.22 267	95.56 189	98.33 91	89.60 228	96.79 237	97.65 162	81.83 427	91.52 262	97.23 183	87.94 123	98.91 200	71.31 450	98.37 136	98.17 210
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvs2		89.77 353	89.93 325	89.31 421	93.68 396	76.37 448	97.64 133	95.90 334	89.84 271	91.49 263	96.26 246	58.77 447	97.10 395	94.65 146	91.13 317	94.46 396

TR-MVS		91.48 287	90.59 295	94.16 273	96.40 255	87.33 302	95.67 329	95.34 366	87.68 346	91.46 264	95.52 288	76.77 342	98.35 276	82.85 380	93.61 282	96.79 286

RPSCF		90.75 321	90.86 279	90.42 404	96.84 206	76.29 449	95.61 335	96.34 314	83.89 407	91.38 265	97.87 120	76.45 345	98.78 215	87.16 323	92.23 297	96.20 299

PLC	91.00 6	94.11 167	93.43 180	96.13 143	98.58 77	91.15 167	96.69 250	97.39 215	87.29 355	91.37 266	96.71 214	88.39 114	99.52 116	87.33 318	97.13 186	97.73 246
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		93.12 212	92.72 210	94.34 262	96.71 226	87.27 305	90.29 449	97.72 154	86.61 367	91.34 267	95.29 295	84.29 203	98.41 267	93.25 181	98.94 111	97.35 267

HQP_MVS		93.78 185	93.43 180	94.82 231	96.21 265	89.99 210	97.74 113	97.51 187	94.85 53	91.34 267	96.64 221	81.32 267	98.60 251	93.02 189	92.23 297	95.86 312

plane_prior3						90.00 208			94.46 78	91.34 267

Fast-Effi-MVS+		93.46 197	92.75 207	95.59 188	96.77 220	90.03 207	96.81 235	97.13 244	88.19 326	91.30 270	94.27 353	86.21 162	98.63 248	87.66 310	96.46 214	98.12 214

EI-MVSNet		93.03 217	92.88 201	93.48 315	95.77 297	86.98 314	96.44 268	97.12 245	90.66 242	91.30 270	97.64 151	86.56 153	98.05 310	89.91 256	90.55 327	95.41 339

MVSTER		93.20 208	92.81 204	94.37 259	96.56 237	89.59 229	97.06 203	97.12 245	91.24 213	91.30 270	95.96 260	82.02 254	98.05 310	93.48 176	90.55 327	95.47 334

ADS-MVSNet2		89.45 357	88.59 359	92.03 364	95.86 291	82.26 404	90.93 445	94.32 412	83.23 418	91.28 273	91.81 423	79.01 315	95.99 421	79.52 409	91.39 313	97.84 240

ADS-MVSNet		89.89 348	88.68 358	93.53 313	95.86 291	84.89 370	90.93 445	95.07 378	83.23 418	91.28 273	91.81 423	79.01 315	97.85 341	79.52 409	91.39 313	97.84 240

testing11		91.68 273	90.75 287	94.47 254	96.53 242	86.56 327	95.76 325	94.51 403	91.10 225	91.24 275	93.59 385	68.59 410	98.86 203	91.10 229	94.29 261	98.00 228

nrg030		94.05 170	93.31 184	96.27 134	95.22 333	94.59 33	98.34 30	97.46 198	92.93 147	91.21 276	96.64 221	87.23 145	98.22 285	94.99 129	85.80 376	95.98 311

Effi-MVS+-dtu		93.08 214	93.21 189	92.68 347	96.02 288	83.25 389	97.14 199	96.72 290	93.85 100	91.20 277	93.44 391	83.08 225	98.30 280	91.69 218	95.73 227	96.50 292

VPNet		92.23 253	91.31 261	94.99 221	95.56 306	90.96 172	97.22 192	97.86 136	92.96 146	90.96 278	96.62 228	75.06 357	98.20 287	91.90 209	83.65 410	95.80 318

JIA-IIPM		88.26 372	87.04 376	91.91 367	93.52 401	81.42 410	89.38 456	94.38 408	80.84 434	90.93 279	80.74 464	79.22 307	97.92 335	82.76 382	91.62 308	96.38 296

MonoMVSNet		91.92 263	91.77 243	92.37 351	92.94 417	83.11 392	97.09 202	95.55 355	92.91 148	90.85 280	94.55 332	81.27 269	96.52 414	93.01 191	87.76 356	97.47 261

WB-MVSnew		89.88 349	89.56 339	90.82 396	94.57 370	83.06 393	95.65 333	92.85 435	87.86 337	90.83 281	94.10 362	79.66 301	96.88 406	76.34 427	94.19 264	92.54 431

test-LLR		91.42 289	91.19 268	92.12 362	94.59 367	80.66 417	94.29 390	92.98 433	91.11 223	90.76 282	92.37 410	79.02 313	98.07 307	88.81 286	96.74 200	97.63 250

test-mter		90.19 341	89.54 340	92.12 362	94.59 367	80.66 417	94.29 390	92.98 433	87.68 346	90.76 282	92.37 410	67.67 415	98.07 307	88.81 286	96.74 200	97.63 250

ACMM	89.79 8	92.96 220	92.50 221	94.35 260	96.30 263	88.71 263	97.58 140	97.36 221	91.40 206	90.53 284	96.65 220	79.77 298	98.75 225	91.24 227	91.64 307	95.59 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
F-COLMAP		93.58 191	92.98 197	95.37 202	98.40 86	88.98 258	97.18 195	97.29 229	87.75 344	90.49 285	97.10 192	85.21 184	99.50 120	86.70 328	96.72 202	97.63 250

TESTMET0.1,1		90.06 343	89.42 343	91.97 365	94.41 375	80.62 419	94.29 390	91.97 445	87.28 356	90.44 286	92.47 409	68.79 407	97.67 360	88.50 293	96.60 206	97.61 254

FIs		94.09 168	93.70 165	95.27 206	95.70 299	92.03 122	98.10 56	98.68 19	93.36 124	90.39 287	96.70 216	87.63 132	97.94 332	92.25 199	90.50 329	95.84 315

GA-MVS		91.38 291	90.31 304	94.59 244	94.65 365	87.62 298	94.34 386	96.19 325	90.73 236	90.35 288	93.83 372	71.84 381	97.96 326	87.22 320	93.61 282	98.21 205

LS3D		93.57 193	92.61 215	96.47 115	97.59 157	91.61 138	97.67 125	97.72 154	85.17 391	90.29 289	98.34 75	84.60 195	99.73 61	83.85 373	98.27 141	98.06 224

FC-MVSNet-test		93.94 177	93.57 169	95.04 217	95.48 310	91.45 149	98.12 55	98.71 13	93.37 122	90.23 290	96.70 216	87.66 129	97.85 341	91.49 221	90.39 330	95.83 316

