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 87	98.28 95	91.49 145	97.61 139	98.71 13	97.10 5	99.70 1	98.93 24	90.95 76	99.77 52	99.35 6	99.53 32	99.65 21

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 102	98.43 83	90.32 206	97.80 105	98.53 29	97.24 4	99.62 2	99.14 2	88.65 109	99.80 40	99.54 1	99.15 93	99.74 10

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 87	98.24 101	91.96 127	97.89 89	98.72 12	96.77 7	99.46 3	99.06 12	87.78 127	99.84 26	99.40 4	99.27 74	99.12 93

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 120	98.42 84	91.37 152	98.04 64	98.00 117	97.30 3	99.45 4	99.21 1	89.28 97	99.80 40	99.27 10	99.35 68	98.12 222

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 35	98.14 114	93.94 57	97.93 84	98.65 23	96.70 8	99.38 5	99.07 11	89.92 91	99.81 35	99.16 14	99.43 52	99.61 30

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 154	97.98 126	90.43 198	97.50 154	98.59 26	96.59 10	99.31 6	99.08 8	84.47 204	99.75 58	99.37 5	98.45 132	97.88 243

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 62	98.21 107	92.75 93	97.83 99	98.73 10	95.04 47	99.30 7	98.84 38	93.34 25	99.78 49	99.32 7	99.13 96	99.50 52

test_fmvsm_n_1920		97.55 16	97.89 4	96.53 106	98.41 86	91.73 131	98.01 67	99.02 1	96.37 13	99.30 7	98.92 25	92.39 44	99.79 46	99.16 14	99.46 45	98.08 230

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 108	97.98 126	91.19 162	97.84 96	98.65 23	97.08 6	99.25 9	99.10 6	87.88 125	99.79 46	99.32 7	99.18 89	98.59 172

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 69	98.25 100	92.59 101	97.81 104	98.68 18	94.93 50	99.24 10	98.87 33	93.52 22	99.79 46	99.32 7	99.21 82	99.40 66

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 90	97.28 170	91.73 131	97.75 111	98.50 30	94.86 54	99.22 11	98.78 42	89.75 94	99.76 54	99.10 17	99.29 72	98.94 123

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 89	98.28 95	91.07 170	97.76 109	98.62 25	97.53 2	99.20 12	99.12 5	88.24 117	99.81 35	99.41 3	99.17 90	99.67 16

SED-MVS		98.05 3	97.99 2	98.24 12	99.42 10	95.30 18	98.25 40	98.27 55	95.13 42	99.19 13	98.89 30	95.54 5	99.85 21	97.52 41	99.66 10	99.56 40

test_241102_ONE					99.42 10	95.30 18		98.27 55	95.09 45	99.19 13	98.81 39	95.54 5	99.65 79

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 158	97.30 168	90.37 204	97.53 151	97.92 127	96.52 11	99.14 15	99.08 8	83.21 228	99.74 59	99.22 11	98.06 150	97.88 243

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 176	97.76 142	89.57 236	97.66 129	98.66 21	95.36 32	99.03 16	98.90 27	88.39 114	99.73 61	99.17 13	98.66 120	98.08 230

SD-MVS		97.41 23	97.53 18	97.06 83	98.57 78	94.46 39	97.92 85	98.14 83	94.82 59	99.01 17	98.55 51	94.18 15	97.41 404	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 52	98.99 18	98.92 25	95.08 9

TestfortrainingZip a		97.79 7	97.62 12	98.28 10	99.56 1	95.15 24	98.69 11	98.35 41	95.63 25	98.95 19	98.95 20	93.45 23	99.88 4	96.63 69	98.41 135	99.82 1

IU-MVS					99.42 10	95.39 12		97.94 124	90.40 266	98.94 20				97.41 48	99.66 10	99.74 10

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 143	95.48 318	90.69 189	97.91 86	98.33 45	94.07 93	98.93 21	99.14 2	87.44 141	99.61 91	98.63 26	98.32 138	98.18 215

DVP-MVS++		98.06 2	97.99 2	98.28 10	98.67 67	95.39 12	99.29 1	98.28 52	94.78 63	98.93 21	98.87 33	96.04 2	99.86 10	97.45 45	99.58 23	99.59 32

test_241102_TWO								98.27 55	95.13 42	98.93 21	98.89 30	94.99 12	99.85 21	97.52 41	99.65 13	99.74 10

test_fmvsmconf_n		97.49 21	97.56 16	97.29 65	97.44 165	92.37 108	97.91 86	98.88 4	95.83 19	98.92 24	99.05 14	91.45 61	99.80 40	99.12 16	99.46 45	99.69 15

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 141	97.64 151	90.72 188	98.00 68	98.73 10	94.55 75	98.91 25	99.08 8	88.22 118	99.63 88	98.91 21	98.37 136	98.25 210

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 80	97.58 161	92.56 102	97.68 125	98.47 34	94.02 95	98.90 26	98.89 30	88.94 103	99.78 49	99.18 12	99.03 105	98.93 127

PC_three_1452									90.77 243	98.89 27	98.28 86	96.24 1	98.35 284	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 82	98.18 76	90.57 259	98.85 28	98.94 23	93.33 26	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	96.01 157	96.67 229	90.25 208	97.91 86	98.38 37	94.48 79	98.84 29	99.14 2	88.06 120	99.62 90	98.82 23	98.60 124	98.15 219

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 152	98.07 121	90.28 207	97.97 78	98.76 9	94.93 50	98.84 29	99.06 12	88.80 106	99.65 79	99.06 18	98.63 122	98.18 215

MED-MVS test				98.00 25	99.56 1	94.50 36	98.69 11	98.70 16	93.45 120	98.73 31	98.53 53		99.86 10	97.40 49	99.58 23	99.65 21

MED-MVS		98.07 1	98.08 1	98.06 21	99.56 1	94.50 36	98.69 11	98.70 16	95.63 25	98.73 31	98.95 20	95.46 7	99.86 10	97.40 49	99.58 23	99.82 1

DVP-MVS		97.91 4	97.81 5	98.22 15	99.45 6	95.36 14	98.21 48	97.85 137	94.92 52	98.73 31	98.87 33	95.08 9	99.84 26	97.52 41	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 63	98.73 31	98.87 33	95.87 4	99.84 26	97.45 45	99.72 2	99.77 4

DPE-MVS		97.86 5	97.65 10	98.47 5	99.17 38	95.78 8	97.21 199	98.35 41	95.16 40	98.71 35	98.80 40	95.05 11	99.89 3	96.70 68	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 15	97.63 11	97.43 59	99.37 19	92.93 87	98.86 7	98.85 5	95.27 36	98.65 36	98.90 27	91.97 52	99.80 40	97.63 37	99.21 82	99.57 36

TSAR-MVS + MP.		97.42 22	97.33 29	97.69 47	99.25 32	94.24 46	98.07 61	97.85 137	93.72 105	98.57 37	98.35 72	93.69 20	99.40 134	97.06 56	99.46 45	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 43	99.40 14	93.77 62	98.53 19	98.29 50	95.55 29	98.56 38	97.81 137	93.90 17	99.65 79	96.62 70	99.21 82	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 72	99.29 1	98.35 41	94.98 48	98.49 39

test_one_0601					99.32 27	95.20 21		98.25 61	95.13 42	98.48 40	98.87 33	95.16 8

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 211	97.29 169	88.38 290	97.23 196	98.47 34	95.14 41	98.43 41	99.09 7	87.58 133	99.72 65	98.80 25	99.21 82	98.02 234

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 74	95.67 309	92.21 115	97.95 81	98.27 55	95.78 23	98.40 42	99.00 16	89.99 89	99.78 49	99.06 18	99.41 58	99.59 32

APDe-MVS		97.82 6	97.73 9	98.08 20	99.15 39	94.82 30	98.81 8	98.30 48	94.76 66	98.30 43	98.90 27	93.77 19	99.68 75	97.93 28	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 24	97.13 31	98.17 17	99.02 48	95.28 20	98.23 44	98.27 55	92.37 173	98.27 44	98.65 47	93.33 26	99.72 65	96.49 75	99.52 34	99.51 49

BridgeMVS		96.84 56	96.89 48	96.68 94	97.63 153	92.22 114	98.17 54	97.82 144	94.44 81	98.23 45	97.36 180	90.97 75	99.22 153	97.74 31	99.66 10	98.61 170

TestfortrainingZip				98.34 8	98.54 79	96.25 4	98.69 11	97.85 137	94.15 91	98.17 46	97.94 111	94.00 16	99.63 88		97.45 171	99.15 87

ME-MVS		97.54 17	97.39 27	98.00 25	99.21 36	94.50 36	97.75 111	98.34 44	94.23 89	98.15 47	98.53 53	93.32 28	99.84 26	97.40 49	99.58 23	99.65 21

SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 29	98.39 89	94.25 45	98.43 27	98.27 55	95.34 34	98.11 48	98.56 49	94.53 13	99.71 67	96.57 73	99.62 17	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
test_vis1_n_1920		94.17 168	94.58 142	92.91 357	97.42 166	82.02 428	97.83 99	97.85 137	94.68 69	98.10 49	98.49 58	70.15 412	99.32 142	97.91 29	98.82 112	97.40 272

test_part2					99.28 30	95.74 9				98.10 49

APD-MVS		96.95 47	96.60 66	98.01 23	99.03 47	94.93 29	97.72 119	98.10 91	91.50 209	98.01 51	98.32 80	92.33 45	99.58 99	94.85 137	99.51 37	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 55	98.99 52	93.01 83	97.79 107	98.21 67	95.73 24	97.99 52	99.03 15	92.63 39	99.82 33	97.80 30	99.42 55	99.67 16

patch_mono-2		96.83 57	97.44 24	95.01 228	99.05 45	85.39 380	96.98 219	98.77 8	94.70 68	97.99 52	98.66 45	93.61 21	99.91 1	97.67 36	99.50 39	99.72 14

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 219	98.09 117	86.63 346	96.00 318	98.15 81	95.43 30	97.95 54	98.56 49	93.40 24	99.36 138	96.77 63	99.48 43	99.45 59

ACMMP_NAP		97.20 33	96.86 49	98.23 13	99.09 40	95.16 23	97.60 140	98.19 74	92.82 156	97.93 55	98.74 44	91.60 59	99.86 10	96.26 80	99.52 34	99.67 16

reproduce-ours		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 121	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

our_new_method		97.53 18	97.51 20	97.60 52	98.97 53	93.31 74	97.71 121	98.20 69	95.80 21	97.88 56	98.98 18	92.91 31	99.81 35	97.68 32	99.43 52	99.67 16

9.14			96.75 61		98.93 56		97.73 116	98.23 66	91.28 220	97.88 56	98.44 64	93.00 30	99.65 79	95.76 106	99.47 44

CNVR-MVS		97.68 8	97.44 24	98.37 7	98.90 59	95.86 7	97.27 190	98.08 93	95.81 20	97.87 59	98.31 81	94.26 14	99.68 75	97.02 57	99.49 42	99.57 36

test_vis1_n		92.37 251	92.26 235	92.72 365	94.75 368	82.64 418	98.02 66	96.80 297	91.18 227	97.77 60	97.93 112	58.02 470	98.29 291	97.63 37	98.21 143	97.23 281

test_cas_vis1_n_1920		94.48 161	94.55 146	94.28 280	96.78 220	86.45 352	97.63 136	97.64 164	93.32 126	97.68 61	98.36 71	73.75 382	99.08 178	96.73 65	99.05 102	97.31 277

test_fmvsmconf0.01_n		96.15 88	95.85 91	97.03 84	92.66 434	91.83 130	97.97 78	97.84 142	95.57 28	97.53 62	99.00 16	84.20 211	99.76 54	98.82 23	99.08 100	99.48 56

MM		97.29 31	96.98 42	98.23 13	98.01 124	95.03 28	98.07 61	95.76 358	97.78 1	97.52 63	98.80 40	88.09 119	99.86 10	99.44 2	99.37 66	99.80 3

VNet		95.89 98	95.45 100	97.21 72	98.07 121	92.94 86	97.50 154	98.15 81	93.87 101	97.52 63	97.61 162	85.29 188	99.53 113	95.81 105	95.27 249	99.16 85

SR-MVS		97.01 44	96.86 49	97.47 57	99.09 40	93.27 76	97.98 72	98.07 98	93.75 104	97.45 65	98.48 61	91.43 63	99.59 96	96.22 83	99.27 74	99.54 45

APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 77	99.01 51	92.31 111	97.98 72	98.06 101	93.11 137	97.44 66	98.55 51	90.93 77	99.55 109	96.06 93	99.25 79	99.51 49

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 68	98.31 93	93.39 68	96.79 243	96.72 300	94.17 90	97.44 66	97.66 154	92.76 34	99.33 140	96.86 62	97.76 162	99.08 99

SR-MVS-dyc-post		96.88 51	96.80 57	97.11 79	99.02 48	92.34 109	97.98 72	98.03 110	93.52 117	97.43 68	98.51 56	91.40 64	99.56 107	96.05 94	99.26 77	99.43 63

RE-MVS-def			96.72 62		99.02 48	92.34 109	97.98 72	98.03 110	93.52 117	97.43 68	98.51 56	90.71 81		96.05 94	99.26 77	99.43 63

dcpmvs_2		96.37 81	97.05 38	94.31 278	98.96 55	84.11 401	97.56 145	97.51 193	93.92 99	97.43 68	98.52 55	92.75 35	99.32 142	97.32 54	99.50 39	99.51 49

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 103	98.07 121	91.97 125	98.14 55	97.79 146	90.43 264	97.34 71	97.52 171	91.29 67	99.19 156	98.12 27	99.64 14	98.60 171

旧先验2							95.94 321		81.66 449	97.34 71			98.82 210	92.26 203

MSLP-MVS++		96.94 48	97.06 35	96.59 103	98.72 64	91.86 129	97.67 126	98.49 31	94.66 71	97.24 73	98.41 67	92.31 47	98.94 196	96.61 71	99.46 45	98.96 116

HFP-MVS		97.14 37	96.92 47	97.83 31	99.42 10	94.12 51	98.52 20	98.32 46	93.21 128	97.18 74	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 22	96.87 204	94.65 32	97.58 141	94.39 425	96.47 12	97.16 75	98.39 68	87.53 136	99.87 8	98.97 20	99.41 58	99.55 43

ACMMPR		97.07 41	96.84 51	97.79 35	99.44 9	93.88 58	98.52 20	98.31 47	93.21 128	97.15 76	98.33 78	91.35 65	99.86 10	95.63 113	99.59 19	99.62 27

region2R		97.07 41	96.84 51	97.77 39	99.46 5	93.79 60	98.52 20	98.24 63	93.19 131	97.14 77	98.34 75	91.59 60	99.87 8	95.46 119	99.59 19	99.64 25

