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.

test_vis1_n_1920		96.71 141	96.84 121	96.31 273	99.11 107	89.74 349	99.05 69	98.58 155	98.08 12	99.87 1	99.37 40	78.48 355	99.93 28	99.29 14	99.69 61	99.27 135

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 50	99.41 59	97.54 80	98.89 110	99.31 12	98.49 8	99.86 2	99.42 31	96.45 24	99.96 4	99.86 1	99.74 51	99.90 3

test_fmvsm_n_1920		98.87 13	99.01 3	98.45 102	99.42 58	96.43 134	98.96 94	99.36 9	98.63 4	99.86 2	99.51 16	95.91 43	99.97 1	99.72 4	99.75 47	98.94 186

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 54	99.43 57	97.48 82	98.88 115	99.30 13	98.47 9	99.85 4	99.43 30	96.71 17	99.96 4	99.86 1	99.80 24	99.89 4

test_fmvsmconf_n		98.92 10	98.87 6	99.04 58	98.88 130	97.25 97	98.82 133	99.34 10	98.75 2	99.80 5	99.61 4	95.16 73	99.95 7	99.70 5	99.80 24	99.93 1

fmvsm_s_conf0.5_n_a		98.38 50	98.42 28	98.27 116	99.09 109	95.41 184	98.86 121	99.37 8	97.69 24	99.78 6	99.61 4	92.38 119	99.91 42	99.58 10	99.43 110	99.49 99

test_cas_vis1_n_1920		97.38 110	97.36 96	97.45 182	98.95 125	93.25 284	99.00 83	98.53 166	97.70 23	99.77 7	99.35 46	84.71 297	99.85 66	98.57 35	99.66 67	99.26 138

fmvsm_s_conf0.1_n_a		98.08 65	98.04 65	98.21 123	97.66 251	95.39 185	98.89 110	99.17 26	97.24 54	99.76 8	99.67 1	91.13 158	99.88 59	99.39 13	99.41 112	99.35 119

fmvsm_s_conf0.5_n		98.42 47	98.51 21	98.13 131	99.30 71	95.25 194	98.85 125	99.39 7	97.94 17	99.74 9	99.62 3	92.59 116	99.91 42	99.65 6	99.52 98	99.25 140

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 79	98.87 69	97.65 25	99.73 10	99.48 21	97.53 7	99.94 9	98.43 50	99.81 15	99.70 56

test_241102_ONE					99.71 19	99.24 5		98.87 69	97.62 27	99.73 10	99.39 34	97.53 7	99.74 114

SD-MVS		98.64 19	98.68 14	98.53 94	99.33 62	98.36 43	98.90 106	98.85 78	97.28 49	99.72 12	99.39 34	96.63 20	97.60 364	98.17 62	99.85 6	99.64 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
fmvsm_s_conf0.1_n		98.18 64	98.21 54	98.11 135	98.54 165	95.24 195	98.87 118	99.24 17	97.50 35	99.70 13	99.67 1	91.33 153	99.89 50	99.47 12	99.54 95	99.21 146

test_fmvs1_n		95.90 176	95.99 158	95.63 302	98.67 152	88.32 378	99.26 27	98.22 230	96.40 99	99.67 14	99.26 59	73.91 389	99.70 122	99.02 21	99.50 100	98.87 190

test_vis1_n		95.47 197	95.13 197	96.49 257	97.77 240	90.41 339	99.27 26	98.11 254	96.58 91	99.66 15	99.18 76	67.00 402	99.62 141	99.21 16	99.40 115	99.44 110

mvsany_test1		97.69 85	97.70 75	97.66 173	98.24 194	94.18 248	97.53 312	97.53 307	95.52 137	99.66 15	99.51 16	94.30 94	99.56 150	98.38 53	98.62 154	99.23 142

test_fmvs1		96.42 152	96.67 133	95.66 301	98.82 137	88.53 374	98.80 142	98.20 233	96.39 100	99.64 17	99.20 70	80.35 343	99.67 129	99.04 20	99.57 86	98.78 199

IU-MVS					99.71 19	99.23 7		98.64 140	95.28 151	99.63 18				98.35 55	99.81 15	99.83 12

PC_three_1452									95.08 164	99.60 19	99.16 80	97.86 2	98.47 293	97.52 108	99.72 57	99.74 39

test0726					99.72 12	99.25 2	99.06 67	98.88 62	97.62 27	99.56 20	99.50 18	97.42 9

TSAR-MVS + MP.		98.78 14	98.62 16	99.24 39	99.69 24	98.28 48	99.14 54	98.66 135	96.84 75	99.56 20	99.31 53	96.34 28	99.70 122	98.32 56	99.73 54	99.73 44
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPE-MVS		98.92 10	98.67 15	99.65 2	99.58 32	99.20 9	98.42 214	98.91 56	97.58 30	99.54 22	99.46 27	97.10 12	99.94 9	97.64 97	99.84 11	99.83 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 97	99.23 7	99.69 1	98.88 62	97.32 46	99.53 23	99.47 23	97.81 3	99.94 9	98.47 46	99.72 57	99.74 39

test_241102_TWO								98.87 69	97.65 25	99.53 23	99.48 21	97.34 11	99.94 9	98.43 50	99.80 24	99.83 12

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 89	98.58 155	97.62 27	99.45 25	99.46 27	97.42 9	99.94 9	98.47 46	99.81 15	99.69 59
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									97.32 46	99.45 25	99.46 27	97.88 1	99.94 9	98.47 46	99.86 2	99.85 9

test_fmvsmconf0.1_n		98.58 26	98.44 27	98.99 60	97.73 245	97.15 102	98.84 129	98.97 42	98.75 2	99.43 27	99.54 11	93.29 107	99.93 28	99.64 8	99.79 30	99.89 4

MSP-MVS		98.74 16	98.55 20	99.29 32	99.75 3	98.23 50	99.26 27	98.88 62	97.52 33	99.41 28	98.78 137	96.00 39	99.79 101	97.79 84	99.59 82	99.85 9
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
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 10	98.93 50	97.38 43	99.41 28	99.54 11	96.66 18	99.84 70	98.86 25	99.85 6	99.87 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FOURS1					99.82 1	98.66 24	99.69 1	98.95 46	97.46 38	99.39 30

SMA-MVS		98.58 26	98.25 48	99.56 8	99.51 40	99.04 15	98.95 95	98.80 96	93.67 242	99.37 31	99.52 14	96.52 22	99.89 50	98.06 67	99.81 15	99.76 36
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
reproduce_model		98.94 7	98.81 10	99.34 25	99.52 39	98.26 49	98.94 98	98.84 79	98.06 13	99.35 32	99.61 4	96.39 27	99.94 9	98.77 28	99.82 14	99.83 12

balanced_conf03		98.45 43	98.35 35	98.74 76	98.65 156	97.55 78	99.19 44	98.60 146	96.72 85	99.35 32	98.77 139	95.06 78	99.55 157	98.95 22	99.87 1	99.12 162

SteuartSystems-ACMMP		98.90 12	98.75 13	99.36 23	99.22 92	98.43 33	99.10 63	98.87 69	97.38 43	99.35 32	99.40 33	97.78 5	99.87 61	97.77 85	99.85 6	99.78 23
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		98.59 24	98.32 44	99.41 17	99.54 35	98.71 22	99.04 73	98.81 89	95.12 159	99.32 35	99.39 34	96.22 30	99.84 70	97.72 88	99.73 54	99.67 68

reproduce-ours		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 121	98.83 81	98.06 13	99.29 36	99.58 7	96.40 25	99.94 9	98.68 30	99.81 15	99.81 17

our_new_method		98.93 8	98.78 11	99.38 18	99.49 46	98.38 35	98.86 121	98.83 81	98.06 13	99.29 36	99.58 7	96.40 25	99.94 9	98.68 30	99.81 15	99.81 17

dcpmvs_2		98.08 65	98.59 17	96.56 249	99.57 33	90.34 341	99.15 51	98.38 202	96.82 77	99.29 36	99.49 20	95.78 47	99.57 147	98.94 23	99.86 2	99.77 29

test_part2					99.63 29	99.18 10				99.27 39

DeepPCF-MVS	96.37 2	97.93 72	98.48 26	96.30 274	99.00 117	89.54 355	97.43 318	98.87 69	98.16 11	99.26 40	99.38 39	96.12 35	99.64 134	98.30 57	99.77 36	99.72 48

APD-MVS		98.35 55	98.00 67	99.42 16	99.51 40	98.72 21	98.80 142	98.82 84	94.52 195	99.23 41	99.25 64	95.54 54	99.80 91	96.52 150	99.77 36	99.74 39
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_one_0601					99.66 26	99.25 2		98.86 75	97.55 32	99.20 42	99.47 23	97.57 6

APD-MVS_3200maxsize		98.53 35	98.33 43	99.15 49	99.50 42	97.92 67	99.15 51	98.81 89	96.24 105	99.20 42	99.37 40	95.30 64	99.80 91	97.73 87	99.67 64	99.72 48

patch_mono-2		98.36 53	98.87 6	96.82 225	99.53 36	90.68 332	98.64 178	99.29 14	97.88 18	99.19 44	99.52 14	96.80 15	99.97 1	99.11 18	99.86 2	99.82 16

MM		98.51 36	98.24 50	99.33 29	99.12 105	98.14 59	98.93 101	97.02 350	98.96 1	99.17 45	99.47 23	91.97 137	99.94 9	99.85 3	99.69 61	99.91 2

SR-MVS-dyc-post		98.54 34	98.35 35	99.13 51	99.49 46	97.86 68	99.11 60	98.80 96	96.49 94	99.17 45	99.35 46	95.34 62	99.82 79	97.72 88	99.65 70	99.71 52

RE-MVS-def			98.34 39		99.49 46	97.86 68	99.11 60	98.80 96	96.49 94	99.17 45	99.35 46	95.29 65		97.72 88	99.65 70	99.71 52

9.14			98.06 63		99.47 50		98.71 163	98.82 84	94.36 201	99.16 48	99.29 55	96.05 37	99.81 84	97.00 123	99.71 59

ACMMP_NAP		98.61 21	98.30 45	99.55 9	99.62 30	98.95 17	98.82 133	98.81 89	95.80 123	99.16 48	99.47 23	95.37 60	99.92 34	97.89 78	99.75 47	99.79 21

SR-MVS		98.57 30	98.35 35	99.24 39	99.53 36	98.18 54	99.09 64	98.82 84	96.58 91	99.10 50	99.32 51	95.39 58	99.82 79	97.70 93	99.63 75	99.72 48

PGM-MVS		98.49 38	98.23 52	99.27 37	99.72 12	98.08 61	98.99 86	99.49 5	95.43 141	99.03 51	99.32 51	95.56 52	99.94 9	96.80 143	99.77 36	99.78 23

VNet		97.79 79	97.40 94	98.96 65	98.88 130	97.55 78	98.63 181	98.93 50	96.74 82	99.02 52	98.84 130	90.33 174	99.83 72	98.53 38	96.66 219	99.50 94

xiu_mvs_v1_base_debu		97.60 93	97.56 81	97.72 163	98.35 178	95.98 152	97.86 285	98.51 172	97.13 63	99.01 53	98.40 177	91.56 145	99.80 91	98.53 38	98.68 149	97.37 264

xiu_mvs_v1_base		97.60 93	97.56 81	97.72 163	98.35 178	95.98 152	97.86 285	98.51 172	97.13 63	99.01 53	98.40 177	91.56 145	99.80 91	98.53 38	98.68 149	97.37 264

xiu_mvs_v1_base_debi		97.60 93	97.56 81	97.72 163	98.35 178	95.98 152	97.86 285	98.51 172	97.13 63	99.01 53	98.40 177	91.56 145	99.80 91	98.53 38	98.68 149	97.37 264

MVSMamba_PlusPlus		98.31 59	98.19 57	98.67 82	98.96 124	97.36 88	99.24 30	98.57 157	94.81 180	98.99 56	98.90 123	95.22 71	99.59 144	99.15 17	99.84 11	99.07 174

TSAR-MVS + GP.		98.38 50	98.24 50	98.81 73	99.22 92	97.25 97	98.11 253	98.29 222	97.19 58	98.99 56	99.02 103	96.22 30	99.67 129	98.52 44	98.56 158	99.51 92

CS-MVS		98.44 44	98.49 24	98.31 114	99.08 110	96.73 118	99.67 3	98.47 183	97.17 59	98.94 58	99.10 89	95.73 48	99.13 212	98.71 29	99.49 102	99.09 166