HQP-NCC					95.86 291		96.65 254		93.55 109	90.14 291

ACMP_Plane					95.86 291		96.65 254		93.55 109	90.14 291

HQP4-MVS										90.14 291			98.50 261			95.78 320

HQP-MVS		93.19 209	92.74 208	94.54 251	95.86 291	89.33 244	96.65 254	97.39 215	93.55 109	90.14 291	95.87 264	80.95 271	98.50 261	92.13 205	92.10 302	95.78 320

UniMVSNet_NR-MVSNet		93.37 202	92.67 211	95.47 199	95.34 322	92.83 89	97.17 196	98.58 28	92.98 145	90.13 295	95.80 269	88.37 116	97.85 341	91.71 216	83.93 405	95.73 326

DU-MVS		92.90 224	92.04 233	95.49 196	94.95 348	92.83 89	97.16 197	98.24 63	93.02 139	90.13 295	95.71 276	83.47 215	97.85 341	91.71 216	83.93 405	95.78 320

LPG-MVS_test		92.94 222	92.56 216	94.10 275	96.16 275	88.26 278	97.65 129	97.46 198	91.29 208	90.12 297	97.16 186	79.05 311	98.73 229	92.25 199	91.89 305	95.31 349

LGP-MVS_train				94.10 275	96.16 275	88.26 278		97.46 198	91.29 208	90.12 297	97.16 186	79.05 311	98.73 229	92.25 199	91.89 305	95.31 349

UniMVSNet (Re)		93.31 204	92.55 217	95.61 187	95.39 316	93.34 71	97.39 172	98.71 13	93.14 135	90.10 299	94.83 318	87.71 128	98.03 314	91.67 219	83.99 404	95.46 335

mvs_anonymous		93.82 183	93.74 164	94.06 277	96.44 253	85.41 356	95.81 321	97.05 260	89.85 270	90.09 300	96.36 240	87.44 140	97.75 355	93.97 162	96.69 203	99.02 103

test_djsdf		93.07 215	92.76 205	94.00 281	93.49 403	88.70 264	98.22 45	97.57 178	91.42 204	90.08 301	95.55 286	82.85 234	97.92 335	94.07 160	91.58 309	95.40 342

dp		88.90 364	88.26 364	90.81 397	94.58 369	76.62 447	92.85 430	94.93 385	85.12 392	90.07 302	93.07 397	75.81 350	98.12 296	80.53 404	87.42 361	97.71 247

PS-MVSNAJss		93.74 186	93.51 175	94.44 256	93.91 388	89.28 248	97.75 110	97.56 182	92.50 162	89.94 303	96.54 231	88.65 109	98.18 290	93.83 169	90.90 323	95.86 312

UniMVSNet_ETH3D		91.34 296	90.22 312	94.68 242	94.86 355	87.86 293	97.23 190	97.46 198	87.99 332	89.90 304	96.92 205	66.35 426	98.23 284	90.30 250	90.99 321	97.96 229

CLD-MVS		92.98 219	92.53 219	94.32 263	96.12 280	89.20 251	95.28 351	97.47 196	92.66 158	89.90 304	95.62 282	80.58 282	98.40 268	92.73 194	92.40 295	95.38 344
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		87.82 375	85.61 388	94.44 256	94.46 372	89.27 249	91.21 444	84.61 471	80.88 433	89.89 306	74.98 467	71.50 383	97.53 374	85.75 346	97.21 182	96.51 291

1112_ss		93.37 202	92.42 224	96.21 139	97.05 186	90.99 170	96.31 289	96.72 290	86.87 363	89.83 307	96.69 218	86.51 155	99.14 166	88.12 295	93.67 279	98.50 174

BH-untuned		92.94 222	92.62 214	93.92 293	97.22 172	86.16 339	96.40 278	96.25 321	90.06 264	89.79 308	96.17 250	83.19 221	98.35 276	87.19 321	97.27 180	97.24 272

VortexMVS		92.88 226	92.64 212	93.58 310	96.58 233	87.53 300	96.93 218	97.28 232	92.78 156	89.75 309	94.99 308	82.73 237	97.76 353	94.60 149	88.16 352	95.46 335

V42		91.58 279	90.87 278	93.73 300	94.05 385	88.50 271	97.32 180	96.97 268	88.80 310	89.71 310	94.33 348	82.54 242	98.05 310	89.01 282	85.07 388	94.64 393

Baseline_NR-MVSNet		91.20 303	90.62 293	92.95 335	93.83 391	88.03 287	97.01 209	95.12 376	88.42 321	89.70 311	95.13 305	83.47 215	97.44 382	89.66 264	83.24 413	93.37 419

v144192		91.06 309	90.28 306	93.39 318	93.66 397	87.23 308	96.83 230	97.07 254	87.43 351	89.69 312	94.28 352	81.48 264	98.00 317	87.18 322	84.92 392	94.93 371

v1144		91.37 293	90.60 294	93.68 305	93.89 389	88.23 280	96.84 229	97.03 264	88.37 322	89.69 312	94.39 342	82.04 253	97.98 319	87.80 302	85.37 381	94.84 377

Test_1112_low_res		92.84 229	91.84 242	95.85 166	97.04 188	89.97 214	95.53 339	96.64 298	85.38 386	89.65 314	95.18 302	85.86 168	99.10 171	87.70 306	93.58 284	98.49 176

v1192		91.07 308	90.23 310	93.58 310	93.70 394	87.82 295	96.73 244	97.07 254	87.77 342	89.58 315	94.32 350	80.90 275	97.97 322	86.52 330	85.48 379	94.95 367

v1240		90.70 324	89.85 328	93.23 324	93.51 402	86.80 318	96.61 260	97.02 266	87.16 358	89.58 315	94.31 351	79.55 303	97.98 319	85.52 348	85.44 380	94.90 374

TranMVSNet+NR-MVSNet		92.50 236	91.63 249	95.14 211	94.76 359	92.07 119	97.53 150	98.11 89	92.90 151	89.56 317	96.12 253	83.16 222	97.60 368	89.30 273	83.20 414	95.75 324

v2v482		91.59 277	90.85 281	93.80 297	93.87 390	88.17 283	96.94 216	96.88 281	89.54 278	89.53 318	94.90 314	81.70 262	98.02 315	89.25 276	85.04 390	95.20 357

v1921920		90.85 318	90.03 321	93.29 322	93.55 399	86.96 317	96.74 243	97.04 262	87.36 353	89.52 319	94.34 347	80.23 290	97.97 322	86.27 333	85.21 385	94.94 369

IterMVS-LS		92.29 249	91.94 238	93.34 320	96.25 264	86.97 315	96.57 266	97.05 260	90.67 240	89.50 320	94.80 320	86.59 152	97.64 363	89.91 256	86.11 374	95.40 342
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cascas		91.20 303	90.08 316	94.58 248	94.97 346	89.16 254	93.65 414	97.59 174	79.90 440	89.40 321	92.92 400	75.36 355	98.36 275	92.14 202	94.75 253	96.23 297

XVG-ACMP-BASELINE		90.93 316	90.21 313	93.09 330	94.31 379	85.89 345	95.33 348	97.26 233	91.06 226	89.38 322	95.44 292	68.61 409	98.60 251	89.46 268	91.05 319	94.79 385