PGM-MVS		96.81 58	96.53 69	97.65 48	99.35 25	93.53 66	97.65 130	98.98 2	92.22 179	97.14 77	98.44 64	91.17 71	99.85 21	94.35 163	99.46 45	99.57 36

PHI-MVS		96.77 60	96.46 76	97.71 46	98.40 87	94.07 53	98.21 48	98.45 36	89.86 276	97.11 79	98.01 104	92.52 42	99.69 73	96.03 97	99.53 32	99.36 72

NCCC		97.30 29	97.03 40	98.11 19	98.77 62	95.06 27	97.34 179	98.04 108	95.96 15	97.09 80	97.88 124	93.18 29	99.71 67	95.84 104	99.17 90	99.56 40

CS-MVS		96.86 52	97.06 35	96.26 136	98.16 113	91.16 167	99.09 3	97.87 132	95.30 35	97.06 81	98.03 101	91.72 54	98.71 242	97.10 55	99.17 90	98.90 132

ZD-MVS					99.05 45	94.59 34		98.08 93	89.22 299	97.03 82	98.10 94	92.52 42	99.65 79	94.58 156	99.31 71

testdata				95.46 209	98.18 112	88.90 271		97.66 160	82.73 439	97.03 82	98.07 97	90.06 87	98.85 206	89.67 270	98.98 107	98.64 169

SPE-MVS-test		96.89 50	97.04 39	96.45 119	98.29 94	91.66 138	99.03 4	97.85 137	95.84 18	96.90 84	97.97 109	91.24 68	98.75 232	96.92 59	99.33 69	98.94 123

mvsany_test1		93.93 186	93.98 165	93.78 313	94.94 358	86.80 339	94.62 388	92.55 459	88.77 321	96.85 85	98.49 58	88.98 101	98.08 314	95.03 127	95.62 239	96.46 306

GDP-MVS		95.62 105	95.13 114	97.09 80	96.79 215	93.26 77	97.89 89	97.83 143	93.58 109	96.80 86	97.82 135	83.06 235	99.16 163	94.40 160	97.95 156	98.87 142

test_fmvs1		93.21 214	93.53 179	92.25 380	96.55 247	81.20 435	97.40 173	96.96 279	90.68 248	96.80 86	98.04 100	69.25 420	98.40 276	97.58 40	98.50 127	97.16 283

test_fmvs1_n		92.73 240	92.88 208	92.29 377	96.08 293	81.05 436	97.98 72	97.08 261	90.72 246	96.79 88	98.18 91	63.07 459	98.45 273	97.62 39	98.42 134	97.36 273

HPM-MVS_fast		96.51 74	96.27 83	97.22 71	99.32 27	92.74 94	98.74 10	98.06 101	90.57 259	96.77 89	98.35 72	90.21 86	99.53 113	94.80 144	99.63 16	99.38 70

h-mvs33		94.15 170	93.52 181	96.04 152	97.81 139	90.22 209	97.62 138	97.58 175	95.19 38	96.74 90	97.45 173	83.67 219	99.61 91	95.85 102	79.73 438	98.29 208

hse-mvs2		93.45 207	92.99 201	94.81 242	97.02 192	88.59 280	96.69 257	96.47 318	95.19 38	96.74 90	96.16 259	83.67 219	98.48 272	95.85 102	79.13 442	97.35 275

GST-MVS		96.85 54	96.52 70	97.82 32	99.36 23	94.14 50	98.29 34	98.13 84	92.72 159	96.70 92	98.06 98	91.35 65	99.86 10	94.83 140	99.28 73	99.47 58

xiu_mvs_v1_base_debu		95.01 136	94.76 133	95.75 182	96.58 240	91.71 134	96.25 300	97.35 230	92.99 141	96.70 92	96.63 233	82.67 246	99.44 130	96.22 83	97.46 167	96.11 318

xiu_mvs_v1_base		95.01 136	94.76 133	95.75 182	96.58 240	91.71 134	96.25 300	97.35 230	92.99 141	96.70 92	96.63 233	82.67 246	99.44 130	96.22 83	97.46 167	96.11 318

xiu_mvs_v1_base_debi		95.01 136	94.76 133	95.75 182	96.58 240	91.71 134	96.25 300	97.35 230	92.99 141	96.70 92	96.63 233	82.67 246	99.44 130	96.22 83	97.46 167	96.11 318

CDPH-MVS		95.97 94	95.38 106	97.77 39	98.93 56	94.44 40	96.35 290	97.88 130	86.98 371	96.65 96	97.89 119	91.99 51	99.47 126	92.26 203	99.46 45	99.39 68

EC-MVSNet		96.42 78	96.47 73	96.26 136	97.01 193	91.52 144	98.89 5	97.75 149	94.42 82	96.64 97	97.68 151	89.32 96	98.60 259	97.45 45	99.11 99	98.67 168

UA-Net		95.95 95	95.53 96	97.20 73	97.67 147	92.98 85	97.65 130	98.13 84	94.81 61	96.61 98	98.35 72	88.87 104	99.51 118	90.36 256	97.35 175	99.11 95

HPM-MVS++		97.34 26	96.97 43	98.47 5	99.08 42	96.16 5	97.55 150	97.97 121	95.59 27	96.61 98	97.89 119	92.57 41	99.84 26	95.95 99	99.51 37	99.40 66

XVS		97.18 34	96.96 45	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	98.29 84	91.70 56	99.80 40	95.66 108	99.40 60	99.62 27

X-MVStestdata		91.71 277	89.67 345	97.81 33	99.38 17	94.03 55	98.59 17	98.20 69	94.85 55	96.59 100	32.69 498	91.70 56	99.80 40	95.66 108	99.40 60	99.62 27

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 37	98.64 73	94.30 42	97.41 169	98.04 108	94.81 61	96.59 100	98.37 70	91.24 68	99.64 87	95.16 124	99.52 34	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 77	99.37 19	92.90 88	97.99 69	97.63 166	95.92 16	96.57 103	97.93 112	85.34 186	99.50 121	94.99 129	99.21 82	98.97 113

SymmetryMVS		95.94 96	95.54 95	97.15 75	97.85 136	92.90 88	97.99 69	96.91 287	95.92 16	96.57 103	97.93 112	85.34 186	99.50 121	94.99 129	96.39 222	99.05 103

diffmvs_AUTHOR		95.33 114	95.27 110	95.50 204	96.37 267	89.08 263	96.08 313	97.38 225	93.09 139	96.53 105	97.74 145	86.45 158	98.68 246	96.32 78	97.48 166	98.75 159

PS-MVSNAJ		95.37 112	95.33 108	95.49 205	97.35 167	90.66 191	95.31 360	97.48 198	93.85 102	96.51 106	95.70 286	88.65 109	99.65 79	94.80 144	98.27 141	96.17 312

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 99	98.24 101	91.20 161	96.89 229	97.73 152	94.74 67	96.49 107	98.49 58	90.88 79	99.58 99	96.44 76	98.32 138	99.13 90

ETV-MVS		96.02 91	95.89 90	96.40 123	97.16 176	92.44 106	97.47 163	97.77 148	94.55 75	96.48 108	94.51 343	91.23 70	98.92 199	95.65 111	98.19 144	97.82 251

alignmvs		95.87 100	95.23 111	97.78 37	97.56 163	95.19 22	97.86 92	97.17 250	94.39 85	96.47 109	96.40 246	85.89 169	99.20 155	96.21 87	95.11 254	98.95 120

KinetiMVS		95.26 118	94.75 136	96.79 91	96.99 195	92.05 121	97.82 101	97.78 147	94.77 65	96.46 110	97.70 148	80.62 291	99.34 139	92.37 202	98.28 140	98.97 113

xiu_mvs_v2_base		95.32 115	95.29 109	95.40 210	97.22 172	90.50 194	95.44 353	97.44 213	93.70 107	96.46 110	96.18 256	88.59 113	99.53 113	94.79 147	97.81 159	96.17 312

CP-MVS		97.02 43	96.81 56	97.64 50	99.33 26	93.54 65	98.80 9	98.28 52	92.99 141	96.45 112	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 60	99.36 23	93.11 81	98.87 6	98.06 101	91.17 228	96.40 113	97.99 107	90.99 74	99.58 99	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 30	99.37 19	94.12 51	98.49 24	98.18 76	92.64 163	96.39 114	98.18 91	91.61 58	99.88 4	95.59 118	99.55 29	99.57 36

balanced_ft_v1		95.56 109	95.40 104	96.07 149	97.16 176	90.36 205	98.23 44	97.31 235	92.89 153	96.36 115	97.11 198	83.28 226	99.26 149	97.40 49	98.80 114	98.58 173

BP-MVS1		95.89 98	95.49 97	97.08 82	96.67 229	93.20 78	98.08 59	96.32 326	94.56 74	96.32 116	97.84 131	84.07 214	99.15 165	96.75 64	98.78 115	98.90 132

diffmvs		95.25 120	95.13 114	95.63 190	96.43 262	89.34 250	95.99 319	97.35 230	92.83 155	96.31 117	97.37 179	86.44 159	98.67 249	96.26 80	97.19 185	98.87 142
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		93.60 197	92.63 220	96.52 108	98.13 116	91.27 156	97.94 82	93.39 447	90.57 259	96.29 118	98.31 81	69.00 422	99.16 163	94.18 165	95.87 231	99.12 93

sasdasda		96.02 91	95.45 100	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 261	87.65 130	99.18 159	96.20 88	94.82 258	98.91 129

canonicalmvs		96.02 91	95.45 100	97.75 41	97.59 157	95.15 24	98.28 35	97.60 171	94.52 77	96.27 119	96.12 261	87.65 130	99.18 159	96.20 88	94.82 258	98.91 129

MVSFormer		95.37 112	95.16 113	95.99 159	96.34 269	91.21 159	98.22 46	97.57 178	91.42 213	96.22 121	97.32 181	86.20 164	97.92 346	94.07 166	99.05 102	98.85 144

lupinMVS		94.99 140	94.56 143	96.29 134	96.34 269	91.21 159	95.83 328	96.27 333	88.93 312	96.22 121	96.88 215	86.20 164	98.85 206	95.27 121	99.05 102	98.82 148

MGCFI-Net		95.94 96	95.40 104	97.56 54	97.59 157	94.62 33	98.21 48	97.57 178	94.41 83	96.17 123	96.16 259	87.54 135	99.17 161	96.19 90	94.73 263	98.91 129

EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 116	98.20 108	90.93 177	96.86 232	97.72 154	94.67 70	96.16 124	98.46 62	90.43 84	99.58 99	96.23 82	97.96 155	98.90 132

MTAPA		97.08 39	96.78 59	97.97 28	99.37 19	94.42 41	97.24 192	98.08 93	95.07 46	96.11 125	98.59 48	90.88 79	99.90 2	96.18 92	99.50 39	99.58 35

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 130	96.62 231	91.73 131	97.98 72	98.30 48	96.19 14	96.10 126	98.95 20	89.42 95	99.76 54	98.90 22	99.08 100	97.43 270

MCST-MVS		97.18 34	96.84 51	98.20 16	99.30 29	95.35 16	97.12 206	98.07 98	93.54 114	96.08 127	97.69 150	93.86 18	99.71 67	96.50 74	99.39 62	99.55 43

TEST9					98.70 65	94.19 47	96.41 281	98.02 113	88.17 337	96.03 128	97.56 168	92.74 36	99.59 96

train_agg		96.30 85	95.83 92	97.72 44	98.70 65	94.19 47	96.41 281	98.02 113	88.58 324	96.03 128	97.56 168	92.73 37	99.59 96	95.04 126	99.37 66	99.39 68

test_prior2							96.35 290		92.80 157	96.03 128	97.59 165	92.01 50		95.01 128	99.38 63

jason		94.84 147	94.39 153	96.18 142	95.52 316	90.93 177	96.09 312	96.52 315	89.28 297	96.01 131	97.32 181	84.70 200	98.77 220	95.15 125	98.91 111	98.85 144
jason: jason.
test_8					98.67 67	94.06 54	96.37 289	98.01 116	88.58 324	95.98 132	97.55 170	92.73 37	99.58 99

mPP-MVS		96.86 52	96.60 66	97.64 50	99.40 14	93.44 67	98.50 23	98.09 92	93.27 127	95.95 133	98.33 78	91.04 73	99.88 4	95.20 122	99.57 28	99.60 31

LuminaMVS		94.89 143	94.35 155	96.53 106	95.48 318	92.80 92	96.88 231	96.18 343	92.85 154	95.92 134	96.87 217	81.44 273	98.83 209	96.43 77	97.10 188	97.94 239

DELS-MVS		96.61 71	96.38 80	97.30 64	97.79 140	93.19 79	95.96 320	98.18 76	95.23 37	95.87 135	97.65 155	91.45 61	99.70 72	95.87 100	99.44 51	99.00 110
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		93.82 190	93.08 199	96.02 154	97.88 135	89.96 220	97.72 119	95.85 354	92.43 171	95.86 136	98.44 64	68.42 429	99.39 135	96.31 79	94.85 256	98.71 165

MVS_111021_HR		96.68 69	96.58 68	96.99 85	98.46 80	92.31 111	96.20 306	98.90 3	94.30 88	95.86 136	97.74 145	92.33 45	99.38 137	96.04 96	99.42 55	99.28 77

MVS_111021_LR		96.24 87	96.19 85	96.39 125	98.23 106	91.35 154	96.24 303	98.79 7	93.99 97	95.80 138	97.65 155	89.92 91	99.24 151	95.87 100	99.20 87	98.58 173

VDDNet		93.05 223	92.07 238	96.02 154	96.84 208	90.39 200	98.08 59	95.85 354	86.22 386	95.79 139	98.46 62	67.59 432	99.19 156	94.92 132	94.85 256	98.47 187

新几何1				97.32 63	98.60 74	93.59 64		97.75 149	81.58 450	95.75 140	97.85 129	90.04 88	99.67 77	86.50 350	99.13 96	98.69 166

guyue		95.17 128	94.96 123	95.82 171	96.97 197	89.65 231	97.56 145	95.58 370	94.82 59	95.72 141	97.42 176	82.90 240	98.84 208	96.71 67	96.93 193	98.96 116

test_yl		94.78 151	94.23 158	96.43 120	97.74 143	91.22 157	96.85 233	97.10 258	91.23 225	95.71 142	96.93 210	84.30 208	99.31 144	93.10 190	95.12 252	98.75 159

DCV-MVSNet		94.78 151	94.23 158	96.43 120	97.74 143	91.22 157	96.85 233	97.10 258	91.23 225	95.71 142	96.93 210	84.30 208	99.31 144	93.10 190	95.12 252	98.75 159

