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.

MM		97.29 19	96.98 26	98.23 11	98.01 107	95.03 25	98.07 52	95.76 281	97.78 1	97.52 40	98.80 22	88.09 102	99.86 8	99.44 1	99.37 56	99.80 1

MVS_0304		97.04 28	96.73 42	97.96 23	97.60 134	94.36 34	98.01 57	94.09 347	97.33 2	96.29 86	98.79 24	89.73 82	99.86 8	99.36 2	99.42 46	99.67 13

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 57	98.25 86	92.59 82	97.81 88	98.68 13	94.93 30	99.24 3	98.87 15	93.52 20	99.79 33	99.32 3	99.21 69	99.40 54

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 50	98.21 92	92.75 76	97.83 84	98.73 9	95.04 28	99.30 1	98.84 20	93.34 22	99.78 35	99.32 3	99.13 77	99.50 40

test_fmvsm_n_1920		97.55 11	97.89 3	96.53 79	98.41 74	91.73 107	98.01 57	99.02 1	96.37 4	99.30 1	98.92 10	92.39 37	99.79 33	99.16 5	99.46 39	98.08 167

test_fmvsmconf_n		97.49 12	97.56 9	97.29 53	97.44 140	92.37 88	97.91 75	98.88 4	95.83 8	98.92 12	99.05 5	91.45 53	99.80 30	99.12 6	99.46 39	99.69 12

fmvsm_s_conf0.5_n		96.85 39	97.13 16	96.04 119	98.07 105	90.28 169	97.97 67	98.76 8	94.93 30	98.84 16	99.06 4	88.80 92	99.65 58	99.06 7	98.63 99	98.18 156

test_fmvsmconf0.1_n		97.09 24	97.06 19	97.19 62	95.67 239	92.21 94	97.95 70	98.27 39	95.78 10	98.40 25	99.00 6	89.99 78	99.78 35	99.06 7	99.41 49	99.59 22

fmvsm_s_conf0.5_n_a		96.75 46	96.93 29	96.20 111	97.64 129	90.72 156	98.00 59	98.73 9	94.55 50	98.91 13	99.08 3	88.22 101	99.63 67	98.91 9	98.37 111	98.25 151

test_fmvsmvis_n_1920		96.70 47	96.84 33	96.31 100	96.62 184	91.73 107	97.98 61	98.30 32	96.19 5	96.10 93	98.95 8	89.42 83	99.76 38	98.90 10	99.08 81	97.43 199

fmvsm_s_conf0.1_n		96.58 54	96.77 40	96.01 123	96.67 182	90.25 170	97.91 75	98.38 23	94.48 53	98.84 16	99.14 1	88.06 103	99.62 68	98.82 11	98.60 101	98.15 160

test_fmvsmconf0.01_n		96.15 65	95.85 68	97.03 67	92.66 357	91.83 106	97.97 67	97.84 120	95.57 12	97.53 39	99.00 6	84.20 161	99.76 38	98.82 11	99.08 81	99.48 44

fmvsm_s_conf0.1_n_a		96.40 58	96.47 53	96.16 113	95.48 247	90.69 157	97.91 75	98.33 29	94.07 64	98.93 9	99.14 1	87.44 117	99.61 69	98.63 13	98.32 113	98.18 156

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 27	98.81 7	98.30 32	94.76 43	98.30 26	98.90 12	93.77 17	99.68 54	97.93 14	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_vis1_n_1920		94.17 114	94.58 97	92.91 280	97.42 141	82.02 341	97.83 84	97.85 116	94.68 46	98.10 29	98.49 38	70.15 337	99.32 117	97.91 15	98.82 92	97.40 201

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

No_MVS				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

patch_mono-2		96.83 41	97.44 13	95.01 172	99.05 39	85.39 302	96.98 176	98.77 7	94.70 45	97.99 32	98.66 27	93.61 19	99.91 1	97.67 18	99.50 33	99.72 11

test_vis1_n		92.37 190	92.26 175	92.72 287	94.75 297	82.64 333	98.02 56	96.80 231	91.18 167	97.77 37	97.93 88	58.02 381	98.29 222	97.63 19	98.21 117	97.23 210

test_fmvs1_n		92.73 180	92.88 147	92.29 297	96.08 226	81.05 349	97.98 61	97.08 201	90.72 182	96.79 62	98.18 70	63.07 373	98.45 207	97.62 20	98.42 110	97.36 202

test_fmvs1		93.21 153	93.53 123	92.25 299	96.55 193	81.20 348	97.40 138	96.96 214	90.68 184	96.80 61	98.04 79	69.25 342	98.40 210	97.58 21	98.50 104	97.16 211

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 39	95.13 23	99.19 4	98.89 13	95.54 5	99.85 18	97.52 22	99.66 10	99.56 29

test_241102_TWO								98.27 39	95.13 23	98.93 9	98.89 13	94.99 11	99.85 18	97.52 22	99.65 12	99.74 8

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 116	94.92 32	98.73 18	98.87 15	95.08 8	99.84 23	97.52 22	99.67 6	99.48 44
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_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 36					99.86 8	97.52 22	99.67 6	99.75 6

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 58	95.39 11	99.29 1	98.28 36	94.78 41	98.93 9	98.87 15	96.04 2	99.86 8	97.45 26	99.58 21	99.59 22

test_0728_THIRD									94.78 41	98.73 18	98.87 15	95.87 4	99.84 23	97.45 26	99.72 2	99.77 2

EC-MVSNet		96.42 57	96.47 53	96.26 106	97.01 162	91.52 119	98.89 5	97.75 123	94.42 55	96.64 71	97.68 107	89.32 84	98.60 195	97.45 26	99.11 80	98.67 121

IU-MVS					99.42 7	95.39 11		97.94 104	90.40 198	98.94 8				97.41 29	99.66 10	99.74 8

dcpmvs_2		96.37 60	97.05 22	94.31 216	98.96 46	84.11 320	97.56 119	97.51 153	93.92 69	97.43 45	98.52 35	92.75 29	99.32 117	97.32 30	99.50 33	99.51 37

CS-MVS		96.86 37	97.06 19	96.26 106	98.16 98	91.16 140	99.09 3	97.87 111	95.30 18	97.06 56	98.03 80	91.72 46	98.71 185	97.10 31	99.17 73	98.90 102

TSAR-MVS + MP.		97.42 13	97.33 15	97.69 40	99.25 27	94.24 39	98.07 52	97.85 116	93.72 75	98.57 21	98.35 51	93.69 18	99.40 110	97.06 32	99.46 39	99.44 49
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		97.68 6	97.44 13	98.37 7	98.90 50	95.86 6	97.27 151	98.08 74	95.81 9	97.87 36	98.31 60	94.26 13	99.68 54	97.02 33	99.49 36	99.57 26

SD-MVS		97.41 14	97.53 11	97.06 66	98.57 69	94.46 31	97.92 73	98.14 64	94.82 38	99.01 6	98.55 33	94.18 14	97.41 325	96.94 34	99.64 13	99.32 62
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
CS-MVS-test		96.89 35	97.04 23	96.45 90	98.29 82	91.66 113	99.03 4	97.85 116	95.84 7	96.90 59	97.97 86	91.24 59	98.75 179	96.92 35	99.33 58	98.94 97

CANet		96.39 59	96.02 64	97.50 45	97.62 131	93.38 61	97.02 171	97.96 102	95.42 15	94.86 125	97.81 99	87.38 119	99.82 28	96.88 36	99.20 71	99.29 63

TSAR-MVS + GP.		96.69 49	96.49 52	97.27 56	98.31 81	93.39 60	96.79 190	96.72 234	94.17 62	97.44 43	97.66 110	92.76 28	99.33 115	96.86 37	97.76 131	99.08 83

DeepPCF-MVS	93.97 1	96.61 52	97.09 18	95.15 163	98.09 101	86.63 279	96.00 253	98.15 62	95.43 14	97.95 33	98.56 31	93.40 21	99.36 114	96.77 38	99.48 37	99.45 47

test_cas_vis1_n_1920		94.48 108	94.55 101	94.28 218	96.78 175	86.45 283	97.63 112	97.64 138	93.32 94	97.68 38	98.36 50	73.75 317	99.08 144	96.73 39	99.05 83	97.31 206

SMA-MVS		97.35 16	97.03 24	98.30 8	99.06 38	95.42 10	97.94 71	98.18 57	90.57 194	98.85 15	98.94 9	93.33 23	99.83 26	96.72 40	99.68 4	99.63 17
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
DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 159	98.35 27	95.16 22	98.71 20	98.80 22	95.05 10	99.89 3	96.70 41	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.59 10	97.54 10	97.73 36	99.40 11	93.77 54	98.53 15	98.29 34	95.55 13	98.56 22	97.81 99	93.90 15	99.65 58	96.62 42	99.21 69	99.77 2
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
MSLP-MVS++		96.94 33	97.06 19	96.59 77	98.72 55	91.86 105	97.67 103	98.49 19	94.66 48	97.24 49	98.41 47	92.31 40	98.94 159	96.61 43	99.46 39	98.96 94

MP-MVS-pluss		96.70 47	96.27 61	97.98 21	99.23 30	94.71 28	96.96 178	98.06 82	90.67 185	95.55 113	98.78 25	91.07 63	99.86 8	96.58 44	99.55 24	99.38 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 77	94.25 38	98.43 24	98.27 39	95.34 17	98.11 28	98.56 31	94.53 12	99.71 46	96.57 45	99.62 15	99.65 15
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 21	96.84 33	98.20 14	99.30 24	95.35 15	97.12 166	98.07 79	93.54 83	96.08 94	97.69 106	93.86 16	99.71 46	96.50 46	99.39 52	99.55 32

SF-MVS		97.39 15	97.13 16	98.17 15	99.02 42	95.28 19	98.23 40	98.27 39	92.37 129	98.27 27	98.65 29	93.33 23	99.72 45	96.49 47	99.52 28	99.51 37

EI-MVSNet-Vis-set		96.51 55	96.47 53	96.63 74	98.24 87	91.20 135	96.89 182	97.73 126	94.74 44	96.49 78	98.49 38	90.88 68	99.58 77	96.44 48	98.32 113	99.13 77

VDD-MVS		93.82 133	93.08 140	96.02 121	97.88 116	89.96 180	97.72 98	95.85 278	92.43 127	95.86 102	98.44 44	68.42 350	99.39 111	96.31 49	94.85 192	98.71 118

ACMMP_NAP		97.20 20	96.86 31	98.23 11	99.09 34	95.16 22	97.60 115	98.19 55	92.82 118	97.93 34	98.74 26	91.60 51	99.86 8	96.26 50	99.52 28	99.67 13

diffmvs		95.25 87	95.13 85	95.63 141	96.43 205	89.34 202	95.99 254	97.35 182	92.83 117	96.31 85	97.37 128	86.44 130	98.67 188	96.26 50	97.19 149	98.87 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-UG-set		96.34 61	96.30 60	96.47 87	98.20 93	90.93 147	96.86 184	97.72 128	94.67 47	96.16 91	98.46 42	90.43 73	99.58 77	96.23 52	97.96 125	98.90 102

SR-MVS		97.01 30	96.86 31	97.47 46	99.09 34	93.27 66	97.98 61	98.07 79	93.75 74	97.45 42	98.48 41	91.43 55	99.59 74	96.22 53	99.27 62	99.54 33

xiu_mvs_v1_base_debu		95.01 93	94.76 91	95.75 133	96.58 188	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 242

xiu_mvs_v1_base		95.01 93	94.76 91	95.75 133	96.58 188	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 242

xiu_mvs_v1_base_debi		95.01 93	94.76 91	95.75 133	96.58 188	91.71 109	96.25 239	97.35 182	92.99 107	96.70 66	96.63 174	82.67 191	99.44 106	96.22 53	97.46 135	96.11 242

alignmvs		95.87 73	95.23 82	97.78 31	97.56 138	95.19 21	97.86 79	97.17 193	94.39 57	96.47 80	96.40 187	85.89 138	99.20 127	96.21 57	95.11 190	98.95 96

canonicalmvs		96.02 68	95.45 75	97.75 35	97.59 135	95.15 23	98.28 32	97.60 142	94.52 52	96.27 88	96.12 200	87.65 111	99.18 130	96.20 58	94.82 194	98.91 101