GBi-Net		91.35 294	90.27 307	94.59 244	96.51 246	91.18 163	97.50 153	96.93 272	88.82 307	89.35 323	94.51 335	73.87 368	97.29 391	86.12 338	88.82 344	95.31 349

test1		91.35 294	90.27 307	94.59 244	96.51 246	91.18 163	97.50 153	96.93 272	88.82 307	89.35 323	94.51 335	73.87 368	97.29 391	86.12 338	88.82 344	95.31 349

FMVSNet3		91.78 268	90.69 292	95.03 218	96.53 242	92.27 112	97.02 206	96.93 272	89.79 273	89.35 323	94.65 328	77.01 339	97.47 379	86.12 338	88.82 344	95.35 346

WR-MVS		92.34 245	91.53 253	94.77 238	95.13 341	90.83 178	96.40 278	97.98 120	91.88 186	89.29 326	95.54 287	82.50 243	97.80 348	89.79 260	85.27 384	95.69 327

DP-MVS		92.76 232	91.51 256	96.52 107	98.77 62	90.99 170	97.38 174	96.08 329	82.38 423	89.29 326	97.87 120	83.77 210	99.69 73	81.37 396	96.69 203	98.89 135

BH-w/o		92.14 257	91.75 245	93.31 321	96.99 193	85.73 349	95.67 329	95.69 346	88.73 312	89.26 328	94.82 319	82.97 230	98.07 307	85.26 353	96.32 216	96.13 306

3Dnovator	91.36 5	95.19 125	94.44 146	97.44 57	96.56 237	93.36 70	98.65 16	98.36 39	94.12 90	89.25 329	98.06 98	82.20 250	99.77 52	93.41 179	99.32 71	99.18 84

tt0805		91.09 307	90.07 319	94.16 273	95.61 303	88.31 275	97.56 144	96.51 306	89.56 277	89.17 330	95.64 281	67.08 423	98.38 274	91.07 230	88.44 350	95.80 318

miper_enhance_ethall		91.54 283	91.01 274	93.15 328	95.35 321	87.07 313	93.97 398	96.90 278	86.79 364	89.17 330	93.43 394	86.55 154	97.64 363	89.97 255	86.93 365	94.74 389

Fast-Effi-MVS+-dtu		92.29 249	91.99 236	93.21 326	95.27 329	85.52 352	97.03 204	96.63 301	92.09 180	89.11 332	95.14 304	80.33 288	98.08 303	87.54 314	94.74 254	96.03 310

WBMVS		90.69 326	89.99 323	92.81 341	96.48 249	85.00 366	95.21 358	96.30 317	89.46 282	89.04 333	94.05 366	72.45 378	97.82 345	89.46 268	87.41 362	95.61 329

XXY-MVS		92.16 255	91.23 266	94.95 227	94.75 360	90.94 173	97.47 162	97.43 210	89.14 291	88.90 334	96.43 236	79.71 299	98.24 283	89.56 266	87.68 357	95.67 328

PCF-MVS	89.48 11	91.56 280	89.95 324	96.36 127	96.60 231	92.52 103	92.51 434	97.26 233	79.41 442	88.90 334	96.56 230	84.04 208	99.55 108	77.01 426	97.30 178	97.01 277
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_ehance_all_eth		91.59 277	91.13 270	92.97 334	95.55 307	86.57 326	94.47 379	96.88 281	87.77 342	88.88 336	94.01 367	86.22 161	97.54 372	89.49 267	86.93 365	94.79 385

SSC-MVS3.2		89.74 354	89.26 347	91.19 390	95.16 336	80.29 425	94.53 376	97.03 264	91.79 188	88.86 337	94.10 362	69.94 398	97.82 345	85.29 351	86.66 370	95.45 337

jajsoiax		92.42 241	91.89 241	94.03 280	93.33 411	88.50 271	97.73 115	97.53 185	92.00 184	88.85 338	96.50 233	75.62 354	98.11 297	93.88 167	91.56 310	95.48 332

eth_miper_zixun_eth		91.02 311	90.59 295	92.34 354	95.33 325	84.35 375	94.10 395	96.90 278	88.56 316	88.84 339	94.33 348	84.08 206	97.60 368	88.77 288	84.37 401	95.06 364

c3_l		91.38 291	90.89 277	92.88 338	95.58 305	86.30 333	94.68 371	96.84 285	88.17 327	88.83 340	94.23 356	85.65 174	97.47 379	89.36 271	84.63 394	94.89 375

mvs_tets		92.31 247	91.76 244	93.94 289	93.41 408	88.29 276	97.63 135	97.53 185	92.04 182	88.76 341	96.45 235	74.62 364	98.09 302	93.91 165	91.48 311	95.45 337

v148		90.99 312	90.38 301	92.81 341	93.83 391	85.80 346	96.78 241	96.68 295	89.45 283	88.75 342	93.93 371	82.96 231	97.82 345	87.83 301	83.25 412	94.80 383

FMVSNet2		91.31 297	90.08 316	94.99 221	96.51 246	92.21 114	97.41 167	96.95 270	88.82 307	88.62 343	94.75 322	73.87 368	97.42 384	85.20 354	88.55 349	95.35 346

PAPM		91.52 284	90.30 305	95.20 208	95.30 328	89.83 219	93.38 420	96.85 284	86.26 374	88.59 344	95.80 269	84.88 192	98.15 292	75.67 431	95.93 221	97.63 250

cl22		91.21 302	90.56 297	93.14 329	96.09 284	86.80 318	94.41 383	96.58 304	87.80 340	88.58 345	93.99 369	80.85 276	97.62 366	89.87 258	86.93 365	94.99 366

3Dnovator+	91.43 4	95.40 110	94.48 144	98.16 17	96.90 200	95.34 17	98.48 25	97.87 132	94.65 70	88.53 346	98.02 103	83.69 211	99.71 67	93.18 183	98.96 110	99.44 61

dmvs_re		90.21 339	89.50 341	92.35 352	95.47 314	85.15 362	95.70 328	94.37 409	90.94 231	88.42 347	93.57 386	74.63 363	95.67 429	82.80 381	89.57 337	96.22 298

anonymousdsp		92.16 255	91.55 252	93.97 285	92.58 426	89.55 232	97.51 152	97.42 212	89.42 284	88.40 348	94.84 317	80.66 280	97.88 340	91.87 211	91.28 315	94.48 395

reproduce_monomvs		91.30 298	91.10 271	91.92 366	96.82 210	82.48 400	97.01 209	97.49 190	94.64 71	88.35 349	95.27 298	70.53 391	98.10 298	95.20 122	84.60 396	95.19 360

WR-MVS_H		92.00 261	91.35 258	93.95 287	95.09 343	89.47 236	98.04 63	98.68 19	91.46 202	88.34 350	94.68 325	85.86 168	97.56 370	85.77 345	84.24 402	94.82 380

v8		91.29 300	90.53 298	93.57 312	94.15 381	88.12 285	97.34 177	97.06 259	88.99 298	88.32 351	94.26 355	83.08 225	98.01 316	87.62 312	83.92 407	94.57 394