AstraMVS		94.82 149	94.64 139	95.34 213	96.36 268	88.09 305	97.58 141	94.56 418	94.98 48	95.70 144	97.92 115	81.93 266	98.93 197	96.87 61	95.88 230	98.99 112

agg_prior					98.67 67	93.79 60		98.00 117		95.68 145			99.57 106

MG-MVS		95.61 106	95.38 106	96.31 130	98.42 84	90.53 193	96.04 315	97.48 198	93.47 119	95.67 146	98.10 94	89.17 99	99.25 150	91.27 232	98.77 116	99.13 90

baseline		95.58 107	95.42 103	96.08 147	96.78 220	90.41 199	97.16 203	97.45 209	93.69 108	95.65 147	97.85 129	87.29 144	98.68 246	95.66 108	97.25 182	99.13 90

MVS_Test		94.89 143	94.62 140	95.68 188	96.83 210	89.55 239	96.70 255	97.17 250	91.17 228	95.60 148	96.11 265	87.87 126	98.76 226	93.01 197	97.17 186	98.72 163

DPM-MVS		95.69 102	94.92 124	98.01 23	98.08 120	95.71 10	95.27 363	97.62 170	90.43 264	95.55 149	97.07 201	91.72 54	99.50 121	89.62 272	98.94 109	98.82 148

MP-MVS-pluss		96.70 65	96.27 83	97.98 27	99.23 35	94.71 31	96.96 221	98.06 101	90.67 249	95.55 149	98.78 42	91.07 72	99.86 10	96.58 72	99.55 29	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 60	96.45 77	97.72 44	99.39 16	93.80 59	98.41 28	98.06 101	93.37 123	95.54 151	98.34 75	90.59 83	99.88 4	94.83 140	99.54 31	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test12				97.65 48	98.46 80	94.26 44		97.66 160		95.52 152		90.89 78	99.46 127		99.25 79	99.22 82

viewmanbaseed2359cas		95.24 121	95.02 120	95.91 162	96.87 204	89.98 217	96.82 238	97.49 196	92.26 177	95.47 153	97.82 135	86.47 157	98.69 244	94.80 144	97.20 184	99.06 102

casdiffmvs		95.64 104	95.49 97	96.08 147	96.76 226	90.45 196	97.29 185	97.44 213	94.00 96	95.46 154	97.98 108	87.52 138	98.73 236	95.64 112	97.33 176	99.08 99
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		95.28 116	95.11 117	95.80 173	97.03 190	89.76 226	96.78 247	97.54 190	92.06 190	95.40 155	97.75 142	87.49 139	98.76 226	94.85 137	97.10 188	98.88 140

viewcassd2359sk11		95.26 118	95.09 118	95.80 173	96.95 199	89.72 228	96.80 242	97.56 186	92.21 181	95.37 156	97.80 139	87.17 147	98.77 220	94.82 142	97.10 188	98.90 132

viewmacassd2359aftdt		95.07 131	94.80 132	95.87 165	96.53 250	89.84 223	96.90 228	97.48 198	92.44 170	95.36 157	97.89 119	85.23 189	98.68 246	94.40 160	97.00 192	99.09 97

E2		95.20 124	95.00 121	95.79 176	96.79 215	89.66 229	96.82 238	97.58 175	92.35 174	95.28 158	97.83 133	86.68 152	98.76 226	94.79 147	96.92 194	98.95 120

E3		95.20 124	95.00 121	95.79 176	96.77 222	89.66 229	96.82 238	97.58 175	92.35 174	95.28 158	97.83 133	86.69 151	98.76 226	94.79 147	96.92 194	98.95 120

test222					98.24 101	92.21 115	95.33 358	97.60 171	79.22 463	95.25 160	97.84 131	88.80 106			99.15 93	98.72 163

test2506		91.60 285	90.78 291	94.04 293	97.66 149	83.81 404	98.27 37	75.53 499	93.43 121	95.23 161	98.21 88	67.21 435	99.07 182	93.01 197	98.49 128	99.25 80

原ACMM1				96.38 126	98.59 75	91.09 169		97.89 128	87.41 363	95.22 162	97.68 151	90.25 85	99.54 111	87.95 309	99.12 98	98.49 184

CPTT-MVS		95.57 108	95.19 112	96.70 93	99.27 31	91.48 147	98.33 31	98.11 89	87.79 352	95.17 163	98.03 101	87.09 148	99.61 91	93.51 181	99.42 55	99.02 104

casdiffmvs_mvg		95.81 101	95.57 94	96.51 112	96.87 204	91.49 145	97.50 154	97.56 186	93.99 97	95.13 164	97.92 115	87.89 124	98.78 216	95.97 98	97.33 176	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 61	99.19 37	94.19 47	97.03 210	98.08 93	88.35 333	95.09 165	97.65 155	89.97 90	99.48 125	92.08 214	98.59 125	98.44 192

E5new		95.04 132	94.88 126	95.52 198	96.62 231	89.02 265	97.29 185	97.57 178	92.54 164	95.04 166	97.89 119	85.65 178	98.77 220	94.92 132	96.44 218	98.78 151

E6new		95.04 132	94.88 126	95.52 198	96.60 236	89.02 265	97.29 185	97.57 178	92.54 164	95.04 166	97.90 117	85.66 176	98.77 220	94.92 132	96.44 218	98.78 151

E6		95.04 132	94.88 126	95.52 198	96.60 236	89.02 265	97.29 185	97.57 178	92.54 164	95.04 166	97.90 117	85.66 176	98.77 220	94.92 132	96.44 218	98.78 151

E5		95.04 132	94.88 126	95.52 198	96.62 231	89.02 265	97.29 185	97.57 178	92.54 164	95.04 166	97.89 119	85.65 178	98.77 220	94.92 132	96.44 218	98.78 151

E4		95.09 129	94.86 130	95.77 179	96.58 240	89.56 237	96.85 233	97.56 186	92.50 168	95.03 170	97.86 127	86.03 167	98.78 216	94.71 150	96.65 208	98.96 116

viewmambaseed2359dif		94.28 164	94.14 160	94.71 250	96.21 273	86.97 336	95.93 322	97.11 257	89.00 307	95.00 171	97.70 148	86.02 168	98.59 263	93.71 177	96.59 210	98.57 175

RRT-MVS		94.51 159	94.35 155	94.98 232	96.40 263	86.55 349	97.56 145	97.41 219	93.19 131	94.93 172	97.04 203	79.12 319	99.30 146	96.19 90	97.32 178	99.09 97

Vis-MVSNet		95.23 122	94.81 131	96.51 112	97.18 175	91.58 142	98.26 39	98.12 86	94.38 86	94.90 173	98.15 93	82.28 256	98.92 199	91.45 229	98.58 126	99.01 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		96.39 80	96.02 87	97.50 55	97.62 154	93.38 69	97.02 212	97.96 122	95.42 31	94.86 174	97.81 137	87.38 143	99.82 33	96.88 60	99.20 87	99.29 75

Elysia		94.00 180	93.12 197	96.64 95	96.08 293	92.72 96	97.50 154	97.63 166	91.15 230	94.82 175	97.12 196	74.98 369	99.06 184	90.78 242	98.02 151	98.12 222

StellarMVS		94.00 180	93.12 197	96.64 95	96.08 293	92.72 96	97.50 154	97.63 166	91.15 230	94.82 175	97.12 196	74.98 369	99.06 184	90.78 242	98.02 151	98.12 222

API-MVS		94.84 147	94.49 149	95.90 163	97.90 134	92.00 124	97.80 105	97.48 198	89.19 300	94.81 177	96.71 222	88.84 105	99.17 161	88.91 294	98.76 117	96.53 301

mvsmamba		94.57 156	94.14 160	95.87 165	97.03 190	89.93 221	97.84 96	95.85 354	91.34 216	94.79 178	96.80 218	80.67 289	98.81 212	94.85 137	98.12 148	98.85 144

OMC-MVS		95.09 129	94.70 137	96.25 139	98.46 80	91.28 155	96.43 277	97.57 178	92.04 191	94.77 179	97.96 110	87.01 149	99.09 176	91.31 231	96.77 199	98.36 199

ECVR-MVS		93.19 216	92.73 216	94.57 260	97.66 149	85.41 378	98.21 48	88.23 483	93.43 121	94.70 180	98.21 88	72.57 391	99.07 182	93.05 194	98.49 128	99.25 80

viewdifsd2359ckpt13		94.87 145	94.52 147	95.90 163	96.88 203	90.19 210	96.92 225	97.36 228	91.26 221	94.65 181	97.46 172	85.79 173	98.64 254	93.64 178	96.76 200	98.88 140

WTY-MVS		94.71 155	94.02 163	96.79 91	97.71 145	92.05 121	96.59 270	97.35 230	90.61 255	94.64 182	96.93 210	86.41 160	99.39 135	91.20 234	94.71 264	98.94 123

test1111		93.19 216	92.82 210	94.30 279	97.58 161	84.56 395	98.21 48	89.02 481	93.53 115	94.58 183	98.21 88	72.69 390	99.05 187	93.06 193	98.48 130	99.28 77

ACMMP		96.27 86	95.93 88	97.28 67	99.24 33	92.62 99	98.25 40	98.81 6	92.99 141	94.56 184	98.39 68	88.96 102	99.85 21	94.57 157	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		94.76 153	94.68 138	95.01 228	96.76 226	87.41 322	96.38 287	97.43 216	92.65 161	94.52 185	97.75 142	85.55 183	98.81 212	94.36 162	96.69 205	98.82 148

Effi-MVS+		94.93 141	94.45 151	96.36 128	96.61 234	91.47 148	96.41 281	97.41 219	91.02 236	94.50 186	95.92 270	87.53 136	98.78 216	93.89 172	96.81 198	98.84 147

sss		94.51 159	93.80 168	96.64 95	97.07 182	91.97 125	96.32 295	98.06 101	88.94 311	94.50 186	96.78 219	84.60 201	99.27 148	91.90 215	96.02 225	98.68 167

mmtdpeth		89.70 364	88.96 362	91.90 389	95.84 304	84.42 396	97.46 165	95.53 376	90.27 267	94.46 188	90.50 442	69.74 418	98.95 194	97.39 53	69.48 479	92.34 455

PVSNet_BlendedMVS		94.06 176	93.92 166	94.47 266	98.27 97	89.46 245	96.73 251	98.36 38	90.17 269	94.36 189	95.24 309	88.02 121	99.58 99	93.44 183	90.72 333	94.36 420

PVSNet_Blended		94.87 145	94.56 143	95.81 172	98.27 97	89.46 245	95.47 351	98.36 38	88.84 315	94.36 189	96.09 266	88.02 121	99.58 99	93.44 183	98.18 145	98.40 195

viewdifsd2359ckpt09		94.81 150	94.37 154	96.12 146	96.91 200	90.75 187	96.94 222	97.31 235	90.51 262	94.31 191	97.38 178	85.70 175	98.71 242	93.54 179	96.75 201	98.90 132

PMMVS		92.86 234	92.34 232	94.42 270	94.92 359	86.73 342	94.53 392	96.38 324	84.78 409	94.27 192	95.12 314	83.13 232	98.40 276	91.47 228	96.49 215	98.12 222

EPP-MVSNet		95.22 123	95.04 119	95.76 180	97.49 164	89.56 237	98.67 15	97.00 277	90.69 247	94.24 193	97.62 161	89.79 93	98.81 212	93.39 186	96.49 215	98.92 128

viewmsd2359difaftdt		93.46 204	93.23 194	94.17 284	96.12 288	85.42 376	96.43 277	97.08 261	92.91 149	94.21 194	98.00 105	80.82 287	98.74 234	94.41 159	89.05 351	98.34 205

viewdifsd2359ckpt11		93.46 204	93.22 195	94.17 284	96.11 290	85.42 376	96.43 277	97.07 264	92.91 149	94.20 195	98.00 105	80.82 287	98.73 236	94.42 158	89.04 353	98.34 205

FA-MVS(test-final)		93.52 202	92.92 206	95.31 214	96.77 222	88.54 283	94.82 384	96.21 340	89.61 286	94.20 195	95.25 308	83.24 227	99.14 168	90.01 260	96.16 224	98.25 210

PVSNet_Blended_VisFu		95.27 117	94.91 125	96.38 126	98.20 108	90.86 180	97.27 190	98.25 61	90.21 268	94.18 197	97.27 187	87.48 140	99.73 61	93.53 180	97.77 161	98.55 176

SSM_0404		94.73 154	94.31 157	95.98 160	97.05 187	90.90 179	97.01 215	97.29 237	91.24 222	94.17 198	97.60 163	85.03 193	98.76 226	92.14 208	97.30 179	98.29 208

FE-MVS		92.05 267	91.05 279	95.08 223	96.83 210	87.93 309	93.91 421	95.70 361	86.30 383	94.15 199	94.97 317	76.59 353	99.21 154	84.10 385	96.86 196	98.09 229

thisisatest0530		93.03 224	92.21 236	95.49 205	97.07 182	89.11 262	97.49 162	92.19 464	90.16 270	94.09 200	96.41 245	76.43 357	99.05 187	90.38 255	95.68 237	98.31 207

XVG-OURS-SEG-HR		93.86 189	93.55 177	94.81 242	97.06 185	88.53 285	95.28 361	97.45 209	91.68 201	94.08 201	97.68 151	82.41 254	98.90 202	93.84 174	92.47 302	96.98 286

XVG-OURS		93.72 194	93.35 190	94.80 245	97.07 182	88.61 279	94.79 385	97.46 204	91.97 194	93.99 202	97.86 127	81.74 269	98.88 203	92.64 201	92.67 301	96.92 291

IS-MVSNet		94.90 142	94.52 147	96.05 151	97.67 147	90.56 192	98.44 26	96.22 338	93.21 128	93.99 202	97.74 145	85.55 183	98.45 273	89.98 261	97.86 157	99.14 89

CSCG		96.05 90	95.91 89	96.46 118	99.24 33	90.47 195	98.30 33	98.57 28	89.01 306	93.97 204	97.57 166	92.62 40	99.76 54	94.66 151	99.27 74	99.15 87

casdiffseed414692147		94.55 157	94.02 163	96.15 144	96.61 234	90.79 183	97.42 167	97.39 221	92.18 186	93.95 205	97.64 158	84.37 207	98.66 252	90.68 247	95.91 229	99.00 110