MTAPA		97.08 25	96.78 39	97.97 22	99.37 16	94.42 33	97.24 153	98.08 74	95.07 27	96.11 92	98.59 30	90.88 68	99.90 2	96.18 59	99.50 33	99.58 25

APD-MVS_3200maxsize		96.81 42	96.71 44	97.12 64	99.01 45	92.31 91	97.98 61	98.06 82	93.11 104	97.44 43	98.55 33	90.93 66	99.55 87	96.06 60	99.25 66	99.51 37

SR-MVS-dyc-post		96.88 36	96.80 38	97.11 65	99.02 42	92.34 89	97.98 61	98.03 91	93.52 85	97.43 45	98.51 36	91.40 56	99.56 85	96.05 61	99.26 64	99.43 51

RE-MVS-def			96.72 43		99.02 42	92.34 89	97.98 61	98.03 91	93.52 85	97.43 45	98.51 36	90.71 70		96.05 61	99.26 64	99.43 51

MVS_111021_HR		96.68 51	96.58 49	96.99 68	98.46 70	92.31 91	96.20 244	98.90 3	94.30 60	95.86 102	97.74 104	92.33 38	99.38 113	96.04 63	99.42 46	99.28 65

PHI-MVS		96.77 44	96.46 56	97.71 39	98.40 75	94.07 46	98.21 43	98.45 22	89.86 207	97.11 54	98.01 83	92.52 35	99.69 52	96.03 64	99.53 27	99.36 60

casdiffmvs_mvg		95.81 74	95.57 71	96.51 83	96.87 167	91.49 120	97.50 125	97.56 149	93.99 67	95.13 122	97.92 89	87.89 107	98.78 174	95.97 65	97.33 143	99.26 67
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS++		97.34 17	96.97 27	98.47 5	99.08 36	96.16 4	97.55 122	97.97 101	95.59 11	96.61 72	97.89 90	92.57 34	99.84 23	95.95 66	99.51 31	99.40 54

DELS-MVS		96.61 52	96.38 59	97.30 52	97.79 120	93.19 67	95.96 255	98.18 57	95.23 19	95.87 101	97.65 111	91.45 53	99.70 51	95.87 67	99.44 45	99.00 92
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_LR		96.24 64	96.19 63	96.39 95	98.23 91	91.35 127	96.24 242	98.79 6	93.99 67	95.80 104	97.65 111	89.92 80	99.24 124	95.87 67	99.20 71	98.58 123

h-mvs33		94.15 116	93.52 125	96.04 119	97.81 119	90.22 171	97.62 114	97.58 145	95.19 20	96.74 64	97.45 124	83.67 168	99.61 69	95.85 69	79.73 365	98.29 150

hse-mvs2		93.45 146	92.99 142	94.81 186	97.02 161	88.59 224	96.69 201	96.47 253	95.19 20	96.74 64	96.16 199	83.67 168	98.48 206	95.85 69	79.13 369	97.35 204

NCCC		97.30 18	97.03 24	98.11 17	98.77 53	95.06 24	97.34 144	98.04 89	95.96 6	97.09 55	97.88 92	93.18 25	99.71 46	95.84 71	99.17 73	99.56 29

VNet		95.89 72	95.45 75	97.21 60	98.07 105	92.94 73	97.50 125	98.15 62	93.87 71	97.52 40	97.61 117	85.29 145	99.53 91	95.81 72	95.27 186	99.16 73

PC_three_1452									90.77 179	98.89 14	98.28 65	96.24 1	98.35 217	95.76 73	99.58 21	99.59 22

9.14			96.75 41		98.93 47		97.73 95	98.23 50	91.28 163	97.88 35	98.44 44	93.00 26	99.65 58	95.76 73	99.47 38

XVS		97.18 21	96.96 28	97.81 28	99.38 14	94.03 48	98.59 12	98.20 52	94.85 34	96.59 74	98.29 63	91.70 48	99.80 30	95.66 75	99.40 50	99.62 18

X-MVStestdata		91.71 215	89.67 276	97.81 28	99.38 14	94.03 48	98.59 12	98.20 52	94.85 34	96.59 74	32.69 403	91.70 48	99.80 30	95.66 75	99.40 50	99.62 18

baseline		95.58 79	95.42 77	96.08 115	96.78 175	90.41 167	97.16 163	97.45 166	93.69 78	95.65 111	97.85 96	87.29 120	98.68 187	95.66 75	97.25 147	99.13 77

ETV-MVS		96.02 68	95.89 67	96.40 93	97.16 148	92.44 86	97.47 131	97.77 122	94.55 50	96.48 79	94.51 275	91.23 61	98.92 161	95.65 78	98.19 118	97.82 181

casdiffmvs		95.64 77	95.49 73	96.08 115	96.76 180	90.45 165	97.29 150	97.44 170	94.00 66	95.46 117	97.98 85	87.52 115	98.73 181	95.64 79	97.33 143	99.08 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HFP-MVS		97.14 23	96.92 30	97.83 26	99.42 7	94.12 44	98.52 16	98.32 30	93.21 96	97.18 50	98.29 63	92.08 42	99.83 26	95.63 80	99.59 17	99.54 33

ACMMPR		97.07 26	96.84 33	97.79 30	99.44 6	93.88 50	98.52 16	98.31 31	93.21 96	97.15 51	98.33 57	91.35 57	99.86 8	95.63 80	99.59 17	99.62 18

HPM-MVS		96.69 49	96.45 57	97.40 48	99.36 18	93.11 69	98.87 6	98.06 82	91.17 168	96.40 83	97.99 84	90.99 65	99.58 77	95.61 82	99.61 16	99.49 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		97.02 29	96.81 37	97.64 43	99.33 21	93.54 57	98.80 8	98.28 36	92.99 107	96.45 82	98.30 62	91.90 45	99.85 18	95.61 82	99.68 4	99.54 33

DeepC-MVS	93.07 3	96.06 66	95.66 70	97.29 53	97.96 109	93.17 68	97.30 149	98.06 82	93.92 69	93.38 158	98.66 27	86.83 125	99.73 42	95.60 84	99.22 68	98.96 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		96.96 31	96.67 45	97.85 25	99.37 16	94.12 44	98.49 20	98.18 57	92.64 124	96.39 84	98.18 70	91.61 50	99.88 4	95.59 85	99.55 24	99.57 26

mvsmamba		93.83 132	93.46 128	94.93 181	94.88 290	90.85 150	98.55 14	95.49 298	94.24 61	91.29 214	96.97 149	83.04 182	98.14 234	95.56 86	91.17 258	95.78 256

region2R		97.07 26	96.84 33	97.77 33	99.46 2	93.79 52	98.52 16	98.24 47	93.19 99	97.14 52	98.34 54	91.59 52	99.87 7	95.46 87	99.59 17	99.64 16

iter_conf05		93.18 158	92.63 159	94.83 183	96.64 183	90.69 157	97.60 115	95.53 297	92.52 125	91.58 201	96.64 168	76.35 293	98.13 235	95.43 88	91.42 253	95.68 266

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 66	96.04 2	99.24 124	95.36 89	99.59 17	99.56 29

iter_conf_final		93.60 139	93.11 139	95.04 169	97.13 151	91.30 128	97.92 73	95.65 290	92.98 112	91.60 200	96.64 168	79.28 253	98.13 235	95.34 90	91.49 250	95.70 264

lupinMVS		94.99 97	94.56 98	96.29 104	96.34 209	91.21 133	95.83 262	96.27 261	88.93 239	96.22 89	96.88 155	86.20 135	98.85 168	95.27 91	99.05 83	98.82 111

mPP-MVS		96.86 37	96.60 47	97.64 43	99.40 11	93.44 59	98.50 19	98.09 73	93.27 95	95.95 100	98.33 57	91.04 64	99.88 4	95.20 92	99.57 23	99.60 21

DeepC-MVS_fast	93.89 2	96.93 34	96.64 46	97.78 31	98.64 64	94.30 35	97.41 134	98.04 89	94.81 39	96.59 74	98.37 49	91.24 59	99.64 66	95.16 93	99.52 28	99.42 53
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		94.84 102	94.39 107	96.18 112	95.52 245	90.93 147	96.09 248	96.52 250	89.28 225	96.01 98	97.32 129	84.70 152	98.77 177	95.15 94	98.91 91	98.85 108
jason: jason.
train_agg		96.30 62	95.83 69	97.72 37	98.70 56	94.19 40	96.41 223	98.02 94	88.58 251	96.03 95	97.56 121	92.73 31	99.59 74	95.04 95	99.37 56	99.39 56

mvsany_test1		93.93 128	93.98 111	93.78 246	94.94 285	86.80 272	94.62 306	92.55 370	88.77 248	96.85 60	98.49 38	88.98 88	98.08 246	95.03 96	95.62 180	96.46 231

test_prior2							96.35 231		92.80 119	96.03 95	97.59 118	92.01 43		95.01 97	99.38 53

nrg030		94.05 123	93.31 135	96.27 105	95.22 269	94.59 29	98.34 27	97.46 161	92.93 115	91.21 218	96.64 168	87.23 122	98.22 226	94.99 98	85.80 314	95.98 246

VDDNet		93.05 164	92.07 178	96.02 121	96.84 169	90.39 168	98.08 51	95.85 278	86.22 310	95.79 105	98.46 42	67.59 353	99.19 128	94.92 99	94.85 192	98.47 135

APD-MVS		96.95 32	96.60 47	98.01 19	99.03 41	94.93 26	97.72 98	98.10 72	91.50 153	98.01 31	98.32 59	92.33 38	99.58 77	94.85 100	99.51 31	99.53 36
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
GST-MVS		96.85 39	96.52 51	97.82 27	99.36 18	94.14 43	98.29 31	98.13 65	92.72 121	96.70 66	98.06 77	91.35 57	99.86 8	94.83 101	99.28 61	99.47 46

MP-MVS		96.77 44	96.45 57	97.72 37	99.39 13	93.80 51	98.41 25	98.06 82	93.37 91	95.54 115	98.34 54	90.59 72	99.88 4	94.83 101	99.54 26	99.49 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test9_res														94.81 103	99.38 53	99.45 47

PS-MVSNAJ		95.37 83	95.33 80	95.49 151	97.35 142	90.66 160	95.31 288	97.48 156	93.85 72	96.51 77	95.70 224	88.65 95	99.65 58	94.80 104	98.27 115	96.17 237

HPM-MVS_fast		96.51 55	96.27 61	97.22 59	99.32 22	92.74 77	98.74 9	98.06 82	90.57 194	96.77 63	98.35 51	90.21 75	99.53 91	94.80 104	99.63 14	99.38 58

xiu_mvs_v2_base		95.32 85	95.29 81	95.40 156	97.22 144	90.50 163	95.44 282	97.44 170	93.70 77	96.46 81	96.18 196	88.59 98	99.53 91	94.79 106	97.81 128	96.17 237

CSCG		96.05 67	95.91 66	96.46 89	99.24 28	90.47 164	98.30 30	98.57 18	89.01 234	93.97 145	97.57 119	92.62 33	99.76 38	94.66 107	99.27 62	99.15 75

test_fmvs2		89.77 293	89.93 265	89.31 351	93.68 334	76.37 379	97.64 110	95.90 275	89.84 210	91.49 204	96.26 194	58.77 380	97.10 335	94.65 108	91.13 259	94.46 332

EIA-MVS		95.53 81	95.47 74	95.71 138	97.06 157	89.63 186	97.82 86	97.87 111	93.57 79	93.92 146	95.04 250	90.61 71	98.95 158	94.62 109	98.68 97	98.54 125

SDMVSNet		94.17 114	93.61 119	95.86 128	98.09 101	91.37 126	97.35 143	98.20 52	93.18 100	91.79 195	97.28 131	79.13 255	98.93 160	94.61 110	92.84 227	97.28 207

