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.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 1

UA-Net		97.35 4	97.24 11	97.69 5	98.22 67	93.87 29	98.42 4	98.19 33	96.95 13	95.46 125	99.23 4	93.45 73	99.57 13	95.34 12	99.89 2	99.63 9

test_part1		94.39 109	94.55 106	93.92 144	96.14 190	82.86 204	95.54 70	98.09 49	95.36 35	98.27 20	98.36 28	75.91 292	99.44 23	93.41 54	99.84 3	99.47 17

PS-CasMVS		96.69 20	97.43 5	94.49 124	99.13 5	84.09 189	96.61 24	97.97 72	97.91 5	98.64 13	98.13 32	95.24 36	99.65 3	93.39 55	99.84 3	99.72 2

WR-MVS_H		96.60 25	97.05 14	95.24 92	99.02 11	86.44 152	96.78 21	98.08 50	97.42 8	98.48 16	97.86 45	91.76 116	99.63 6	94.23 26	99.84 3	99.66 6

FC-MVSNet-test		95.32 73	95.88 57	93.62 154	98.49 53	81.77 213	95.90 57	98.32 19	93.93 53	97.53 37	97.56 56	88.48 173	99.40 41	92.91 75	99.83 6	99.68 4

PEN-MVS		96.69 20	97.39 8	94.61 113	99.16 3	84.50 180	96.54 27	98.05 57	98.06 4	98.64 13	98.25 31	95.01 47	99.65 3	92.95 74	99.83 6	99.68 4

DTE-MVSNet		96.74 17	97.43 5	94.67 111	99.13 5	84.68 179	96.51 28	97.94 78	98.14 3	98.67 12	98.32 29	95.04 44	99.69 2	93.27 61	99.82 8	99.62 10

CP-MVSNet		96.19 46	96.80 17	94.38 130	98.99 13	83.82 192	96.31 41	97.53 109	97.60 6	98.34 19	97.52 59	91.98 112	99.63 6	93.08 70	99.81 9	99.70 3

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 26	98.81 23	93.86 30	99.07 2	98.98 4	97.01 12	98.92 4	98.78 14	95.22 37	98.61 173	96.85 2	99.77 10	99.31 27
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
v7n		96.82 10	97.31 10	95.33 86	98.54 41	86.81 142	96.83 18	98.07 53	96.59 19	98.46 17	98.43 27	92.91 91	99.52 17	96.25 6	99.76 11	99.65 8

TranMVSNet+NR-MVSNet		96.07 50	96.26 37	95.50 80	98.26 65	87.69 126	93.75 133	97.86 80	95.96 29	97.48 39	97.14 84	95.33 32	99.44 23	90.79 123	99.76 11	99.38 22

Anonymous20231211		96.60 25	97.13 12	95.00 100	97.46 117	86.35 156	97.11 14	98.24 29	97.58 7	98.72 8	98.97 7	93.15 85	99.15 83	93.18 64	99.74 13	99.50 16

UniMVSNet_ETH3D		97.13 6	97.72 3	95.35 84	99.51 2	87.38 129	97.70 6	97.54 107	98.16 2	98.94 2	99.33 2	97.84 4	99.08 95	90.73 124	99.73 14	99.59 12

pmmvs6		96.80 13	97.36 9	95.15 96	99.12 7	87.82 125	96.68 22	97.86 80	96.10 25	98.14 23	99.28 3	97.94 3	98.21 210	91.38 115	99.69 15	99.42 19

FIs		94.90 87	95.35 74	93.55 157	98.28 63	81.76 214	95.33 76	98.14 41	93.05 67	97.07 51	97.18 82	87.65 187	99.29 68	91.72 105	99.69 15	99.61 11

OurMVSNet-221017-0		96.80 13	96.75 18	96.96 36	99.03 10	91.85 57	97.98 5	98.01 66	94.15 48	98.93 3	99.07 5	88.07 180	99.57 13	95.86 9	99.69 15	99.46 18

Anonymous20240521		92.86 157	93.57 136	90.74 249	96.57 157	75.50 307	94.15 120	95.60 213	89.38 156	95.90 108	97.90 44	80.39 260	97.96 231	92.60 84	99.68 18	98.75 84

ANet_high		94.83 93	96.28 36	90.47 257	96.65 151	73.16 323	94.33 115	98.74 6	96.39 22	98.09 24	98.93 8	93.37 77	98.70 163	90.38 131	99.68 18	99.53 14

DeepC-MVS	91.39 4	95.43 68	95.33 76	95.71 73	97.67 104	90.17 78	93.86 131	98.02 64	87.35 200	96.22 92	97.99 38	94.48 61	99.05 101	92.73 80	99.68 18	97.93 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		95.28 76	95.28 79	95.26 91	97.75 95	87.21 133	95.08 87	97.37 117	93.92 54	97.65 30	95.90 159	90.10 158	99.33 64	90.11 145	99.66 21	99.26 29