ACMP	89.59 10	92.62 235	92.14 230	94.05 278	96.40 255	88.20 281	97.36 175	97.25 235	91.52 199	88.30 352	96.64 221	78.46 323	98.72 234	91.86 212	91.48 311	95.23 356
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		91.04 310	90.23 310	93.49 314	94.12 382	88.16 284	97.32 180	97.08 251	88.26 325	88.29 353	94.22 358	82.17 251	97.97 322	86.45 332	84.12 403	94.33 401

QAPM		93.45 200	92.27 227	96.98 85	96.77 220	92.62 98	98.39 29	98.12 86	84.50 401	88.27 354	97.77 135	82.39 247	99.81 35	85.40 350	98.81 115	98.51 173

Anonymous20231211		90.63 327	89.42 343	94.27 268	98.24 100	89.19 253	98.05 62	97.89 128	79.95 439	88.25 355	94.96 310	72.56 377	98.13 293	89.70 262	85.14 386	95.49 331

CP-MVSNet		91.89 266	91.24 265	93.82 296	95.05 344	88.57 267	97.82 100	98.19 74	91.70 191	88.21 356	95.76 274	81.96 255	97.52 376	87.86 300	84.65 393	95.37 345

DIV-MVS_self_test		90.97 314	90.33 302	92.88 338	95.36 320	86.19 338	94.46 381	96.63 301	87.82 338	88.18 357	94.23 356	82.99 228	97.53 374	87.72 303	85.57 378	94.93 371

IMVS_0404		92.44 239	91.92 239	94.00 281	96.19 269	86.16 339	93.84 406	97.24 236	91.54 195	88.17 358	97.04 195	76.96 341	97.09 396	90.68 241	95.59 232	98.76 147

cl____		90.96 315	90.32 303	92.89 337	95.37 319	86.21 336	94.46 381	96.64 298	87.82 338	88.15 359	94.18 359	82.98 229	97.54 372	87.70 306	85.59 377	94.92 373

tpmvs		89.83 352	89.15 350	91.89 369	94.92 351	80.30 424	93.11 425	95.46 359	86.28 373	88.08 360	92.65 403	80.44 285	98.52 260	81.47 392	89.92 333	96.84 284

PS-CasMVS		91.55 281	90.84 282	93.69 304	94.96 347	88.28 277	97.84 95	98.24 63	91.46 202	88.04 361	95.80 269	79.67 300	97.48 378	87.02 325	84.54 399	95.31 349

MIMVSNet		88.50 369	86.76 379	93.72 302	94.84 356	87.77 296	91.39 440	94.05 416	86.41 370	87.99 362	92.59 406	63.27 438	95.82 426	77.44 420	92.84 288	97.57 257

GG-mvs-BLEND				93.62 307	93.69 395	89.20 251	92.39 436	83.33 473		87.98 363	89.84 440	71.00 387	96.87 407	82.08 388	95.40 239	94.80 383

miper_lstm_enhance		90.50 332	90.06 320	91.83 371	95.33 325	83.74 383	93.86 404	96.70 294	87.56 349	87.79 364	93.81 375	83.45 217	96.92 404	87.39 316	84.62 395	94.82 380

PEN-MVS		91.20 303	90.44 299	93.48 315	94.49 371	87.91 292	97.76 108	98.18 76	91.29 208	87.78 365	95.74 275	80.35 287	97.33 389	85.46 349	82.96 415	95.19 360

ITE_SJBPF				92.43 350	95.34 322	85.37 359		95.92 332	91.47 201	87.75 366	96.39 239	71.00 387	97.96 326	82.36 386	89.86 334	93.97 411

v7n		90.76 320	89.86 327	93.45 317	93.54 400	87.60 299	97.70 123	97.37 219	88.85 304	87.65 367	94.08 365	81.08 270	98.10 298	84.68 359	83.79 409	94.66 392

Patchmtry		88.64 368	87.25 371	92.78 343	94.09 383	86.64 322	89.82 454	95.68 348	80.81 435	87.63 368	92.36 413	80.91 273	97.03 399	78.86 415	85.12 387	94.67 391

testing3		87.67 377	86.88 378	90.05 409	96.14 278	80.71 416	97.10 201	92.85 435	90.15 262	87.54 369	94.55 332	55.70 454	94.10 446	73.77 441	94.10 268	95.35 346

pmmvs4		90.93 316	89.85 328	94.17 270	93.34 410	90.79 180	94.60 373	96.02 330	84.62 399	87.45 370	95.15 303	81.88 259	97.45 381	87.70 306	87.87 355	94.27 405

tpm cat1		88.36 370	87.21 373	91.81 373	95.13 341	80.55 420	92.58 433	95.70 344	74.97 453	87.45 370	91.96 421	78.01 333	98.17 291	80.39 405	88.74 347	96.72 288

FMVSNet1		89.88 349	88.31 362	94.59 244	95.41 315	91.18 163	97.50 153	96.93 272	86.62 366	87.41 372	94.51 335	65.94 431	97.29 391	83.04 377	87.43 360	95.31 349

IterMVS-SCA-FT		90.31 334	89.81 330	91.82 372	95.52 308	84.20 378	94.30 389	96.15 327	90.61 246	87.39 373	94.27 353	75.80 351	96.44 415	87.34 317	86.88 369	94.82 380

MVS		91.71 270	90.44 299	95.51 193	95.20 335	91.59 140	96.04 307	97.45 203	73.44 457	87.36 374	95.60 283	85.42 179	99.10 171	85.97 342	97.46 167	95.83 316

EU-MVSNet		88.72 367	88.90 355	88.20 425	93.15 414	74.21 453	96.63 259	94.22 414	85.18 390	87.32 375	95.97 259	76.16 348	94.98 438	85.27 352	86.17 372	95.41 339

IterMVS		90.15 342	89.67 336	91.61 379	95.48 310	83.72 384	94.33 387	96.12 328	89.99 265	87.31 376	94.15 361	75.78 353	96.27 419	86.97 326	86.89 368	94.83 378
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UWE-MVS-28		86.81 386	86.41 381	88.02 427	92.87 418	74.60 452	95.38 346	86.70 467	88.17 327	87.28 377	94.67 327	70.83 389	93.30 455	67.45 457	94.31 260	96.17 301

pmmvs5		89.86 351	88.87 356	92.82 340	92.86 419	86.23 335	96.26 292	95.39 360	84.24 403	87.12 378	94.51 335	74.27 366	97.36 388	87.61 313	87.57 358	94.86 376

DTE-MVSNet		90.56 328	89.75 334	93.01 332	93.95 386	87.25 306	97.64 133	97.65 162	90.74 235	87.12 378	95.68 279	79.97 295	97.00 402	83.33 374	81.66 421	94.78 387

mvs5depth		86.53 387	85.08 394	90.87 394	88.74 454	82.52 399	91.91 438	94.23 413	86.35 371	87.11 380	93.70 378	66.52 424	97.76 353	81.37 396	75.80 443	92.31 436