ZD-MVS					99.05 39	94.59 29		98.08 74	89.22 227	97.03 57	98.10 73	92.52 35	99.65 58	94.58 111	99.31 60

ACMMP		96.27 63	95.93 65	97.28 55	99.24 28	92.62 80	98.25 36	98.81 5	92.99 107	94.56 131	98.39 48	88.96 89	99.85 18	94.57 112	97.63 132	99.36 60
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
PGM-MVS		96.81 42	96.53 50	97.65 41	99.35 20	93.53 58	97.65 106	98.98 2	92.22 131	97.14 52	98.44 44	91.17 62	99.85 18	94.35 113	99.46 39	99.57 26

RRT_MVS		93.10 160	92.83 149	93.93 239	94.76 295	88.04 243	98.47 22	96.55 249	93.44 88	90.01 245	97.04 146	80.64 227	97.93 278	94.33 114	90.21 275	95.83 251

ET-MVSNet_ETH3D		91.49 229	90.11 257	95.63 141	96.40 206	91.57 118	95.34 285	93.48 360	90.60 193	75.58 382	95.49 235	80.08 238	96.79 347	94.25 115	89.76 279	98.52 127

LFMVS		93.60 139	92.63 159	96.52 80	98.13 100	91.27 130	97.94 71	93.39 361	90.57 194	96.29 86	98.31 60	69.00 343	99.16 132	94.18 116	95.87 173	99.12 80

MVSFormer		95.37 83	95.16 84	95.99 124	96.34 209	91.21 133	98.22 41	97.57 146	91.42 157	96.22 89	97.32 129	86.20 135	97.92 279	94.07 117	99.05 83	98.85 108

test_djsdf		93.07 163	92.76 152	94.00 230	93.49 340	88.70 222	98.22 41	97.57 146	91.42 157	90.08 243	95.55 232	82.85 188	97.92 279	94.07 117	91.58 248	95.40 279

mvs_anonymous		93.82 133	93.74 115	94.06 226	96.44 204	85.41 300	95.81 263	97.05 206	89.85 209	90.09 242	96.36 189	87.44 117	97.75 295	93.97 119	96.69 160	99.02 86

VPA-MVSNet		93.24 152	92.48 169	95.51 149	95.70 237	92.39 87	97.86 79	98.66 16	92.30 130	92.09 189	95.37 238	80.49 230	98.40 210	93.95 120	85.86 313	95.75 261

agg_prior2														93.94 121	99.38 53	99.50 40

mvs_tets		92.31 194	91.76 188	93.94 237	93.41 343	88.29 233	97.63 112	97.53 151	92.04 140	88.76 281	96.45 184	74.62 309	98.09 245	93.91 122	91.48 251	95.45 275

Effi-MVS+		94.93 98	94.45 105	96.36 98	96.61 185	91.47 122	96.41 223	97.41 175	91.02 174	94.50 132	95.92 208	87.53 114	98.78 174	93.89 123	96.81 155	98.84 110

jajsoiax		92.42 187	91.89 186	94.03 229	93.33 346	88.50 229	97.73 95	97.53 151	92.00 142	88.85 278	96.50 182	75.62 301	98.11 241	93.88 124	91.56 249	95.48 270

XVG-OURS-SEG-HR		93.86 131	93.55 121	94.81 186	97.06 157	88.53 228	95.28 289	97.45 166	91.68 149	94.08 142	97.68 107	82.41 199	98.90 164	93.84 125	92.47 233	96.98 214

PS-MVSNAJss		93.74 136	93.51 126	94.44 206	93.91 326	89.28 207	97.75 92	97.56 149	92.50 126	89.94 246	96.54 180	88.65 95	98.18 231	93.83 126	90.90 265	95.86 247

EPNet		95.20 90	94.56 98	97.14 63	92.80 354	92.68 79	97.85 82	94.87 330	96.64 3	92.46 174	97.80 101	86.23 132	99.65 58	93.72 127	98.62 100	99.10 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		95.27 86	94.91 89	96.38 96	98.20 93	90.86 149	97.27 151	98.25 45	90.21 199	94.18 139	97.27 133	87.48 116	99.73 42	93.53 128	97.77 130	98.55 124

CPTT-MVS		95.57 80	95.19 83	96.70 71	99.27 26	91.48 121	98.33 28	98.11 70	87.79 277	95.17 121	98.03 80	87.09 123	99.61 69	93.51 129	99.42 46	99.02 86

MVSTER		93.20 154	92.81 151	94.37 210	96.56 191	89.59 189	97.06 168	97.12 196	91.24 164	91.30 211	95.96 206	82.02 206	98.05 253	93.48 130	90.55 270	95.47 273

PVSNet_BlendedMVS		94.06 122	93.92 112	94.47 204	98.27 83	89.46 197	96.73 195	98.36 24	90.17 200	94.36 134	95.24 244	88.02 104	99.58 77	93.44 131	90.72 268	94.36 336

PVSNet_Blended		94.87 101	94.56 98	95.81 130	98.27 83	89.46 197	95.47 281	98.36 24	88.84 242	94.36 134	96.09 204	88.02 104	99.58 77	93.44 131	98.18 119	98.40 143

3Dnovator	91.36 5	95.19 91	94.44 106	97.44 47	96.56 191	93.36 63	98.65 11	98.36 24	94.12 63	89.25 271	98.06 77	82.20 203	99.77 37	93.41 133	99.32 59	99.18 72

EPP-MVSNet		95.22 89	95.04 87	95.76 131	97.49 139	89.56 190	98.67 10	97.00 212	90.69 183	94.24 137	97.62 116	89.79 81	98.81 172	93.39 134	96.49 164	98.92 100

CHOSEN 280x420		93.12 159	92.72 157	94.34 213	96.71 181	87.27 260	90.29 379	97.72 128	86.61 303	91.34 208	95.29 240	84.29 160	98.41 209	93.25 135	98.94 89	97.35 204

3Dnovator+	91.43 4	95.40 82	94.48 104	98.16 16	96.90 166	95.34 16	98.48 21	97.87 111	94.65 49	88.53 286	98.02 82	83.69 167	99.71 46	93.18 136	98.96 88	99.44 49

test_yl		94.78 104	94.23 108	96.43 91	97.74 122	91.22 131	96.85 185	97.10 198	91.23 165	95.71 107	96.93 150	84.30 158	99.31 119	93.10 137	95.12 188	98.75 113

DCV-MVSNet		94.78 104	94.23 108	96.43 91	97.74 122	91.22 131	96.85 185	97.10 198	91.23 165	95.71 107	96.93 150	84.30 158	99.31 119	93.10 137	95.12 188	98.75 113

test_vis1_rt		86.16 330	85.06 331	89.46 349	93.47 342	80.46 356	96.41 223	86.61 397	85.22 324	79.15 375	88.64 376	52.41 389	97.06 336	93.08 139	90.57 269	90.87 380

test1111		93.19 155	92.82 150	94.30 217	97.58 137	84.56 315	98.21 43	89.02 389	93.53 84	94.58 130	98.21 67	72.69 320	99.05 151	93.06 140	98.48 107	99.28 65

ECVR-MVS		93.19 155	92.73 156	94.57 201	97.66 127	85.41 300	98.21 43	88.23 391	93.43 89	94.70 128	98.21 67	72.57 321	99.07 148	93.05 141	98.49 105	99.25 68

HQP_MVS		93.78 135	93.43 131	94.82 184	96.21 213	89.99 176	97.74 93	97.51 153	94.85 34	91.34 208	96.64 168	81.32 217	98.60 195	93.02 142	92.23 236	95.86 247

plane_prior5								97.51 153					98.60 195	93.02 142	92.23 236	95.86 247

test2506		91.60 221	90.78 227	94.04 228	97.66 127	83.81 323	98.27 33	75.53 406	93.43 89	95.23 119	98.21 67	67.21 356	99.07 148	93.01 144	98.49 105	99.25 68

MVS_Test		94.89 100	94.62 95	95.68 139	96.83 171	89.55 191	96.70 199	97.17 193	91.17 168	95.60 112	96.11 203	87.87 108	98.76 178	93.01 144	97.17 150	98.72 116

bld_raw_dy_0_64		92.37 190	91.69 192	94.39 209	94.28 318	89.73 185	97.71 100	93.65 358	92.78 120	90.46 227	96.67 166	75.88 296	97.97 265	92.92 146	90.89 266	95.48 270

CLD-MVS		92.98 167	92.53 166	94.32 214	96.12 223	89.20 210	95.28 289	97.47 159	92.66 122	89.90 247	95.62 228	80.58 228	98.40 210	92.73 147	92.40 234	95.38 281
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 137	93.35 134	94.80 189	97.07 154	88.61 223	94.79 303	97.46 161	91.97 143	93.99 143	97.86 95	81.74 212	98.88 165	92.64 148	92.67 232	96.92 218

旧先验2							95.94 256		81.66 362	97.34 48			98.82 170	92.26 149

CDPH-MVS		95.97 70	95.38 78	97.77 33	98.93 47	94.44 32	96.35 231	97.88 109	86.98 296	96.65 70	97.89 90	91.99 44	99.47 102	92.26 149	99.46 39	99.39 56

FIs		94.09 121	93.70 116	95.27 159	95.70 237	92.03 101	98.10 49	98.68 13	93.36 93	90.39 229	96.70 162	87.63 112	97.94 275	92.25 151	90.50 272	95.84 250

LPG-MVS_test		92.94 170	92.56 163	94.10 224	96.16 218	88.26 235	97.65 106	97.46 161	91.29 160	90.12 239	97.16 139	79.05 257	98.73 181	92.25 151	91.89 244	95.31 286

LGP-MVS_train				94.10 224	96.16 218	88.26 235		97.46 161	91.29 160	90.12 239	97.16 139	79.05 257	98.73 181	92.25 151	91.89 244	95.31 286

cascas		91.20 245	90.08 258	94.58 200	94.97 281	89.16 213	93.65 345	97.59 144	79.90 373	89.40 263	92.92 334	75.36 302	98.36 216	92.14 154	94.75 196	96.23 233

OPM-MVS		93.28 151	92.76 152	94.82 184	94.63 303	90.77 154	96.65 205	97.18 191	93.72 75	91.68 199	97.26 134	79.33 252	98.63 192	92.13 155	92.28 235	95.07 299
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 155

HQP-MVS		93.19 155	92.74 155	94.54 202	95.86 230	89.33 203	96.65 205	97.39 176	93.55 80	90.14 233	95.87 210	80.95 220	98.50 203	92.13 155	92.10 241	95.78 256

DP-MVS Recon		95.68 76	95.12 86	97.37 49	99.19 31	94.19 40	97.03 169	98.08 74	88.35 260	95.09 123	97.65 111	89.97 79	99.48 101	92.08 158	98.59 102	98.44 140

VPNet		92.23 200	91.31 206	94.99 173	95.56 243	90.96 145	97.22 158	97.86 115	92.96 114	90.96 220	96.62 177	75.06 304	98.20 228	91.90 159	83.65 347	95.80 254

sss		94.51 107	93.80 114	96.64 72	97.07 154	91.97 103	96.32 234	98.06 82	88.94 238	94.50 132	96.78 157	84.60 153	99.27 122	91.90 159	96.02 169	98.68 120

anonymousdsp		92.16 202	91.55 197	93.97 233	92.58 359	89.55 191	97.51 124	97.42 174	89.42 222	88.40 288	94.84 259	80.66 226	97.88 284	91.87 161	91.28 256	94.48 331

test_fmvs3		83.21 345	83.02 342	83.78 367	86.77 390	68.34 393	96.76 193	94.91 325	86.49 304	84.14 349	89.48 372	36.04 397	91.73 389	91.86 162	80.77 362	91.26 379

ACMP	89.59 10	92.62 182	92.14 177	94.05 227	96.40 206	88.20 238	97.36 142	97.25 190	91.52 152	88.30 291	96.64 168	78.46 269	98.72 184	91.86 162	91.48 251	95.23 293
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 138	92.92 145	95.87 127	98.24 87	89.88 181	94.58 308	98.49 19	85.06 328	93.78 148	95.78 219	82.86 187	98.67 188	91.77 164	95.71 178	99.07 85