HFP-MVS		98.63 20	98.40 29	99.32 31	99.72 12	98.29 47	99.23 32	98.96 45	96.10 112	98.94 58	99.17 77	96.06 36	99.92 34	97.62 98	99.78 34	99.75 37

region2R		98.61 21	98.38 31	99.29 32	99.74 7	98.16 56	99.23 32	98.93 50	96.15 109	98.94 58	99.17 77	95.91 43	99.94 9	97.55 105	99.79 30	99.78 23

HPM-MVS_fast		98.38 50	98.13 58	99.12 53	99.75 3	97.86 68	99.44 9	98.82 84	94.46 198	98.94 58	99.20 70	95.16 73	99.74 114	97.58 101	99.85 6	99.77 29

test_fmvsmconf0.01_n		97.86 74	97.54 84	98.83 72	95.48 368	96.83 113	98.95 95	98.60 146	98.58 5	98.93 62	99.55 9	88.57 216	99.91 42	99.54 11	99.61 78	99.77 29

ACMMPR		98.59 24	98.36 33	99.29 32	99.74 7	98.15 57	99.23 32	98.95 46	96.10 112	98.93 62	99.19 75	95.70 49	99.94 9	97.62 98	99.79 30	99.78 23

DeepC-MVS_fast	96.70 1	98.55 33	98.34 39	99.18 45	99.25 84	98.04 62	98.50 203	98.78 103	97.72 20	98.92 64	99.28 56	95.27 66	99.82 79	97.55 105	99.77 36	99.69 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		98.49 38	98.50 23	98.46 101	99.20 95	97.05 104	99.64 4	98.50 177	97.45 39	98.88 65	99.14 84	95.25 68	99.15 209	98.83 26	99.56 92	99.20 147

MVS_0304		98.23 61	97.91 70	99.21 42	98.06 215	97.96 66	98.58 187	95.51 387	98.58 5	98.87 66	99.26 59	92.99 111	99.95 7	99.62 9	99.67 64	99.73 44

EC-MVSNet		98.21 63	98.11 60	98.49 98	98.34 183	97.26 96	99.61 5	98.43 192	96.78 78	98.87 66	98.84 130	93.72 103	99.01 233	98.91 24	99.50 100	99.19 151

EI-MVSNet-Vis-set		98.47 41	98.39 30	98.69 80	99.46 52	96.49 131	98.30 226	98.69 124	97.21 56	98.84 68	99.36 44	95.41 57	99.78 104	98.62 33	99.65 70	99.80 20

MSLP-MVS++		98.56 32	98.57 18	98.55 90	99.26 83	96.80 114	98.71 163	99.05 36	97.28 49	98.84 68	99.28 56	96.47 23	99.40 181	98.52 44	99.70 60	99.47 103

PHI-MVS		98.34 56	98.06 63	99.18 45	99.15 103	98.12 60	99.04 73	99.09 31	93.32 257	98.83 70	99.10 89	96.54 21	99.83 72	97.70 93	99.76 42	99.59 82

GDP-MVS		97.64 89	97.28 99	98.71 79	98.30 191	97.33 89	99.05 69	98.52 169	96.34 102	98.80 71	99.05 101	89.74 184	99.51 164	96.86 140	98.86 143	99.28 134

MVSFormer		97.57 97	97.49 87	97.84 150	98.07 212	95.76 171	99.47 7	98.40 196	94.98 169	98.79 72	98.83 132	92.34 120	98.41 306	96.91 128	99.59 82	99.34 121

lupinMVS		97.44 105	97.22 104	98.12 134	98.07 212	95.76 171	97.68 301	97.76 286	94.50 196	98.79 72	98.61 155	92.34 120	99.30 192	97.58 101	99.59 82	99.31 127

CDPH-MVS		97.94 71	97.49 87	99.28 35	99.47 50	98.44 31	97.91 275	98.67 132	92.57 289	98.77 74	98.85 129	95.93 42	99.72 116	95.56 184	99.69 61	99.68 64

CNVR-MVS		98.78 14	98.56 19	99.45 15	99.32 65	98.87 19	98.47 206	98.81 89	97.72 20	98.76 75	99.16 80	97.05 13	99.78 104	98.06 67	99.66 67	99.69 59

EI-MVSNet-UG-set		98.41 48	98.34 39	98.61 86	99.45 55	96.32 141	98.28 229	98.68 127	97.17 59	98.74 76	99.37 40	95.25 68	99.79 101	98.57 35	99.54 95	99.73 44

diffmvs		97.58 96	97.40 94	98.13 131	98.32 189	95.81 170	98.06 259	98.37 204	96.20 107	98.74 76	98.89 125	91.31 155	99.25 196	98.16 63	98.52 160	99.34 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		98.43 46	98.12 59	99.34 25	99.72 12	98.38 35	99.09 64	98.82 84	95.71 129	98.73 78	99.06 100	95.27 66	99.93 28	97.07 122	99.63 75	99.72 48

UA-Net		97.96 69	97.62 77	98.98 62	98.86 133	97.47 84	98.89 110	99.08 32	96.67 88	98.72 79	99.54 11	93.15 109	99.81 84	94.87 204	98.83 145	99.65 72

h-mvs33		96.17 163	95.62 176	97.81 154	99.03 113	94.45 234	98.64 178	98.75 109	97.48 36	98.67 80	98.72 147	89.76 182	99.86 65	97.95 72	81.59 391	99.11 164

hse-mvs2		95.71 185	95.30 191	96.93 217	98.50 167	93.53 269	98.36 216	98.10 257	97.48 36	98.67 80	97.99 217	89.76 182	99.02 231	97.95 72	80.91 396	98.22 237

ZD-MVS					99.46 52	98.70 23		98.79 101	93.21 262	98.67 80	98.97 110	95.70 49	99.83 72	96.07 162	99.58 85

旧先验2							97.57 311		91.30 330	98.67 80			99.80 91	95.70 181

PS-MVSNAJ		97.73 81	97.77 72	97.62 175	98.68 151	95.58 175	97.34 327	98.51 172	97.29 48	98.66 84	97.88 228	94.51 87	99.90 48	97.87 79	99.17 127	97.39 262

xiu_mvs_v2_base		97.66 88	97.70 75	97.56 179	98.61 160	95.46 182	97.44 316	98.46 184	97.15 61	98.65 85	98.15 204	94.33 93	99.80 91	97.84 82	98.66 153	97.41 260

LFMVS		95.86 178	94.98 206	98.47 100	98.87 132	96.32 141	98.84 129	96.02 379	93.40 254	98.62 86	99.20 70	74.99 383	99.63 137	97.72 88	97.20 204	99.46 107

HPM-MVS		98.36 53	98.10 62	99.13 51	99.74 7	97.82 72	99.53 6	98.80 96	94.63 188	98.61 87	98.97 110	95.13 75	99.77 109	97.65 96	99.83 13	99.79 21
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testdata				98.26 119	99.20 95	95.36 187		98.68 127	91.89 311	98.60 88	99.10 89	94.44 92	99.82 79	94.27 228	99.44 109	99.58 86

CP-MVS		98.57 30	98.36 33	99.19 43	99.66 26	97.86 68	99.34 16	98.87 69	95.96 115	98.60 88	99.13 85	96.05 37	99.94 9	97.77 85	99.86 2	99.77 29

jason		97.32 113	97.08 110	98.06 139	97.45 271	95.59 174	97.87 283	97.91 280	94.79 181	98.55 90	98.83 132	91.12 159	99.23 199	97.58 101	99.60 80	99.34 121
jason: jason.
MCST-MVS		98.65 18	98.37 32	99.48 13	99.60 31	98.87 19	98.41 215	98.68 127	97.04 67	98.52 91	98.80 135	96.78 16	99.83 72	97.93 74	99.61 78	99.74 39

BP-MVS1		97.82 77	97.51 86	98.76 75	98.25 193	97.39 87	99.15 51	97.68 289	96.69 86	98.47 92	99.10 89	90.29 175	99.51 164	98.60 34	99.35 119	99.37 117

XVS		98.70 17	98.49 24	99.34 25	99.70 22	98.35 44	99.29 22	98.88 62	97.40 40	98.46 93	99.20 70	95.90 45	99.89 50	97.85 80	99.74 51	99.78 23

X-MVStestdata		94.06 300	92.30 324	99.34 25	99.70 22	98.35 44	99.29 22	98.88 62	97.40 40	98.46 93	43.50 420	95.90 45	99.89 50	97.85 80	99.74 51	99.78 23

MG-MVS		97.81 78	97.60 78	98.44 104	99.12 105	95.97 157	97.75 296	98.78 103	96.89 74	98.46 93	99.22 67	93.90 102	99.68 128	94.81 208	99.52 98	99.67 68

test_fmvsmvis_n_1920		98.44 44	98.51 21	98.23 122	98.33 186	96.15 148	98.97 89	99.15 28	98.55 7	98.45 96	99.55 9	94.26 96	99.97 1	99.65 6	99.66 67	98.57 221

NCCC		98.61 21	98.35 35	99.38 18	99.28 80	98.61 26	98.45 207	98.76 107	97.82 19	98.45 96	98.93 119	96.65 19	99.83 72	97.38 114	99.41 112	99.71 52

MVS_Test		97.28 114	97.00 113	98.13 131	98.33 186	95.97 157	98.74 154	98.07 264	94.27 203	98.44 98	98.07 209	92.48 117	99.26 195	96.43 153	98.19 176	99.16 157

MVS_111021_LR		98.34 56	98.23 52	98.67 82	99.27 81	96.90 110	97.95 270	99.58 3	97.14 62	98.44 98	99.01 107	95.03 79	99.62 141	97.91 76	99.75 47	99.50 94

ETV-MVS		97.96 69	97.81 71	98.40 109	98.42 171	97.27 92	98.73 158	98.55 162	96.84 75	98.38 100	97.44 268	95.39 58	99.35 186	97.62 98	98.89 139	98.58 220

test2506		94.44 272	93.91 269	96.04 283	99.02 114	88.99 366	99.06 67	79.47 425	96.96 71	98.36 101	99.26 59	77.21 367	99.52 163	96.78 144	99.04 130	99.59 82

VDDNet		95.36 208	94.53 227	97.86 149	98.10 211	95.13 201	98.85 125	97.75 287	90.46 347	98.36 101	99.39 34	73.27 391	99.64 134	97.98 71	96.58 222	98.81 195

mPP-MVS		98.51 36	98.26 47	99.25 38	99.75 3	98.04 62	99.28 24	98.81 89	96.24 105	98.35 103	99.23 65	95.46 55	99.94 9	97.42 112	99.81 15	99.77 29

DELS-MVS		98.40 49	98.20 55	98.99 60	99.00 117	97.66 73	97.75 296	98.89 59	97.71 22	98.33 104	98.97 110	94.97 80	99.88 59	98.42 52	99.76 42	99.42 114
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
MVS_111021_HR		98.47 41	98.34 39	98.88 71	99.22 92	97.32 90	97.91 275	99.58 3	97.20 57	98.33 104	99.00 108	95.99 40	99.64 134	98.05 69	99.76 42	99.69 59

ZNCC-MVS		98.49 38	98.20 55	99.35 24	99.73 11	98.39 34	99.19 44	98.86 75	95.77 125	98.31 106	99.10 89	95.46 55	99.93 28	97.57 104	99.81 15	99.74 39

HPM-MVS++		98.58 26	98.25 48	99.55 9	99.50 42	99.08 11	98.72 162	98.66 135	97.51 34	98.15 107	98.83 132	95.70 49	99.92 34	97.53 107	99.67 64	99.66 71

mvsmamba		97.25 116	96.99 114	98.02 141	98.34 183	95.54 179	99.18 48	97.47 313	95.04 165	98.15 107	98.57 163	89.46 191	99.31 191	97.68 95	99.01 133	99.22 144

新几何1				99.16 48	99.34 60	98.01 64		98.69 124	90.06 355	98.13 109	98.95 117	94.60 85	99.89 50	91.97 297	99.47 105	99.59 82

API-MVS		97.41 108	97.25 101	97.91 147	98.70 147	96.80 114	98.82 133	98.69 124	94.53 193	98.11 110	98.28 192	94.50 90	99.57 147	94.12 233	99.49 102	97.37 264

ECVR-MVS		95.95 171	95.71 170	96.65 235	99.02 114	90.86 327	99.03 76	91.80 412	96.96 71	98.10 111	99.26 59	81.31 330	99.51 164	96.90 131	99.04 130	99.59 82

CPTT-MVS		97.72 82	97.32 98	98.92 67	99.64 28	97.10 103	99.12 58	98.81 89	92.34 297	98.09 112	99.08 98	93.01 110	99.92 34	96.06 165	99.77 36	99.75 37

test12				99.18 45	99.16 101	98.19 53		98.53 166		98.07 113		95.13 75	99.72 116		99.56 92	99.63 76