EIA-MVS		95.53 110	95.47 99	95.71 187	97.06 185	89.63 232	97.82 101	97.87 132	93.57 110	93.92 206	95.04 315	90.61 82	98.95 194	94.62 153	98.68 119	98.54 177

tttt0517		92.96 227	92.33 233	94.87 239	97.11 180	87.16 332	97.97 78	92.09 465	90.63 253	93.88 207	97.01 209	76.50 354	99.06 184	90.29 258	95.45 246	98.38 197

HyFIR lowres test		93.66 196	92.92 206	95.87 165	98.24 101	89.88 222	94.58 390	98.49 31	85.06 404	93.78 208	95.78 281	82.86 241	98.67 249	91.77 220	95.71 236	99.07 101

CHOSEN 1792x2688		94.15 170	93.51 182	96.06 150	98.27 97	89.38 248	95.18 372	98.48 33	85.60 394	93.76 209	97.11 198	83.15 231	99.61 91	91.33 230	98.72 118	99.19 83

mamba_0408		93.70 195	92.99 201	95.83 170	96.79 215	90.38 201	88.69 480	97.07 264	90.96 238	93.68 210	97.31 183	84.97 196	98.76 226	90.95 238	96.51 211	98.35 201

SSM_04072		93.51 203	92.99 201	95.05 224	96.79 215	90.38 201	88.69 480	97.07 264	90.96 238	93.68 210	97.31 183	84.97 196	96.42 436	90.95 238	96.51 211	98.35 201

SSM_0407		94.54 158	94.12 162	95.80 173	96.79 215	90.38 201	96.79 243	97.29 237	91.24 222	93.68 210	97.60 163	85.03 193	98.67 249	92.14 208	96.51 211	98.35 201

Anonymous202405211		92.07 266	90.83 290	95.76 180	98.19 110	88.75 274	97.58 141	95.00 398	86.00 389	93.64 213	97.45 173	66.24 444	99.53 113	90.68 247	92.71 299	99.01 107

IMVS_0403		93.98 182	93.79 169	94.55 261	96.19 277	86.16 361	96.35 290	97.24 244	91.54 204	93.59 214	97.04 203	85.86 170	98.73 236	90.68 247	95.59 240	98.76 155

CDS-MVSNet		94.14 173	93.54 178	95.93 161	96.18 281	91.46 149	96.33 294	97.04 272	88.97 310	93.56 215	96.51 240	87.55 134	97.89 350	89.80 266	95.95 227	98.44 192
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MDTV_nov1_ep13_2view						70.35 482	93.10 444		83.88 420	93.55 216		82.47 253		86.25 353		98.38 197

Anonymous20240529		91.98 269	90.73 296	95.73 185	98.14 114	89.40 247	97.99 69	97.72 154	79.63 461	93.54 217	97.41 177	69.94 414	99.56 107	91.04 237	91.11 326	98.22 212

CANet_DTU		94.37 162	93.65 174	96.55 105	96.46 260	92.13 119	96.21 304	96.67 307	94.38 86	93.53 218	97.03 208	79.34 315	99.71 67	90.76 244	98.45 132	97.82 251

icg_test_0407_2		93.58 198	93.46 184	93.94 303	96.19 277	86.16 361	93.73 427	97.24 244	91.54 204	93.50 219	97.04 203	85.64 181	96.91 425	90.68 247	95.59 240	98.76 155

IMVS_0407		93.94 184	93.75 170	94.49 265	96.19 277	86.16 361	96.35 290	97.24 244	91.54 204	93.50 219	97.04 203	85.64 181	98.54 266	90.68 247	95.59 240	98.76 155

tpmrst		91.44 297	91.32 267	91.79 395	95.15 347	79.20 462	93.42 437	95.37 380	88.55 327	93.49 221	93.67 390	82.49 252	98.27 293	90.41 254	89.34 347	97.90 241

TAMVS		94.01 179	93.46 184	95.64 189	96.16 283	90.45 196	96.71 254	96.89 290	89.27 298	93.46 222	96.92 213	87.29 144	97.94 343	88.70 300	95.74 234	98.53 178

thisisatest0515		92.29 256	91.30 269	95.25 216	96.60 236	88.90 271	94.36 403	92.32 462	87.92 344	93.43 223	94.57 339	77.28 348	99.00 191	89.42 277	95.86 232	97.86 247

DeepC-MVS	93.07 3	96.06 89	95.66 93	97.29 65	97.96 128	93.17 80	97.30 184	98.06 101	93.92 99	93.38 224	98.66 45	86.83 150	99.73 61	95.60 117	99.22 81	98.96 116
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		92.49 245	91.60 257	95.18 218	97.91 133	89.47 243	97.65 130	94.66 414	92.18 186	93.33 225	94.91 321	78.06 341	99.10 173	81.61 409	94.06 281	96.98 286

thres100view900		92.43 247	91.58 258	94.98 232	97.92 132	89.37 249	97.71 121	94.66 414	92.20 182	93.31 226	94.90 322	78.06 341	99.08 178	81.40 413	94.08 277	96.48 304

thres200		92.23 260	91.39 264	94.75 249	97.61 155	89.03 264	96.60 269	95.09 395	92.08 189	93.28 227	94.00 376	78.39 335	99.04 190	81.26 419	94.18 273	96.19 311

tfpn200view9		92.38 250	91.52 261	94.95 236	97.85 136	89.29 253	97.41 169	94.88 406	92.19 184	93.27 228	94.46 348	78.17 337	99.08 178	81.40 413	94.08 277	96.48 304

thres400		92.42 248	91.52 261	95.12 222	97.85 136	89.29 253	97.41 169	94.88 406	92.19 184	93.27 228	94.46 348	78.17 337	99.08 178	81.40 413	94.08 277	96.98 286

testing3-2		92.10 265	92.05 239	92.27 378	97.71 145	79.56 456	97.42 167	94.41 424	93.53 115	93.22 230	95.49 297	69.16 421	99.11 171	93.25 187	94.22 271	98.13 220

ab-mvs		93.57 200	92.55 224	96.64 95	97.28 170	91.96 127	95.40 354	97.45 209	89.81 280	93.22 230	96.28 252	79.62 312	99.46 127	90.74 245	93.11 293	98.50 182

Vis-MVSNet (Re-imp)		94.15 170	93.88 167	94.95 236	97.61 155	87.92 310	98.10 57	95.80 357	92.22 179	93.02 232	97.45 173	84.53 203	97.91 349	88.24 304	97.97 154	99.02 104

114514_t		93.95 183	93.06 200	96.63 99	99.07 43	91.61 139	97.46 165	97.96 122	77.99 468	93.00 233	97.57 166	86.14 166	99.33 140	89.22 284	99.15 93	98.94 123

UGNet		94.04 178	93.28 192	96.31 130	96.85 207	91.19 162	97.88 91	97.68 159	94.40 84	93.00 233	96.18 256	73.39 386	99.61 91	91.72 221	98.46 131	98.13 220
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	93.87 188	92.95 205	96.63 99	97.10 181	92.49 105	95.64 343	96.64 308	89.05 305	93.00 233	95.79 280	85.77 174	99.45 129	89.16 288	94.35 266	97.96 237

PVSNet	86.66 18	92.24 259	91.74 254	93.73 314	97.77 141	83.69 408	92.88 447	96.72 300	87.91 345	93.00 233	94.86 324	78.51 332	99.05 187	86.53 348	97.45 171	98.47 187

MAR-MVS		94.22 166	93.46 184	96.51 112	98.00 125	92.19 118	97.67 126	97.47 202	88.13 341	93.00 233	95.84 274	84.86 199	99.51 118	87.99 308	98.17 146	97.83 250
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		95.01 136	94.59 141	96.26 136	98.89 60	90.68 190	97.24 192	97.73 152	91.80 196	92.93 238	96.62 236	89.13 100	99.14 168	89.21 285	97.78 160	98.97 113

MDTV_nov1_ep13			90.76 292		95.22 341	80.33 445	93.03 445	95.28 385	88.14 340	92.84 239	93.83 380	81.34 274	98.08 314	82.86 397	94.34 267

CostFormer		91.18 315	90.70 298	92.62 369	94.84 364	81.76 430	94.09 414	94.43 422	84.15 415	92.72 240	93.77 384	79.43 314	98.20 298	90.70 246	92.18 308	97.90 241

EPNet		95.20 124	94.56 143	97.14 76	92.80 431	92.68 98	97.85 95	94.87 409	96.64 9	92.46 241	97.80 139	86.23 161	99.65 79	93.72 176	98.62 123	99.10 96
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		90.82 328	89.77 341	93.95 301	94.45 381	87.19 330	90.23 471	95.68 365	86.89 373	92.40 242	92.36 423	80.91 283	97.05 418	81.09 420	93.95 282	97.60 263

RPMNet		88.98 370	87.05 384	94.77 247	94.45 381	87.19 330	90.23 471	98.03 110	77.87 470	92.40 242	87.55 470	80.17 301	99.51 118	68.84 477	93.95 282	97.60 263

EPMVS		90.70 333	89.81 339	93.37 340	94.73 370	84.21 399	93.67 431	88.02 484	89.50 290	92.38 244	93.49 398	77.82 345	97.78 361	86.03 360	92.68 300	98.11 228

baseline1		92.82 237	91.90 247	95.55 196	97.20 174	90.77 185	97.19 200	94.58 417	92.20 182	92.36 245	96.34 249	84.16 212	98.21 297	89.20 286	83.90 418	97.68 257

PatchT		88.87 374	87.42 378	93.22 346	94.08 392	85.10 386	89.51 476	94.64 416	81.92 446	92.36 245	88.15 463	80.05 303	97.01 421	72.43 466	93.65 288	97.54 266

UWE-MVS		89.91 355	89.48 351	91.21 409	95.88 298	78.23 467	94.91 381	90.26 477	89.11 302	92.35 247	94.52 342	68.76 424	97.96 337	83.95 389	95.59 240	97.42 271

ETVMVS		90.52 339	89.14 360	94.67 252	96.81 214	87.85 314	95.91 324	93.97 438	89.71 282	92.34 248	92.48 418	65.41 450	97.96 337	81.37 416	94.27 270	98.21 213

PAPR		94.18 167	93.42 189	96.48 115	97.64 151	91.42 151	95.55 346	97.71 158	88.99 308	92.34 248	95.82 276	89.19 98	99.11 171	86.14 356	97.38 173	98.90 132

SCA		91.84 274	91.18 276	93.83 309	95.59 312	84.95 391	94.72 386	95.58 370	90.82 241	92.25 250	93.69 387	75.80 361	98.10 309	86.20 354	95.98 226	98.45 189

CVMVSNet		91.23 310	91.75 252	89.67 435	95.77 305	74.69 474	96.44 275	94.88 406	85.81 391	92.18 251	97.64 158	79.07 320	95.58 452	88.06 307	95.86 232	98.74 162

AUN-MVS		91.76 276	90.75 294	94.81 242	97.00 194	88.57 281	96.65 261	96.49 317	89.63 285	92.15 252	96.12 261	78.66 330	98.50 269	90.83 240	79.18 441	97.36 273

AdaColmap		94.34 163	93.68 173	96.31 130	98.59 75	91.68 137	96.59 270	97.81 145	89.87 275	92.15 252	97.06 202	83.62 221	99.54 111	89.34 279	98.07 149	97.70 256

GeoE		93.89 187	93.28 192	95.72 186	96.96 198	89.75 227	98.24 43	96.92 286	89.47 291	92.12 254	97.21 191	84.42 205	98.39 281	87.71 318	96.50 214	99.01 107

PatchmatchNet		91.91 271	91.35 265	93.59 328	95.38 325	84.11 401	93.15 442	95.39 378	89.54 288	92.10 255	93.68 389	82.82 243	98.13 304	84.81 376	95.32 248	98.52 179
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		93.24 213	92.48 229	95.51 202	95.70 307	92.39 107	97.86 92	98.66 21	92.30 176	92.09 256	95.37 301	80.49 294	98.40 276	93.95 169	85.86 385	95.75 335

tpm		90.25 346	89.74 344	91.76 398	93.92 395	79.73 454	93.98 415	93.54 445	88.28 334	91.99 257	93.25 406	77.51 347	97.44 401	87.30 338	87.94 364	98.12 222

myMVS_eth3d28		91.52 293	90.97 282	93.17 348	96.91 200	83.24 412	95.61 344	94.96 402	92.24 178	91.98 258	93.28 405	69.31 419	98.40 276	88.71 299	95.68 237	97.88 243

UBG		91.55 290	90.76 292	93.94 303	96.52 253	85.06 387	95.22 367	94.54 419	90.47 263	91.98 258	92.71 412	72.02 394	98.74 234	88.10 306	95.26 250	98.01 235

CNLPA		94.28 164	93.53 179	96.52 108	98.38 90	92.55 103	96.59 270	96.88 291	90.13 272	91.91 260	97.24 189	85.21 190	99.09 176	87.64 327	97.83 158	97.92 240

testing91		91.90 272	91.02 280	94.53 263	96.54 248	86.55 349	95.86 326	95.64 367	91.77 198	91.89 261	93.47 400	69.94 414	98.86 204	90.23 259	93.86 284	98.18 215

BH-RMVSNet		92.72 241	91.97 244	94.97 234	97.16 176	87.99 308	96.15 310	95.60 368	90.62 254	91.87 262	97.15 195	78.41 334	98.57 264	83.16 394	97.60 164	98.36 199

PatchMatch-RL		92.90 231	92.02 242	95.56 194	98.19 110	90.80 182	95.27 363	97.18 248	87.96 343	91.86 263	95.68 287	80.44 295	98.99 192	84.01 387	97.54 165	96.89 292

SDMVSNet		94.17 168	93.61 175	95.86 168	98.09 117	91.37 152	97.35 178	98.20 69	93.18 133	91.79 264	97.28 185	79.13 318	98.93 197	94.61 154	92.84 296	97.28 278

sd_testset		93.10 220	92.45 230	95.05 224	98.09 117	89.21 257	96.89 229	97.64 164	93.18 133	91.79 264	97.28 185	75.35 366	98.65 253	88.99 291	92.84 296	97.28 278

testing99		91.62 284	90.72 297	94.32 276	96.48 257	86.11 366	95.81 330	94.76 411	91.55 203	91.75 266	93.44 401	68.55 427	98.82 210	90.43 253	93.69 286	98.04 233

testing222		90.31 343	88.96 362	94.35 272	96.54 248	87.29 324	95.50 349	93.84 442	90.97 237	91.75 266	92.96 409	62.18 465	98.00 328	82.86 397	94.08 277	97.76 253

OPM-MVS		93.28 212	92.76 212	94.82 240	94.63 374	90.77 185	96.65 261	97.18 248	93.72 105	91.68 268	97.26 188	79.33 316	98.63 256	92.13 211	92.28 304	95.07 376
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tpm2		89.96 354	89.21 357	92.23 381	94.91 361	81.25 433	93.78 425	94.42 423	80.62 457	91.56 269	93.44 401	76.44 356	97.94 343	85.60 366	92.08 312	97.49 267