UGNet		94.04 124	93.28 136	96.31 100	96.85 168	91.19 136	97.88 78	97.68 133	94.40 56	93.00 166	96.18 196	73.39 319	99.61 69	91.72 165	98.46 108	98.13 161
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
UniMVSNet_NR-MVSNet		93.37 148	92.67 158	95.47 154	95.34 258	92.83 74	97.17 162	98.58 17	92.98 112	90.13 237	95.80 215	88.37 100	97.85 285	91.71 166	83.93 342	95.73 263

DU-MVS		92.90 172	92.04 179	95.49 151	94.95 283	92.83 74	97.16 163	98.24 47	93.02 106	90.13 237	95.71 222	83.47 171	97.85 285	91.71 166	83.93 342	95.78 256

Effi-MVS+-dtu		93.08 162	93.21 138	92.68 290	96.02 227	83.25 330	97.14 165	96.72 234	93.85 72	91.20 219	93.44 326	83.08 180	98.30 221	91.69 168	95.73 177	96.50 228

UniMVSNet (Re)		93.31 150	92.55 164	95.61 143	95.39 252	93.34 64	97.39 139	98.71 11	93.14 103	90.10 241	94.83 260	87.71 109	98.03 257	91.67 169	83.99 341	95.46 274

LCM-MVSNet-Re		92.50 183	92.52 167	92.44 292	96.82 173	81.89 342	96.92 180	93.71 357	92.41 128	84.30 345	94.60 271	85.08 148	97.03 338	91.51 170	97.36 141	98.40 143

FC-MVSNet-test		93.94 127	93.57 120	95.04 169	95.48 247	91.45 124	98.12 48	98.71 11	93.37 91	90.23 232	96.70 162	87.66 110	97.85 285	91.49 171	90.39 273	95.83 251

PMMVS		92.86 174	92.34 172	94.42 208	94.92 286	86.73 275	94.53 310	96.38 257	84.78 333	94.27 136	95.12 249	83.13 179	98.40 210	91.47 172	96.49 164	98.12 162

Vis-MVSNet		95.23 88	94.81 90	96.51 83	97.18 147	91.58 117	98.26 35	98.12 67	94.38 58	94.90 124	98.15 72	82.28 201	98.92 161	91.45 173	98.58 103	99.01 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 116	93.51 126	96.06 117	98.27 83	89.38 200	95.18 295	98.48 21	85.60 318	93.76 149	97.11 142	83.15 178	99.61 69	91.33 174	98.72 96	99.19 71

OMC-MVS		95.09 92	94.70 94	96.25 109	98.46 70	91.28 129	96.43 221	97.57 146	92.04 140	94.77 127	97.96 87	87.01 124	99.09 142	91.31 175	96.77 156	98.36 147

MG-MVS		95.61 78	95.38 78	96.31 100	98.42 73	90.53 162	96.04 250	97.48 156	93.47 87	95.67 110	98.10 73	89.17 86	99.25 123	91.27 176	98.77 94	99.13 77

ACMM	89.79 8	92.96 168	92.50 168	94.35 211	96.30 211	88.71 221	97.58 117	97.36 181	91.40 159	90.53 225	96.65 167	79.77 244	98.75 179	91.24 177	91.64 246	95.59 268
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 106	94.02 110	96.79 70	97.71 124	92.05 100	96.59 214	97.35 182	90.61 191	94.64 129	96.93 150	86.41 131	99.39 111	91.20 178	94.71 198	98.94 97

testing11		91.68 218	90.75 229	94.47 204	96.53 196	86.56 281	95.76 267	94.51 338	91.10 172	91.24 217	93.59 320	68.59 347	98.86 166	91.10 179	94.29 202	98.00 170

tt0805		91.09 249	90.07 261	94.16 222	95.61 240	88.31 232	97.56 119	96.51 251	89.56 216	89.17 272	95.64 227	67.08 360	98.38 215	91.07 180	88.44 292	95.80 254

Anonymous20240529		91.98 208	90.73 231	95.73 136	98.14 99	89.40 199	97.99 60	97.72 128	79.63 374	93.54 153	97.41 127	69.94 339	99.56 85	91.04 181	91.11 260	98.22 153

AUN-MVS		91.76 214	90.75 229	94.81 186	97.00 163	88.57 225	96.65 205	96.49 252	89.63 214	92.15 185	96.12 200	78.66 266	98.50 203	90.83 182	79.18 368	97.36 202

mvsany_test3		83.59 343	82.44 347	87.03 361	83.80 393	73.82 384	93.70 341	90.92 383	86.42 305	82.51 360	90.26 365	46.76 392	95.71 361	90.82 183	76.76 375	91.57 374

CANet_DTU		94.37 109	93.65 118	96.55 78	96.46 203	92.13 98	96.21 243	96.67 241	94.38 58	93.53 154	97.03 147	79.34 251	99.71 46	90.76 184	98.45 109	97.82 181

ab-mvs		93.57 142	92.55 164	96.64 72	97.28 143	91.96 104	95.40 283	97.45 166	89.81 211	93.22 164	96.28 192	79.62 248	99.46 103	90.74 185	93.11 224	98.50 130

CostFormer		91.18 248	90.70 233	92.62 291	94.84 292	81.76 343	94.09 329	94.43 339	84.15 339	92.72 173	93.77 312	79.43 250	98.20 228	90.70 186	92.18 239	97.90 174

Anonymous202405211		92.07 205	90.83 226	95.76 131	98.19 95	88.75 220	97.58 117	95.00 320	86.00 313	93.64 150	97.45 124	66.24 364	99.53 91	90.68 187	92.71 230	99.01 89

testing99		91.62 220	90.72 232	94.32 214	96.48 201	86.11 292	95.81 263	94.76 331	91.55 151	91.75 197	93.44 326	68.55 348	98.82 170	90.43 188	93.69 217	98.04 169

tpmrst		91.44 231	91.32 205	91.79 311	95.15 274	79.20 371	93.42 350	95.37 302	88.55 254	93.49 155	93.67 317	82.49 197	98.27 223	90.41 189	89.34 283	97.90 174

thisisatest0530		93.03 165	92.21 176	95.49 151	97.07 154	89.11 214	97.49 130	92.19 372	90.16 201	94.09 141	96.41 186	76.43 292	99.05 151	90.38 190	95.68 179	98.31 149

UA-Net		95.95 71	95.53 72	97.20 61	97.67 125	92.98 72	97.65 106	98.13 65	94.81 39	96.61 72	98.35 51	88.87 90	99.51 96	90.36 191	97.35 142	99.11 81

UniMVSNet_ETH3D		91.34 239	90.22 254	94.68 194	94.86 291	87.86 250	97.23 157	97.46 161	87.99 268	89.90 247	96.92 153	66.35 362	98.23 225	90.30 192	90.99 263	97.96 171

tttt0517		92.96 168	92.33 173	94.87 182	97.11 152	87.16 266	97.97 67	92.09 373	90.63 189	93.88 147	97.01 148	76.50 289	99.06 150	90.29 193	95.45 183	98.38 145

testing91		91.90 210	91.02 217	94.53 203	96.54 194	86.55 282	95.86 260	95.64 291	91.77 146	91.89 192	93.47 325	69.94 339	98.86 166	90.23 194	93.86 216	98.18 156

FA-MVS(test-final)		93.52 144	92.92 145	95.31 158	96.77 177	88.54 227	94.82 302	96.21 266	89.61 215	94.20 138	95.25 243	83.24 175	99.14 135	90.01 195	96.16 168	98.25 151

IS-MVSNet		94.90 99	94.52 102	96.05 118	97.67 125	90.56 161	98.44 23	96.22 264	93.21 96	93.99 143	97.74 104	85.55 143	98.45 207	89.98 196	97.86 126	99.14 76

miper_enhance_ethall		91.54 227	91.01 218	93.15 272	95.35 257	87.07 268	93.97 331	96.90 222	86.79 300	89.17 272	93.43 329	86.55 128	97.64 303	89.97 197	86.93 304	94.74 325

EI-MVSNet		93.03 165	92.88 147	93.48 260	95.77 235	86.98 269	96.44 219	97.12 196	90.66 187	91.30 211	97.64 114	86.56 127	98.05 253	89.91 198	90.55 270	95.41 276

IterMVS-LS		92.29 196	91.94 184	93.34 265	96.25 212	86.97 270	96.57 217	97.05 206	90.67 185	89.50 262	94.80 262	86.59 126	97.64 303	89.91 198	86.11 312	95.40 279
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 244	90.56 239	93.14 273	96.09 225	86.80 272	94.41 316	96.58 248	87.80 276	88.58 285	93.99 305	80.85 225	97.62 306	89.87 200	86.93 304	94.99 302

CDS-MVSNet		94.14 119	93.54 122	95.93 125	96.18 216	91.46 123	96.33 233	97.04 208	88.97 237	93.56 151	96.51 181	87.55 113	97.89 283	89.80 201	95.95 171	98.44 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 192	91.53 198	94.77 191	95.13 276	90.83 151	96.40 227	97.98 100	91.88 144	89.29 268	95.54 233	82.50 196	97.80 290	89.79 202	85.27 322	95.69 265

NR-MVSNet		92.34 192	91.27 209	95.53 148	94.95 283	93.05 70	97.39 139	98.07 79	92.65 123	84.46 343	95.71 222	85.00 149	97.77 294	89.71 203	83.52 348	95.78 256

Anonymous20231211		90.63 268	89.42 283	94.27 219	98.24 87	89.19 212	98.05 54	97.89 107	79.95 372	88.25 294	94.96 252	72.56 322	98.13 235	89.70 204	85.14 324	95.49 269

testdata				95.46 155	98.18 97	88.90 218		97.66 134	82.73 354	97.03 57	98.07 76	90.06 76	98.85 168	89.67 205	98.98 87	98.64 122

Baseline_NR-MVSNet		91.20 245	90.62 235	92.95 279	93.83 329	88.03 244	97.01 174	95.12 316	88.42 258	89.70 253	95.13 248	83.47 171	97.44 322	89.66 206	83.24 350	93.37 353

DPM-MVS		95.69 75	94.92 88	98.01 19	98.08 104	95.71 9	95.27 291	97.62 141	90.43 197	95.55 113	97.07 144	91.72 46	99.50 99	89.62 207	98.94 89	98.82 111

XXY-MVS		92.16 202	91.23 211	94.95 178	94.75 297	90.94 146	97.47 131	97.43 173	89.14 229	88.90 275	96.43 185	79.71 245	98.24 224	89.56 208	87.68 297	95.67 267

miper_ehance_all_eth		91.59 222	91.13 215	92.97 278	95.55 244	86.57 280	94.47 312	96.88 225	87.77 278	88.88 277	94.01 303	86.22 133	97.54 312	89.49 209	86.93 304	94.79 321

XVG-ACMP-BASELINE		90.93 258	90.21 255	93.09 274	94.31 316	85.89 293	95.33 286	97.26 188	91.06 173	89.38 264	95.44 237	68.61 346	98.60 195	89.46 210	91.05 261	94.79 321

thisisatest0515		92.29 196	91.30 207	95.25 160	96.60 186	88.90 218	94.36 318	92.32 371	87.92 270	93.43 157	94.57 272	77.28 284	99.00 155	89.42 211	95.86 174	97.86 177

c3_l		91.38 234	90.89 220	92.88 282	95.58 242	86.30 286	94.68 305	96.84 229	88.17 264	88.83 280	94.23 294	85.65 142	97.47 319	89.36 212	84.63 332	94.89 311

AdaColmap		94.34 110	93.68 117	96.31 100	98.59 66	91.68 112	96.59 214	97.81 121	89.87 206	92.15 185	97.06 145	83.62 170	99.54 89	89.34 213	98.07 122	97.70 186

TranMVSNet+NR-MVSNet		92.50 183	91.63 194	95.14 164	94.76 295	92.07 99	97.53 123	98.11 70	92.90 116	89.56 259	96.12 200	83.16 177	97.60 308	89.30 214	83.20 351	95.75 261

D2MVS		91.30 241	90.95 219	92.35 294	94.71 300	85.52 298	96.18 245	98.21 51	88.89 240	86.60 326	93.82 310	79.92 242	97.95 274	89.29 215	90.95 264	93.56 349