RRT-MVS		97.03 128	96.78 125	97.77 159	97.90 232	94.34 241	99.12 58	98.35 207	95.87 120	98.06 114	98.70 148	86.45 263	99.63 137	98.04 70	98.54 159	99.35 119

test222					99.23 91	97.17 101	97.40 319	98.66 135	88.68 374	98.05 115	98.96 115	94.14 98			99.53 97	99.61 78

DP-MVS Recon		97.86 74	97.46 90	99.06 57	99.53 36	98.35 44	98.33 219	98.89 59	92.62 286	98.05 115	98.94 118	95.34 62	99.65 132	96.04 166	99.42 111	99.19 151

Vis-MVSNet		97.42 107	97.11 108	98.34 112	98.66 153	96.23 144	99.22 36	99.00 39	96.63 90	98.04 117	99.21 68	88.05 232	99.35 186	96.01 168	99.21 124	99.45 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 173	95.78 164	96.41 266	98.99 120	90.12 343	99.04 73	92.45 411	96.99 70	98.03 118	99.27 58	81.40 329	99.48 173	96.87 137	99.04 130	99.63 76

baseline		97.64 89	97.44 92	98.25 120	98.35 178	96.20 145	99.00 83	98.32 212	96.33 104	98.03 118	99.17 77	91.35 152	99.16 206	98.10 65	98.29 175	99.39 115

test_yl		97.22 117	96.78 125	98.54 92	98.73 142	96.60 124	98.45 207	98.31 214	94.70 182	98.02 120	98.42 175	90.80 165	99.70 122	96.81 141	96.79 216	99.34 121

DCV-MVSNet		97.22 117	96.78 125	98.54 92	98.73 142	96.60 124	98.45 207	98.31 214	94.70 182	98.02 120	98.42 175	90.80 165	99.70 122	96.81 141	96.79 216	99.34 121

MTAPA		98.58 26	98.29 46	99.46 14	99.76 2	98.64 25	98.90 106	98.74 111	97.27 53	98.02 120	99.39 34	94.81 83	99.96 4	97.91 76	99.79 30	99.77 29

sss		97.39 109	96.98 116	98.61 86	98.60 161	96.61 123	98.22 235	98.93 50	93.97 217	98.01 123	98.48 170	91.98 135	99.85 66	96.45 152	98.15 177	99.39 115

alignmvs		97.56 98	97.07 111	99.01 59	98.66 153	98.37 42	98.83 131	98.06 269	96.74 82	98.00 124	97.65 250	90.80 165	99.48 173	98.37 54	96.56 223	99.19 151

OMC-MVS		97.55 99	97.34 97	98.20 125	99.33 62	95.92 164	98.28 229	98.59 150	95.52 137	97.97 125	99.10 89	93.28 108	99.49 168	95.09 199	98.88 140	99.19 151

VDD-MVS		95.82 181	95.23 193	97.61 176	98.84 136	93.98 252	98.68 170	97.40 322	95.02 167	97.95 126	99.34 50	74.37 388	99.78 104	98.64 32	96.80 215	99.08 170

casdiffmvs		97.63 91	97.41 93	98.28 115	98.33 186	96.14 149	98.82 133	98.32 212	96.38 101	97.95 126	99.21 68	91.23 157	99.23 199	98.12 64	98.37 169	99.48 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		96.73 140	96.60 135	97.12 204	99.25 84	95.35 189	98.26 232	99.26 15	94.28 202	97.94 128	97.46 265	92.74 114	99.81 84	96.88 134	93.32 288	96.20 354

PVSNet_Blended		97.38 110	97.12 107	98.14 128	99.25 84	95.35 189	97.28 332	99.26 15	93.13 267	97.94 128	98.21 200	92.74 114	99.81 84	96.88 134	99.40 115	99.27 135

DPM-MVS		97.55 99	96.99 114	99.23 41	99.04 112	98.55 27	97.17 342	98.35 207	94.85 179	97.93 130	98.58 160	95.07 77	99.71 121	92.60 276	99.34 120	99.43 112

MP-MVS		98.33 58	98.01 66	99.28 35	99.75 3	98.18 54	99.22 36	98.79 101	96.13 110	97.92 131	99.23 65	94.54 86	99.94 9	96.74 146	99.78 34	99.73 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDTV_nov1_ep13_2view						84.26 393	96.89 362		90.97 339	97.90 132		89.89 181		93.91 240		99.18 156

test_prior2							97.80 292		96.12 111	97.89 133	98.69 149	95.96 41		96.89 132	99.60 80

mamv4		97.13 124	98.11 60	94.17 353	98.97 123	83.70 395	98.66 175	98.71 119	94.63 188	97.83 134	98.90 123	96.25 29	99.55 157	99.27 15	99.76 42	99.27 135

原ACMM1				98.65 84	99.32 65	96.62 121		98.67 132	93.27 261	97.81 135	98.97 110	95.18 72	99.83 72	93.84 242	99.46 108	99.50 94

114514_t		96.93 132	96.27 147	98.92 67	99.50 42	97.63 75	98.85 125	98.90 57	84.80 394	97.77 136	99.11 87	92.84 112	99.66 131	94.85 205	99.77 36	99.47 103

casdiffmvs_mvg		97.72 82	97.48 89	98.44 104	98.42 171	96.59 126	98.92 103	98.44 188	96.20 107	97.76 137	99.20 70	91.66 143	99.23 199	98.27 61	98.41 168	99.49 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
PMMVS		96.60 144	96.33 145	97.41 186	97.90 232	93.93 253	97.35 326	98.41 194	92.84 279	97.76 137	97.45 267	91.10 161	99.20 203	96.26 158	97.91 184	99.11 164

PVSNet	91.96 18	96.35 156	96.15 151	96.96 215	99.17 97	92.05 305	96.08 380	98.68 127	93.69 238	97.75 139	97.80 238	88.86 211	99.69 127	94.26 229	99.01 133	99.15 158

TEST9					99.31 67	98.50 29	97.92 273	98.73 114	92.63 285	97.74 140	98.68 150	96.20 32	99.80 91

train_agg		97.97 68	97.52 85	99.33 29	99.31 67	98.50 29	97.92 273	98.73 114	92.98 273	97.74 140	98.68 150	96.20 32	99.80 91	96.59 147	99.57 86	99.68 64

FE-MVS		95.62 191	94.90 210	97.78 156	98.37 177	94.92 212	97.17 342	97.38 324	90.95 340	97.73 142	97.70 244	85.32 285	99.63 137	91.18 309	98.33 172	98.79 196

mmtdpeth		93.12 321	92.61 317	94.63 339	97.60 255	89.68 352	99.21 39	97.32 327	94.02 211	97.72 143	94.42 385	77.01 372	99.44 178	99.05 19	77.18 407	94.78 385

CANet		98.05 67	97.76 73	98.90 70	98.73 142	97.27 92	98.35 217	98.78 103	97.37 45	97.72 143	98.96 115	91.53 149	99.92 34	98.79 27	99.65 70	99.51 92

test_8					99.29 76	98.44 31	97.89 281	98.72 116	92.98 273	97.70 145	98.66 153	96.20 32	99.80 91

MP-MVS-pluss		98.31 59	97.92 69	99.49 12	99.72 12	98.88 18	98.43 212	98.78 103	94.10 207	97.69 146	99.42 31	95.25 68	99.92 34	98.09 66	99.80 24	99.67 68
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
sasdasda		97.67 86	97.23 102	98.98 62	98.70 147	98.38 35	99.34 16	98.39 198	96.76 80	97.67 147	97.40 272	92.26 123	99.49 168	98.28 58	96.28 237	99.08 170

canonicalmvs		97.67 86	97.23 102	98.98 62	98.70 147	98.38 35	99.34 16	98.39 198	96.76 80	97.67 147	97.40 272	92.26 123	99.49 168	98.28 58	96.28 237	99.08 170

PVSNet_Blended_VisFu		97.70 84	97.46 90	98.44 104	99.27 81	95.91 165	98.63 181	99.16 27	94.48 197	97.67 147	98.88 126	92.80 113	99.91 42	97.11 120	99.12 128	99.50 94

WTY-MVS		97.37 112	96.92 118	98.72 78	98.86 133	96.89 112	98.31 224	98.71 119	95.26 152	97.67 147	98.56 164	92.21 127	99.78 104	95.89 170	96.85 214	99.48 101

Effi-MVS+		97.12 125	96.69 131	98.39 110	98.19 202	96.72 119	97.37 323	98.43 192	93.71 235	97.65 151	98.02 213	92.20 128	99.25 196	96.87 137	97.79 189	99.19 151

thisisatest0530		96.01 168	95.36 185	97.97 144	98.38 175	95.52 180	98.88 115	94.19 402	94.04 209	97.64 152	98.31 190	83.82 319	99.46 176	95.29 194	97.70 194	98.93 187

tttt0517		96.07 166	95.51 178	97.78 156	98.41 173	94.84 215	99.28 24	94.33 400	94.26 204	97.64 152	98.64 154	84.05 312	99.47 175	95.34 190	97.60 197	99.03 176

HyFIR lowres test		96.90 134	96.49 140	98.14 128	99.33 62	95.56 176	97.38 321	99.65 2	92.34 297	97.61 154	98.20 201	89.29 196	99.10 220	96.97 125	97.60 197	99.77 29

ACMMP		98.23 61	97.95 68	99.09 55	99.74 7	97.62 76	99.03 76	99.41 6	95.98 114	97.60 155	99.36 44	94.45 91	99.93 28	97.14 119	98.85 144	99.70 56
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
MGCFI-Net		97.62 92	97.19 105	98.92 67	98.66 153	98.20 52	99.32 21	98.38 202	96.69 86	97.58 156	97.42 271	92.10 131	99.50 167	98.28 58	96.25 240	99.08 170

agg_prior					99.30 71	98.38 35		98.72 116		97.57 157			99.81 84

tpmrst		95.63 190	95.69 173	95.44 310	97.54 262	88.54 373	96.97 352	97.56 300	93.50 249	97.52 158	96.93 320	89.49 188	99.16 206	95.25 196	96.42 228	98.64 214

MDTV_nov1_ep13			95.40 180		97.48 266	88.34 377	96.85 365	97.29 329	93.74 231	97.48 159	97.26 281	89.18 199	99.05 224	91.92 298	97.43 201

FA-MVS(test-final)		96.41 155	95.94 159	97.82 153	98.21 198	95.20 197	97.80 292	97.58 297	93.21 262	97.36 160	97.70 244	89.47 190	99.56 150	94.12 233	97.99 181	98.71 206

EPMVS		94.99 231	94.48 230	96.52 255	97.22 286	91.75 310	97.23 334	91.66 413	94.11 206	97.28 161	96.81 328	85.70 276	98.84 258	93.04 265	97.28 203	98.97 182

EIA-MVS		97.75 80	97.58 79	98.27 116	98.38 175	96.44 133	99.01 81	98.60 146	95.88 119	97.26 162	97.53 262	94.97 80	99.33 189	97.38 114	99.20 125	99.05 175

IS-MVSNet		97.22 117	96.88 119	98.25 120	98.85 135	96.36 139	99.19 44	97.97 274	95.39 143	97.23 163	98.99 109	91.11 160	98.93 245	94.60 215	98.59 156	99.47 103

EPP-MVSNet		97.46 101	97.28 99	97.99 143	98.64 157	95.38 186	99.33 20	98.31 214	93.61 246	97.19 164	99.07 99	94.05 99	99.23 199	96.89 132	98.43 167	99.37 117

thisisatest0515		95.61 194	94.89 211	97.76 160	98.15 208	95.15 200	96.77 368	94.41 398	92.95 275	97.18 165	97.43 269	84.78 294	99.45 177	94.63 212	97.73 193	98.68 208

CANet_DTU		96.96 131	96.55 137	98.21 123	98.17 207	96.07 151	97.98 268	98.21 231	97.24 54	97.13 166	98.93 119	86.88 255	99.91 42	95.00 202	99.37 118	98.66 212

CHOSEN 1792x2688		97.12 125	96.80 122	98.08 137	99.30 71	94.56 232	98.05 260	99.71 1	93.57 247	97.09 167	98.91 122	88.17 226	99.89 50	96.87 137	99.56 92	99.81 17

PatchT		93.06 322	91.97 328	96.35 270	96.69 321	92.67 296	94.48 404	97.08 342	86.62 382	97.08 168	92.23 404	87.94 234	97.90 350	78.89 401	96.69 218	98.49 224