TAPA-MVS	90.10 7	92.30 255	91.22 274	95.56 194	98.33 92	89.60 234	96.79 243	97.65 162	81.83 447	91.52 270	97.23 190	87.94 123	98.91 201	71.31 470	98.37 136	98.17 218
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvs2		89.77 362	89.93 334	89.31 442	93.68 404	76.37 471	97.64 134	95.90 351	89.84 279	91.49 271	96.26 254	58.77 468	97.10 415	94.65 152	91.13 325	94.46 416

TR-MVS		91.48 296	90.59 304	94.16 287	96.40 263	87.33 323	95.67 338	95.34 384	87.68 357	91.46 272	95.52 296	76.77 352	98.35 284	82.85 399	93.61 290	96.79 295

RPSCF		90.75 330	90.86 286	90.42 426	96.84 208	76.29 472	95.61 344	96.34 325	83.89 419	91.38 273	97.87 125	76.45 355	98.78 216	87.16 342	92.23 305	96.20 310

PLC	91.00 6	94.11 174	93.43 187	96.13 145	98.58 77	91.15 168	96.69 257	97.39 221	87.29 366	91.37 274	96.71 222	88.39 114	99.52 117	87.33 337	97.13 187	97.73 254
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		93.12 219	92.72 217	94.34 274	96.71 228	87.27 326	90.29 470	97.72 154	86.61 378	91.34 275	95.29 303	84.29 210	98.41 275	93.25 187	98.94 109	97.35 275

HQP_MVS		93.78 192	93.43 187	94.82 240	96.21 273	89.99 215	97.74 114	97.51 193	94.85 55	91.34 275	96.64 229	81.32 275	98.60 259	93.02 195	92.23 305	95.86 323

plane_prior3						90.00 213			94.46 80	91.34 275

Fast-Effi-MVS+		93.46 204	92.75 214	95.59 193	96.77 222	90.03 212	96.81 241	97.13 252	88.19 336	91.30 278	94.27 361	86.21 163	98.63 256	87.66 326	96.46 217	98.12 222

EI-MVSNet		93.03 224	92.88 208	93.48 336	95.77 305	86.98 335	96.44 275	97.12 253	90.66 251	91.30 278	97.64 158	86.56 154	98.05 321	89.91 263	90.55 335	95.41 350

MVSTER		93.20 215	92.81 211	94.37 271	96.56 245	89.59 235	97.06 209	97.12 253	91.24 222	91.30 278	95.96 268	82.02 262	98.05 321	93.48 182	90.55 335	95.47 345

ADS-MVSNet2		89.45 366	88.59 368	92.03 385	95.86 299	82.26 426	90.93 466	94.32 430	83.23 432	91.28 281	91.81 433	79.01 325	95.99 441	79.52 429	91.39 321	97.84 248

ADS-MVSNet		89.89 357	88.68 367	93.53 332	95.86 299	84.89 392	90.93 466	95.07 396	83.23 432	91.28 281	91.81 433	79.01 325	97.85 352	79.52 429	91.39 321	97.84 248

testing11		91.68 280	90.75 294	94.47 266	96.53 250	86.56 348	95.76 334	94.51 421	91.10 234	91.24 283	93.59 395	68.59 426	98.86 204	91.10 235	94.29 269	98.00 236

nrg030		94.05 177	93.31 191	96.27 135	95.22 341	94.59 34	98.34 30	97.46 204	92.93 148	91.21 284	96.64 229	87.23 146	98.22 296	94.99 129	85.80 386	95.98 322

Effi-MVS+-dtu		93.08 221	93.21 196	92.68 368	96.02 296	83.25 411	97.14 205	96.72 300	93.85 102	91.20 285	93.44 401	83.08 233	98.30 290	91.69 224	95.73 235	96.50 303

VPNet		92.23 260	91.31 268	94.99 230	95.56 314	90.96 173	97.22 198	97.86 136	92.96 147	90.96 286	96.62 236	75.06 367	98.20 298	91.90 215	83.65 420	95.80 329

JIA-IIPM		88.26 381	87.04 385	91.91 388	93.52 411	81.42 432	89.38 477	94.38 426	80.84 454	90.93 287	80.74 486	79.22 317	97.92 346	82.76 401	91.62 316	96.38 307

MonoMVSNet		91.92 270	91.77 250	92.37 372	92.94 427	83.11 414	97.09 208	95.55 372	92.91 149	90.85 288	94.55 340	81.27 277	96.52 434	93.01 197	87.76 366	97.47 269

WB-MVSnew		89.88 358	89.56 348	90.82 418	94.57 378	83.06 415	95.65 342	92.85 454	87.86 348	90.83 289	94.10 370	79.66 311	96.88 426	76.34 447	94.19 272	92.54 452

test-LLR		91.42 298	91.19 275	92.12 383	94.59 375	80.66 439	94.29 408	92.98 452	91.11 232	90.76 290	92.37 420	79.02 323	98.07 318	88.81 296	96.74 202	97.63 258

test-mter		90.19 350	89.54 349	92.12 383	94.59 375	80.66 439	94.29 408	92.98 452	87.68 357	90.76 290	92.37 420	67.67 431	98.07 318	88.81 296	96.74 202	97.63 258

ACMM	89.79 8	92.96 227	92.50 228	94.35 272	96.30 271	88.71 275	97.58 141	97.36 228	91.40 215	90.53 292	96.65 228	79.77 308	98.75 232	91.24 233	91.64 315	95.59 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
F-COLMAP		93.58 198	92.98 204	95.37 211	98.40 87	88.98 269	97.18 201	97.29 237	87.75 355	90.49 293	97.10 200	85.21 190	99.50 121	86.70 347	96.72 204	97.63 258

TESTMET0.1,1		90.06 352	89.42 352	91.97 386	94.41 383	80.62 441	94.29 408	91.97 467	87.28 367	90.44 294	92.47 419	68.79 423	97.67 371	88.50 303	96.60 209	97.61 262

FIs		94.09 175	93.70 172	95.27 215	95.70 307	92.03 123	98.10 57	98.68 18	93.36 125	90.39 295	96.70 224	87.63 132	97.94 343	92.25 205	90.50 337	95.84 326

GA-MVS		91.38 300	90.31 313	94.59 255	94.65 373	87.62 319	94.34 404	96.19 342	90.73 245	90.35 296	93.83 380	71.84 396	97.96 337	87.22 339	93.61 290	98.21 213

LS3D		93.57 200	92.61 222	96.47 116	97.59 157	91.61 139	97.67 126	97.72 154	85.17 402	90.29 297	98.34 75	84.60 201	99.73 61	83.85 392	98.27 141	98.06 232

FC-MVSNet-test		93.94 184	93.57 176	95.04 226	95.48 318	91.45 150	98.12 56	98.71 13	93.37 123	90.23 298	96.70 224	87.66 129	97.85 352	91.49 227	90.39 338	95.83 327

HQP-NCC					95.86 299		96.65 261		93.55 111	90.14 299

ACMP_Plane					95.86 299		96.65 261		93.55 111	90.14 299

HQP4-MVS										90.14 299			98.50 269			95.78 331

HQP-MVS		93.19 216	92.74 215	94.54 262	95.86 299	89.33 251	96.65 261	97.39 221	93.55 111	90.14 299	95.87 272	80.95 281	98.50 269	92.13 211	92.10 310	95.78 331

UniMVSNet_NR-MVSNet		93.37 209	92.67 218	95.47 208	95.34 330	92.83 90	97.17 202	98.58 27	92.98 146	90.13 303	95.80 277	88.37 116	97.85 352	91.71 222	83.93 415	95.73 337

DU-MVS		92.90 231	92.04 240	95.49 205	94.95 356	92.83 90	97.16 203	98.24 63	93.02 140	90.13 303	95.71 284	83.47 222	97.85 352	91.71 222	83.93 415	95.78 331

LPG-MVS_test		92.94 229	92.56 223	94.10 289	96.16 283	88.26 294	97.65 130	97.46 204	91.29 217	90.12 305	97.16 193	79.05 321	98.73 236	92.25 205	91.89 313	95.31 360

LGP-MVS_train				94.10 289	96.16 283	88.26 294		97.46 204	91.29 217	90.12 305	97.16 193	79.05 321	98.73 236	92.25 205	91.89 313	95.31 360

UniMVSNet (Re)		93.31 211	92.55 224	95.61 192	95.39 324	93.34 72	97.39 174	98.71 13	93.14 136	90.10 307	94.83 326	87.71 128	98.03 325	91.67 225	83.99 414	95.46 346

mvs_anonymous		93.82 190	93.74 171	94.06 291	96.44 261	85.41 378	95.81 330	97.05 270	89.85 278	90.09 308	96.36 248	87.44 141	97.75 366	93.97 168	96.69 205	99.02 104

test_djsdf		93.07 222	92.76 212	94.00 295	93.49 413	88.70 276	98.22 46	97.57 178	91.42 213	90.08 309	95.55 294	82.85 242	97.92 346	94.07 166	91.58 317	95.40 353

dp		88.90 373	88.26 373	90.81 419	94.58 377	76.62 470	92.85 448	94.93 403	85.12 403	90.07 310	93.07 407	75.81 360	98.12 307	80.53 424	87.42 371	97.71 255

PS-MVSNAJss		93.74 193	93.51 182	94.44 268	93.91 396	89.28 255	97.75 111	97.56 186	92.50 168	89.94 311	96.54 239	88.65 109	98.18 301	93.83 175	90.90 331	95.86 323

UniMVSNet_ETH3D		91.34 305	90.22 321	94.68 251	94.86 363	87.86 313	97.23 196	97.46 204	87.99 342	89.90 312	96.92 213	66.35 442	98.23 295	90.30 257	90.99 329	97.96 237

CLD-MVS		92.98 226	92.53 226	94.32 276	96.12 288	89.20 258	95.28 361	97.47 202	92.66 160	89.90 312	95.62 290	80.58 292	98.40 276	92.73 200	92.40 303	95.38 355
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		87.82 384	85.61 397	94.44 268	94.46 380	89.27 256	91.21 464	84.61 493	80.88 453	89.89 314	74.98 489	71.50 398	97.53 393	85.75 365	97.21 183	96.51 302

1112_ss		93.37 209	92.42 231	96.21 140	97.05 187	90.99 171	96.31 296	96.72 300	86.87 374	89.83 315	96.69 226	86.51 156	99.14 168	88.12 305	93.67 287	98.50 182

BH-untuned		92.94 229	92.62 221	93.92 307	97.22 172	86.16 361	96.40 285	96.25 337	90.06 273	89.79 316	96.17 258	83.19 229	98.35 284	87.19 340	97.27 181	97.24 280

VortexMVS		92.88 233	92.64 219	93.58 329	96.58 240	87.53 321	96.93 224	97.28 240	92.78 158	89.75 317	94.99 316	82.73 245	97.76 364	94.60 155	88.16 362	95.46 346

V42		91.58 288	90.87 285	93.73 314	94.05 393	88.50 286	97.32 182	96.97 278	88.80 320	89.71 318	94.33 356	82.54 250	98.05 321	89.01 290	85.07 398	94.64 413

Baseline_NR-MVSNet		91.20 312	90.62 302	92.95 356	93.83 399	88.03 306	97.01 215	95.12 394	88.42 331	89.70 319	95.13 313	83.47 222	97.44 401	89.66 271	83.24 423	93.37 440

v144192		91.06 318	90.28 315	93.39 339	93.66 405	87.23 329	96.83 237	97.07 264	87.43 362	89.69 320	94.28 360	81.48 272	98.00 328	87.18 341	84.92 402	94.93 384

v1144		91.37 302	90.60 303	93.68 321	93.89 397	88.23 296	96.84 236	97.03 274	88.37 332	89.69 320	94.39 350	82.04 261	97.98 330	87.80 313	85.37 391	94.84 393

Test_1112_low_res		92.84 236	91.84 249	95.85 169	97.04 189	89.97 219	95.53 348	96.64 308	85.38 397	89.65 322	95.18 310	85.86 170	99.10 173	87.70 319	93.58 292	98.49 184

v1192		91.07 317	90.23 319	93.58 329	93.70 402	87.82 315	96.73 251	97.07 264	87.77 353	89.58 323	94.32 358	80.90 285	97.97 333	86.52 349	85.48 389	94.95 380

v1240		90.70 333	89.85 337	93.23 345	93.51 412	86.80 339	96.61 267	97.02 276	87.16 369	89.58 323	94.31 359	79.55 313	97.98 330	85.52 367	85.44 390	94.90 387

TranMVSNet+NR-MVSNet		92.50 243	91.63 256	95.14 220	94.76 367	92.07 120	97.53 151	98.11 89	92.90 152	89.56 325	96.12 261	83.16 230	97.60 381	89.30 280	83.20 424	95.75 335

v2v482		91.59 286	90.85 288	93.80 311	93.87 398	88.17 302	96.94 222	96.88 291	89.54 288	89.53 326	94.90 322	81.70 270	98.02 326	89.25 283	85.04 400	95.20 368

v1921920		90.85 327	90.03 330	93.29 343	93.55 409	86.96 338	96.74 250	97.04 272	87.36 364	89.52 327	94.34 355	80.23 300	97.97 333	86.27 352	85.21 395	94.94 382

IterMVS-LS		92.29 256	91.94 245	93.34 341	96.25 272	86.97 336	96.57 273	97.05 270	90.67 249	89.50 328	94.80 328	86.59 153	97.64 376	89.91 263	86.11 384	95.40 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cascas		91.20 312	90.08 325	94.58 259	94.97 354	89.16 261	93.65 432	97.59 174	79.90 460	89.40 329	92.92 410	75.36 365	98.36 283	92.14 208	94.75 261	96.23 308

XVG-ACMP-BASELINE		90.93 325	90.21 322	93.09 351	94.31 387	85.89 367	95.33 358	97.26 241	91.06 235	89.38 330	95.44 300	68.61 425	98.60 259	89.46 275	91.05 327	94.79 404

GBi-Net		91.35 303	90.27 316	94.59 255	96.51 254	91.18 164	97.50 154	96.93 282	88.82 317	89.35 331	94.51 343	73.87 378	97.29 411	86.12 357	88.82 354	95.31 360

test1		91.35 303	90.27 316	94.59 255	96.51 254	91.18 164	97.50 154	96.93 282	88.82 317	89.35 331	94.51 343	73.87 378	97.29 411	86.12 357	88.82 354	95.31 360