1314		92.81 178	92.03 180	95.14 164	95.33 261	89.52 194	96.04 250	97.44 170	87.72 281	86.25 329	95.33 239	83.84 165	98.79 173	89.26 216	97.05 152	97.11 212

v2v482		91.59 222	90.85 224	93.80 244	93.87 328	88.17 240	96.94 179	96.88 225	89.54 217	89.53 260	94.90 256	81.70 213	98.02 258	89.25 217	85.04 328	95.20 294

114514_t		93.95 126	93.06 141	96.63 74	99.07 37	91.61 114	97.46 133	97.96 102	77.99 380	93.00 166	97.57 119	86.14 137	99.33 115	89.22 218	99.15 75	98.94 97

PAPM_NR		95.01 93	94.59 96	96.26 106	98.89 51	90.68 159	97.24 153	97.73 126	91.80 145	92.93 171	96.62 177	89.13 87	99.14 135	89.21 219	97.78 129	98.97 93

baseline1		92.82 177	91.90 185	95.55 147	97.20 146	90.77 154	97.19 160	94.58 336	92.20 133	92.36 178	96.34 190	84.16 162	98.21 227	89.20 220	83.90 345	97.68 187

IB-MVS	87.33 17	89.91 286	88.28 301	94.79 190	95.26 268	87.70 254	95.12 297	93.95 352	89.35 224	87.03 318	92.49 340	70.74 332	99.19 128	89.18 221	81.37 359	97.49 197
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
HY-MVS	89.66 9	93.87 130	92.95 144	96.63 74	97.10 153	92.49 85	95.64 274	96.64 242	89.05 233	93.00 166	95.79 218	85.77 141	99.45 105	89.16 222	94.35 200	97.96 171

V42		91.58 224	90.87 221	93.73 247	94.05 323	88.50 229	97.32 147	96.97 213	88.80 247	89.71 252	94.33 286	82.54 195	98.05 253	89.01 223	85.07 326	94.64 329

sd_testset		93.10 160	92.45 170	95.05 168	98.09 101	89.21 209	96.89 182	97.64 138	93.18 100	91.79 195	97.28 131	75.35 303	98.65 190	88.99 224	92.84 227	97.28 207

OurMVSNet-221017-0		90.51 272	90.19 256	91.44 320	93.41 343	81.25 346	96.98 176	96.28 260	91.68 149	86.55 327	96.30 191	74.20 312	97.98 262	88.96 225	87.40 302	95.09 298

API-MVS		94.84 102	94.49 103	95.90 126	97.90 115	92.00 102	97.80 89	97.48 156	89.19 228	94.81 126	96.71 160	88.84 91	99.17 131	88.91 226	98.76 95	96.53 226

test-LLR		91.42 232	91.19 213	92.12 301	94.59 304	80.66 352	94.29 323	92.98 363	91.11 170	90.76 223	92.37 343	79.02 259	98.07 250	88.81 227	96.74 157	97.63 188

test-mter		90.19 282	89.54 280	92.12 301	94.59 304	80.66 352	94.29 323	92.98 363	87.68 282	90.76 223	92.37 343	67.67 352	98.07 250	88.81 227	96.74 157	97.63 188

eth_miper_zixun_eth		91.02 253	90.59 237	92.34 296	95.33 261	84.35 316	94.10 328	96.90 222	88.56 253	88.84 279	94.33 286	84.08 163	97.60 308	88.77 229	84.37 338	95.06 300

TAMVS		94.01 125	93.46 128	95.64 140	96.16 218	90.45 165	96.71 198	96.89 224	89.27 226	93.46 156	96.92 153	87.29 120	97.94 275	88.70 230	95.74 176	98.53 126

Patchmatch-RL test		87.38 317	86.24 320	90.81 332	88.74 385	78.40 375	88.12 390	93.17 362	87.11 295	82.17 362	89.29 373	81.95 208	95.60 365	88.64 231	77.02 373	98.41 142

baseline2		91.63 219	90.86 222	93.94 237	94.33 314	86.32 285	95.92 257	91.64 377	89.37 223	86.94 322	94.69 266	81.62 214	98.69 186	88.64 231	94.57 199	96.81 221

TESTMET0.1,1		90.06 284	89.42 283	91.97 304	94.41 312	80.62 354	94.29 323	91.97 375	87.28 292	90.44 228	92.47 342	68.79 344	97.67 300	88.50 233	96.60 162	97.61 192

Vis-MVSNet (Re-imp)		94.15 116	93.88 113	94.95 178	97.61 132	87.92 247	98.10 49	95.80 280	92.22 131	93.02 165	97.45 124	84.53 155	97.91 282	88.24 234	97.97 124	99.02 86

1112_ss		93.37 148	92.42 171	96.21 110	97.05 159	90.99 143	96.31 235	96.72 234	86.87 299	89.83 250	96.69 164	86.51 129	99.14 135	88.12 235	93.67 218	98.50 130

CVMVSNet		91.23 243	91.75 189	89.67 347	95.77 235	74.69 382	96.44 219	94.88 327	85.81 315	92.18 184	97.64 114	79.07 256	95.58 366	88.06 236	95.86 174	98.74 115

MAR-MVS		94.22 112	93.46 128	96.51 83	98.00 108	92.19 97	97.67 103	97.47 159	88.13 267	93.00 166	95.84 212	84.86 151	99.51 96	87.99 237	98.17 120	97.83 180
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
原ACMM1				96.38 96	98.59 66	91.09 142		97.89 107	87.41 288	95.22 120	97.68 107	90.25 74	99.54 89	87.95 238	99.12 79	98.49 132

CP-MVSNet		91.89 211	91.24 210	93.82 243	95.05 279	88.57 225	97.82 86	98.19 55	91.70 148	88.21 295	95.76 220	81.96 207	97.52 316	87.86 239	84.65 331	95.37 282

v148		90.99 254	90.38 243	92.81 285	93.83 329	85.80 294	96.78 192	96.68 239	89.45 221	88.75 282	93.93 307	82.96 186	97.82 289	87.83 240	83.25 349	94.80 319

v1144		91.37 236	90.60 236	93.68 252	93.89 327	88.23 237	96.84 187	97.03 210	88.37 259	89.69 254	94.39 282	82.04 205	97.98 262	87.80 241	85.37 319	94.84 313

DIV-MVS_self_test		90.97 256	90.33 244	92.88 282	95.36 256	86.19 290	94.46 314	96.63 245	87.82 274	88.18 296	94.23 294	82.99 183	97.53 314	87.72 242	85.57 316	94.93 307

gm-plane-assit					93.22 347	78.89 374			84.82 332		93.52 322		98.64 191	87.72 242

GeoE		93.89 129	93.28 136	95.72 137	96.96 165	89.75 184	98.24 39	96.92 221	89.47 220	92.12 187	97.21 137	84.42 156	98.39 214	87.71 244	96.50 163	99.01 89

cl____		90.96 257	90.32 245	92.89 281	95.37 255	86.21 289	94.46 314	96.64 242	87.82 274	88.15 297	94.18 297	82.98 184	97.54 312	87.70 245	85.59 315	94.92 309

pmmvs4		90.93 258	89.85 268	94.17 221	93.34 345	90.79 153	94.60 307	96.02 271	84.62 334	87.45 308	95.15 246	81.88 210	97.45 321	87.70 245	87.87 296	94.27 341

Test_1112_low_res		92.84 176	91.84 187	95.85 129	97.04 160	89.97 179	95.53 278	96.64 242	85.38 321	89.65 256	95.18 245	85.86 139	99.10 139	87.70 245	93.58 223	98.49 132

无先验							95.79 265	97.87 111	83.87 344				99.65 58	87.68 248		98.89 105

Fast-Effi-MVS+		93.46 145	92.75 154	95.59 144	96.77 177	90.03 173	96.81 189	97.13 195	88.19 263	91.30 211	94.27 291	86.21 134	98.63 192	87.66 249	96.46 166	98.12 162

CNLPA		94.28 111	93.53 123	96.52 80	98.38 78	92.55 83	96.59 214	96.88 225	90.13 203	91.91 191	97.24 135	85.21 146	99.09 142	87.64 250	97.83 127	97.92 173

v8		91.29 242	90.53 240	93.57 257	94.15 319	88.12 242	97.34 144	97.06 205	88.99 235	88.32 290	94.26 293	83.08 180	98.01 259	87.62 251	83.92 344	94.57 330

pmmvs5		89.86 291	88.87 294	92.82 284	92.86 352	86.23 288	96.26 238	95.39 300	84.24 338	87.12 315	94.51 275	74.27 311	97.36 328	87.61 252	87.57 298	94.86 312

Fast-Effi-MVS+-dtu		92.29 196	91.99 182	93.21 271	95.27 265	85.52 298	97.03 169	96.63 245	92.09 138	89.11 274	95.14 247	80.33 234	98.08 246	87.54 253	94.74 197	96.03 245

OpenMVS	89.19 12	92.86 174	91.68 193	96.40 93	95.34 258	92.73 78	98.27 33	98.12 67	84.86 331	85.78 332	97.75 103	78.89 264	99.74 41	87.50 254	98.65 98	96.73 223

miper_lstm_enhance		90.50 273	90.06 262	91.83 308	95.33 261	83.74 324	93.86 337	96.70 238	87.56 285	87.79 302	93.81 311	83.45 173	96.92 343	87.39 255	84.62 333	94.82 316

IterMVS-SCA-FT		90.31 275	89.81 270	91.82 309	95.52 245	84.20 319	94.30 322	96.15 268	90.61 191	87.39 311	94.27 291	75.80 298	96.44 350	87.34 256	86.88 308	94.82 316

PLC	91.00 6	94.11 120	93.43 131	96.13 114	98.58 68	91.15 141	96.69 201	97.39 176	87.29 291	91.37 207	96.71 160	88.39 99	99.52 95	87.33 257	97.13 151	97.73 184
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 278	89.74 275	91.76 314	93.92 325	79.73 365	93.98 330	93.54 359	88.28 261	91.99 190	93.25 330	77.51 283	97.44 322	87.30 258	87.94 295	98.12 162

GA-MVS		91.38 234	90.31 246	94.59 196	94.65 302	87.62 255	94.34 319	96.19 267	90.73 181	90.35 230	93.83 308	71.84 324	97.96 270	87.22 259	93.61 221	98.21 154

BH-untuned		92.94 170	92.62 161	93.92 240	97.22 144	86.16 291	96.40 227	96.25 263	90.06 204	89.79 251	96.17 198	83.19 176	98.35 217	87.19 260	97.27 146	97.24 209

v144192		91.06 251	90.28 248	93.39 263	93.66 335	87.23 263	96.83 188	97.07 203	87.43 287	89.69 254	94.28 290	81.48 215	98.00 260	87.18 261	84.92 330	94.93 307

RPSCF		90.75 263	90.86 222	90.42 339	96.84 169	76.29 380	95.61 275	96.34 258	83.89 342	91.38 206	97.87 93	76.45 290	98.78 174	87.16 262	92.23 236	96.20 235

test_f		80.57 351	79.62 353	83.41 368	83.38 395	67.80 395	93.57 348	93.72 356	80.80 369	77.91 379	87.63 384	33.40 398	92.08 388	87.14 263	79.04 370	90.34 383

PS-CasMVS		91.55 226	90.84 225	93.69 251	94.96 282	88.28 234	97.84 83	98.24 47	91.46 155	88.04 299	95.80 215	79.67 246	97.48 318	87.02 264	84.54 336	95.31 286

pm-mvs1		90.72 265	89.65 278	93.96 234	94.29 317	89.63 186	97.79 90	96.82 230	89.07 231	86.12 331	95.48 236	78.61 267	97.78 292	86.97 265	81.67 357	94.46 332

IterMVS		90.15 283	89.67 276	91.61 316	95.48 247	83.72 325	94.33 320	96.12 269	89.99 205	87.31 314	94.15 299	75.78 300	96.27 353	86.97 265	86.89 307	94.83 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 141	92.98 143	95.37 157	98.40 75	88.98 216	97.18 161	97.29 187	87.75 280	90.49 226	97.10 143	85.21 146	99.50 99	86.70 267	96.72 159	97.63 188