PatchmatchNet		95.71 185	95.52 177	96.29 275	97.58 257	90.72 331	96.84 366	97.52 308	94.06 208	97.08 168	96.96 316	89.24 198	98.90 251	92.03 294	98.37 169	99.26 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 133	96.40 143	98.45 102	98.69 150	96.90 110	98.66 175	98.68 127	92.40 296	97.07 170	97.96 220	91.54 148	99.75 112	93.68 246	98.92 137	98.69 207
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		97.46 101	97.11 108	98.50 96	99.50 42	96.41 136	98.63 181	98.60 146	95.18 156	97.06 171	98.06 210	94.26 96	99.57 147	93.80 244	98.87 142	99.52 89

TAMVS		97.02 129	96.79 124	97.70 166	98.06 215	95.31 192	98.52 197	98.31 214	93.95 218	97.05 172	98.61 155	93.49 105	98.52 288	95.33 191	97.81 188	99.29 132

CSCG		97.85 76	97.74 74	98.20 125	99.67 25	95.16 198	99.22 36	99.32 11	93.04 271	97.02 173	98.92 121	95.36 61	99.91 42	97.43 111	99.64 74	99.52 89

CDS-MVSNet		96.99 130	96.69 131	97.90 148	98.05 217	95.98 152	98.20 238	98.33 211	93.67 242	96.95 174	98.49 169	93.54 104	98.42 299	95.24 197	97.74 192	99.31 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS-SEG-HR		96.51 149	96.34 144	97.02 210	98.77 140	93.76 258	97.79 294	98.50 177	95.45 140	96.94 175	99.09 96	87.87 237	99.55 157	96.76 145	95.83 251	97.74 250

CR-MVSNet		94.76 246	94.15 250	96.59 245	97.00 300	93.43 272	94.96 394	97.56 300	92.46 290	96.93 176	96.24 347	88.15 227	97.88 354	87.38 363	96.65 220	98.46 226

RPMNet		92.81 324	91.34 334	97.24 193	97.00 300	93.43 272	94.96 394	98.80 96	82.27 401	96.93 176	92.12 405	86.98 253	99.82 79	76.32 406	96.65 220	98.46 226

SCA		95.46 198	95.13 197	96.46 263	97.67 249	91.29 319	97.33 328	97.60 296	94.68 185	96.92 178	97.10 291	83.97 314	98.89 252	92.59 278	98.32 174	99.20 147

PatchMatch-RL		96.59 145	96.03 156	98.27 116	99.31 67	96.51 130	97.91 275	99.06 34	93.72 234	96.92 178	98.06 210	88.50 221	99.65 132	91.77 301	99.00 135	98.66 212

DeepC-MVS	95.98 3	97.88 73	97.58 79	98.77 74	99.25 84	96.93 108	98.83 131	98.75 109	96.96 71	96.89 180	99.50 18	90.46 171	99.87 61	97.84 82	99.76 42	99.52 89
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVG-OURS		96.55 148	96.41 142	96.99 211	98.75 141	93.76 258	97.50 315	98.52 169	95.67 131	96.83 181	99.30 54	88.95 210	99.53 160	95.88 171	96.26 239	97.69 253

AdaColmap		97.15 123	96.70 130	98.48 99	99.16 101	96.69 120	98.01 264	98.89 59	94.44 199	96.83 181	98.68 150	90.69 168	99.76 110	94.36 223	99.29 123	98.98 181

CostFormer		94.95 236	94.73 217	95.60 304	97.28 282	89.06 363	97.53 312	96.89 359	89.66 362	96.82 183	96.72 332	86.05 270	98.95 244	95.53 186	96.13 245	98.79 196

UGNet		96.78 139	96.30 146	98.19 127	98.24 194	95.89 167	98.88 115	98.93 50	97.39 42	96.81 184	97.84 232	82.60 324	99.90 48	96.53 149	99.49 102	98.79 196
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
CNLPA		97.45 104	97.03 112	98.73 77	99.05 111	97.44 86	98.07 258	98.53 166	95.32 149	96.80 185	98.53 165	93.32 106	99.72 116	94.31 227	99.31 122	99.02 177

CHOSEN 280x420		97.18 121	97.18 106	97.20 195	98.81 138	93.27 281	95.78 387	99.15 28	95.25 153	96.79 186	98.11 207	92.29 122	99.07 223	98.56 37	99.85 6	99.25 140

HY-MVS	93.96 8	96.82 138	96.23 150	98.57 88	98.46 170	97.00 105	98.14 248	98.21 231	93.95 218	96.72 187	97.99 217	91.58 144	99.76 110	94.51 219	96.54 224	98.95 185

PAPR		96.84 137	96.24 149	98.65 84	98.72 146	96.92 109	97.36 325	98.57 157	93.33 256	96.67 188	97.57 259	94.30 94	99.56 150	91.05 317	98.59 156	99.47 103

Anonymous20240529		95.10 224	94.22 244	97.75 161	99.01 116	94.26 245	98.87 118	98.83 81	85.79 390	96.64 189	98.97 110	78.73 352	99.85 66	96.27 157	94.89 257	99.12 162

UWE-MVS		94.30 279	93.89 272	95.53 305	97.83 236	88.95 367	97.52 314	93.25 406	94.44 199	96.63 190	97.07 298	78.70 353	99.28 194	91.99 295	97.56 199	98.36 231

thres600view7		95.49 196	94.77 214	97.67 170	98.98 121	95.02 204	98.85 125	96.90 357	95.38 144	96.63 190	96.90 321	84.29 304	99.59 144	88.65 353	96.33 230	98.40 228

thres100view900		95.38 205	94.70 219	97.41 186	98.98 121	94.92 212	98.87 118	96.90 357	95.38 144	96.61 192	96.88 322	84.29 304	99.56 150	88.11 356	96.29 234	97.76 248

Vis-MVSNet (Re-imp)		96.87 135	96.55 137	97.83 151	98.73 142	95.46 182	99.20 42	98.30 220	94.96 171	96.60 193	98.87 127	90.05 178	98.59 283	93.67 248	98.60 155	99.46 107

CVMVSNet		95.43 201	96.04 155	93.57 358	97.93 230	83.62 396	98.12 251	98.59 150	95.68 130	96.56 194	99.02 103	87.51 243	97.51 369	93.56 252	97.44 200	99.60 80

RPSCF		94.87 240	95.40 180	93.26 364	98.89 129	82.06 402	98.33 219	98.06 269	90.30 352	96.56 194	99.26 59	87.09 250	99.49 168	93.82 243	96.32 231	98.24 235

tfpn200view9		95.32 212	94.62 223	97.43 184	98.94 126	94.98 208	98.68 170	96.93 355	95.33 147	96.55 196	96.53 340	84.23 308	99.56 150	88.11 356	96.29 234	97.76 248

thres400		95.38 205	94.62 223	97.65 174	98.94 126	94.98 208	98.68 170	96.93 355	95.33 147	96.55 196	96.53 340	84.23 308	99.56 150	88.11 356	96.29 234	98.40 228

thres200		95.25 215	94.57 225	97.28 192	98.81 138	94.92 212	98.20 238	97.11 340	95.24 155	96.54 198	96.22 351	84.58 301	99.53 160	87.93 361	96.50 226	97.39 262

ab-mvs		96.42 152	95.71 170	98.55 90	98.63 158	96.75 117	97.88 282	98.74 111	93.84 224	96.54 198	98.18 203	85.34 283	99.75 112	95.93 169	96.35 229	99.15 158

Anonymous202405211		95.28 214	94.49 229	97.67 170	99.00 117	93.75 260	98.70 167	97.04 347	90.66 343	96.49 200	98.80 135	78.13 359	99.83 72	96.21 161	95.36 256	99.44 110

ADS-MVSNet2		94.58 258	94.40 238	95.11 320	98.00 221	88.74 370	96.04 381	97.30 328	90.15 353	96.47 201	96.64 337	87.89 235	97.56 367	90.08 329	97.06 207	99.02 177

ADS-MVSNet		95.00 229	94.45 234	96.63 239	98.00 221	91.91 307	96.04 381	97.74 288	90.15 353	96.47 201	96.64 337	87.89 235	98.96 239	90.08 329	97.06 207	99.02 177

Effi-MVS+-dtu		96.29 158	96.56 136	95.51 306	97.89 234	90.22 342	98.80 142	98.10 257	96.57 93	96.45 203	96.66 334	90.81 164	98.91 248	95.72 178	97.99 181	97.40 261

ETVMVS		94.50 266	93.44 299	97.68 169	98.18 204	95.35 189	98.19 241	97.11 340	93.73 232	96.40 204	95.39 374	74.53 385	98.84 258	91.10 311	96.31 232	98.84 193

PLC	95.07 4	97.20 120	96.78 125	98.44 104	99.29 76	96.31 143	98.14 248	98.76 107	92.41 295	96.39 205	98.31 190	94.92 82	99.78 104	94.06 236	98.77 148	99.23 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 292	93.80 278	95.12 319	96.50 330	87.91 383	97.44 316	95.89 385	92.62 286	96.37 206	96.30 346	84.13 311	98.30 320	93.24 258	91.66 309	99.14 160

TAPA-MVS	93.98 7	95.35 209	94.56 226	97.74 162	99.13 104	94.83 217	98.33 219	98.64 140	86.62 382	96.29 207	98.61 155	94.00 101	99.29 193	80.00 397	99.41 112	99.09 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.84 179	95.12 199	98.01 142	98.49 169	95.98 152	98.73 158	97.03 348	95.37 146	96.22 208	98.19 202	89.96 180	99.16 206	94.60 215	87.48 361	98.90 189

tpm2		94.19 287	93.76 283	95.46 309	97.23 285	89.04 364	97.31 330	96.85 363	87.08 381	96.21 209	96.79 329	83.75 320	98.74 269	92.43 286	96.23 242	98.59 218

UBG		95.32 212	94.72 218	97.13 202	98.05 217	93.26 282	97.87 283	97.20 336	94.96 171	96.18 210	95.66 371	80.97 335	99.35 186	94.47 221	97.08 206	98.78 199

F-COLMAP		97.09 127	96.80 122	97.97 144	99.45 55	94.95 211	98.55 195	98.62 145	93.02 272	96.17 211	98.58 160	94.01 100	99.81 84	93.95 238	98.90 138	99.14 160

GeoE		96.58 147	96.07 153	98.10 136	98.35 178	95.89 167	99.34 16	98.12 251	93.12 268	96.09 212	98.87 127	89.71 185	98.97 235	92.95 268	98.08 180	99.43 112

JIA-IIPM		93.35 311	92.49 320	95.92 289	96.48 332	90.65 333	95.01 393	96.96 353	85.93 388	96.08 213	87.33 410	87.70 241	98.78 267	91.35 307	95.58 254	98.34 232

BH-RMVSNet		95.92 175	95.32 189	97.69 167	98.32 189	94.64 224	98.19 241	97.45 318	94.56 191	96.03 214	98.61 155	85.02 288	99.12 214	90.68 322	99.06 129	99.30 130

dp		94.15 291	93.90 270	94.90 327	97.31 281	86.82 389	96.97 352	97.19 337	91.22 335	96.02 215	96.61 339	85.51 279	99.02 231	90.00 333	94.30 259	98.85 191

EPNet		97.28 114	96.87 120	98.51 95	94.98 377	96.14 149	98.90 106	97.02 350	98.28 10	95.99 216	99.11 87	91.36 151	99.89 50	96.98 124	99.19 126	99.50 94
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 122	96.66 134	98.68 81	98.53 166	97.19 100	98.93 101	98.90 57	92.83 280	95.99 216	99.37 40	92.12 130	99.87 61	93.67 248	99.57 86	98.97 182

SDMVSNet		96.85 136	96.42 141	98.14 128	99.30 71	96.38 137	99.21 39	99.23 20	95.92 116	95.96 218	98.76 144	85.88 273	99.44 178	97.93 74	95.59 252	98.60 216

sd_testset		96.17 163	95.76 165	97.42 185	99.30 71	94.34 241	98.82 133	99.08 32	95.92 116	95.96 218	98.76 144	82.83 323	99.32 190	95.56 184	95.59 252	98.60 216

AUN-MVS		94.53 263	93.73 285	96.92 220	98.50 167	93.52 270	98.34 218	98.10 257	93.83 226	95.94 220	97.98 219	85.59 278	99.03 228	94.35 224	80.94 395	98.22 237

testing222		94.12 294	93.03 308	97.37 191	98.02 220	94.66 222	97.94 272	96.65 371	94.63 188	95.78 221	95.76 363	71.49 393	98.92 246	91.17 310	95.88 249	98.52 222

TR-MVS		94.94 238	94.20 245	97.17 199	97.75 241	94.14 249	97.59 309	97.02 350	92.28 301	95.75 222	97.64 253	83.88 316	98.96 239	89.77 335	96.15 244	98.40 228