Patchmatch-test		89.42 358	87.99 365	93.70 303	95.27 329	85.11 363	88.98 457	94.37 409	81.11 431	87.10 381	93.69 379	82.28 248	97.50 377	74.37 437	94.76 252	98.48 178

IB-MVS	87.33 17	89.91 346	88.28 363	94.79 237	95.26 332	87.70 297	95.12 362	93.95 420	89.35 286	87.03 382	92.49 407	70.74 390	99.19 154	89.18 280	81.37 422	97.49 259
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		91.71 270	91.28 263	92.99 333	93.76 393	83.71 385	96.69 250	95.28 367	93.15 134	87.02 383	95.95 261	83.37 218	97.38 387	79.46 412	96.84 195	97.88 235
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Syy-MVS		87.13 382	87.02 377	87.47 429	95.16 336	73.21 457	95.00 364	93.93 421	88.55 317	86.96 384	91.99 419	75.90 349	94.00 447	61.59 463	94.11 266	95.20 357

myMVS_eth3d		87.18 381	86.38 382	89.58 415	95.16 336	79.53 434	95.00 364	93.93 421	88.55 317	86.96 384	91.99 419	56.23 453	94.00 447	75.47 433	94.11 266	95.20 357

baseline2		91.63 274	90.86 279	93.94 289	94.33 377	86.32 332	95.92 315	91.64 447	89.37 285	86.94 386	94.69 324	81.62 263	98.69 237	88.64 291	94.57 257	96.81 285

MSDG		91.42 289	90.24 309	94.96 226	97.15 178	88.91 259	93.69 412	96.32 315	85.72 382	86.93 387	96.47 234	80.24 289	98.98 192	80.57 403	95.05 247	96.98 278

test0.0.03 1		89.37 359	88.70 357	91.41 384	92.47 428	85.63 350	95.22 356	92.70 438	91.11 223	86.91 388	93.65 383	79.02 313	93.19 457	78.00 419	89.18 340	95.41 339

COLMAP_ROB	87.81 15	90.40 333	89.28 346	93.79 298	97.95 129	87.13 312	96.92 219	95.89 336	82.83 420	86.88 389	97.18 185	73.77 371	99.29 146	78.44 417	93.62 281	94.95 367
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
D2MVS		91.30 298	90.95 276	92.35 352	94.71 363	85.52 352	96.18 300	98.21 67	88.89 303	86.60 390	93.82 374	79.92 296	97.95 330	89.29 274	90.95 322	93.56 415

SD_0403		90.01 344	90.02 322	89.96 411	95.65 302	76.76 446	95.76 325	96.46 309	90.58 249	86.59 391	96.29 243	82.12 252	94.78 440	73.00 445	93.76 277	98.35 193

OurMVSNet-221017-0		90.51 331	90.19 314	91.44 383	93.41 408	81.25 411	96.98 213	96.28 318	91.68 192	86.55 392	96.30 242	74.20 367	97.98 319	88.96 284	87.40 363	95.09 362

sc_t1		86.48 389	84.10 405	93.63 306	93.45 406	85.76 348	96.79 237	94.71 394	73.06 458	86.45 393	94.35 345	55.13 455	97.95 330	84.38 364	78.55 435	97.18 274

MS-PatchMatch		90.27 336	89.77 332	91.78 375	94.33 377	84.72 372	95.55 337	96.73 289	86.17 376	86.36 394	95.28 297	71.28 385	97.80 348	84.09 367	98.14 147	92.81 425

1314		92.81 231	92.03 234	95.14 211	95.33 325	89.52 235	96.04 307	97.44 207	87.72 345	86.25 395	95.33 294	83.84 209	98.79 214	89.26 275	97.05 189	97.11 276

tfpnnormal		89.70 355	88.40 361	93.60 308	95.15 339	90.10 206	97.56 144	98.16 80	87.28 356	86.16 396	94.63 329	77.57 336	98.05 310	74.48 435	84.59 397	92.65 428

pm-mvs1		90.72 323	89.65 338	93.96 286	94.29 380	89.63 226	97.79 106	96.82 286	89.07 293	86.12 397	95.48 291	78.61 321	97.78 350	86.97 326	81.67 420	94.46 396

OpenMVS	89.19 12	92.86 227	91.68 248	96.40 122	95.34 322	92.73 94	98.27 37	98.12 86	84.86 396	85.78 398	97.75 136	78.89 318	99.74 59	87.50 315	98.65 122	96.73 287

LTVRE_ROB	88.41 13	90.99 312	89.92 326	94.19 269	96.18 273	89.55 232	96.31 289	97.09 250	87.88 336	85.67 399	95.91 263	78.79 319	98.57 256	81.50 390	89.98 332	94.44 398
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		87.97 373	87.21 373	90.24 407	92.86 419	80.76 415	96.67 253	94.97 382	91.74 190	85.52 400	95.83 267	62.66 442	94.47 443	76.25 428	88.36 351	95.48 332

AllTest		90.23 338	88.98 352	93.98 283	97.94 130	86.64 322	96.51 267	95.54 356	85.38 386	85.49 401	96.77 212	70.28 393	99.15 163	80.02 407	92.87 286	96.15 304

TestCases				93.98 283	97.94 130	86.64 322		95.54 356	85.38 386	85.49 401	96.77 212	70.28 393	99.15 163	80.02 407	92.87 286	96.15 304

DSMNet-mixed		86.34 392	86.12 386	87.00 433	89.88 445	70.43 459	94.93 366	90.08 456	77.97 448	85.42 403	92.78 401	74.44 365	93.96 449	74.43 436	95.14 243	96.62 289

ppachtmachnet_test		88.35 371	87.29 370	91.53 380	92.45 429	83.57 387	93.75 408	95.97 331	84.28 402	85.32 404	94.18 359	79.00 317	96.93 403	75.71 430	84.99 391	94.10 406

CL-MVSNet_self_test		86.31 393	85.15 393	89.80 413	88.83 452	81.74 409	93.93 401	96.22 322	86.67 365	85.03 405	90.80 431	78.09 330	94.50 441	74.92 434	71.86 454	93.15 421

our_test_3		88.78 366	87.98 366	91.20 389	92.45 429	82.53 398	93.61 416	95.69 346	85.77 381	84.88 406	93.71 377	79.99 294	96.78 411	79.47 411	86.24 371	94.28 404

MVP-Stereo		90.74 322	90.08 316	92.71 345	93.19 413	88.20 281	95.86 318	96.27 319	86.07 377	84.86 407	94.76 321	77.84 334	97.75 355	83.88 372	98.01 153	92.17 440
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	87.92 14	90.20 340	89.18 349	93.25 323	96.48 249	86.45 330	96.99 212	96.68 295	88.83 306	84.79 408	96.22 247	70.16 395	98.53 259	84.42 363	88.04 353	94.77 388

NR-MVSNet		92.34 245	91.27 264	95.53 192	94.95 348	93.05 81	97.39 172	98.07 98	92.65 159	84.46 409	95.71 276	85.00 189	97.77 352	89.71 261	83.52 411	95.78 320