PVSNet	86.66 18	92.24 199	91.74 191	93.73 247	97.77 121	83.69 327	92.88 360	96.72 234	87.91 271	93.00 166	94.86 258	78.51 268	99.05 151	86.53 268	97.45 139	98.47 135

v1192		91.07 250	90.23 252	93.58 256	93.70 332	87.82 252	96.73 195	97.07 203	87.77 278	89.58 257	94.32 288	80.90 224	97.97 265	86.52 269	85.48 317	94.95 303

新几何1				97.32 51	98.60 65	93.59 56		97.75 123	81.58 363	95.75 106	97.85 96	90.04 77	99.67 56	86.50 270	99.13 77	98.69 119

v10		91.04 252	90.23 252	93.49 259	94.12 320	88.16 241	97.32 147	97.08 201	88.26 262	88.29 292	94.22 296	82.17 204	97.97 265	86.45 271	84.12 340	94.33 337

v1921920		90.85 260	90.03 263	93.29 267	93.55 336	86.96 271	96.74 194	97.04 208	87.36 289	89.52 261	94.34 285	80.23 236	97.97 265	86.27 272	85.21 323	94.94 305

MDTV_nov1_ep13_2view						70.35 389	93.10 357		83.88 343	93.55 152		82.47 198		86.25 273		98.38 145

test_post1							92.81 362				16.58 407	80.53 229	97.68 299	86.20 274

SCA		91.84 212	91.18 214	93.83 242	95.59 241	84.95 311	94.72 304	95.58 294	90.82 177	92.25 183	93.69 314	75.80 298	98.10 242	86.20 274	95.98 170	98.45 137

PAPR		94.18 113	93.42 133	96.48 86	97.64 129	91.42 125	95.55 276	97.71 132	88.99 235	92.34 181	95.82 214	89.19 85	99.11 138	86.14 276	97.38 140	98.90 102

GBi-Net		91.35 237	90.27 249	94.59 196	96.51 198	91.18 137	97.50 125	96.93 217	88.82 244	89.35 265	94.51 275	73.87 313	97.29 331	86.12 277	88.82 286	95.31 286

test1		91.35 237	90.27 249	94.59 196	96.51 198	91.18 137	97.50 125	96.93 217	88.82 244	89.35 265	94.51 275	73.87 313	97.29 331	86.12 277	88.82 286	95.31 286

FMVSNet3		91.78 213	90.69 234	95.03 171	96.53 196	92.27 93	97.02 171	96.93 217	89.79 212	89.35 265	94.65 269	77.01 285	97.47 319	86.12 277	88.82 286	95.35 283

EPMVS		90.70 266	89.81 270	93.37 264	94.73 299	84.21 318	93.67 344	88.02 392	89.50 219	92.38 177	93.49 323	77.82 281	97.78 292	86.03 280	92.68 231	98.11 165

MVS		91.71 215	90.44 241	95.51 149	95.20 271	91.59 116	96.04 250	97.45 166	73.44 388	87.36 312	95.60 229	85.42 144	99.10 139	85.97 281	97.46 135	95.83 251

testdata2													99.67 56	85.96 282

K. test v3		87.64 316	86.75 318	90.32 340	93.02 351	79.48 369	96.61 211	92.08 374	90.66 187	80.25 371	94.09 301	67.21 356	96.65 349	85.96 282	80.83 361	94.83 314

WR-MVS_H		92.00 207	91.35 203	93.95 235	95.09 278	89.47 195	98.04 55	98.68 13	91.46 155	88.34 289	94.68 267	85.86 139	97.56 310	85.77 284	84.24 339	94.82 316

gg-mvs-nofinetune		87.82 313	85.61 325	94.44 206	94.46 309	89.27 208	91.21 374	84.61 400	80.88 366	89.89 249	74.98 394	71.50 326	97.53 314	85.75 285	97.21 148	96.51 227

tpm2		89.96 285	89.21 287	92.23 300	94.91 288	81.25 346	93.78 339	94.42 340	80.62 370	91.56 202	93.44 326	76.44 291	97.94 275	85.60 286	92.08 243	97.49 197

v1240		90.70 266	89.85 268	93.23 269	93.51 339	86.80 272	96.61 211	97.02 211	87.16 294	89.58 257	94.31 289	79.55 249	97.98 262	85.52 287	85.44 318	94.90 310

PEN-MVS		91.20 245	90.44 241	93.48 260	94.49 308	87.91 249	97.76 91	98.18 57	91.29 160	87.78 303	95.74 221	80.35 233	97.33 329	85.46 288	82.96 352	95.19 297

QAPM		93.45 146	92.27 174	96.98 69	96.77 177	92.62 80	98.39 26	98.12 67	84.50 336	88.27 293	97.77 102	82.39 200	99.81 29	85.40 289	98.81 93	98.51 129

EU-MVSNet		88.72 305	88.90 293	88.20 355	93.15 349	74.21 383	96.63 210	94.22 346	85.18 325	87.32 313	95.97 205	76.16 294	94.98 371	85.27 290	86.17 310	95.41 276

BH-w/o		92.14 204	91.75 189	93.31 266	96.99 164	85.73 295	95.67 270	95.69 286	88.73 249	89.26 270	94.82 261	82.97 185	98.07 250	85.26 291	96.32 167	96.13 241

FMVSNet2		91.31 240	90.08 258	94.99 173	96.51 198	92.21 94	97.41 134	96.95 215	88.82 244	88.62 283	94.75 264	73.87 313	97.42 324	85.20 292	88.55 291	95.35 283

PM-MVS		83.48 344	81.86 350	88.31 354	87.83 388	77.59 377	93.43 349	91.75 376	86.91 297	80.63 367	89.91 369	44.42 393	95.84 359	85.17 293	76.73 376	91.50 376

LF4IMVS		87.94 312	87.25 309	89.98 344	92.38 364	80.05 363	94.38 317	95.25 310	87.59 284	84.34 344	94.74 265	64.31 370	97.66 302	84.83 294	87.45 299	92.23 368

PatchmatchNet		91.91 209	91.35 203	93.59 255	95.38 253	84.11 320	93.15 355	95.39 300	89.54 217	92.10 188	93.68 316	82.82 189	98.13 235	84.81 295	95.32 185	98.52 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 314	86.19 321	92.69 289	91.32 369	86.30 286	97.34 144	96.41 256	80.59 371	84.05 352	94.37 284	67.37 355	97.67 300	84.75 296	79.51 367	94.09 344

v7n		90.76 262	89.86 267	93.45 262	93.54 337	87.60 256	97.70 102	97.37 179	88.85 241	87.65 305	94.08 302	81.08 219	98.10 242	84.68 297	83.79 346	94.66 328

SixPastTwentyTwo		89.15 298	88.54 298	90.98 328	93.49 340	80.28 360	96.70 199	94.70 332	90.78 178	84.15 348	95.57 230	71.78 325	97.71 298	84.63 298	85.07 326	94.94 305

TDRefinement		86.53 324	84.76 335	91.85 307	82.23 397	84.25 317	96.38 229	95.35 303	84.97 330	84.09 350	94.94 253	65.76 367	98.34 220	84.60 299	74.52 379	92.97 356

ACMH	87.59 16	90.53 270	89.42 283	93.87 241	96.21 213	87.92 247	97.24 153	96.94 216	88.45 257	83.91 353	96.27 193	71.92 323	98.62 194	84.43 300	89.43 282	95.05 301
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 281	89.18 288	93.25 268	96.48 201	86.45 283	96.99 175	96.68 239	88.83 243	84.79 342	96.22 195	70.16 336	98.53 201	84.42 301	88.04 294	94.77 324

test_vis3_rt		72.73 357	70.55 360	79.27 371	80.02 398	68.13 394	93.92 335	74.30 408	76.90 383	58.99 397	73.58 397	20.29 406	95.37 369	84.16 302	72.80 384	74.31 396

FE-MVS		92.05 206	91.05 216	95.08 167	96.83 171	87.93 246	93.91 336	95.70 284	86.30 307	94.15 140	94.97 251	76.59 288	99.21 126	84.10 303	96.86 153	98.09 166

MS-PatchMatch		90.27 277	89.77 272	91.78 312	94.33 314	84.72 314	95.55 276	96.73 233	86.17 311	86.36 328	95.28 242	71.28 328	97.80 290	84.09 304	98.14 121	92.81 359

PatchMatch-RL		92.90 172	92.02 181	95.56 145	98.19 95	90.80 152	95.27 291	97.18 191	87.96 269	91.86 194	95.68 225	80.44 231	98.99 156	84.01 305	97.54 134	96.89 219

lessismore_v0				90.45 338	91.96 367	79.09 373		87.19 395		80.32 370	94.39 282	66.31 363	97.55 311	84.00 306	76.84 374	94.70 326

UWE-MVS		89.91 286	89.48 282	91.21 324	95.88 229	78.23 376	94.91 301	90.26 385	89.11 230	92.35 180	94.52 274	68.76 345	97.96 270	83.95 307	95.59 181	97.42 200

CMPMVS	62.92 21	85.62 336	84.92 333	87.74 357	89.14 382	73.12 387	94.17 326	96.80 231	73.98 386	73.65 385	94.93 254	66.36 361	97.61 307	83.95 307	91.28 256	92.48 366
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 264	90.08 258	92.71 288	93.19 348	88.20 238	95.86 260	96.27 261	86.07 312	84.86 341	94.76 263	77.84 280	97.75 295	83.88 309	98.01 123	92.17 371
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 142	92.61 162	96.47 87	97.59 135	91.61 114	97.67 103	97.72 128	85.17 326	90.29 231	98.34 54	84.60 153	99.73 42	83.85 310	98.27 115	98.06 168

DTE-MVSNet		90.56 269	89.75 274	93.01 276	93.95 324	87.25 261	97.64 110	97.65 136	90.74 180	87.12 315	95.68 225	79.97 241	97.00 341	83.33 311	81.66 358	94.78 323

BH-RMVSNet		92.72 181	91.97 183	94.97 176	97.16 148	87.99 245	96.15 246	95.60 292	90.62 190	91.87 193	97.15 141	78.41 270	98.57 199	83.16 312	97.60 133	98.36 147

pmmvs-eth3d		86.22 329	84.45 336	91.53 317	88.34 386	87.25 261	94.47 312	95.01 319	83.47 349	79.51 374	89.61 371	69.75 341	95.71 361	83.13 313	76.73 376	91.64 372

FMVSNet1		89.88 289	88.31 300	94.59 196	95.41 251	91.18 137	97.50 125	96.93 217	86.62 302	87.41 310	94.51 275	65.94 366	97.29 331	83.04 314	87.43 300	95.31 286

testing222		90.31 275	88.96 292	94.35 211	96.54 194	87.29 258	95.50 279	93.84 355	90.97 175	91.75 197	92.96 333	62.18 377	98.00 260	82.86 315	94.08 209	97.76 183

MDTV_nov1_ep13			90.76 228		95.22 269	80.33 358	93.03 358	95.28 307	88.14 266	92.84 172	93.83 308	81.34 216	98.08 246	82.86 315	94.34 201

TR-MVS		91.48 230	90.59 237	94.16 222	96.40 206	87.33 257	95.67 270	95.34 306	87.68 282	91.46 205	95.52 234	76.77 287	98.35 217	82.85 317	93.61 221	96.79 222

dmvs_re		90.21 280	89.50 281	92.35 294	95.47 250	85.15 306	95.70 269	94.37 342	90.94 176	88.42 287	93.57 321	74.63 308	95.67 363	82.80 318	89.57 281	96.22 234

JIA-IIPM		88.26 310	87.04 314	91.91 305	93.52 338	81.42 345	89.38 385	94.38 341	80.84 367	90.93 221	80.74 392	79.22 254	97.92 279	82.76 319	91.62 247	96.38 232