Baseline_NR-MVSNet		94.47 108	95.09 86	92.60 191	98.50 52	80.82 228	92.08 187	96.68 171	93.82 55	96.29 86	98.56 20	90.10 158	97.75 251	90.10 147	99.66 21	99.24 31

UniMVSNet (Re)		95.32 73	95.15 83	95.80 67	97.79 93	88.91 99	92.91 152	98.07 53	93.46 62	96.31 84	95.97 158	90.14 154	99.34 59	92.11 91	99.64 23	99.16 36

WR-MVS		93.49 133	93.72 129	92.80 183	97.57 110	80.03 238	90.14 252	95.68 211	93.70 57	96.62 72	95.39 191	87.21 195	99.04 104	87.50 199	99.64 23	99.33 25

MIMVSNet1		95.52 65	95.45 71	95.72 72	99.14 4	89.02 97	96.23 46	96.87 161	93.73 56	97.87 26	98.49 24	90.73 144	99.05 101	86.43 217	99.60 25	99.10 44

ACMH+	88.43 11	96.48 30	96.82 16	95.47 81	98.54 41	89.06 96	95.65 65	98.61 7	96.10 25	98.16 22	97.52 59	96.90 7	98.62 172	90.30 137	99.60 25	98.72 90

VPA-MVSNet		95.14 80	95.67 67	93.58 156	97.76 94	83.15 200	94.58 106	97.58 104	93.39 63	97.05 54	98.04 35	93.25 80	98.51 186	89.75 155	99.59 27	99.08 45

LPG-MVS_test		96.38 40	96.23 38	96.84 40	98.36 60	92.13 52	95.33 76	98.25 26	91.78 102	97.07 51	97.22 80	96.38 13	99.28 70	92.07 94	99.59 27	99.11 41

LGP-MVS_train				96.84 40	98.36 60	92.13 52		98.25 26	91.78 102	97.07 51	97.22 80	96.38 13	99.28 70	92.07 94	99.59 27	99.11 41

ACMH	88.36 12	96.59 27	97.43 5	94.07 137	98.56 36	85.33 172	96.33 39	98.30 22	94.66 39	98.72 8	98.30 30	97.51 5	98.00 227	94.87 14	99.59 27	98.86 72
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_NR-MVSNet		95.35 71	95.21 81	95.76 70	97.69 102	88.59 107	92.26 181	97.84 84	94.91 37	96.80 65	95.78 169	90.42 149	99.41 36	91.60 109	99.58 31	99.29 28

DU-MVS		95.28 76	95.12 85	95.75 71	97.75 95	88.59 107	92.58 161	97.81 87	93.99 50	96.80 65	95.90 159	90.10 158	99.41 36	91.60 109	99.58 31	99.26 29

ACMP	88.15 13	95.71 60	95.43 73	96.54 46	98.17 70	91.73 60	94.24 117	98.08 50	89.46 155	96.61 73	96.47 125	95.85 17	99.12 89	90.45 128	99.56 33	98.77 83
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		94.68 99	95.27 80	92.90 179	96.57 157	80.15 232	94.65 103	97.57 105	90.68 132	97.43 41	98.00 37	88.18 177	99.15 83	94.84 15	99.55 34	99.41 20

PS-MVSNAJss		96.01 51	96.04 51	95.89 63	98.82 22	88.51 111	95.57 68	97.88 79	88.72 171	98.81 6	98.86 10	90.77 140	99.60 8	95.43 11	99.53 35	99.57 13

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 11	95.95 5	98.61 3	98.81 5	97.41 9	97.28 46	98.46 25	94.62 57	98.84 134	94.64 17	99.53 35	98.99 53

IS-MVSNet		94.49 107	94.35 113	94.92 102	98.25 66	86.46 151	97.13 13	94.31 251	96.24 23	96.28 89	96.36 138	82.88 235	99.35 56	88.19 186	99.52 37	98.96 60

nrg030		96.32 41	96.55 26	95.62 75	97.83 92	88.55 109	95.77 61	98.29 25	92.68 69	98.03 25	97.91 42	95.13 40	98.95 119	93.85 33	99.49 38	99.36 24

MP-MVS-pluss		96.08 49	95.92 56	96.57 45	99.06 9	91.21 64	93.25 144	98.32 19	87.89 188	96.86 62	97.38 67	95.55 24	99.39 46	95.47 10	99.47 39	99.11 41
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_tets		96.83 9	96.71 19	97.17 27	98.83 21	92.51 48	96.58 26	97.61 102	87.57 198	98.80 7	98.90 9	96.50 10	99.59 12	96.15 7	99.47 39	99.40 21

v8		94.65 100	95.29 78	92.74 184	96.65 151	79.77 247	94.59 104	97.17 138	91.86 94	97.47 40	97.93 40	88.16 178	99.08 95	94.32 22	99.47 39	99.38 22