WB-MVSnew		94.19 287	94.04 256	94.66 337	96.82 314	92.14 301	97.86 285	95.96 382	93.50 249	95.64 223	96.77 330	88.06 231	97.99 344	84.87 380	96.86 213	93.85 397

MonoMVSNet		95.51 195	95.45 179	95.68 299	95.54 364	90.87 326	98.92 103	97.37 325	95.79 124	95.53 224	97.38 274	89.58 187	97.68 361	96.40 154	92.59 298	98.49 224

VPA-MVSNet		95.75 183	95.11 200	97.69 167	97.24 284	97.27 92	98.94 98	99.23 20	95.13 158	95.51 225	97.32 278	85.73 275	98.91 248	97.33 116	89.55 336	96.89 287

testing91		94.98 233	94.25 243	97.20 195	97.94 228	93.41 274	98.00 266	97.58 297	94.99 168	95.45 226	96.04 357	77.20 368	99.42 180	94.97 203	96.02 247	98.78 199

testing99		94.83 241	94.08 254	97.07 208	97.94 228	93.13 288	98.10 255	97.17 338	94.86 177	95.34 227	96.00 360	76.31 376	99.40 181	95.08 200	95.90 248	98.68 208

HQP_MVS		96.14 165	95.90 161	96.85 223	97.42 273	94.60 230	98.80 142	98.56 160	97.28 49	95.34 227	98.28 192	87.09 250	99.03 228	96.07 162	94.27 260	96.92 279

plane_prior3						94.61 228			97.02 68	95.34 227

testing11		95.00 229	94.28 241	97.16 200	97.96 227	93.36 279	98.09 256	97.06 346	94.94 175	95.33 230	96.15 353	76.89 373	99.40 181	95.77 177	96.30 233	98.72 203

Fast-Effi-MVS+		96.28 160	95.70 172	98.03 140	98.29 192	95.97 157	98.58 187	98.25 228	91.74 314	95.29 231	97.23 285	91.03 163	99.15 209	92.90 270	97.96 183	98.97 182

test_fmvs2		93.43 309	93.58 292	92.95 368	96.97 303	83.91 394	99.19 44	97.24 334	95.74 126	95.20 232	98.27 195	69.65 395	98.72 271	96.26 158	93.73 277	96.24 352

EI-MVSNet		95.96 170	95.83 163	96.36 269	97.93 230	93.70 264	98.12 251	98.27 223	93.70 237	95.07 233	99.02 103	92.23 126	98.54 286	94.68 210	93.46 283	96.84 294

MVSTER		96.06 167	95.72 167	97.08 207	98.23 196	95.93 163	98.73 158	98.27 223	94.86 177	95.07 233	98.09 208	88.21 225	98.54 286	96.59 147	93.46 283	96.79 297

OPM-MVS		95.69 188	95.33 188	96.76 228	96.16 345	94.63 225	98.43 212	98.39 198	96.64 89	95.02 235	98.78 137	85.15 287	99.05 224	95.21 198	94.20 263	96.60 320
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 177	95.85 162	95.91 290	97.74 244	91.74 311	98.69 169	98.15 247	95.56 135	94.92 236	97.68 249	88.98 208	98.79 266	93.19 260	97.78 190	97.20 268

TESTMET0.1,1		94.18 290	93.69 288	95.63 302	96.92 306	89.12 362	96.91 357	94.78 395	93.17 264	94.88 237	96.45 343	78.52 354	98.92 246	93.09 262	98.50 162	98.85 191

VPNet		94.99 231	94.19 246	97.40 188	97.16 293	96.57 127	98.71 163	98.97 42	95.67 131	94.84 238	98.24 199	80.36 342	98.67 276	96.46 151	87.32 365	96.96 275

1112_ss		96.63 143	96.00 157	98.50 96	98.56 162	96.37 138	98.18 246	98.10 257	92.92 276	94.84 238	98.43 173	92.14 129	99.58 146	94.35 224	96.51 225	99.56 88

test-LLR		95.10 224	94.87 212	95.80 295	96.77 315	89.70 350	96.91 357	95.21 390	95.11 160	94.83 240	95.72 368	87.71 239	98.97 235	93.06 263	98.50 162	98.72 203

test-mter		94.08 298	93.51 296	95.80 295	96.77 315	89.70 350	96.91 357	95.21 390	92.89 277	94.83 240	95.72 368	77.69 362	98.97 235	93.06 263	98.50 162	98.72 203

Test_1112_low_res		96.34 157	95.66 175	98.36 111	98.56 162	95.94 160	97.71 299	98.07 264	92.10 306	94.79 242	97.29 280	91.75 140	99.56 150	94.17 231	96.50 226	99.58 86

GA-MVS		94.81 242	94.03 258	97.14 201	97.15 294	93.86 255	96.76 369	97.58 297	94.00 215	94.76 243	97.04 306	80.91 336	98.48 290	91.79 300	96.25 240	99.09 166

BH-untuned		95.95 171	95.72 167	96.65 235	98.55 164	92.26 300	98.23 234	97.79 285	93.73 232	94.62 244	98.01 215	88.97 209	99.00 234	93.04 265	98.51 161	98.68 208

test_djsdf		96.00 169	95.69 173	96.93 217	95.72 359	95.49 181	99.47 7	98.40 196	94.98 169	94.58 245	97.86 229	89.16 200	98.41 306	96.91 128	94.12 268	96.88 288

cascas		94.63 254	93.86 274	96.93 217	96.91 308	94.27 244	96.00 384	98.51 172	85.55 391	94.54 246	96.23 349	84.20 310	98.87 255	95.80 175	96.98 212	97.66 254

DP-MVS		96.59 145	95.93 160	98.57 88	99.34 60	96.19 147	98.70 167	98.39 198	89.45 366	94.52 247	99.35 46	91.85 138	99.85 66	92.89 272	98.88 140	99.68 64

gg-mvs-nofinetune		92.21 332	90.58 340	97.13 202	96.75 318	95.09 202	95.85 385	89.40 418	85.43 392	94.50 248	81.98 413	80.80 339	98.40 312	92.16 288	98.33 172	97.88 245

mvs_anonymous		96.70 142	96.53 139	97.18 198	98.19 202	93.78 257	98.31 224	98.19 235	94.01 214	94.47 249	98.27 195	92.08 133	98.46 294	97.39 113	97.91 184	99.31 127

HQP-NCC					97.20 288		98.05 260		96.43 96	94.45 250

ACMP_Plane					97.20 288		98.05 260		96.43 96	94.45 250

HQP4-MVS										94.45 250			98.96 239			96.87 291

HQP-MVS		95.72 184	95.40 180	96.69 233	97.20 288	94.25 246	98.05 260	98.46 184	96.43 96	94.45 250	97.73 241	86.75 256	98.96 239	95.30 192	94.18 264	96.86 293

MSDG		95.93 174	95.30 191	97.83 151	98.90 128	95.36 187	96.83 367	98.37 204	91.32 329	94.43 254	98.73 146	90.27 176	99.60 143	90.05 331	98.82 146	98.52 222

dmvs_re		94.48 269	94.18 248	95.37 312	97.68 248	90.11 344	98.54 196	97.08 342	94.56 191	94.42 255	97.24 284	84.25 306	97.76 359	91.02 318	92.83 295	98.24 235

nrg030		96.28 160	95.72 167	97.96 146	96.90 309	98.15 57	99.39 10	98.31 214	95.47 139	94.42 255	98.35 183	92.09 132	98.69 272	97.50 109	89.05 345	97.04 271

CLD-MVS		95.62 191	95.34 186	96.46 263	97.52 265	93.75 260	97.27 333	98.46 184	95.53 136	94.42 255	98.00 216	86.21 267	98.97 235	96.25 160	94.37 258	96.66 315
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		95.62 191	95.34 186	96.47 260	97.46 268	93.54 267	98.99 86	98.54 164	94.67 186	94.36 258	98.77 139	85.39 280	99.11 216	95.71 179	94.15 266	96.76 300

LGP-MVS_train				96.47 260	97.46 268	93.54 267		98.54 164	94.67 186	94.36 258	98.77 139	85.39 280	99.11 216	95.71 179	94.15 266	96.76 300

v144192		94.39 275	93.70 287	96.48 259	96.06 348	94.35 240	98.58 187	98.16 246	91.45 322	94.33 260	97.02 309	87.50 245	98.45 295	91.08 314	89.11 344	96.63 317

V42		94.78 244	94.14 251	96.70 232	96.33 338	95.22 196	98.97 89	98.09 261	92.32 299	94.31 261	97.06 302	88.39 222	98.55 285	92.90 270	88.87 349	96.34 348

ACMM	93.85 9	95.69 188	95.38 184	96.61 242	97.61 254	93.84 256	98.91 105	98.44 188	95.25 153	94.28 262	98.47 171	86.04 272	99.12 214	95.50 187	93.95 273	96.87 291
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 198	95.21 194	96.22 277	98.12 209	93.72 263	98.32 223	98.13 250	93.71 235	94.26 263	97.31 279	92.24 125	98.10 334	94.63 212	90.12 327	96.84 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 286	93.47 298	96.40 268	95.98 351	94.08 250	98.52 197	98.15 247	91.33 328	94.25 264	97.20 288	86.41 264	98.42 299	90.04 332	89.39 341	96.69 314

BH-w/o		95.38 205	95.08 201	96.26 276	98.34 183	91.79 308	97.70 300	97.43 320	92.87 278	94.24 265	97.22 286	88.66 214	98.84 258	91.55 305	97.70 194	98.16 240

XVG-ACMP-BASELINE		94.54 261	94.14 251	95.75 298	96.55 327	91.65 313	98.11 253	98.44 188	94.96 171	94.22 266	97.90 225	79.18 351	99.11 216	94.05 237	93.85 275	96.48 342

v1144		94.59 257	93.92 267	96.60 244	96.21 340	94.78 221	98.59 185	98.14 249	91.86 313	94.21 267	97.02 309	87.97 233	98.41 306	91.72 302	89.57 334	96.61 319

v1192		94.32 278	93.58 292	96.53 254	96.10 346	94.45 234	98.50 203	98.17 244	91.54 320	94.19 268	97.06 302	86.95 254	98.43 298	90.14 327	89.57 334	96.70 309

PAPM		94.95 236	94.00 262	97.78 156	97.04 299	95.65 173	96.03 383	98.25 228	91.23 334	94.19 268	97.80 238	91.27 156	98.86 257	82.61 391	97.61 196	98.84 193

Patchmatch-test		94.42 273	93.68 289	96.63 239	97.60 255	91.76 309	94.83 398	97.49 312	89.45 366	94.14 270	97.10 291	88.99 205	98.83 261	85.37 377	98.13 178	99.29 132

v1240		94.06 300	93.29 304	96.34 271	96.03 350	93.90 254	98.44 210	98.17 244	91.18 337	94.13 271	97.01 311	86.05 270	98.42 299	89.13 348	89.50 338	96.70 309

GBi-Net		94.49 267	93.80 278	96.56 249	98.21 198	95.00 205	98.82 133	98.18 238	92.46 290	94.09 272	97.07 298	81.16 332	97.95 346	92.08 290	92.14 301	96.72 305

test1		94.49 267	93.80 278	96.56 249	98.21 198	95.00 205	98.82 133	98.18 238	92.46 290	94.09 272	97.07 298	81.16 332	97.95 346	92.08 290	92.14 301	96.72 305

FMVSNet3		94.97 235	94.26 242	97.11 205	98.18 204	96.62 121	98.56 194	98.26 227	93.67 242	94.09 272	97.10 291	84.25 306	98.01 341	92.08 290	92.14 301	96.70 309

MIMVSNet		93.26 315	92.21 325	96.41 266	97.73 245	93.13 288	95.65 388	97.03 348	91.27 333	94.04 275	96.06 356	75.33 381	97.19 374	86.56 367	96.23 242	98.92 188

FIs		96.51 149	96.12 152	97.67 170	97.13 295	97.54 80	99.36 13	99.22 23	95.89 118	94.03 276	98.35 183	91.98 135	98.44 297	96.40 154	92.76 296	97.01 272

v2v482		94.69 247	94.03 258	96.65 235	96.17 343	94.79 220	98.67 173	98.08 262	92.72 282	94.00 277	97.16 289	87.69 242	98.45 295	92.91 269	88.87 349	96.72 305

testing3		93.19 318	92.48 321	95.30 315	98.07 212	92.27 299	98.64 178	97.17 338	93.94 220	93.98 278	97.04 306	67.97 399	96.01 394	88.40 354	97.14 205	97.63 255

FC-MVSNet-test		96.42 152	96.05 154	97.53 180	96.95 304	97.27 92	99.36 13	99.23 20	95.83 122	93.93 279	98.37 181	92.00 134	98.32 316	96.02 167	92.72 297	97.00 273