PVSNet_0	82.17 19	85.46 337	83.64 340	90.92 329	95.27 265	79.49 368	90.55 378	95.60 292	83.76 345	83.00 359	89.95 368	71.09 329	97.97 265	82.75 320	60.79 398	95.31 286

ambc				86.56 363	83.60 394	70.00 390	85.69 392	94.97 322		80.60 368	88.45 377	37.42 396	96.84 346	82.69 321	75.44 378	92.86 358

USDC		88.94 300	87.83 305	92.27 298	94.66 301	84.96 310	93.86 337	95.90 275	87.34 290	83.40 355	95.56 231	67.43 354	98.19 230	82.64 322	89.67 280	93.66 348

ITE_SJBPF				92.43 293	95.34 258	85.37 303		95.92 273	91.47 154	87.75 304	96.39 188	71.00 330	97.96 270	82.36 323	89.86 278	93.97 345

UnsupCasMVSNet_eth		85.99 332	84.45 336	90.62 336	89.97 377	82.40 338	93.62 346	97.37 179	89.86 207	78.59 377	92.37 343	65.25 369	95.35 370	82.27 324	70.75 386	94.10 342

GG-mvs-BLEND				93.62 253	93.69 333	89.20 210	92.39 367	83.33 402		87.98 301	89.84 370	71.00 330	96.87 345	82.08 325	95.40 184	94.80 319

thres600view7		92.49 185	91.60 195	95.18 162	97.91 114	89.47 195	97.65 106	94.66 333	92.18 137	93.33 159	94.91 255	78.06 277	99.10 139	81.61 326	94.06 213	96.98 214

LTVRE_ROB	88.41 13	90.99 254	89.92 266	94.19 220	96.18 216	89.55 191	96.31 235	97.09 200	87.88 272	85.67 333	95.91 209	78.79 265	98.57 199	81.50 327	89.98 276	94.44 334
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
tpmvs		89.83 292	89.15 289	91.89 306	94.92 286	80.30 359	93.11 356	95.46 299	86.28 308	88.08 298	92.65 336	80.44 231	98.52 202	81.47 328	89.92 277	96.84 220

thres100view900		92.43 186	91.58 196	94.98 175	97.92 113	89.37 201	97.71 100	94.66 333	92.20 133	93.31 160	94.90 256	78.06 277	99.08 144	81.40 329	94.08 209	96.48 229

tfpn200view9		92.38 189	91.52 199	94.95 178	97.85 117	89.29 205	97.41 134	94.88 327	92.19 135	93.27 162	94.46 280	78.17 273	99.08 144	81.40 329	94.08 209	96.48 229

thres400		92.42 187	91.52 199	95.12 166	97.85 117	89.29 205	97.41 134	94.88 327	92.19 135	93.27 162	94.46 280	78.17 273	99.08 144	81.40 329	94.08 209	96.98 214

ETVMVS		90.52 271	89.14 290	94.67 195	96.81 174	87.85 251	95.91 258	93.97 351	89.71 213	92.34 181	92.48 341	65.41 368	97.96 270	81.37 332	94.27 203	98.21 154

DP-MVS		92.76 179	91.51 201	96.52 80	98.77 53	90.99 143	97.38 141	96.08 270	82.38 356	89.29 268	97.87 93	83.77 166	99.69 52	81.37 332	96.69 160	98.89 105

thres200		92.23 200	91.39 202	94.75 193	97.61 132	89.03 215	96.60 213	95.09 317	92.08 139	93.28 161	94.00 304	78.39 271	99.04 154	81.26 334	94.18 205	96.19 236

CR-MVSNet		90.82 261	89.77 272	93.95 235	94.45 310	87.19 264	90.23 380	95.68 288	86.89 298	92.40 175	92.36 346	80.91 222	97.05 337	81.09 335	93.95 214	97.60 193

MSDG		91.42 232	90.24 251	94.96 177	97.15 150	88.91 217	93.69 343	96.32 259	85.72 317	86.93 323	96.47 183	80.24 235	98.98 157	80.57 336	95.05 191	96.98 214

dp		88.90 302	88.26 302	90.81 332	94.58 306	76.62 378	92.85 361	94.93 324	85.12 327	90.07 244	93.07 331	75.81 297	98.12 240	80.53 337	87.42 301	97.71 185

tpm cat1		88.36 308	87.21 311	91.81 310	95.13 276	80.55 355	92.58 364	95.70 284	74.97 385	87.45 308	91.96 353	78.01 279	98.17 232	80.39 338	88.74 289	96.72 224

KD-MVS_self_test		85.95 333	84.95 332	88.96 352	89.55 381	79.11 372	95.13 296	96.42 255	85.91 314	84.07 351	90.48 363	70.03 338	94.82 372	80.04 339	72.94 383	92.94 357

AllTest		90.23 279	88.98 291	93.98 231	97.94 111	86.64 276	96.51 218	95.54 295	85.38 321	85.49 335	96.77 158	70.28 334	99.15 133	80.02 340	92.87 225	96.15 239

TestCases				93.98 231	97.94 111	86.64 276		95.54 295	85.38 321	85.49 335	96.77 158	70.28 334	99.15 133	80.02 340	92.87 225	96.15 239

ADS-MVSNet2		89.45 295	88.59 297	92.03 303	95.86 230	82.26 339	90.93 375	94.32 345	83.23 351	91.28 215	91.81 355	79.01 261	95.99 355	79.52 342	91.39 254	97.84 178

ADS-MVSNet		89.89 288	88.68 296	93.53 258	95.86 230	84.89 312	90.93 375	95.07 318	83.23 351	91.28 215	91.81 355	79.01 261	97.85 285	79.52 342	91.39 254	97.84 178

our_test_3		88.78 304	87.98 304	91.20 326	92.45 362	82.53 335	93.61 347	95.69 286	85.77 316	84.88 340	93.71 313	79.99 240	96.78 348	79.47 344	86.24 309	94.28 340

EPNet_dtu		91.71 215	91.28 208	92.99 277	93.76 331	83.71 326	96.69 201	95.28 307	93.15 102	87.02 319	95.95 207	83.37 174	97.38 327	79.46 345	96.84 154	97.88 176
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 300	87.56 306	93.08 275	94.35 313	88.45 231	97.73 95	95.23 311	87.47 286	84.26 346	95.29 240	79.86 243	97.33 329	79.44 346	74.44 380	93.45 352

EG-PatchMatch MVS		87.02 322	85.44 326	91.76 314	92.67 356	85.00 309	96.08 249	96.45 254	83.41 350	79.52 373	93.49 323	57.10 383	97.72 297	79.34 347	90.87 267	92.56 363

Patchmtry		88.64 306	87.25 309	92.78 286	94.09 321	86.64 276	89.82 383	95.68 288	80.81 368	87.63 306	92.36 346	80.91 222	97.03 338	78.86 348	85.12 325	94.67 327

FMVSNet5		87.29 318	85.79 324	91.78 312	94.80 294	87.28 259	95.49 280	95.28 307	84.09 340	83.85 354	91.82 354	62.95 374	94.17 377	78.48 349	85.34 321	93.91 346

COLMAP_ROB	87.81 15	90.40 274	89.28 286	93.79 245	97.95 110	87.13 267	96.92 180	95.89 277	82.83 353	86.88 325	97.18 138	73.77 316	99.29 121	78.44 350	93.62 220	94.95 303
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 326	85.44 326	89.34 350	90.33 374	79.79 364	96.73 195	95.92 273	83.71 346	83.25 356	91.36 359	63.92 371	96.01 354	78.39 351	85.36 320	92.22 369

test0.0.03 1		89.37 297	88.70 295	91.41 321	92.47 361	85.63 296	95.22 294	92.70 368	91.11 170	86.91 324	93.65 318	79.02 259	93.19 386	78.00 352	89.18 284	95.41 276

MIMVSNet		88.50 307	86.76 317	93.72 249	94.84 292	87.77 253	91.39 370	94.05 348	86.41 306	87.99 300	92.59 339	63.27 372	95.82 360	77.44 353	92.84 227	97.57 195

MDA-MVSNet_test_wron		85.87 334	84.23 338	90.80 334	92.38 364	82.57 334	93.17 353	95.15 314	82.15 357	67.65 389	92.33 349	78.20 272	95.51 367	77.33 354	79.74 364	94.31 339

YYNet1		85.87 334	84.23 338	90.78 335	92.38 364	82.46 337	93.17 353	95.14 315	82.12 358	67.69 388	92.36 346	78.16 275	95.50 368	77.31 355	79.73 365	94.39 335

UnsupCasMVSNet_bld		82.13 349	79.46 354	90.14 342	88.00 387	82.47 336	90.89 377	96.62 247	78.94 377	75.61 381	84.40 390	56.63 384	96.31 352	77.30 356	66.77 393	91.63 373

KD-MVS_2432*1600		84.81 340	82.64 344	91.31 322	91.07 371	85.34 304	91.22 372	95.75 282	85.56 319	83.09 357	90.21 366	67.21 356	95.89 356	77.18 357	62.48 396	92.69 360

miper_refine_blended		84.81 340	82.64 344	91.31 322	91.07 371	85.34 304	91.22 372	95.75 282	85.56 319	83.09 357	90.21 366	67.21 356	95.89 356	77.18 357	62.48 396	92.69 360

PCF-MVS	89.48 11	91.56 225	89.95 264	96.36 98	96.60 186	92.52 84	92.51 365	97.26 188	79.41 375	88.90 275	96.56 179	84.04 164	99.55 87	77.01 359	97.30 145	97.01 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		89.88 289	89.56 279	90.82 331	94.57 307	83.06 331	95.65 273	92.85 365	87.86 273	90.83 222	94.10 300	79.66 247	96.88 344	76.34 360	94.19 204	92.54 364

testgi		87.97 311	87.21 311	90.24 341	92.86 352	80.76 350	96.67 204	94.97 322	91.74 147	85.52 334	95.83 213	62.66 375	94.47 375	76.25 361	88.36 293	95.48 270

TinyColmap		86.82 323	85.35 329	91.21 324	94.91 288	82.99 332	93.94 333	94.02 350	83.58 347	81.56 363	94.68 267	62.34 376	98.13 235	75.78 362	87.35 303	92.52 365

ppachtmachnet_test		88.35 309	87.29 308	91.53 317	92.45 362	83.57 328	93.75 340	95.97 272	84.28 337	85.32 338	94.18 297	79.00 263	96.93 342	75.71 363	84.99 329	94.10 342

PAPM		91.52 228	90.30 247	95.20 161	95.30 264	89.83 182	93.38 351	96.85 228	86.26 309	88.59 284	95.80 215	84.88 150	98.15 233	75.67 364	95.93 172	97.63 188

WAC-MVS						79.53 366								75.56 365

myMVS_eth3d		87.18 319	86.38 319	89.58 348	95.16 272	79.53 366	95.00 298	93.93 353	88.55 254	86.96 320	91.99 351	56.23 385	94.00 379	75.47 366	94.11 206	95.20 294

CL-MVSNet_self_test		86.31 328	85.15 330	89.80 346	88.83 384	81.74 344	93.93 334	96.22 264	86.67 301	85.03 339	90.80 362	78.09 276	94.50 373	74.92 367	71.86 385	93.15 355

tfpnnormal		89.70 294	88.40 299	93.60 254	95.15 274	90.10 172	97.56 119	98.16 61	87.28 292	86.16 330	94.63 270	77.57 282	98.05 253	74.48 368	84.59 334	92.65 362

DSMNet-mixed		86.34 327	86.12 323	87.00 362	89.88 378	70.43 388	94.93 300	90.08 386	77.97 381	85.42 337	92.78 335	74.44 310	93.96 381	74.43 369	95.14 187	96.62 225

Patchmatch-test		89.42 296	87.99 303	93.70 250	95.27 265	85.11 307	88.98 386	94.37 342	81.11 364	87.10 317	93.69 314	82.28 201	97.50 317	74.37 370	94.76 195	98.48 134