CLD-MVS		91.82 183	91.41 189	93.04 171	96.37 166	83.65 194	86.82 316	97.29 130	84.65 246	92.27 234	89.67 324	92.20 106	97.85 241	83.95 244	99.47 39	97.62 183
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
jajsoiax		96.59 27	96.42 29	97.12 29	98.76 26	92.49 49	96.44 33	97.42 115	86.96 207	98.71 10	98.72 17	95.36 31	99.56 16	95.92 8	99.45 43	99.32 26

test_djsdf		96.62 23	96.49 28	97.01 33	98.55 39	91.77 59	97.15 11	97.37 117	88.98 165	98.26 21	98.86 10	93.35 78	99.60 8	96.41 4	99.45 43	99.66 6

CP-MVS		96.44 35	96.08 48	97.54 11	98.29 62	94.62 13	96.80 19	98.08 50	92.67 71	95.08 144	96.39 135	94.77 53	99.42 28	93.17 65	99.44 45	98.58 105

COLMAP_ROB	91.06 5	96.75 16	96.62 23	97.13 28	98.38 57	94.31 15	96.79 20	98.32 19	96.69 16	96.86 62	97.56 56	95.48 25	98.77 151	90.11 145	99.44 45	98.31 122
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_0728_THIRD									93.26 65	97.40 44	97.35 72	94.69 54	99.34 59	93.88 32	99.42 47	98.89 69

zzz-MVS		96.47 31	96.14 44	97.47 15	98.95 15	94.05 21	93.69 135	97.62 99	94.46 44	96.29 86	96.94 94	93.56 71	99.37 53	94.29 24	99.42 47	98.99 53

MTAPA		96.65 22	96.38 33	97.47 15	98.95 15	94.05 21	95.88 58	97.62 99	94.46 44	96.29 86	96.94 94	93.56 71	99.37 53	94.29 24	99.42 47	98.99 53

pm-mvs1		95.43 68	95.94 54	93.93 143	98.38 57	85.08 176	95.46 73	97.12 142	91.84 98	97.28 46	98.46 25	95.30 34	97.71 253	90.17 143	99.42 47	98.99 53

XVG-ACMP-BASELINE		95.68 61	95.34 75	96.69 43	98.40 55	93.04 41	94.54 111	98.05 57	90.45 138	96.31 84	96.76 108	92.91 91	98.72 157	91.19 116	99.42 47	98.32 120

wuyk23d		87.83 266	90.79 205	78.96 343	90.46 330	88.63 105	92.72 156	90.67 306	91.65 110	98.68 11	97.64 53	96.06 16	77.53 363	59.84 358	99.41 52	70.73 361

anonymousdsp		96.74 17	96.42 29	97.68 7	98.00 84	94.03 24	96.97 15	97.61 102	87.68 195	98.45 18	98.77 15	94.20 66	99.50 19	96.70 3	99.40 53	99.53 14

SixPastTwentyTwo		94.91 86	95.21 81	93.98 139	98.52 44	83.19 199	95.93 55	94.84 237	94.86 38	98.49 15	98.74 16	81.45 251	99.60 8	94.69 16	99.39 54	99.15 37

HPM-MVS_fast		97.01 7	96.89 15	97.39 22	99.12 7	93.92 27	97.16 10	98.17 37	93.11 66	96.48 76	97.36 71	96.92 6	99.34 59	94.31 23	99.38 55	98.92 67

HPM-MVS		96.81 12	96.62 23	97.36 24	98.89 18	93.53 37	97.51 7	98.44 10	92.35 78	95.95 104	96.41 130	96.71 8	99.42 28	93.99 31	99.36 56	99.13 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DIV-MVS_2432*1600		94.10 122	94.73 98	92.19 202	97.66 105	79.49 252	94.86 95	97.12 142	89.59 154	96.87 61	97.65 52	90.40 152	98.34 200	89.08 170	99.35 57	98.75 84

ACMMP_NAP		96.21 45	96.12 46	96.49 49	98.90 17	91.42 62	94.57 107	98.03 62	90.42 139	96.37 79	97.35 72	95.68 19	99.25 74	94.44 20	99.34 58	98.80 79