LF4IMVS		87.94 374	87.25 371	89.98 410	92.38 431	80.05 430	94.38 384	95.25 370	87.59 348	84.34 410	94.74 323	64.31 436	97.66 362	84.83 356	87.45 359	92.23 437

LCM-MVSNet-Re		92.50 236	92.52 220	92.44 349	96.82 210	81.89 407	96.92 219	93.71 425	92.41 165	84.30 411	94.60 330	85.08 186	97.03 399	91.51 220	97.36 173	98.40 187

TransMVSNet (Re)		88.94 362	87.56 368	93.08 331	94.35 376	88.45 273	97.73 115	95.23 371	87.47 350	84.26 412	95.29 295	79.86 297	97.33 389	79.44 413	74.44 449	93.45 418

Anonymous20231206		87.09 383	86.14 385	89.93 412	91.22 437	80.35 422	96.11 303	95.35 363	83.57 414	84.16 413	93.02 398	73.54 373	95.61 430	72.16 447	86.14 373	93.84 413

SixPastTwentyTwo		89.15 360	88.54 360	90.98 392	93.49 403	80.28 426	96.70 248	94.70 395	90.78 233	84.15 414	95.57 284	71.78 382	97.71 358	84.63 360	85.07 388	94.94 369

test_fmvs3		83.21 414	83.02 409	83.78 438	86.77 462	68.34 464	96.76 242	94.91 386	86.49 368	84.14 415	89.48 442	36.04 469	91.73 460	91.86 212	80.77 425	91.26 450

TDRefinement		86.53 387	84.76 399	91.85 370	82.23 470	84.25 376	96.38 280	95.35 363	84.97 395	84.09 416	94.94 311	65.76 432	98.34 279	84.60 361	74.52 448	92.97 422

KD-MVS_self_test		85.95 398	84.95 396	88.96 422	89.55 448	79.11 440	95.13 361	96.42 311	85.91 379	84.07 417	90.48 433	70.03 397	94.82 439	80.04 406	72.94 452	92.94 423

pmmvs6		87.81 376	86.19 384	92.69 346	91.32 436	86.30 333	97.34 177	96.41 312	80.59 438	84.05 418	94.37 344	67.37 418	97.67 360	84.75 358	79.51 430	94.09 408

ACMH	87.59 16	90.53 329	89.42 343	93.87 294	96.21 265	87.92 290	97.24 186	96.94 271	88.45 320	83.91 419	96.27 245	71.92 380	98.62 250	84.43 362	89.43 338	95.05 365
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		87.29 380	85.79 387	91.78 375	94.80 358	87.28 304	95.49 341	95.28 367	84.09 405	83.85 420	91.82 422	62.95 440	94.17 445	78.48 416	85.34 383	93.91 412

USDC		88.94 362	87.83 367	92.27 357	94.66 364	84.96 368	93.86 404	95.90 334	87.34 354	83.40 421	95.56 285	67.43 417	98.19 289	82.64 385	89.67 336	93.66 414

ttmdpeth		85.91 399	84.76 399	89.36 419	89.14 449	80.25 427	95.66 332	93.16 432	83.77 410	83.39 422	95.26 299	66.24 428	95.26 437	80.65 402	75.57 444	92.57 429

Anonymous20240521		86.42 391	85.44 389	89.34 420	90.33 441	79.79 431	96.73 244	95.92 332	83.71 412	83.25 423	91.36 428	63.92 437	96.01 420	78.39 418	85.36 382	92.22 438

KD-MVS_2432*1600		84.81 408	82.64 411	91.31 385	91.07 438	85.34 360	91.22 442	95.75 342	85.56 384	83.09 424	90.21 436	67.21 419	95.89 422	77.18 424	62.48 467	92.69 426

miper_refine_blended		84.81 408	82.64 411	91.31 385	91.07 438	85.34 360	91.22 442	95.75 342	85.56 384	83.09 424	90.21 436	67.21 419	95.89 422	77.18 424	62.48 467	92.69 426

PVSNet_0	82.17 19	85.46 403	83.64 406	90.92 393	95.27 329	79.49 436	90.55 448	95.60 351	83.76 411	83.00 426	89.95 438	71.09 386	97.97 322	82.75 383	60.79 469	95.31 349

tt0320		85.39 404	83.12 407	92.19 361	93.44 407	85.79 347	96.19 299	94.87 391	71.19 460	82.92 427	91.76 425	58.43 448	96.81 409	81.03 401	78.26 436	93.98 410

mvsany_test3		83.59 412	82.44 414	87.03 432	83.80 465	73.82 454	93.70 410	90.92 453	86.42 369	82.51 428	90.26 435	46.76 464	95.71 427	90.82 235	76.76 440	91.57 444

test_0402		86.46 390	84.79 398	91.45 382	95.02 345	85.55 351	96.29 291	94.89 387	80.90 432	82.21 429	93.97 370	68.21 414	97.29 391	62.98 461	88.68 348	91.51 445

Patchmatch-RL test		87.38 379	86.24 383	90.81 397	88.74 454	78.40 443	88.12 464	93.17 430	87.11 359	82.17 430	89.29 443	81.95 256	95.60 431	88.64 291	77.02 438	98.41 186

tt0320-xc		84.83 407	82.33 415	92.31 355	93.66 397	86.20 337	96.17 301	94.06 415	71.26 459	82.04 431	92.22 417	55.07 456	96.72 412	81.49 391	75.04 447	94.02 409

TinyColmap		86.82 385	85.35 392	91.21 387	94.91 353	82.99 394	93.94 400	94.02 418	83.58 413	81.56 432	94.68 325	62.34 443	98.13 293	75.78 429	87.35 364	92.52 432

test20.03		86.14 396	85.40 391	88.35 423	90.12 442	80.06 429	95.90 317	95.20 372	88.59 313	81.29 433	93.62 384	71.43 384	92.65 458	71.26 451	81.17 423	92.34 434

N_pmnet		78.73 424	78.71 425	78.79 443	92.80 421	46.50 482	94.14 394	43.71 484	78.61 445	80.83 434	91.66 426	74.94 361	96.36 417	67.24 458	84.45 400	93.50 416

MVS-HIRNet		82.47 417	81.21 420	86.26 435	95.38 317	69.21 462	88.96 458	89.49 457	66.28 464	80.79 435	74.08 469	68.48 412	97.39 386	71.93 448	95.47 237	92.18 439

PM-MVS		83.48 413	81.86 419	88.31 424	87.83 458	77.59 445	93.43 418	91.75 446	86.91 361	80.63 436	89.91 439	44.42 465	95.84 425	85.17 355	76.73 441	91.50 447

ambc				86.56 434	83.60 467	70.00 461	85.69 466	94.97 382		80.60 437	88.45 448	37.42 468	96.84 408	82.69 384	75.44 446	92.86 424

MIMVSNet1		84.93 406	83.05 408	90.56 402	89.56 447	84.84 371	95.40 344	95.35 363	83.91 406	80.38 438	92.21 418	57.23 450	93.34 454	70.69 453	82.75 418	93.50 416

lessismore_v0				90.45 403	91.96 434	79.09 441		87.19 465		80.32 439	94.39 342	66.31 427	97.55 371	84.00 369	76.84 439	94.70 390