LCM-MVSNet		72.55 358	69.39 362	82.03 369	70.81 407	65.42 398	90.12 382	94.36 344	55.02 397	65.88 391	81.72 391	24.16 405	89.96 390	74.32 371	68.10 391	90.71 382

new-patchmatchnet		83.18 346	81.87 349	87.11 360	86.88 389	75.99 381	93.70 341	95.18 313	85.02 329	77.30 380	88.40 378	65.99 365	93.88 382	74.19 372	70.18 387	91.47 377

testing3		87.67 315	86.88 316	90.05 343	96.14 221	80.71 351	97.10 167	92.85 365	90.15 202	87.54 307	94.55 273	55.70 386	94.10 378	73.77 373	94.10 208	95.35 283

MDA-MVSNet-bldmvs		85.00 338	82.95 343	91.17 327	93.13 350	83.33 329	94.56 309	95.00 320	84.57 335	65.13 393	92.65 336	70.45 333	95.85 358	73.57 374	77.49 372	94.33 337

pmmvs3		79.97 352	77.50 357	87.39 359	82.80 396	79.38 370	92.70 363	90.75 384	70.69 389	78.66 376	87.47 386	51.34 390	93.40 384	73.39 375	69.65 388	89.38 385

test_method		66.11 365	64.89 367	69.79 382	72.62 405	35.23 413	65.19 400	92.83 367	20.35 403	65.20 392	88.08 382	43.14 394	82.70 400	73.12 376	63.46 395	91.45 378

PatchT		88.87 303	87.42 307	93.22 270	94.08 322	85.10 308	89.51 384	94.64 335	81.92 359	92.36 178	88.15 381	80.05 239	97.01 340	72.43 377	93.65 219	97.54 196

Anonymous20231206		87.09 321	86.14 322	89.93 345	91.22 370	80.35 357	96.11 247	95.35 303	83.57 348	84.16 347	93.02 332	73.54 318	95.61 364	72.16 378	86.14 311	93.84 347

MVS-HIRNet		82.47 348	81.21 351	86.26 364	95.38 253	69.21 391	88.96 387	89.49 387	66.28 391	80.79 366	74.08 396	68.48 349	97.39 326	71.93 379	95.47 182	92.18 370

new_pmnet		82.89 347	81.12 352	88.18 356	89.63 379	80.18 361	91.77 369	92.57 369	76.79 384	75.56 383	88.23 380	61.22 378	94.48 374	71.43 380	82.92 353	89.87 384

TAPA-MVS	90.10 7	92.30 195	91.22 212	95.56 145	98.33 80	89.60 188	96.79 190	97.65 136	81.83 360	91.52 203	97.23 136	87.94 106	98.91 163	71.31 381	98.37 111	98.17 159
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 331	85.40 328	88.35 353	90.12 375	80.06 362	95.90 259	95.20 312	88.59 250	81.29 364	93.62 319	71.43 327	92.65 387	71.26 382	81.17 360	92.34 367

tmp_tt		51.94 371	53.82 371	46.29 387	33.73 411	45.30 411	78.32 397	67.24 410	18.02 404	50.93 400	87.05 387	52.99 388	53.11 406	70.76 383	25.29 404	40.46 402

MIMVSNet1		84.93 339	83.05 341	90.56 337	89.56 380	84.84 313	95.40 283	95.35 303	83.91 341	80.38 369	92.21 350	57.23 382	93.34 385	70.69 384	82.75 355	93.50 350

APD_test1		79.31 353	77.70 356	84.14 366	89.11 383	69.07 392	92.36 368	91.50 378	69.07 390	73.87 384	92.63 338	39.93 395	94.32 376	70.54 385	80.25 363	89.02 386

RPMNet		88.98 299	87.05 313	94.77 191	94.45 310	87.19 264	90.23 380	98.03 91	77.87 382	92.40 175	87.55 385	80.17 237	99.51 96	68.84 386	93.95 214	97.60 193

N_pmnet		78.73 354	78.71 355	78.79 372	92.80 354	46.50 409	94.14 327	43.71 411	78.61 378	80.83 365	91.66 357	74.94 306	96.36 351	67.24 387	84.45 337	93.50 350

OpenMVS_ROB	81.14 20	84.42 342	82.28 348	90.83 330	90.06 376	84.05 322	95.73 268	94.04 349	73.89 387	80.17 372	91.53 358	59.15 379	97.64 303	66.92 388	89.05 285	90.80 381

PMMVS2		70.19 360	66.92 363	80.01 370	76.35 401	65.67 397	86.22 391	87.58 394	64.83 393	62.38 394	80.29 393	26.78 403	88.49 397	63.79 389	54.07 399	85.88 387

test_0402		86.46 325	84.79 334	91.45 319	95.02 280	85.55 297	96.29 237	94.89 326	80.90 365	82.21 361	93.97 306	68.21 351	97.29 331	62.98 390	88.68 290	91.51 375

DeepMVS_CX				74.68 381	90.84 373	64.34 399		81.61 404	65.34 392	67.47 390	88.01 383	48.60 391	80.13 402	62.33 391	73.68 382	79.58 393

Syy-MVS		87.13 320	87.02 315	87.47 358	95.16 272	73.21 386	95.00 298	93.93 353	88.55 254	86.96 320	91.99 351	75.90 295	94.00 379	61.59 392	94.11 206	95.20 294

testf1		69.31 361	66.76 364	76.94 376	78.61 399	61.93 400	88.27 388	86.11 398	55.62 395	59.69 395	85.31 388	20.19 407	89.32 391	57.62 393	69.44 389	79.58 393

APD_test2		69.31 361	66.76 364	76.94 376	78.61 399	61.93 400	88.27 388	86.11 398	55.62 395	59.69 395	85.31 388	20.19 407	89.32 391	57.62 393	69.44 389	79.58 393

EGC-MVSNET		68.77 363	63.01 368	86.07 365	92.49 360	82.24 340	93.96 332	90.96 382	0.71 408	2.62 409	90.89 361	53.66 387	93.46 383	57.25 395	84.55 335	82.51 391

dmvs_testset		81.38 350	82.60 346	77.73 373	91.74 368	51.49 406	93.03 358	84.21 401	89.07 231	78.28 378	91.25 360	76.97 286	88.53 396	56.57 396	82.24 356	93.16 354

FPMVS		71.27 359	69.85 361	75.50 379	74.64 402	59.03 402	91.30 371	91.50 378	58.80 394	57.92 398	88.28 379	29.98 401	85.53 399	53.43 397	82.84 354	81.95 392

ANet_high		63.94 366	59.58 369	77.02 375	61.24 409	66.06 396	85.66 393	87.93 393	78.53 379	42.94 401	71.04 398	25.42 404	80.71 401	52.60 398	30.83 402	84.28 390

Gipuma		67.86 364	65.41 366	75.18 380	92.66 357	73.45 385	66.50 399	94.52 337	53.33 398	57.80 399	66.07 399	30.81 399	89.20 393	48.15 399	78.88 371	62.90 399
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	53.92 22	58.58 367	55.40 370	68.12 383	51.00 410	48.64 407	78.86 396	87.10 396	46.77 399	35.84 405	74.28 395	8.76 409	86.34 398	42.07 400	73.91 381	69.38 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 369	48.81 374	66.58 384	65.34 408	57.50 403	72.49 398	70.94 409	40.15 402	39.28 404	63.51 400	6.89 411	73.48 405	38.29 401	42.38 400	68.76 398
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		76.77 355	76.63 358	77.18 374	85.32 391	56.82 404	94.53 310	89.39 388	82.66 355	71.35 386	89.18 374	75.03 305	88.88 394	35.42 402	66.79 392	85.84 388

SSC-MVS		76.05 356	75.83 359	76.72 378	84.77 392	56.22 405	94.32 321	88.96 390	81.82 361	70.52 387	88.91 375	74.79 307	88.71 395	33.69 403	64.71 394	85.23 389

E-PMN		53.28 368	52.56 372	55.43 385	74.43 403	47.13 408	83.63 395	76.30 405	42.23 400	42.59 402	62.22 401	28.57 402	74.40 403	31.53 404	31.51 401	44.78 400

EMVS		52.08 370	51.31 373	54.39 386	72.62 405	45.39 410	83.84 394	75.51 407	41.13 401	40.77 403	59.65 402	30.08 400	73.60 404	28.31 405	29.90 403	44.18 401

wuyk23d		25.11 372	24.57 376	26.74 388	73.98 404	39.89 412	57.88 401	9.80 412	12.27 405	10.39 406	6.97 408	7.03 410	36.44 407	25.43 406	17.39 405	3.89 405

testmvs		13.36 374	16.33 377	4.48 390	5.04 412	2.26 415	93.18 352	3.28 413	2.70 406	8.24 407	21.66 404	2.29 413	2.19 408	7.58 407	2.96 406	9.00 404

test123		13.04 375	15.66 378	5.18 389	4.51 413	3.45 414	92.50 366	1.81 414	2.50 407	7.58 408	20.15 405	3.67 412	2.18 409	7.13 408	1.07 407	9.90 403

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

cdsmvs_eth3d_5k		23.24 373	30.99 375	0.00 391	0.00 414	0.00 416	0.00 402	97.63 140	0.00 409	0.00 410	96.88 155	84.38 157	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		7.39 377	9.85 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	88.65 95	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

ab-mvs-re		8.06 376	10.74 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	96.69 164	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

FOURS1					99.55 1	93.34 64	99.29 1	98.35 27	94.98 29	98.49 23

test_one_0601					99.32 22	95.20 20		98.25 45	95.13 23	98.48 24	98.87 15	95.16 7

eth-test2					0.00 414

eth-test					0.00 414

test_241102_ONE					99.42 7	95.30 17		98.27 39	95.09 26	99.19 4	98.81 21	95.54 5	99.65 58

save fliter					98.91 49	94.28 36	97.02 171	98.02 94	95.35 16

test0726					99.45 3	95.36 13	98.31 29	98.29 34	94.92 32	98.99 7	98.92 10	95.08 8

GSMVS																98.45 137

test_part2					99.28 25	95.74 8				98.10 29

sam_mvs1												82.76 190				98.45 137

sam_mvs												81.94 209

MTGPA								98.08 74

test_post											17.58 406	81.76 211	98.08 246

patchmatchnet-post											90.45 364	82.65 194	98.10 242

MTMP							97.86 79	82.03 403

TEST9					98.70 56	94.19 40	96.41 223	98.02 94	88.17 264	96.03 95	97.56 121	92.74 30	99.59 74

test_8					98.67 58	94.06 47	96.37 230	98.01 97	88.58 251	95.98 99	97.55 123	92.73 31	99.58 77

agg_prior					98.67 58	93.79 52		98.00 98		95.68 109			99.57 84

test_prior4						93.66 55	96.42 222

test_prior				97.23 58	98.67 58	92.99 71		98.00 98					99.41 109			99.29 63

新几何2							95.79 265

旧先验1					98.38 78	93.38 61		97.75 123			98.09 75	92.30 41			99.01 86	99.16 73

原ACMM2							95.67 270

test222					98.24 87	92.21 94	95.33 286	97.60 142	79.22 376	95.25 118	97.84 98	88.80 92			99.15 75	98.72 116

segment_acmp												92.89 27

testdata1							95.26 293		93.10 105

test12				97.65 41	98.46 70	94.26 37		97.66 134		95.52 116		90.89 67	99.46 103		99.25 66	99.22 70

plane_prior7					96.21 213	89.98 178

plane_prior6					96.10 224	90.00 174						81.32 217

plane_prior4											96.64 168

plane_prior3						90.00 174			94.46 54	91.34 208

plane_prior2							97.74 93		94.85 34

plane_prior1					96.14 221

plane_prior						89.99 176	97.24 153		94.06 65						92.16 240

n2								0.00 415

nn								0.00 415

door-mid								91.06 381

test11								97.88 109

door								91.13 380

HQP5-MVS						89.33 203

HQP-NCC					95.86 230		96.65 205		93.55 80	90.14 233

ACMP_Plane					95.86 230		96.65 205		93.55 80	90.14 233

HQP4-MVS										90.14 233			98.50 203			95.78 256

HQP3-MVS								97.39 176							92.10 241

HQP2-MVS												80.95 220

NP-MVS					95.99 228	89.81 183					95.87 210

ACMMP++_ref															90.30 274

ACMMP++															91.02 262

Test By Simon												88.73 94

High-resolution multi-view benchmark