UniMVSNet (Re)		95.78 182	95.19 195	97.58 177	96.99 302	97.47 84	98.79 148	99.18 25	95.60 133	93.92 280	97.04 306	91.68 141	98.48 290	95.80 175	87.66 360	96.79 297

miper_enhance_ethall		95.10 224	94.75 216	96.12 281	97.53 264	93.73 262	96.61 374	98.08 262	92.20 305	93.89 281	96.65 336	92.44 118	98.30 320	94.21 230	91.16 315	96.34 348

UniMVSNet_NR-MVSNet		95.71 185	95.15 196	97.40 188	96.84 312	96.97 106	98.74 154	99.24 17	95.16 157	93.88 282	97.72 243	91.68 141	98.31 318	95.81 173	87.25 366	96.92 279

DU-MVS		95.42 202	94.76 215	97.40 188	96.53 328	96.97 106	98.66 175	98.99 41	95.43 141	93.88 282	97.69 246	88.57 216	98.31 318	95.81 173	87.25 366	96.92 279

Baseline_NR-MVSNet		94.35 276	93.81 277	95.96 288	96.20 341	94.05 251	98.61 184	96.67 369	91.44 323	93.85 284	97.60 256	88.57 216	98.14 331	94.39 222	86.93 369	95.68 366

PS-MVSNAJss		96.43 151	96.26 148	96.92 220	95.84 357	95.08 203	99.16 50	98.50 177	95.87 120	93.84 285	98.34 187	94.51 87	98.61 280	96.88 134	93.45 285	97.06 270

UniMVSNet_ETH3D		94.24 284	93.33 302	96.97 214	97.19 291	93.38 277	98.74 154	98.57 157	91.21 336	93.81 286	98.58 160	72.85 392	98.77 268	95.05 201	93.93 274	98.77 202

tt0805		94.54 261	93.85 275	96.63 239	97.98 225	93.06 293	98.77 150	97.84 283	93.67 242	93.80 287	98.04 212	76.88 374	98.96 239	94.79 209	92.86 294	97.86 247

tpmvs		94.60 255	94.36 239	95.33 314	97.46 268	88.60 372	96.88 363	97.68 289	91.29 331	93.80 287	96.42 344	88.58 215	99.24 198	91.06 315	96.04 246	98.17 239

WBMVS		94.56 259	94.04 256	96.10 282	98.03 219	93.08 292	97.82 291	98.18 238	94.02 211	93.77 289	96.82 327	81.28 331	98.34 313	95.47 189	91.00 318	96.88 288

3Dnovator	94.51 5	97.46 101	96.93 117	99.07 56	97.78 239	97.64 74	99.35 15	99.06 34	97.02 68	93.75 290	99.16 80	89.25 197	99.92 34	97.22 118	99.75 47	99.64 74

eth_miper_zixun_eth		94.68 249	94.41 237	95.47 308	97.64 252	91.71 312	96.73 371	98.07 264	92.71 283	93.64 291	97.21 287	90.54 170	98.17 329	93.38 254	89.76 331	96.54 329

ITE_SJBPF				95.44 310	97.42 273	91.32 318		97.50 310	95.09 163	93.59 292	98.35 183	81.70 327	98.88 254	89.71 337	93.39 287	96.12 356

TranMVSNet+NR-MVSNet		95.14 222	94.48 230	97.11 205	96.45 333	96.36 139	99.03 76	99.03 37	95.04 165	93.58 293	97.93 222	88.27 224	98.03 340	94.13 232	86.90 371	96.95 277

COLMAP_ROB	93.27 12	95.33 211	94.87 212	96.71 230	99.29 76	93.24 285	98.58 187	98.11 254	89.92 357	93.57 294	99.10 89	86.37 265	99.79 101	90.78 320	98.10 179	97.09 269
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 310	92.80 312	95.07 323	97.58 257	87.97 382	96.76 369	97.86 282	82.17 402	93.53 295	96.04 357	86.13 268	99.13 212	89.24 346	95.87 250	98.10 241

AllTest		95.24 216	94.65 222	96.99 211	99.25 84	93.21 286	98.59 185	98.18 238	91.36 325	93.52 296	98.77 139	84.67 298	99.72 116	89.70 338	97.87 186	98.02 243

TestCases				96.99 211	99.25 84	93.21 286		98.18 238	91.36 325	93.52 296	98.77 139	84.67 298	99.72 116	89.70 338	97.87 186	98.02 243

miper_ehance_all_eth		95.01 228	94.69 220	95.97 287	97.70 247	93.31 280	97.02 350	98.07 264	92.23 302	93.51 298	96.96 316	91.85 138	98.15 330	93.68 246	91.16 315	96.44 345

FMVSNet2		94.47 270	93.61 291	97.04 209	98.21 198	96.43 134	98.79 148	98.27 223	92.46 290	93.50 299	97.09 295	81.16 332	98.00 343	91.09 312	91.93 304	96.70 309

v148		94.29 281	93.76 283	95.91 290	96.10 346	92.93 294	98.58 187	97.97 274	92.59 288	93.47 300	96.95 318	88.53 220	98.32 316	92.56 280	87.06 368	96.49 340

c3_l		94.79 243	94.43 236	95.89 292	97.75 241	93.12 290	97.16 344	98.03 271	92.23 302	93.46 301	97.05 305	91.39 150	98.01 341	93.58 251	89.21 343	96.53 331

Syy-MVS		92.55 328	92.61 317	92.38 371	97.39 277	83.41 397	97.91 275	97.46 314	93.16 265	93.42 302	95.37 375	84.75 295	96.12 392	77.00 405	96.99 209	97.60 256

myMVS_eth3d		92.73 325	92.01 327	94.89 328	97.39 277	90.94 324	97.91 275	97.46 314	93.16 265	93.42 302	95.37 375	68.09 398	96.12 392	88.34 355	96.99 209	97.60 256

pmmvs4		94.69 247	93.99 264	96.81 226	95.74 358	95.94 160	97.40 319	97.67 291	90.42 349	93.37 304	97.59 257	89.08 203	98.20 327	92.97 267	91.67 308	96.30 351

PCF-MVS	93.45 11	94.68 249	93.43 300	98.42 108	98.62 159	96.77 116	95.48 391	98.20 233	84.63 395	93.34 305	98.32 189	88.55 219	99.81 84	84.80 383	98.96 136	98.68 208
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 249	94.19 246	96.13 280	98.11 210	93.60 265	96.94 354	98.31 214	92.43 294	93.32 306	96.87 324	86.51 259	98.28 324	94.10 235	91.16 315	96.51 337

XXY-MVS		95.20 219	94.45 234	97.46 181	96.75 318	96.56 128	98.86 121	98.65 139	93.30 259	93.27 307	98.27 195	84.85 292	98.87 255	94.82 207	91.26 314	96.96 275

jajsoiax		95.45 200	95.03 203	96.73 229	95.42 372	94.63 225	99.14 54	98.52 169	95.74 126	93.22 308	98.36 182	83.87 317	98.65 277	96.95 127	94.04 269	96.91 284

reproduce_monomvs		94.77 245	94.67 221	95.08 322	98.40 174	89.48 356	98.80 142	98.64 140	97.57 31	93.21 309	97.65 250	80.57 341	98.83 261	97.72 88	89.47 339	96.93 278

mvs_tets		95.41 204	95.00 204	96.65 235	95.58 363	94.42 236	99.00 83	98.55 162	95.73 128	93.21 309	98.38 180	83.45 321	98.63 278	97.09 121	94.00 271	96.91 284

anonymousdsp		95.42 202	94.91 209	96.94 216	95.10 376	95.90 166	99.14 54	98.41 194	93.75 229	93.16 311	97.46 265	87.50 245	98.41 306	95.63 183	94.03 270	96.50 339

v8		94.47 270	93.77 281	96.57 248	96.36 336	94.83 217	99.05 69	98.19 235	91.92 310	93.16 311	96.97 314	88.82 213	98.48 290	91.69 303	87.79 358	96.39 346

WR-MVS		95.15 221	94.46 232	97.22 194	96.67 323	96.45 132	98.21 236	98.81 89	94.15 205	93.16 311	97.69 246	87.51 243	98.30 320	95.29 194	88.62 351	96.90 286

EPNet_dtu		95.21 218	94.95 208	95.99 285	96.17 343	90.45 337	98.16 247	97.27 332	96.77 79	93.14 314	98.33 188	90.34 173	98.42 299	85.57 374	98.81 147	99.09 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 158	95.40 180	98.96 65	97.85 235	97.60 77	99.23 32	98.93 50	89.76 360	93.11 315	99.02 103	89.11 202	99.93 28	91.99 295	99.62 77	99.34 121

GG-mvs-BLEND				96.59 245	96.34 337	94.98 208	96.51 377	88.58 419		93.10 316	94.34 390	80.34 344	98.05 339	89.53 341	96.99 209	96.74 302

v10		94.29 281	93.55 294	96.51 256	96.39 335	94.80 219	98.99 86	98.19 235	91.35 327	93.02 317	96.99 312	88.09 229	98.41 306	90.50 324	88.41 353	96.33 350

3Dnovator+	94.38 6	97.43 106	96.78 125	99.38 18	97.83 236	98.52 28	99.37 12	98.71 119	97.09 66	92.99 318	99.13 85	89.36 194	99.89 50	96.97 125	99.57 86	99.71 52

D2MVS		95.18 220	95.08 201	95.48 307	97.10 297	92.07 304	98.30 226	99.13 30	94.02 211	92.90 319	96.73 331	89.48 189	98.73 270	94.48 220	93.60 282	95.65 367

Patchmtry		93.22 316	92.35 323	95.84 294	96.77 315	93.09 291	94.66 401	97.56 300	87.37 380	92.90 319	96.24 347	88.15 227	97.90 350	87.37 364	90.10 328	96.53 331

DIV-MVS_self_test		94.52 264	94.03 258	95.99 285	97.57 261	93.38 277	97.05 348	97.94 277	91.74 314	92.81 321	97.10 291	89.12 201	98.07 338	92.60 276	90.30 324	96.53 331

Anonymous20231211		94.10 296	93.26 305	96.61 242	99.11 107	94.28 243	99.01 81	98.88 62	86.43 384	92.81 321	97.57 259	81.66 328	98.68 275	94.83 206	89.02 347	96.88 288

cl____		94.51 265	94.01 261	96.02 284	97.58 257	93.40 276	97.05 348	97.96 276	91.73 316	92.76 323	97.08 297	89.06 204	98.13 332	92.61 275	90.29 325	96.52 334

miper_lstm_enhance		94.33 277	94.07 255	95.11 320	97.75 241	90.97 323	97.22 335	98.03 271	91.67 318	92.76 323	96.97 314	90.03 179	97.78 358	92.51 283	89.64 333	96.56 326

v7n		94.19 287	93.43 300	96.47 260	95.90 354	94.38 239	99.26 27	98.34 210	91.99 308	92.76 323	97.13 290	88.31 223	98.52 288	89.48 343	87.70 359	96.52 334

MVS		94.67 252	93.54 295	98.08 137	96.88 310	96.56 128	98.19 241	98.50 177	78.05 406	92.69 326	98.02 213	91.07 162	99.63 137	90.09 328	98.36 171	98.04 242

DSMNet-mixed		92.52 330	92.58 319	92.33 372	94.15 387	82.65 400	98.30 226	94.26 401	89.08 371	92.65 327	95.73 366	85.01 289	95.76 396	86.24 369	97.76 191	98.59 218

EU-MVSNet		93.66 305	94.14 251	92.25 374	95.96 353	83.38 398	98.52 197	98.12 251	94.69 184	92.61 328	98.13 206	87.36 248	96.39 390	91.82 299	90.00 329	96.98 274

IterMVS-SCA-FT		94.11 295	93.87 273	94.85 330	97.98 225	90.56 336	97.18 340	98.11 254	93.75 229	92.58 329	97.48 264	83.97 314	97.41 371	92.48 285	91.30 312	96.58 322

pmmvs5		93.65 307	92.97 310	95.68 299	95.49 367	92.37 298	98.20 238	97.28 331	89.66 362	92.58 329	97.26 281	82.14 325	98.09 336	93.18 261	90.95 319	96.58 322

WR-MVS_H		95.05 227	94.46 232	96.81 226	96.86 311	95.82 169	99.24 30	99.24 17	93.87 223	92.53 331	96.84 326	90.37 172	98.24 326	93.24 258	87.93 357	96.38 347

ACMP	93.49 10	95.34 210	94.98 206	96.43 265	97.67 249	93.48 271	98.73 158	98.44 188	94.94 175	92.53 331	98.53 165	84.50 303	99.14 211	95.48 188	94.00 271	96.66 315
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 298	93.51 296	95.80 295	95.53 366	92.89 295	97.38 321	95.97 381	95.11 160	92.51 333	96.66 334	87.71 239	96.94 378	87.03 365	93.67 278	97.57 258