FMVSNet3		91.78 275	90.69 299	95.03 227	96.53 250	92.27 113	97.02 212	96.93 282	89.79 281	89.35 331	94.65 336	77.01 349	97.47 398	86.12 357	88.82 354	95.35 357

WR-MVS		92.34 252	91.53 260	94.77 247	95.13 349	90.83 181	96.40 285	97.98 120	91.88 195	89.29 334	95.54 295	82.50 251	97.80 359	89.79 267	85.27 394	95.69 338

DP-MVS		92.76 239	91.51 263	96.52 108	98.77 62	90.99 171	97.38 176	96.08 346	82.38 443	89.29 334	97.87 125	83.77 217	99.69 73	81.37 416	96.69 205	98.89 138

BH-w/o		92.14 264	91.75 252	93.31 342	96.99 195	85.73 371	95.67 338	95.69 363	88.73 322	89.26 336	94.82 327	82.97 238	98.07 318	85.26 372	96.32 223	96.13 317

3Dnovator	91.36 5	95.19 127	94.44 152	97.44 58	96.56 245	93.36 71	98.65 16	98.36 38	94.12 92	89.25 337	98.06 98	82.20 258	99.77 52	93.41 185	99.32 70	99.18 84

usedtu_dtu_shiyan1		91.65 281	90.67 300	94.60 253	93.65 407	90.95 174	94.86 382	97.12 253	89.69 283	89.21 338	93.62 392	81.17 278	97.67 371	87.54 330	89.14 349	95.17 373

FE-MVSNET3		91.65 281	90.67 300	94.60 253	93.65 407	90.95 174	94.86 382	97.12 253	89.69 283	89.21 338	93.62 392	81.17 278	97.67 371	87.54 330	89.14 349	95.17 373

tt0805		91.09 316	90.07 328	94.16 287	95.61 311	88.31 291	97.56 145	96.51 316	89.56 287	89.17 340	95.64 289	67.08 439	98.38 282	91.07 236	88.44 360	95.80 329

miper_enhance_ethall		91.54 292	91.01 281	93.15 349	95.35 329	87.07 334	93.97 416	96.90 288	86.79 375	89.17 340	93.43 404	86.55 155	97.64 376	89.97 262	86.93 375	94.74 409

Fast-Effi-MVS+-dtu		92.29 256	91.99 243	93.21 347	95.27 337	85.52 374	97.03 210	96.63 311	92.09 188	89.11 342	95.14 312	80.33 298	98.08 314	87.54 330	94.74 262	96.03 321

WBMVS		90.69 335	89.99 332	92.81 362	96.48 257	85.00 388	95.21 369	96.30 328	89.46 292	89.04 343	94.05 374	72.45 393	97.82 356	89.46 275	87.41 372	95.61 340

XXY-MVS		92.16 262	91.23 273	94.95 236	94.75 368	90.94 176	97.47 163	97.43 216	89.14 301	88.90 344	96.43 244	79.71 309	98.24 294	89.56 273	87.68 367	95.67 339

PCF-MVS	89.48 11	91.56 289	89.95 333	96.36 128	96.60 236	92.52 104	92.51 453	97.26 241	79.41 462	88.90 344	96.56 238	84.04 215	99.55 109	77.01 446	97.30 179	97.01 285
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_ehance_all_eth		91.59 286	91.13 277	92.97 355	95.55 315	86.57 347	94.47 397	96.88 291	87.77 353	88.88 346	94.01 375	86.22 162	97.54 391	89.49 274	86.93 375	94.79 404

SSC-MVS3.2		89.74 363	89.26 356	91.19 412	95.16 344	80.29 447	94.53 392	97.03 274	91.79 197	88.86 347	94.10 370	69.94 414	97.82 356	85.29 370	86.66 380	95.45 348

jajsoiax		92.42 248	91.89 248	94.03 294	93.33 421	88.50 286	97.73 116	97.53 191	92.00 193	88.85 348	96.50 241	75.62 364	98.11 308	93.88 173	91.56 318	95.48 343

eth_miper_zixun_eth		91.02 320	90.59 304	92.34 375	95.33 333	84.35 397	94.10 413	96.90 288	88.56 326	88.84 349	94.33 356	84.08 213	97.60 381	88.77 298	84.37 411	95.06 377

c3_l		91.38 300	90.89 284	92.88 359	95.58 313	86.30 355	94.68 387	96.84 295	88.17 337	88.83 350	94.23 364	85.65 178	97.47 398	89.36 278	84.63 404	94.89 388

mvs_tets		92.31 254	91.76 251	93.94 303	93.41 418	88.29 292	97.63 136	97.53 191	92.04 191	88.76 351	96.45 243	74.62 374	98.09 313	93.91 171	91.48 319	95.45 348

v148		90.99 321	90.38 310	92.81 362	93.83 399	85.80 368	96.78 247	96.68 305	89.45 293	88.75 352	93.93 379	82.96 239	97.82 356	87.83 311	83.25 422	94.80 402

FMVSNet2		91.31 306	90.08 325	94.99 230	96.51 254	92.21 115	97.41 169	96.95 280	88.82 317	88.62 353	94.75 330	73.87 378	97.42 403	85.20 373	88.55 359	95.35 357

PAPM		91.52 293	90.30 314	95.20 217	95.30 336	89.83 224	93.38 438	96.85 294	86.26 385	88.59 354	95.80 277	84.88 198	98.15 303	75.67 451	95.93 228	97.63 258

cl22		91.21 311	90.56 306	93.14 350	96.09 292	86.80 339	94.41 401	96.58 314	87.80 351	88.58 355	93.99 377	80.85 286	97.62 379	89.87 265	86.93 375	94.99 379

3Dnovator+	91.43 4	95.40 111	94.48 150	98.16 18	96.90 202	95.34 17	98.48 25	97.87 132	94.65 72	88.53 356	98.02 103	83.69 218	99.71 67	93.18 189	98.96 108	99.44 61

dmvs_re		90.21 348	89.50 350	92.35 373	95.47 322	85.15 384	95.70 337	94.37 427	90.94 240	88.42 357	93.57 396	74.63 373	95.67 449	82.80 400	89.57 345	96.22 309

anonymousdsp		92.16 262	91.55 259	93.97 299	92.58 436	89.55 239	97.51 153	97.42 218	89.42 294	88.40 358	94.84 325	80.66 290	97.88 351	91.87 217	91.28 323	94.48 415

reproduce_monomvs		91.30 307	91.10 278	91.92 387	96.82 212	82.48 422	97.01 215	97.49 196	94.64 73	88.35 359	95.27 306	70.53 407	98.10 309	95.20 122	84.60 406	95.19 371

WR-MVS_H		92.00 268	91.35 265	93.95 301	95.09 351	89.47 243	98.04 64	98.68 18	91.46 211	88.34 360	94.68 333	85.86 170	97.56 384	85.77 364	84.24 412	94.82 399

v8		91.29 309	90.53 307	93.57 331	94.15 389	88.12 304	97.34 179	97.06 269	88.99 308	88.32 361	94.26 363	83.08 233	98.01 327	87.62 328	83.92 417	94.57 414

ACMP	89.59 10	92.62 242	92.14 237	94.05 292	96.40 263	88.20 300	97.36 177	97.25 243	91.52 208	88.30 362	96.64 229	78.46 333	98.72 241	91.86 218	91.48 319	95.23 367
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		91.04 319	90.23 319	93.49 335	94.12 390	88.16 303	97.32 182	97.08 261	88.26 335	88.29 363	94.22 366	82.17 259	97.97 333	86.45 351	84.12 413	94.33 421

QAPM		93.45 207	92.27 234	96.98 86	96.77 222	92.62 99	98.39 29	98.12 86	84.50 412	88.27 364	97.77 141	82.39 255	99.81 35	85.40 369	98.81 113	98.51 181

Anonymous20231211		90.63 336	89.42 352	94.27 281	98.24 101	89.19 260	98.05 63	97.89 128	79.95 459	88.25 365	94.96 318	72.56 392	98.13 304	89.70 269	85.14 396	95.49 342

CP-MVSNet		91.89 273	91.24 272	93.82 310	95.05 352	88.57 281	97.82 101	98.19 74	91.70 200	88.21 366	95.76 282	81.96 263	97.52 395	87.86 310	84.65 403	95.37 356

DIV-MVS_self_test		90.97 323	90.33 311	92.88 359	95.36 328	86.19 360	94.46 399	96.63 311	87.82 349	88.18 367	94.23 364	82.99 236	97.53 393	87.72 316	85.57 388	94.93 384

IMVS_0404		92.44 246	91.92 246	94.00 295	96.19 277	86.16 361	93.84 424	97.24 244	91.54 204	88.17 368	97.04 203	76.96 351	97.09 416	90.68 247	95.59 240	98.76 155

cl____		90.96 324	90.32 312	92.89 358	95.37 327	86.21 358	94.46 399	96.64 308	87.82 349	88.15 369	94.18 367	82.98 237	97.54 391	87.70 319	85.59 387	94.92 386

tpmvs		89.83 361	89.15 359	91.89 390	94.92 359	80.30 446	93.11 443	95.46 377	86.28 384	88.08 370	92.65 413	80.44 295	98.52 268	81.47 412	89.92 341	96.84 293

PS-CasMVS		91.55 290	90.84 289	93.69 318	94.96 355	88.28 293	97.84 96	98.24 63	91.46 211	88.04 371	95.80 277	79.67 310	97.48 397	87.02 344	84.54 409	95.31 360

MIMVSNet		88.50 378	86.76 388	93.72 316	94.84 364	87.77 316	91.39 460	94.05 435	86.41 381	87.99 372	92.59 416	63.27 458	95.82 446	77.44 440	92.84 296	97.57 265

GG-mvs-BLEND				93.62 326	93.69 403	89.20 258	92.39 455	83.33 495		87.98 373	89.84 450	71.00 403	96.87 427	82.08 408	95.40 247	94.80 402

miper_lstm_enhance		90.50 341	90.06 329	91.83 392	95.33 333	83.74 405	93.86 422	96.70 304	87.56 360	87.79 374	93.81 383	83.45 224	96.92 424	87.39 335	84.62 405	94.82 399

PEN-MVS		91.20 312	90.44 308	93.48 336	94.49 379	87.91 312	97.76 109	98.18 76	91.29 217	87.78 375	95.74 283	80.35 297	97.33 409	85.46 368	82.96 425	95.19 371

ITE_SJBPF				92.43 371	95.34 330	85.37 381		95.92 349	91.47 210	87.75 376	96.39 247	71.00 403	97.96 337	82.36 406	89.86 342	93.97 431

v7n		90.76 329	89.86 336	93.45 338	93.54 410	87.60 320	97.70 124	97.37 226	88.85 314	87.65 377	94.08 373	81.08 280	98.10 309	84.68 378	83.79 419	94.66 412

Patchmtry		88.64 377	87.25 380	92.78 364	94.09 391	86.64 343	89.82 475	95.68 365	80.81 455	87.63 378	92.36 423	80.91 283	97.03 419	78.86 435	85.12 397	94.67 411

testing3		87.67 386	86.88 387	90.05 430	96.14 286	80.71 438	97.10 207	92.85 454	90.15 271	87.54 379	94.55 340	55.70 475	94.10 468	73.77 461	94.10 276	95.35 357

pmmvs4		90.93 325	89.85 337	94.17 284	93.34 420	90.79 183	94.60 389	96.02 347	84.62 410	87.45 380	95.15 311	81.88 267	97.45 400	87.70 319	87.87 365	94.27 425

tpm cat1		88.36 379	87.21 382	91.81 394	95.13 349	80.55 442	92.58 452	95.70 361	74.97 474	87.45 380	91.96 431	78.01 343	98.17 302	80.39 425	88.74 357	96.72 297

FMVSNet1		89.88 358	88.31 371	94.59 255	95.41 323	91.18 164	97.50 154	96.93 282	86.62 377	87.41 382	94.51 343	65.94 447	97.29 411	83.04 396	87.43 370	95.31 360

IterMVS-SCA-FT		90.31 343	89.81 339	91.82 393	95.52 316	84.20 400	94.30 407	96.15 344	90.61 255	87.39 383	94.27 361	75.80 361	96.44 435	87.34 336	86.88 379	94.82 399

MVS		91.71 277	90.44 308	95.51 202	95.20 343	91.59 141	96.04 315	97.45 209	73.44 478	87.36 384	95.60 291	85.42 185	99.10 173	85.97 361	97.46 167	95.83 327

EU-MVSNet		88.72 376	88.90 364	88.20 447	93.15 424	74.21 476	96.63 266	94.22 432	85.18 401	87.32 385	95.97 267	76.16 358	94.98 459	85.27 371	86.17 382	95.41 350

IterMVS		90.15 351	89.67 345	91.61 400	95.48 318	83.72 406	94.33 405	96.12 345	89.99 274	87.31 386	94.15 369	75.78 363	96.27 439	86.97 345	86.89 378	94.83 394
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UWE-MVS-28		86.81 403	86.41 390	88.02 449	92.87 428	74.60 475	95.38 356	86.70 489	88.17 337	87.28 387	94.67 335	70.83 405	93.30 477	67.45 478	94.31 268	96.17 312

pmmvs5		89.86 360	88.87 365	92.82 361	92.86 429	86.23 357	96.26 299	95.39 378	84.24 414	87.12 388	94.51 343	74.27 376	97.36 408	87.61 329	87.57 368	94.86 389

DTE-MVSNet		90.56 337	89.75 343	93.01 353	93.95 394	87.25 327	97.64 134	97.65 162	90.74 244	87.12 388	95.68 287	79.97 305	97.00 422	83.33 393	81.66 431	94.78 406

mvs5depth		86.53 404	85.08 408	90.87 416	88.74 470	82.52 421	91.91 457	94.23 431	86.35 382	87.11 390	93.70 386	66.52 440	97.76 364	81.37 416	75.80 454	92.31 457

Patchmatch-test		89.42 367	87.99 374	93.70 317	95.27 337	85.11 385	88.98 478	94.37 427	81.11 451	87.10 391	93.69 387	82.28 256	97.50 396	74.37 457	94.76 260	98.48 186

IB-MVS	87.33 17	89.91 355	88.28 372	94.79 246	95.26 340	87.70 317	95.12 376	93.95 439	89.35 296	87.03 392	92.49 417	70.74 406	99.19 156	89.18 287	81.37 432	97.49 267
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		91.71 277	91.28 270	92.99 354	93.76 401	83.71 407	96.69 257	95.28 385	93.15 135	87.02 393	95.95 269	83.37 225	97.38 407	79.46 432	96.84 197	97.88 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Syy-MVS		87.13 396	87.02 386	87.47 451	95.16 344	73.21 479	95.00 378	93.93 440	88.55 327	86.96 394	91.99 429	75.90 359	94.00 469	61.59 484	94.11 274	95.20 368

myMVS_eth3d		87.18 395	86.38 391	89.58 436	95.16 344	79.53 457	95.00 378	93.93 440	88.55 327	86.96 394	91.99 429	56.23 474	94.00 469	75.47 453	94.11 274	95.20 368

baseline2		91.63 283	90.86 286	93.94 303	94.33 385	86.32 354	95.92 323	91.64 469	89.37 295	86.94 396	94.69 332	81.62 271	98.69 244	88.64 301	94.57 265	96.81 294