K. test v3		87.64 378	86.75 380	90.32 406	93.02 416	79.48 437	96.61 260	92.08 444	90.66 242	80.25 440	94.09 364	67.21 419	96.65 413	85.96 343	80.83 424	94.83 378

OpenMVS_ROB	81.14 20	84.42 410	82.28 416	90.83 395	90.06 443	84.05 381	95.73 327	94.04 417	73.89 456	80.17 441	91.53 427	59.15 446	97.64 363	66.92 459	89.05 341	90.80 452

EG-PatchMatch MVS		87.02 384	85.44 389	91.76 377	92.67 423	85.00 366	96.08 305	96.45 310	83.41 417	79.52 442	93.49 388	57.10 451	97.72 357	79.34 414	90.87 324	92.56 430

pmmvs-eth3d		86.22 394	84.45 401	91.53 380	88.34 456	87.25 306	94.47 379	95.01 379	83.47 415	79.51 443	89.61 441	69.75 401	95.71 427	83.13 376	76.73 441	91.64 442

test_vis1_rt		86.16 395	85.06 395	89.46 417	93.47 405	80.46 421	96.41 274	86.61 468	85.22 389	79.15 444	88.64 447	52.41 459	97.06 397	93.08 186	90.57 326	90.87 451

FE-MVSNET		83.85 411	81.97 417	89.51 416	87.19 460	83.19 391	95.21 358	93.17 430	83.45 416	78.90 445	89.05 445	65.46 433	93.84 451	69.71 455	75.56 445	91.51 445

pmmvs3		79.97 422	77.50 427	87.39 430	82.80 469	79.38 438	92.70 432	90.75 454	70.69 461	78.66 446	87.47 457	51.34 460	93.40 453	73.39 443	69.65 457	89.38 456

UnsupCasMVSNet_eth		85.99 397	84.45 401	90.62 401	89.97 444	82.40 403	93.62 415	97.37 219	89.86 268	78.59 447	92.37 410	65.25 435	95.35 436	82.27 387	70.75 455	94.10 406

dmvs_testset		81.38 420	82.60 413	77.73 444	91.74 435	51.49 479	93.03 427	84.21 472	89.07 293	78.28 448	91.25 429	76.97 340	88.53 467	56.57 467	82.24 419	93.16 420

test_f		80.57 421	79.62 423	83.41 439	83.38 468	67.80 466	93.57 417	93.72 424	80.80 436	77.91 449	87.63 455	33.40 470	92.08 459	87.14 324	79.04 433	90.34 454

new-patchmatchnet		83.18 415	81.87 418	87.11 431	86.88 461	75.99 450	93.70 410	95.18 373	85.02 394	77.30 450	88.40 449	65.99 430	93.88 450	74.19 439	70.18 456	91.47 448

UnsupCasMVSNet_bld		82.13 419	79.46 424	90.14 408	88.00 457	82.47 401	90.89 447	96.62 303	78.94 444	75.61 451	84.40 462	56.63 452	96.31 418	77.30 423	66.77 463	91.63 443

ET-MVSNet_ETH3D		91.49 286	90.11 315	95.63 185	96.40 255	91.57 142	95.34 347	93.48 427	90.60 248	75.58 452	95.49 289	80.08 292	96.79 410	94.25 158	89.76 335	98.52 171

new_pmnet		82.89 416	81.12 421	88.18 426	89.63 446	80.18 428	91.77 439	92.57 439	76.79 451	75.56 453	88.23 451	61.22 445	94.48 442	71.43 449	82.92 416	89.87 455

dongtai		69.99 431	69.33 433	71.98 453	88.78 453	61.64 473	89.86 453	59.93 483	75.67 452	74.96 454	85.45 459	50.19 461	81.66 472	43.86 471	55.27 470	72.63 468

APD_test1		79.31 423	77.70 426	84.14 437	89.11 451	69.07 463	92.36 437	91.50 448	69.07 462	73.87 455	92.63 405	39.93 467	94.32 444	70.54 454	80.25 426	89.02 457

CMPMVS	62.92 21	85.62 402	84.92 397	87.74 428	89.14 449	73.12 458	94.17 393	96.80 287	73.98 454	73.65 456	94.93 312	66.36 425	97.61 367	83.95 370	91.28 315	92.48 433
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		82.38 418	80.04 422	89.37 418	87.63 459	82.83 395	95.03 363	93.37 429	73.90 455	73.50 457	94.35 345	62.89 441	93.25 456	73.80 440	65.92 464	92.04 441

WB-MVS		76.77 425	76.63 428	77.18 445	85.32 463	56.82 477	94.53 376	89.39 458	82.66 422	71.35 458	89.18 444	75.03 358	88.88 465	35.42 474	66.79 462	85.84 459

SSC-MVS		76.05 426	75.83 429	76.72 449	84.77 464	56.22 478	94.32 388	88.96 460	81.82 428	70.52 459	88.91 446	74.79 362	88.71 466	33.69 475	64.71 465	85.23 460

YYNet1		85.87 400	84.23 403	90.78 400	92.38 431	82.46 402	93.17 422	95.14 375	82.12 425	67.69 460	92.36 413	78.16 329	95.50 434	77.31 422	79.73 428	94.39 399

kuosan		65.27 437	64.66 439	67.11 456	83.80 465	61.32 474	88.53 461	60.77 482	68.22 463	67.67 461	80.52 465	49.12 462	70.76 478	29.67 477	53.64 472	69.26 470

MDA-MVSNet_test_wron		85.87 400	84.23 403	90.80 399	92.38 431	82.57 397	93.17 422	95.15 374	82.15 424	67.65 462	92.33 416	78.20 326	95.51 433	77.33 421	79.74 427	94.31 403

DeepMVS_CX				74.68 452	90.84 440	64.34 470		81.61 475	65.34 465	67.47 463	88.01 454	48.60 463	80.13 474	62.33 462	73.68 451	79.58 464

LCM-MVSNet		72.55 428	69.39 432	82.03 440	70.81 480	65.42 469	90.12 452	94.36 411	55.02 470	65.88 464	81.72 463	24.16 477	89.96 461	74.32 438	68.10 461	90.71 453

test_method		66.11 436	64.89 438	69.79 454	72.62 478	35.23 486	65.19 474	92.83 437	20.35 476	65.20 465	88.08 453	43.14 466	82.70 471	73.12 444	63.46 466	91.45 449

MDA-MVSNet-bldmvs		85.00 405	82.95 410	91.17 391	93.13 415	83.33 388	94.56 375	95.00 380	84.57 400	65.13 466	92.65 403	70.45 392	95.85 424	73.57 442	77.49 437	94.33 401

PMMVS2		70.19 430	66.92 434	80.01 441	76.35 474	65.67 468	86.22 465	87.58 464	64.83 466	62.38 467	80.29 466	26.78 475	88.49 468	63.79 460	54.07 471	85.88 458

testf1		69.31 432	66.76 435	76.94 447	78.61 472	61.93 471	88.27 462	86.11 469	55.62 468	59.69 468	85.31 460	20.19 479	89.32 462	57.62 464	69.44 459	79.58 464