IB-MVS	91.98 17	93.27 314	91.97 328	97.19 197	97.47 267	93.41 274	97.09 347	95.99 380	93.32 257	92.47 334	95.73 366	78.06 360	99.53 160	94.59 217	82.98 386	98.62 215
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
IterMVS		94.09 297	93.85 275	94.80 333	97.99 223	90.35 340	97.18 340	98.12 251	93.68 240	92.46 335	97.34 275	84.05 312	97.41 371	92.51 283	91.33 311	96.62 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CP-MVSNet		94.94 238	94.30 240	96.83 224	96.72 320	95.56 176	99.11 60	98.95 46	93.89 221	92.42 336	97.90 225	87.19 249	98.12 333	94.32 226	88.21 354	96.82 296

PS-CasMVS		94.67 252	93.99 264	96.71 230	96.68 322	95.26 193	99.13 57	99.03 37	93.68 240	92.33 337	97.95 221	85.35 282	98.10 334	93.59 250	88.16 356	96.79 297

FMVSNet1		93.19 318	92.07 326	96.56 249	97.54 262	95.00 205	98.82 133	98.18 238	90.38 350	92.27 338	97.07 298	73.68 390	97.95 346	89.36 345	91.30 312	96.72 305

PEN-MVS		94.42 273	93.73 285	96.49 257	96.28 339	94.84 215	99.17 49	99.00 39	93.51 248	92.23 339	97.83 235	86.10 269	97.90 350	92.55 281	86.92 370	96.74 302

OurMVSNet-221017-0		94.21 285	94.00 262	94.85 330	95.60 362	89.22 361	98.89 110	97.43 320	95.29 150	92.18 340	98.52 168	82.86 322	98.59 283	93.46 253	91.76 306	96.74 302

MS-PatchMatch		93.84 304	93.63 290	94.46 347	96.18 342	89.45 357	97.76 295	98.27 223	92.23 302	92.13 341	97.49 263	79.50 348	98.69 272	89.75 336	99.38 117	95.25 372

ppachtmachnet_test		93.22 316	92.63 316	94.97 325	95.45 370	90.84 328	96.88 363	97.88 281	90.60 344	92.08 342	97.26 281	88.08 230	97.86 355	85.12 379	90.33 323	96.22 353

1314		96.25 162	95.73 166	97.79 155	97.13 295	95.55 178	98.19 241	98.59 150	93.47 251	92.03 343	97.82 236	91.33 153	99.49 168	94.62 214	98.44 165	98.32 234

baseline2		95.11 223	94.52 228	96.87 222	96.65 324	93.56 266	98.27 231	94.10 404	93.45 252	92.02 344	97.43 269	87.45 247	99.19 204	93.88 241	97.41 202	97.87 246

DTE-MVSNet		93.98 302	93.26 305	96.14 279	96.06 348	94.39 238	99.20 42	98.86 75	93.06 270	91.78 345	97.81 237	85.87 274	97.58 366	90.53 323	86.17 375	96.46 344

LF4IMVS		93.14 320	92.79 313	94.20 351	95.88 355	88.67 371	97.66 303	97.07 344	93.81 227	91.71 346	97.65 250	77.96 361	98.81 264	91.47 306	91.92 305	95.12 375

mvs5depth		91.23 340	90.17 344	94.41 349	92.09 400	89.79 347	95.26 392	96.50 373	90.73 342	91.69 347	97.06 302	76.12 378	98.62 279	88.02 359	84.11 383	94.82 382

our_test_3		93.65 307	93.30 303	94.69 335	95.45 370	89.68 352	96.91 357	97.65 292	91.97 309	91.66 348	96.88 322	89.67 186	97.93 349	88.02 359	91.49 310	96.48 342

testgi		93.06 322	92.45 322	94.88 329	96.43 334	89.90 345	98.75 151	97.54 306	95.60 133	91.63 349	97.91 224	74.46 387	97.02 376	86.10 370	93.67 278	97.72 252

tfpnnormal		93.66 305	92.70 315	96.55 253	96.94 305	95.94 160	98.97 89	99.19 24	91.04 338	91.38 350	97.34 275	84.94 290	98.61 280	85.45 376	89.02 347	95.11 376

LTVRE_ROB	92.95 15	94.60 255	93.90 270	96.68 234	97.41 276	94.42 236	98.52 197	98.59 150	91.69 317	91.21 351	98.35 183	84.87 291	99.04 227	91.06 315	93.44 286	96.60 320
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
OpenMVS	93.04 13	95.83 180	95.00 204	98.32 113	97.18 292	97.32 90	99.21 39	98.97 42	89.96 356	91.14 352	99.05 101	86.64 258	99.92 34	93.38 254	99.47 105	97.73 251

pm-mvs1		93.94 303	93.06 307	96.59 245	96.49 331	95.16 198	98.95 95	98.03 271	92.32 299	91.08 353	97.84 232	84.54 302	98.41 306	92.16 288	86.13 378	96.19 355

MVS-HIRNet		89.46 358	88.40 357	92.64 369	97.58 257	82.15 401	94.16 407	93.05 410	75.73 409	90.90 354	82.52 412	79.42 349	98.33 315	83.53 388	98.68 149	97.43 259

FMVSNet5		91.81 333	90.92 336	94.49 344	97.21 287	92.09 303	98.00 266	97.55 305	89.31 369	90.86 355	95.61 372	74.48 386	95.32 400	85.57 374	89.70 332	96.07 358

USDC		93.33 313	92.71 314	95.21 316	96.83 313	90.83 329	96.91 357	97.50 310	93.84 224	90.72 356	98.14 205	77.69 362	98.82 263	89.51 342	93.21 291	95.97 360

MVP-Stereo		94.28 283	93.92 267	95.35 313	94.95 378	92.60 297	97.97 269	97.65 292	91.61 319	90.68 357	97.09 295	86.32 266	98.42 299	89.70 338	99.34 120	95.02 380
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 279	93.77 281	95.88 293	97.81 238	92.04 306	98.71 163	98.37 204	93.99 216	90.60 358	98.47 171	80.86 338	99.05 224	92.75 274	92.40 300	96.55 328

CL-MVSNet_self_test		90.11 350	89.14 353	93.02 367	91.86 402	88.23 380	96.51 377	98.07 264	90.49 345	90.49 359	94.41 386	84.75 295	95.34 399	80.79 395	74.95 410	95.50 368

KD-MVS_self_test		90.38 348	89.38 351	93.40 361	92.85 397	88.94 368	97.95 270	97.94 277	90.35 351	90.25 360	93.96 391	79.82 345	95.94 395	84.62 385	76.69 408	95.33 370

ttmdpeth		92.61 327	91.96 330	94.55 341	94.10 388	90.60 335	98.52 197	97.29 329	92.67 284	90.18 361	97.92 223	79.75 347	97.79 357	91.09 312	86.15 377	95.26 371

Anonymous20231206		91.66 335	91.10 335	93.33 362	94.02 392	87.35 386	98.58 187	97.26 333	90.48 346	90.16 362	96.31 345	83.83 318	96.53 388	79.36 399	89.90 330	96.12 356

SixPastTwentyTwo		93.34 312	92.86 311	94.75 334	95.67 360	89.41 359	98.75 151	96.67 369	93.89 221	90.15 363	98.25 198	80.87 337	98.27 325	90.90 319	90.64 321	96.57 324

PVSNet_0	88.72 19	91.28 339	90.03 346	95.00 324	97.99 223	87.29 387	94.84 397	98.50 177	92.06 307	89.86 364	95.19 377	79.81 346	99.39 184	92.27 287	69.79 413	98.33 233

ACMH	92.88 16	94.55 260	93.95 266	96.34 271	97.63 253	93.26 282	98.81 141	98.49 182	93.43 253	89.74 365	98.53 165	81.91 326	99.08 222	93.69 245	93.30 289	96.70 309
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		91.77 334	90.63 339	95.17 318	94.69 384	91.24 320	98.67 173	97.92 279	86.14 386	89.62 366	97.56 261	75.79 380	98.34 313	90.75 321	84.56 380	95.94 361

TinyColmap		92.31 331	91.53 332	94.65 338	96.92 306	89.75 348	96.92 355	96.68 368	90.45 348	89.62 366	97.85 231	76.06 379	98.81 264	86.74 366	92.51 299	95.41 369

Anonymous20240521		91.18 341	90.44 341	93.42 359	93.70 393	88.47 375	98.94 98	97.56 300	88.46 375	89.56 368	95.08 380	77.15 370	96.97 377	83.92 386	89.55 336	94.82 382

TransMVSNet (Re)		92.67 326	91.51 333	96.15 278	96.58 326	94.65 223	98.90 106	96.73 365	90.86 341	89.46 369	97.86 229	85.62 277	98.09 336	86.45 368	81.12 393	95.71 365

NR-MVSNet		94.98 233	94.16 249	97.44 183	96.53 328	97.22 99	98.74 154	98.95 46	94.96 171	89.25 370	97.69 246	89.32 195	98.18 328	94.59 217	87.40 363	96.92 279

LCM-MVSNet-Re		95.22 217	95.32 189	94.91 326	98.18 204	87.85 384	98.75 151	95.66 386	95.11 160	88.96 371	96.85 325	90.26 177	97.65 362	95.65 182	98.44 165	99.22 144

KD-MVS_2432*1600		89.61 355	87.96 363	94.54 342	94.06 390	91.59 314	95.59 389	97.63 294	89.87 358	88.95 372	94.38 388	78.28 357	96.82 380	84.83 381	68.05 414	95.21 373

miper_refine_blended		89.61 355	87.96 363	94.54 342	94.06 390	91.59 314	95.59 389	97.63 294	89.87 358	88.95 372	94.38 388	78.28 357	96.82 380	84.83 381	68.05 414	95.21 373

test_fmvs3		87.17 365	87.06 368	87.50 383	91.21 404	75.66 408	99.05 69	96.61 372	92.79 281	88.85 374	92.78 400	43.72 415	93.49 406	93.95 238	84.56 380	93.34 400

TDRefinement		91.06 343	89.68 348	95.21 316	85.35 418	91.49 316	98.51 202	97.07 344	91.47 321	88.83 375	97.84 232	77.31 366	99.09 221	92.79 273	77.98 405	95.04 379

N_pmnet		87.12 367	87.77 365	85.17 387	95.46 369	61.92 423	97.37 323	70.66 428	85.83 389	88.73 376	96.04 357	85.33 284	97.76 359	80.02 396	90.48 322	95.84 362

test_0402		91.32 337	90.27 343	94.48 345	96.60 325	91.12 321	98.50 203	97.22 335	86.10 387	88.30 377	96.98 313	77.65 364	97.99 344	78.13 403	92.94 293	94.34 386

test20.03		90.89 345	90.38 342	92.43 370	93.48 394	88.14 381	98.33 219	97.56 300	93.40 254	87.96 378	96.71 333	80.69 340	94.13 405	79.15 400	86.17 375	95.01 381

MIMVSNet1		89.67 354	88.28 359	93.82 356	92.81 398	91.08 322	98.01 264	97.45 318	87.95 377	87.90 379	95.87 362	67.63 401	94.56 404	78.73 402	88.18 355	95.83 363

mvsany_test3		88.80 360	88.04 360	91.09 378	89.78 408	81.57 403	97.83 290	95.49 388	93.81 227	87.53 380	93.95 392	56.14 411	97.43 370	94.68 210	83.13 385	94.26 387

Patchmatch-RL test		91.49 336	90.85 337	93.41 360	91.37 403	84.40 392	92.81 408	95.93 384	91.87 312	87.25 381	94.87 381	88.99 205	96.53 388	92.54 282	82.00 388	99.30 130

pmmvs3		86.67 368	84.86 373	92.11 375	88.16 412	87.19 388	96.63 373	94.75 396	79.88 404	87.22 382	92.75 402	66.56 403	95.20 401	81.24 394	76.56 409	93.96 395

dongtai		82.47 372	81.88 375	84.22 389	95.19 375	76.03 406	94.59 403	74.14 427	82.63 399	87.19 383	96.09 355	64.10 405	87.85 417	58.91 415	84.11 383	88.78 409

test_vis1_rt		91.29 338	90.65 338	93.19 366	97.45 271	86.25 390	98.57 193	90.90 416	93.30 259	86.94 384	93.59 394	62.07 408	99.11 216	97.48 110	95.58 254	94.22 389