MSDG		91.42 298	90.24 318	94.96 235	97.15 179	88.91 270	93.69 430	96.32 326	85.72 393	86.93 397	96.47 242	80.24 299	98.98 193	80.57 423	95.05 255	96.98 286

test0.0.03 1		89.37 368	88.70 366	91.41 405	92.47 438	85.63 372	95.22 367	92.70 457	91.11 232	86.91 398	93.65 391	79.02 323	93.19 479	78.00 439	89.18 348	95.41 350

COLMAP_ROB	87.81 15	90.40 342	89.28 355	93.79 312	97.95 129	87.13 333	96.92 225	95.89 353	82.83 435	86.88 399	97.18 192	73.77 381	99.29 147	78.44 437	93.62 289	94.95 380
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
D2MVS		91.30 307	90.95 283	92.35 373	94.71 371	85.52 374	96.18 308	98.21 67	88.89 313	86.60 400	93.82 382	79.92 306	97.95 341	89.29 281	90.95 330	93.56 436

SD_0403		90.01 353	90.02 331	89.96 432	95.65 310	76.76 469	95.76 334	96.46 319	90.58 258	86.59 401	96.29 251	82.12 260	94.78 461	73.00 465	93.76 285	98.35 201

OurMVSNet-221017-0		90.51 340	90.19 323	91.44 404	93.41 418	81.25 433	96.98 219	96.28 332	91.68 201	86.55 402	96.30 250	74.20 377	97.98 330	88.96 293	87.40 373	95.09 375

sc_t1		86.48 406	84.10 423	93.63 325	93.45 416	85.76 370	96.79 243	94.71 412	73.06 479	86.45 403	94.35 353	55.13 476	97.95 341	84.38 383	78.55 445	97.18 282

MS-PatchMatch		90.27 345	89.77 341	91.78 396	94.33 385	84.72 394	95.55 346	96.73 299	86.17 387	86.36 404	95.28 305	71.28 400	97.80 359	84.09 386	98.14 147	92.81 446

blended_shiyan8		87.58 388	85.55 398	93.66 323	88.76 469	88.54 283	95.21 369	96.29 331	82.81 436	86.25 405	87.73 467	73.70 383	97.58 383	87.81 312	71.42 471	94.85 392

1314		92.81 238	92.03 241	95.14 220	95.33 333	89.52 242	96.04 315	97.44 213	87.72 356	86.25 405	95.33 302	83.84 216	98.79 215	89.26 282	97.05 191	97.11 284

blend_shiyan4		86.87 400	84.61 417	93.67 322	88.87 465	88.70 276	95.17 373	96.30 328	82.80 437	86.16 407	87.11 472	65.12 455	97.55 386	87.73 314	72.21 468	94.75 408

tfpnnormal		89.70 364	88.40 370	93.60 327	95.15 347	90.10 211	97.56 145	98.16 80	87.28 367	86.16 407	94.63 337	77.57 346	98.05 321	74.48 455	84.59 407	92.65 449

gbinet_0.2-2-1-0.02		87.30 391	85.16 406	93.69 318	88.70 472	88.81 273	95.14 374	96.20 341	83.03 434	86.14 409	87.06 473	71.26 401	97.40 405	87.46 334	71.49 470	94.86 389

pm-mvs1		90.72 332	89.65 347	93.96 300	94.29 388	89.63 232	97.79 107	96.82 296	89.07 303	86.12 410	95.48 299	78.61 331	97.78 361	86.97 345	81.67 430	94.46 416

blended_shiyan6		87.55 389	85.52 399	93.64 324	88.78 467	88.50 286	95.23 366	96.30 328	82.80 437	86.09 411	87.70 468	73.69 384	97.56 384	87.70 319	71.36 472	94.86 389

0.4-1-1-0.1		86.83 401	84.27 420	94.50 264	91.39 446	88.23 296	92.62 451	92.27 463	84.04 417	86.01 412	83.30 482	65.29 452	98.31 288	89.08 289	74.45 460	96.96 290

wanda-best-256-512		87.29 392	85.21 404	93.53 332	88.54 473	88.21 298	94.51 395	96.27 333	82.69 440	85.92 413	86.89 475	73.04 387	97.55 386	87.68 323	71.36 472	94.83 394

FE-blended-shiyan7		87.29 392	85.21 404	93.53 332	88.54 473	88.21 298	94.51 395	96.27 333	82.69 440	85.92 413	86.89 475	73.03 388	97.55 386	87.68 323	71.36 472	94.83 394

usedtu_blend_shiyan5		87.06 398	84.84 412	93.69 318	88.54 473	88.70 276	95.83 328	95.54 373	78.74 465	85.92 413	86.89 475	73.03 388	97.55 386	87.73 314	71.36 472	94.83 394

OpenMVS	89.19 12	92.86 234	91.68 255	96.40 123	95.34 330	92.73 95	98.27 37	98.12 86	84.86 407	85.78 416	97.75 142	78.89 328	99.74 59	87.50 333	98.65 121	96.73 296

LTVRE_ROB	88.41 13	90.99 321	89.92 335	94.19 283	96.18 281	89.55 239	96.31 296	97.09 260	87.88 346	85.67 417	95.91 271	78.79 329	98.57 264	81.50 410	89.98 340	94.44 418
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		87.97 382	87.21 382	90.24 428	92.86 429	80.76 437	96.67 260	94.97 400	91.74 199	85.52 418	95.83 275	62.66 463	94.47 464	76.25 448	88.36 361	95.48 343

AllTest		90.23 347	88.98 361	93.98 297	97.94 130	86.64 343	96.51 274	95.54 373	85.38 397	85.49 419	96.77 220	70.28 409	99.15 165	80.02 427	92.87 294	96.15 315

TestCases				93.98 297	97.94 130	86.64 343		95.54 373	85.38 397	85.49 419	96.77 220	70.28 409	99.15 165	80.02 427	92.87 294	96.15 315

DSMNet-mixed		86.34 410	86.12 395	87.00 455	89.88 458	70.43 481	94.93 380	90.08 478	77.97 469	85.42 421	92.78 411	74.44 375	93.96 471	74.43 456	95.14 251	96.62 300

ppachtmachnet_test		88.35 380	87.29 379	91.53 401	92.45 439	83.57 409	93.75 426	95.97 348	84.28 413	85.32 422	94.18 367	79.00 327	96.93 423	75.71 450	84.99 401	94.10 426

0.4-1-1-0.2		86.27 412	83.62 425	94.20 282	90.38 453	87.69 318	91.04 465	92.52 460	83.43 430	85.22 423	81.49 485	65.31 451	98.29 291	88.90 295	74.30 462	96.64 299

CL-MVSNet_self_test		86.31 411	85.15 407	89.80 434	88.83 466	81.74 431	93.93 419	96.22 338	86.67 376	85.03 424	90.80 441	78.09 340	94.50 462	74.92 454	71.86 469	93.15 442

our_test_3		88.78 375	87.98 375	91.20 411	92.45 439	82.53 420	93.61 434	95.69 363	85.77 392	84.88 425	93.71 385	79.99 304	96.78 431	79.47 431	86.24 381	94.28 424

MVP-Stereo		90.74 331	90.08 325	92.71 366	93.19 423	88.20 300	95.86 326	96.27 333	86.07 388	84.86 426	94.76 329	77.84 344	97.75 366	83.88 391	98.01 153	92.17 461
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	87.92 14	90.20 349	89.18 358	93.25 344	96.48 257	86.45 352	96.99 218	96.68 305	88.83 316	84.79 427	96.22 255	70.16 411	98.53 267	84.42 382	88.04 363	94.77 407

0.3-1-1-0.015		86.11 416	83.37 426	94.34 274	90.58 452	88.02 307	91.64 459	92.45 461	83.56 427	84.46 428	81.84 483	62.73 462	98.31 288	88.98 292	74.09 463	96.70 298

NR-MVSNet		92.34 252	91.27 271	95.53 197	94.95 356	93.05 82	97.39 174	98.07 98	92.65 161	84.46 428	95.71 284	85.00 195	97.77 363	89.71 268	83.52 421	95.78 331

LF4IMVS		87.94 383	87.25 380	89.98 431	92.38 441	80.05 452	94.38 402	95.25 388	87.59 359	84.34 430	94.74 331	64.31 456	97.66 375	84.83 375	87.45 369	92.23 458

LCM-MVSNet-Re		92.50 243	92.52 227	92.44 370	96.82 212	81.89 429	96.92 225	93.71 444	92.41 172	84.30 431	94.60 338	85.08 192	97.03 419	91.51 226	97.36 174	98.40 195

TransMVSNet (Re)		88.94 371	87.56 377	93.08 352	94.35 384	88.45 289	97.73 116	95.23 389	87.47 361	84.26 432	95.29 303	79.86 307	97.33 409	79.44 433	74.44 461	93.45 439

Anonymous20231206		87.09 397	86.14 394	89.93 433	91.22 448	80.35 444	96.11 311	95.35 381	83.57 426	84.16 433	93.02 408	73.54 385	95.61 450	72.16 467	86.14 383	93.84 433

SixPastTwentyTwo		89.15 369	88.54 369	90.98 414	93.49 413	80.28 448	96.70 255	94.70 413	90.78 242	84.15 434	95.57 292	71.78 397	97.71 369	84.63 379	85.07 398	94.94 382

test_fmvs3		83.21 434	83.02 429	83.78 460	86.77 483	68.34 486	96.76 249	94.91 404	86.49 379	84.14 435	89.48 453	36.04 491	91.73 482	91.86 218	80.77 435	91.26 472

TDRefinement		86.53 404	84.76 414	91.85 391	82.23 491	84.25 398	96.38 287	95.35 381	84.97 406	84.09 436	94.94 319	65.76 448	98.34 287	84.60 380	74.52 459	92.97 443

KD-MVS_self_test		85.95 418	84.95 410	88.96 444	89.55 461	79.11 463	95.13 375	96.42 321	85.91 390	84.07 437	90.48 443	70.03 413	94.82 460	80.04 426	72.94 466	92.94 444

pmmvs6		87.81 385	86.19 393	92.69 367	91.32 447	86.30 355	97.34 179	96.41 322	80.59 458	84.05 438	94.37 352	67.37 434	97.67 371	84.75 377	79.51 440	94.09 428

ACMH	87.59 16	90.53 338	89.42 352	93.87 308	96.21 273	87.92 310	97.24 192	96.94 281	88.45 330	83.91 439	96.27 253	71.92 395	98.62 258	84.43 381	89.43 346	95.05 378
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		87.29 392	85.79 396	91.78 396	94.80 366	87.28 325	95.49 350	95.28 385	84.09 416	83.85 440	91.82 432	62.95 460	94.17 467	78.48 436	85.34 393	93.91 432

USDC		88.94 371	87.83 376	92.27 378	94.66 372	84.96 390	93.86 422	95.90 351	87.34 365	83.40 441	95.56 293	67.43 433	98.19 300	82.64 404	89.67 344	93.66 435

ttmdpeth		85.91 419	84.76 414	89.36 440	89.14 462	80.25 449	95.66 341	93.16 451	83.77 422	83.39 442	95.26 307	66.24 444	95.26 458	80.65 422	75.57 455	92.57 450

Anonymous20240521		86.42 408	85.44 400	89.34 441	90.33 454	79.79 453	96.73 251	95.92 349	83.71 424	83.25 443	91.36 438	63.92 457	96.01 440	78.39 438	85.36 392	92.22 459

KD-MVS_2432*1600		84.81 428	82.64 431	91.31 407	91.07 449	85.34 382	91.22 462	95.75 359	85.56 395	83.09 444	90.21 446	67.21 435	95.89 442	77.18 444	62.48 489	92.69 447

miper_refine_blended		84.81 428	82.64 431	91.31 407	91.07 449	85.34 382	91.22 462	95.75 359	85.56 395	83.09 444	90.21 446	67.21 435	95.89 442	77.18 444	62.48 489	92.69 447

PVSNet_0	82.17 19	85.46 423	83.64 424	90.92 415	95.27 337	79.49 459	90.55 469	95.60 368	83.76 423	83.00 446	89.95 448	71.09 402	97.97 333	82.75 402	60.79 491	95.31 360

tt0320		85.39 424	83.12 427	92.19 382	93.44 417	85.79 369	96.19 307	94.87 409	71.19 482	82.92 447	91.76 435	58.43 469	96.81 429	81.03 421	78.26 446	93.98 430

mvsany_test3		83.59 432	82.44 434	87.03 454	83.80 486	73.82 477	93.70 428	90.92 475	86.42 380	82.51 448	90.26 445	46.76 485	95.71 447	90.82 241	76.76 451	91.57 466

test_0402		86.46 407	84.79 413	91.45 403	95.02 353	85.55 373	96.29 298	94.89 405	80.90 452	82.21 449	93.97 378	68.21 430	97.29 411	62.98 482	88.68 358	91.51 467

Patchmatch-RL test		87.38 390	86.24 392	90.81 419	88.74 470	78.40 466	88.12 485	93.17 449	87.11 370	82.17 450	89.29 454	81.95 264	95.60 451	88.64 301	77.02 449	98.41 194

tt0320-xc		84.83 427	82.33 435	92.31 376	93.66 405	86.20 359	96.17 309	94.06 434	71.26 481	82.04 451	92.22 427	55.07 477	96.72 432	81.49 411	75.04 458	94.02 429

TinyColmap		86.82 402	85.35 403	91.21 409	94.91 361	82.99 416	93.94 418	94.02 437	83.58 425	81.56 452	94.68 333	62.34 464	98.13 304	75.78 449	87.35 374	92.52 453

test20.03		86.14 415	85.40 402	88.35 445	90.12 455	80.06 451	95.90 325	95.20 390	88.59 323	81.29 453	93.62 392	71.43 399	92.65 480	71.26 471	81.17 433	92.34 455

N_pmnet		78.73 445	78.71 445	78.79 465	92.80 431	46.50 504	94.14 412	43.71 506	78.61 466	80.83 454	91.66 436	74.94 371	96.36 437	67.24 479	84.45 410	93.50 437