APD_test2		69.31 432	66.76 435	76.94 447	78.61 472	61.93 471	88.27 462	86.11 469	55.62 468	59.69 468	85.31 460	20.19 479	89.32 462	57.62 464	69.44 459	79.58 464

test_vis3_rt		72.73 427	70.55 430	79.27 442	80.02 471	68.13 465	93.92 402	74.30 479	76.90 450	58.99 470	73.58 470	20.29 478	95.37 435	84.16 365	72.80 453	74.31 467

FPMVS		71.27 429	69.85 431	75.50 450	74.64 475	59.03 475	91.30 441	91.50 448	58.80 467	57.92 471	88.28 450	29.98 473	85.53 470	53.43 468	82.84 417	81.95 463

Gipuma		67.86 435	65.41 437	75.18 451	92.66 424	73.45 455	66.50 473	94.52 402	53.33 471	57.80 472	66.07 472	30.81 471	89.20 464	48.15 470	78.88 434	62.90 472
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		51.94 443	53.82 443	46.29 460	33.73 484	45.30 484	78.32 471	67.24 481	18.02 477	50.93 473	87.05 458	52.99 458	53.11 479	70.76 452	25.29 477	40.46 475

ANet_high		63.94 438	59.58 441	77.02 446	61.24 482	66.06 467	85.66 467	87.93 463	78.53 446	42.94 474	71.04 471	25.42 476	80.71 473	52.60 469	30.83 475	84.28 461

E-PMN		53.28 440	52.56 444	55.43 458	74.43 476	47.13 481	83.63 469	76.30 476	42.23 473	42.59 475	62.22 474	28.57 474	74.40 475	31.53 476	31.51 474	44.78 473

EMVS		52.08 442	51.31 445	54.39 459	72.62 478	45.39 483	83.84 468	75.51 478	41.13 474	40.77 476	59.65 475	30.08 472	73.60 476	28.31 478	29.90 476	44.18 474

MVE	50.73 23	53.25 441	48.81 446	66.58 457	65.34 481	57.50 476	72.49 472	70.94 480	40.15 475	39.28 477	63.51 473	6.89 483	73.48 477	38.29 473	42.38 473	68.76 471
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	53.92 22	58.58 439	55.40 442	68.12 455	51.00 483	48.64 480	78.86 470	87.10 466	46.77 472	35.84 478	74.28 468	8.76 481	86.34 469	42.07 472	73.91 450	69.38 469
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 444	24.57 448	26.74 461	73.98 477	39.89 485	57.88 475	9.80 485	12.27 478	10.39 479	6.97 481	7.03 482	36.44 480	25.43 479	17.39 478	3.89 478

testmvs		13.36 446	16.33 449	4.48 463	5.04 485	2.26 488	93.18 421	3.28 486	2.70 479	8.24 480	21.66 477	2.29 485	2.19 481	7.58 480	2.96 479	9.00 477

test123		13.04 447	15.66 450	5.18 462	4.51 486	3.45 487	92.50 435	1.81 487	2.50 480	7.58 481	20.15 478	3.67 484	2.18 482	7.13 481	1.07 480	9.90 476

EGC-MVSNET		68.77 434	63.01 440	86.07 436	92.49 427	82.24 405	93.96 399	90.96 452	0.71 481	2.62 482	90.89 430	53.66 457	93.46 452	57.25 466	84.55 398	82.51 462

mmdepth		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

monomultidepth		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

test_blank		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uanet_test		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

DCPMVS		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

cdsmvs_eth3d_5k		23.24 445	30.99 447	0.00 464	0.00 487	0.00 489	0.00 476	97.63 166	0.00 482	0.00 483	96.88 207	84.38 200	0.00 483	0.00 482	0.00 481	0.00 479

pcd_1.5k_mvsjas		7.39 449	9.85 452	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	88.65 109	0.00 483	0.00 482	0.00 481	0.00 479

sosnet-low-res		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

sosnet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uncertanet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

Regformer		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

ab-mvs-re		8.06 448	10.74 451	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	96.69 218	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uanet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

TestfortrainingZip							98.69 11

WAC-MVS						79.53 434								75.56 432

MSC_two_6792asdad				98.86 1	98.67 67	96.94 1		97.93 125					99.86 9	97.68 33	99.67 6	99.77 3

No_MVS				98.86 1	98.67 67	96.94 1		97.93 125					99.86 9	97.68 33	99.67 6	99.77 3

eth-test2					0.00 487

eth-test					0.00 487

OPU-MVS				98.55 4	98.82 61	96.86 3	98.25 40				98.26 87	96.04 2	99.24 149	95.36 120	99.59 19	99.56 40

save fliter					98.91 58	94.28 42	97.02 206	98.02 113	95.35 31

test_0728_SECOND				98.51 5	99.45 6	95.93 6	98.21 47	98.28 52					99.86 9	97.52 42	99.67 6	99.75 7

GSMVS																98.45 181

sam_mvs1												82.76 236				98.45 181

sam_mvs												81.94 257

MTGPA								98.08 93

test_post1							92.81 431				16.58 480	80.53 283	97.68 359	86.20 335

test_post											17.58 479	81.76 260	98.08 303

patchmatchnet-post											90.45 434	82.65 241	98.10 298

MTMP							97.86 91	82.03 474

gm-plane-assit					93.22 412	78.89 442			84.82 397		93.52 387		98.64 246	87.72 303

test9_res														94.81 138	99.38 64	99.45 59

agg_prior2														93.94 164	99.38 64	99.50 52

test_prior4						93.66 62	96.42 273

test_prior				97.23 69	98.67 67	92.99 83		98.00 117					99.41 132			99.29 75

新几何2							95.79 323

旧先验1					98.38 89	93.38 68		97.75 149			98.09 96	92.30 48			99.01 108	99.16 85

无先验							95.79 323	97.87 132	83.87 409				99.65 79	87.68 309		98.89 135

原ACMM2							95.67 329

testdata2													99.67 77	85.96 343

segment_acmp												92.89 33

testdata1							95.26 355		93.10 137

plane_prior7					96.21 265	89.98 212

plane_prior6					96.10 283	90.00 208						81.32 267

plane_prior5								97.51 187					98.60 251	93.02 189	92.23 297	95.86 312

plane_prior4											96.64 221

plane_prior2							97.74 113		94.85 53

plane_prior1					96.14 278

plane_prior						89.99 210	97.24 186		94.06 92						92.16 301

n2								0.00 488

nn								0.00 488

door-mid								91.06 451

test11								97.88 130

door								91.13 450

HQP5-MVS						89.33 244

BP-MVS														92.13 205

HQP3-MVS								97.39 215							92.10 302

HQP2-MVS												80.95 271

NP-MVS					95.99 289	89.81 220					95.87 264

ACMMP++_ref															90.30 331

ACMMP++															91.02 320

Test By Simon												88.73 108

High-resolution multi-view benchmark