K. test v3		92.55 328	91.91 331	94.48 345	95.64 361	89.24 360	99.07 66	94.88 394	94.04 209	86.78 385	97.59 257	77.64 365	97.64 363	92.08 290	89.43 340	96.57 324

lessismore_v0				94.45 348	94.93 379	88.44 376		91.03 415		86.77 386	97.64 253	76.23 377	98.42 299	90.31 326	85.64 379	96.51 337

APD_test1		88.22 362	88.01 361	88.86 381	95.98 351	74.66 413	97.21 336	96.44 375	83.96 397	86.66 387	97.90 225	60.95 409	97.84 356	82.73 389	90.23 326	94.09 392

ambc				89.49 380	86.66 415	75.78 407	92.66 409	96.72 366		86.55 388	92.50 403	46.01 413	97.90 350	90.32 325	82.09 387	94.80 384

PM-MVS		87.77 363	86.55 369	91.40 377	91.03 406	83.36 399	96.92 355	95.18 392	91.28 332	86.48 389	93.42 395	53.27 412	96.74 382	89.43 344	81.97 389	94.11 391

OpenMVS_ROB	86.42 20	89.00 359	87.43 367	93.69 357	93.08 396	89.42 358	97.91 275	96.89 359	78.58 405	85.86 390	94.69 382	69.48 396	98.29 323	77.13 404	93.29 290	93.36 399

UnsupCasMVSNet_eth		90.99 344	89.92 347	94.19 352	94.08 389	89.83 346	97.13 346	98.67 132	93.69 238	85.83 391	96.19 352	75.15 382	96.74 382	89.14 347	79.41 400	96.00 359

new_pmnet		90.06 351	89.00 355	93.22 365	94.18 386	88.32 378	96.42 379	96.89 359	86.19 385	85.67 392	93.62 393	77.18 369	97.10 375	81.61 393	89.29 342	94.23 388

dmvs_testset		87.64 364	88.93 356	83.79 390	95.25 373	63.36 422	97.20 337	91.17 414	93.07 269	85.64 393	95.98 361	85.30 286	91.52 412	69.42 411	87.33 364	96.49 340

test_f		86.07 369	85.39 370	88.10 382	89.28 410	75.57 409	97.73 298	96.33 377	89.41 368	85.35 394	91.56 406	43.31 417	95.53 397	91.32 308	84.23 382	93.21 401

EG-PatchMatch MVS		91.13 342	90.12 345	94.17 353	94.73 383	89.00 365	98.13 250	97.81 284	89.22 370	85.32 395	96.46 342	67.71 400	98.42 299	87.89 362	93.82 276	95.08 377

pmmvs-eth3d		90.36 349	89.05 354	94.32 350	91.10 405	92.12 302	97.63 308	96.95 354	88.86 373	84.91 396	93.13 399	78.32 356	96.74 382	88.70 351	81.81 390	94.09 392

DeepMVS_CX				86.78 384	97.09 298	72.30 414		95.17 393	75.92 408	84.34 397	95.19 377	70.58 394	95.35 398	79.98 398	89.04 346	92.68 402

new-patchmatchnet		88.50 361	87.45 366	91.67 376	90.31 407	85.89 391	97.16 344	97.33 326	89.47 365	83.63 398	92.77 401	76.38 375	95.06 402	82.70 390	77.29 406	94.06 394

UnsupCasMVSNet_bld		87.17 365	85.12 372	93.31 363	91.94 401	88.77 369	94.92 396	98.30 220	84.30 396	82.30 399	90.04 407	63.96 406	97.25 373	85.85 373	74.47 412	93.93 396

WB-MVS		84.86 370	85.33 371	83.46 391	89.48 409	69.56 417	98.19 241	96.42 376	89.55 364	81.79 400	94.67 383	84.80 293	90.12 413	52.44 417	80.64 397	90.69 404

CMPMVS	66.06 21	89.70 353	89.67 349	89.78 379	93.19 395	76.56 405	97.00 351	98.35 207	80.97 403	81.57 401	97.75 240	74.75 384	98.61 280	89.85 334	93.63 280	94.17 390
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		84.27 371	84.71 374	82.96 395	89.19 411	68.83 418	98.08 257	96.30 378	89.04 372	81.37 402	94.47 384	84.60 300	89.89 414	49.80 419	79.52 399	90.15 405

MVStest1		89.53 357	87.99 362	94.14 355	94.39 385	90.42 338	98.25 233	96.84 364	82.81 398	81.18 403	97.33 277	77.09 371	96.94 378	85.27 378	78.79 401	95.06 378

test_method		79.03 374	78.17 376	81.63 396	86.06 417	54.40 428	82.75 416	96.89 359	39.54 420	80.98 404	95.57 373	58.37 410	94.73 403	84.74 384	78.61 402	95.75 364

kuosan		78.45 378	77.69 379	80.72 397	92.73 399	75.32 410	94.63 402	74.51 426	75.96 407	80.87 405	93.19 398	63.23 407	79.99 421	42.56 421	81.56 392	86.85 413

ET-MVSNet_ETH3D		94.13 292	92.98 309	97.58 177	98.22 197	96.20 145	97.31 330	95.37 389	94.53 193	79.56 406	97.63 255	86.51 259	97.53 368	96.91 128	90.74 320	99.02 177

LCM-MVSNet		78.70 377	76.24 383	86.08 385	77.26 424	71.99 415	94.34 405	96.72 366	61.62 415	76.53 407	89.33 408	33.91 423	92.78 410	81.85 392	74.60 411	93.46 398

PMMVS2		77.95 380	75.44 384	85.46 386	82.54 419	74.95 411	94.23 406	93.08 409	72.80 410	74.68 408	87.38 409	36.36 420	91.56 411	73.95 407	63.94 416	89.87 406

testf1		79.02 375	77.70 377	82.99 393	88.10 413	66.90 419	94.67 399	93.11 407	71.08 411	74.02 409	93.41 396	34.15 421	93.25 407	72.25 409	78.50 403	88.82 407

APD_test2		79.02 375	77.70 377	82.99 393	88.10 413	66.90 419	94.67 399	93.11 407	71.08 411	74.02 409	93.41 396	34.15 421	93.25 407	72.25 409	78.50 403	88.82 407

Gipuma		78.40 379	76.75 382	83.38 392	95.54 364	80.43 404	79.42 417	97.40 322	64.67 414	73.46 411	80.82 415	45.65 414	93.14 409	66.32 413	87.43 362	76.56 417
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		90.70 347	89.39 350	94.62 340	94.79 382	90.65 333	97.20 337	97.46 314	87.54 379	72.54 412	95.74 364	86.51 259	96.66 386	86.00 371	86.76 373	96.54 329

MDA-MVSNet_test_wron		90.71 346	89.38 351	94.68 336	94.83 380	90.78 330	97.19 339	97.46 314	87.60 378	72.41 413	95.72 368	86.51 259	96.71 385	85.92 372	86.80 372	96.56 326

MDA-MVSNet-bldmvs		89.97 352	88.35 358	94.83 332	95.21 374	91.34 317	97.64 305	97.51 309	88.36 376	71.17 414	96.13 354	79.22 350	96.63 387	83.65 387	86.27 374	96.52 334

FPMVS		77.62 381	77.14 381	79.05 399	79.25 422	60.97 424	95.79 386	95.94 383	65.96 413	67.93 415	94.40 387	37.73 419	88.88 416	68.83 412	88.46 352	87.29 410

test_vis3_rt		79.22 373	77.40 380	84.67 388	86.44 416	74.85 412	97.66 303	81.43 423	84.98 393	67.12 416	81.91 414	28.09 425	97.60 364	88.96 349	80.04 398	81.55 414

tmp_tt		68.90 384	66.97 386	74.68 401	50.78 428	59.95 425	87.13 413	83.47 422	38.80 421	62.21 417	96.23 349	64.70 404	76.91 423	88.91 350	30.49 421	87.19 411

E-PMN		64.94 386	64.25 388	67.02 403	82.28 420	59.36 426	91.83 411	85.63 420	52.69 417	60.22 418	77.28 417	41.06 418	80.12 420	46.15 420	41.14 418	61.57 419

EMVS		64.07 387	63.26 390	66.53 404	81.73 421	58.81 427	91.85 410	84.75 421	51.93 419	59.09 419	75.13 418	43.32 416	79.09 422	42.03 422	39.47 419	61.69 418

MVE	62.14 22	63.28 388	59.38 391	74.99 400	74.33 425	65.47 421	85.55 414	80.50 424	52.02 418	51.10 420	75.00 419	10.91 429	80.50 419	51.60 418	53.40 417	78.99 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		69.08 383	65.37 387	80.22 398	65.99 426	71.96 416	90.91 412	90.09 417	82.62 400	49.93 421	78.39 416	29.36 424	81.75 418	62.49 414	38.52 420	86.95 412

PMVS	61.03 23	65.95 385	63.57 389	73.09 402	57.90 427	51.22 429	85.05 415	93.93 405	54.45 416	44.32 422	83.57 411	13.22 426	89.15 415	58.68 416	81.00 394	78.91 416
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		21.48 391	24.95 394	11.09 407	14.89 429	6.47 432	96.56 375	9.87 430	7.55 423	17.93 423	39.02 421	9.43 430	5.90 426	16.56 425	12.72 423	20.91 421

test123		20.95 392	23.72 395	12.64 406	13.54 430	8.19 431	96.55 376	6.13 431	7.48 424	16.74 424	37.98 422	12.97 427	6.05 425	16.69 424	5.43 424	23.68 420

wuyk23d		30.17 389	30.18 393	30.16 405	78.61 423	43.29 430	66.79 418	14.21 429	17.31 422	14.82 425	11.93 425	11.55 428	41.43 424	37.08 423	19.30 422	5.76 422

EGC-MVSNET		75.22 382	69.54 385	92.28 373	94.81 381	89.58 354	97.64 305	96.50 373	1.82 425	5.57 426	95.74 364	68.21 397	96.26 391	73.80 408	91.71 307	90.99 403

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		23.98 390	31.98 392	0.00 408	0.00 431	0.00 433	0.00 419	98.59 150	0.00 426	0.00 427	98.61 155	90.60 169	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		7.88 394	10.50 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	94.51 87	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.20 393	10.94 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	98.43 173	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						90.94 324								88.66 352

MSC_two_6792asdad				99.62 6	99.17 97	99.08 11		98.63 143					99.94 9	98.53 38	99.80 24	99.86 7

No_MVS				99.62 6	99.17 97	99.08 11		98.63 143					99.94 9	98.53 38	99.80 24	99.86 7

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				99.37 22	99.24 90	99.05 14	99.02 79				99.16 80	97.81 3	99.37 185	97.24 117	99.73 54	99.70 56

save fliter					99.46 52	98.38 35	98.21 236	98.71 119	97.95 16

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 89	98.88 62					99.94 9	98.47 46	99.81 15	99.84 11

GSMVS																99.20 147

sam_mvs1												89.45 192				99.20 147

sam_mvs												88.99 205

MTGPA								98.74 111

test_post1							96.68 372				30.43 424	87.85 238	98.69 272	92.59 278

test_post											31.83 423	88.83 212	98.91 248

patchmatchnet-post											95.10 379	89.42 193	98.89 252

MTMP							98.89 110	94.14 403

gm-plane-assit					95.88 355	87.47 385			89.74 361		96.94 319		99.19 204	93.32 257

test9_res														96.39 156	99.57 86	99.69 59

agg_prior2														95.87 172	99.57 86	99.68 64

test_prior4						98.01 64	97.86 285

test_prior				99.19 43	99.31 67	98.22 51		98.84 79					99.70 122			99.65 72

新几何2							97.64 305

旧先验1					99.29 76	97.48 82		98.70 123			99.09 96	95.56 52			99.47 105	99.61 78

无先验							97.58 310	98.72 116	91.38 324				99.87 61	93.36 256		99.60 80

原ACMM2							97.67 302

testdata2													99.89 50	91.65 304

segment_acmp												96.85 14

testdata1							97.32 329		96.34 102

plane_prior7					97.42 273	94.63 225

plane_prior6					97.35 280	94.61 228						87.09 250

plane_prior5								98.56 160					99.03 228	96.07 162	94.27 260	96.92 279

plane_prior4											98.28 192

plane_prior2							98.80 142		97.28 49

plane_prior1					97.37 279

plane_prior						94.60 230	98.44 210		96.74 82						94.22 262

n2								0.00 432

nn								0.00 432

door-mid								94.37 399

test11								98.66 135

door								94.64 397

HQP5-MVS						94.25 246

BP-MVS														95.30 192

HQP3-MVS								98.46 184							94.18 264

HQP2-MVS												86.75 256

NP-MVS					97.28 282	94.51 233					97.73 241

ACMMP++_ref															92.97 292

ACMMP++															93.61 281

Test By Simon												94.64 84

High-resolution multi-view benchmark