MVS-HIRNet		82.47 437	81.21 440	86.26 457	95.38 325	69.21 484	88.96 479	89.49 479	66.28 486	80.79 455	74.08 491	68.48 428	97.39 406	71.93 468	95.47 245	92.18 460

PM-MVS		83.48 433	81.86 439	88.31 446	87.83 478	77.59 468	93.43 436	91.75 468	86.91 372	80.63 456	89.91 449	44.42 487	95.84 445	85.17 374	76.73 452	91.50 469

ambc				86.56 456	83.60 488	70.00 483	85.69 487	94.97 400		80.60 457	88.45 459	37.42 490	96.84 428	82.69 403	75.44 457	92.86 445

MIMVSNet1		84.93 426	83.05 428	90.56 424	89.56 460	84.84 393	95.40 354	95.35 381	83.91 418	80.38 458	92.21 428	57.23 471	93.34 476	70.69 473	82.75 428	93.50 437

lessismore_v0				90.45 425	91.96 444	79.09 464		87.19 487		80.32 459	94.39 350	66.31 443	97.55 386	84.00 388	76.84 450	94.70 410

K. test v3		87.64 387	86.75 389	90.32 427	93.02 426	79.48 460	96.61 267	92.08 466	90.66 251	80.25 460	94.09 372	67.21 435	96.65 433	85.96 362	80.83 434	94.83 394

OpenMVS_ROB	81.14 20	84.42 430	82.28 436	90.83 417	90.06 456	84.05 403	95.73 336	94.04 436	73.89 477	80.17 461	91.53 437	59.15 467	97.64 376	66.92 480	89.05 351	90.80 474

EG-PatchMatch MVS		87.02 399	85.44 400	91.76 398	92.67 433	85.00 388	96.08 313	96.45 320	83.41 431	79.52 462	93.49 398	57.10 472	97.72 368	79.34 434	90.87 332	92.56 451

pmmvs-eth3d		86.22 413	84.45 418	91.53 401	88.34 476	87.25 327	94.47 397	95.01 397	83.47 428	79.51 463	89.61 452	69.75 417	95.71 447	83.13 395	76.73 452	91.64 464

FE-MVSNET2		86.36 409	84.68 416	91.39 406	87.67 479	86.47 351	96.21 304	96.41 322	87.87 347	79.31 464	89.64 451	65.29 452	95.58 452	82.42 405	77.28 448	92.14 462

test_vis1_rt		86.16 414	85.06 409	89.46 438	93.47 415	80.46 443	96.41 281	86.61 490	85.22 400	79.15 465	88.64 458	52.41 480	97.06 417	93.08 192	90.57 334	90.87 473

FE-MVSNET		83.85 431	81.97 437	89.51 437	87.19 481	83.19 413	95.21 369	93.17 449	83.45 429	78.90 466	89.05 456	65.46 449	93.84 473	69.71 476	75.56 456	91.51 467

pmmvs3		79.97 443	77.50 447	87.39 452	82.80 490	79.38 461	92.70 450	90.75 476	70.69 483	78.66 467	87.47 471	51.34 481	93.40 475	73.39 463	69.65 478	89.38 478

UnsupCasMVSNet_eth		85.99 417	84.45 418	90.62 423	89.97 457	82.40 425	93.62 433	97.37 226	89.86 276	78.59 468	92.37 420	65.25 454	95.35 457	82.27 407	70.75 476	94.10 426

dmvs_testset		81.38 440	82.60 433	77.73 466	91.74 445	51.49 501	93.03 445	84.21 494	89.07 303	78.28 469	91.25 439	76.97 350	88.53 489	56.57 488	82.24 429	93.16 441

test_f		80.57 441	79.62 443	83.41 461	83.38 489	67.80 488	93.57 435	93.72 443	80.80 456	77.91 470	87.63 469	33.40 492	92.08 481	87.14 343	79.04 443	90.34 476

new-patchmatchnet		83.18 435	81.87 438	87.11 453	86.88 482	75.99 473	93.70 428	95.18 391	85.02 405	77.30 471	88.40 460	65.99 446	93.88 472	74.19 459	70.18 477	91.47 470

usedtu_dtu_shiyan2		80.00 442	76.91 448	89.27 443	82.13 492	79.69 455	95.45 352	94.20 433	72.95 480	75.80 472	87.75 466	44.44 486	94.30 466	70.64 474	68.81 482	93.84 433

UnsupCasMVSNet_bld		82.13 439	79.46 444	90.14 429	88.00 477	82.47 423	90.89 468	96.62 313	78.94 464	75.61 473	84.40 481	56.63 473	96.31 438	77.30 443	66.77 485	91.63 465

ET-MVSNet_ETH3D		91.49 295	90.11 324	95.63 190	96.40 263	91.57 143	95.34 357	93.48 446	90.60 257	75.58 474	95.49 297	80.08 302	96.79 430	94.25 164	89.76 343	98.52 179

new_pmnet		82.89 436	81.12 441	88.18 448	89.63 459	80.18 450	91.77 458	92.57 458	76.79 472	75.56 475	88.23 462	61.22 466	94.48 463	71.43 469	82.92 426	89.87 477

dongtai		69.99 452	69.33 454	71.98 475	88.78 467	61.64 495	89.86 474	59.93 505	75.67 473	74.96 476	85.45 478	50.19 482	81.66 494	43.86 492	55.27 492	72.63 490

APD_test1		79.31 444	77.70 446	84.14 459	89.11 464	69.07 485	92.36 456	91.50 470	69.07 484	73.87 477	92.63 415	39.93 489	94.32 465	70.54 475	80.25 436	89.02 479

CMPMVS	62.92 21	85.62 422	84.92 411	87.74 450	89.14 462	73.12 480	94.17 411	96.80 297	73.98 475	73.65 478	94.93 320	66.36 441	97.61 380	83.95 389	91.28 323	92.48 454
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		82.38 438	80.04 442	89.37 439	87.63 480	82.83 417	95.03 377	93.37 448	73.90 476	73.50 479	94.35 353	62.89 461	93.25 478	73.80 460	65.92 486	92.04 463

WB-MVS		76.77 446	76.63 449	77.18 467	85.32 484	56.82 499	94.53 392	89.39 480	82.66 442	71.35 480	89.18 455	75.03 368	88.88 487	35.42 495	66.79 484	85.84 481

SSC-MVS		76.05 447	75.83 450	76.72 471	84.77 485	56.22 500	94.32 406	88.96 482	81.82 448	70.52 481	88.91 457	74.79 372	88.71 488	33.69 496	64.71 487	85.23 482

YYNet1		85.87 420	84.23 421	90.78 422	92.38 441	82.46 424	93.17 440	95.14 393	82.12 445	67.69 482	92.36 423	78.16 339	95.50 455	77.31 442	79.73 438	94.39 419

kuosan		65.27 458	64.66 460	67.11 478	83.80 486	61.32 496	88.53 482	60.77 504	68.22 485	67.67 483	80.52 487	49.12 483	70.76 500	29.67 498	53.64 494	69.26 492

MDA-MVSNet_test_wron		85.87 420	84.23 421	90.80 421	92.38 441	82.57 419	93.17 440	95.15 392	82.15 444	67.65 484	92.33 426	78.20 336	95.51 454	77.33 441	79.74 437	94.31 423

DeepMVS_CX				74.68 474	90.84 451	64.34 492		81.61 497	65.34 487	67.47 485	88.01 465	48.60 484	80.13 496	62.33 483	73.68 465	79.58 486

LCM-MVSNet		72.55 449	69.39 453	82.03 462	70.81 502	65.42 491	90.12 473	94.36 429	55.02 492	65.88 486	81.72 484	24.16 499	89.96 483	74.32 458	68.10 483	90.71 475

test_method		66.11 457	64.89 459	69.79 476	72.62 500	35.23 508	65.19 495	92.83 456	20.35 498	65.20 487	88.08 464	43.14 488	82.70 493	73.12 464	63.46 488	91.45 471

MDA-MVSNet-bldmvs		85.00 425	82.95 430	91.17 413	93.13 425	83.33 410	94.56 391	95.00 398	84.57 411	65.13 488	92.65 413	70.45 408	95.85 444	73.57 462	77.49 447	94.33 421

PMMVS2		70.19 451	66.92 455	80.01 463	76.35 496	65.67 490	86.22 486	87.58 486	64.83 488	62.38 489	80.29 488	26.78 497	88.49 490	63.79 481	54.07 493	85.88 480

testf1		69.31 453	66.76 456	76.94 469	78.61 494	61.93 493	88.27 483	86.11 491	55.62 490	59.69 490	85.31 479	20.19 501	89.32 484	57.62 485	69.44 480	79.58 486

APD_test2		69.31 453	66.76 456	76.94 469	78.61 494	61.93 493	88.27 483	86.11 491	55.62 490	59.69 490	85.31 479	20.19 501	89.32 484	57.62 485	69.44 480	79.58 486

test_vis3_rt		72.73 448	70.55 451	79.27 464	80.02 493	68.13 487	93.92 420	74.30 501	76.90 471	58.99 492	73.58 492	20.29 500	95.37 456	84.16 384	72.80 467	74.31 489

FPMVS		71.27 450	69.85 452	75.50 472	74.64 497	59.03 497	91.30 461	91.50 470	58.80 489	57.92 493	88.28 461	29.98 495	85.53 492	53.43 489	82.84 427	81.95 485

Gipuma		67.86 456	65.41 458	75.18 473	92.66 434	73.45 478	66.50 494	94.52 420	53.33 493	57.80 494	66.07 494	30.81 493	89.20 486	48.15 491	78.88 444	62.90 494
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		51.94 464	53.82 464	46.29 482	33.73 506	45.30 506	78.32 492	67.24 503	18.02 499	50.93 495	87.05 474	52.99 479	53.11 501	70.76 472	25.29 499	40.46 497

ANet_high		63.94 459	59.58 462	77.02 468	61.24 504	66.06 489	85.66 488	87.93 485	78.53 467	42.94 496	71.04 493	25.42 498	80.71 495	52.60 490	30.83 497	84.28 483

E-PMN		53.28 461	52.56 465	55.43 480	74.43 498	47.13 503	83.63 490	76.30 498	42.23 495	42.59 497	62.22 496	28.57 496	74.40 497	31.53 497	31.51 496	44.78 495

EMVS		52.08 463	51.31 466	54.39 481	72.62 500	45.39 505	83.84 489	75.51 500	41.13 496	40.77 498	59.65 497	30.08 494	73.60 498	28.31 499	29.90 498	44.18 496

MVE	50.73 23	53.25 462	48.81 467	66.58 479	65.34 503	57.50 498	72.49 493	70.94 502	40.15 497	39.28 499	63.51 495	6.89 505	73.48 499	38.29 494	42.38 495	68.76 493
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	53.92 22	58.58 460	55.40 463	68.12 477	51.00 505	48.64 502	78.86 491	87.10 488	46.77 494	35.84 500	74.28 490	8.76 503	86.34 491	42.07 493	73.91 464	69.38 491
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 465	24.57 469	26.74 483	73.98 499	39.89 507	57.88 496	9.80 507	12.27 500	10.39 501	6.97 503	7.03 504	36.44 502	25.43 500	17.39 500	3.89 500

testmvs		13.36 467	16.33 470	4.48 485	5.04 507	2.26 510	93.18 439	3.28 508	2.70 501	8.24 502	21.66 499	2.29 507	2.19 503	7.58 501	2.96 501	9.00 499

test123		13.04 468	15.66 471	5.18 484	4.51 508	3.45 509	92.50 454	1.81 509	2.50 502	7.58 503	20.15 500	3.67 506	2.18 504	7.13 502	1.07 502	9.90 498

EGC-MVSNET		68.77 455	63.01 461	86.07 458	92.49 437	82.24 427	93.96 417	90.96 474	0.71 503	2.62 504	90.89 440	53.66 478	93.46 474	57.25 487	84.55 408	82.51 484

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

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

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		23.24 466	30.99 468	0.00 486	0.00 509	0.00 511	0.00 497	97.63 166	0.00 504	0.00 505	96.88 215	84.38 206	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		7.39 470	9.85 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	88.65 109	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.06 469	10.74 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	96.69 226	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						79.53 457								75.56 452

MSC_two_6792asdad				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

No_MVS				98.86 1	98.67 67	96.94 1		97.93 125					99.86 10	97.68 32	99.67 6	99.77 4

eth-test2					0.00 509

eth-test					0.00 509

OPU-MVS				98.55 3	98.82 61	96.86 3	98.25 40				98.26 87	96.04 2	99.24 151	95.36 120	99.59 19	99.56 40

save fliter					98.91 58	94.28 43	97.02 212	98.02 113	95.35 33

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 10	97.52 41	99.67 6	99.75 8

GSMVS																98.45 189

sam_mvs1												82.76 244				98.45 189

sam_mvs												81.94 265

MTGPA								98.08 93

test_post1							92.81 449				16.58 502	80.53 293	97.68 370	86.20 354

test_post											17.58 501	81.76 268	98.08 314

patchmatchnet-post											90.45 444	82.65 249	98.10 309

MTMP							97.86 92	82.03 496

gm-plane-assit					93.22 422	78.89 465			84.82 408		93.52 397		98.64 254	87.72 316

test9_res														94.81 143	99.38 63	99.45 59

agg_prior2														93.94 170	99.38 63	99.50 52

test_prior4						93.66 63	96.42 280

test_prior				97.23 70	98.67 67	92.99 84		98.00 117					99.41 133			99.29 75

新几何2							95.79 332

旧先验1					98.38 90	93.38 69		97.75 149			98.09 96	92.30 48			99.01 106	99.16 85

无先验							95.79 332	97.87 132	83.87 421				99.65 79	87.68 323		98.89 138

原ACMM2							95.67 338

testdata2													99.67 77	85.96 362

segment_acmp												92.89 33

testdata1							95.26 365		93.10 138

plane_prior7					96.21 273	89.98 217

plane_prior6					96.10 291	90.00 213						81.32 275

plane_prior5								97.51 193					98.60 259	93.02 195	92.23 305	95.86 323

plane_prior4											96.64 229

plane_prior2							97.74 114		94.85 55

plane_prior1					96.14 286

plane_prior						89.99 215	97.24 192		94.06 94						92.16 309

n2								0.00 510

nn								0.00 510

door-mid								91.06 473

test11								97.88 130

door								91.13 472

HQP5-MVS						89.33 251

BP-MVS														92.13 211

HQP3-MVS								97.39 221							92.10 310

HQP2-MVS												80.95 281

NP-MVS					95.99 297	89.81 225					95.87 272

ACMMP++_ref															90.30 339

ACMMP++															91.02 328

Test By Simon												88.73 108

High-resolution multi-view benchmark