SteuartSystems-ACMMP		96.40 38	96.30 35	96.71 42	98.63 29	91.96 55	95.70 62	98.01 66	93.34 64	96.64 71	96.57 122	94.99 48	99.36 55	93.48 47	99.34 58	98.82 77
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		96.61 24	96.34 34	97.43 19	98.61 32	93.88 28	96.95 16	98.18 34	92.26 81	96.33 82	96.84 104	95.10 42	99.40 41	93.47 48	99.33 60	99.02 50
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
ACMM	88.83 9	96.30 43	96.07 49	96.97 35	98.39 56	92.95 44	94.74 99	98.03 62	90.82 128	97.15 49	96.85 101	96.25 15	99.00 111	93.10 68	99.33 60	98.95 61
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS		95.82 57	96.18 41	94.72 110	98.51 45	86.69 145	95.20 82	97.00 148	91.85 95	97.40 44	97.35 72	95.58 22	99.34 59	93.44 51	99.31 62	98.13 136
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				94.88 103	98.55 39	86.72 144	95.20 82	98.22 31					99.38 52	93.44 51	99.31 62	98.53 107

APDe-MVS		96.46 32	96.64 22	95.93 60	97.68 103	89.38 93	96.90 17	98.41 14	92.52 73	97.43 41	97.92 41	95.11 41	99.50 19	94.45 19	99.30 64	98.92 67

SED-MVS		96.00 52	96.41 32	94.76 108	98.51 45	86.97 138	95.21 80	98.10 46	91.95 88	97.63 31	97.25 77	96.48 11	99.35 56	93.29 59	99.29 65	97.95 153

IU-MVS					98.51 45	86.66 147		96.83 162	72.74 327	95.83 109				93.00 72	99.29 65	98.64 96

SMA-MVS		95.77 58	95.54 68	96.47 50	98.27 64	91.19 65	95.09 86	97.79 91	86.48 211	97.42 43	97.51 61	94.47 62	99.29 68	93.55 42	99.29 65	98.93 63
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
MP-MVS		96.14 47	95.68 66	97.51 13	98.81 23	94.06 19	96.10 48	97.78 92	92.73 68	93.48 192	96.72 113	94.23 65	99.42 28	91.99 96	99.29 65	99.05 48
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_0402		95.73 59	96.22 39	94.26 132	98.19 69	85.77 167	93.24 145	97.24 134	96.88 15	97.69 29	97.77 48	94.12 67	99.13 87	91.54 112	99.29 65	97.88 161

ZNCC-MVS		96.42 36	96.20 40	97.07 30	98.80 25	92.79 46	96.08 49	98.16 40	91.74 106	95.34 129	96.36 138	95.68 19	99.44 23	94.41 21	99.28 70	98.97 59

DPE-MVS		95.89 53	95.88 57	95.92 62	97.93 89	89.83 84	93.46 140	98.30 22	92.37 76	97.75 28	96.95 93	95.14 39	99.51 18	91.74 104	99.28 70	98.41 117
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mPP-MVS		96.46 32	96.05 50	97.69 5	98.62 30	94.65 12	96.45 31	97.74 93	92.59 72	95.47 123	96.68 115	94.50 60	99.42 28	93.10 68	99.26 72	98.99 53

test_241102_TWO								98.10 46	91.95 88	97.54 36	97.25 77	95.37 28	99.35 56	93.29 59	99.25 73	98.49 110

ACMMP++															99.25 73

CSCG		94.69 98	94.75 96	94.52 121	97.55 111	87.87 123	95.01 91	97.57 105	92.68 69	96.20 94	93.44 258	91.92 113	98.78 147	89.11 169	99.24 75	96.92 216

TransMVSNet (Re)		95.27 78	96.04 51	92.97 174	98.37 59	81.92 212	95.07 88	96.76 168	93.97 52	97.77 27	98.57 19	95.72 18	97.90 233	88.89 174	99.23 76	99.08 45

abl_6		97.31 5	97.12 13	97.86 3	98.54 41	95.32 7	96.61 24	98.35 18	95.81 30	97.55 35	97.44 64	96.51 9	99.40 41	94.06 30	99.23 76	98.85 75

bset_n11_16_dypcd		89.99 230	89.15 233	92.53 194	94.75 249	81.34 220	84.19 340	87.56 323	85.13 236	93.77 184	92.46 280	72.82 301	99.01 109	92.46 87	99.21 78	97.23 205

PGM-MVS		96.32 41	95.94 54	97.43 19	98.59 35	93.84 31	95.33 76	98.30 22	91.40 115	95.76 111	96.87 100	95.26 35	99.45 22	92.77 77	99.21 78	99.00 51

SD-MVS		95.19 79	95.73 65	93.55 157	96.62 154	88.88 102	94.67 101	98.05 57	91.26 118	97.25 48	96.40 131	95.42 26	94.36 336	92.72 81	99.19 80	97.40 197
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
Vis-MVSNet (Re-imp)		90.42 213	90.16 216	91.20 234	97.66 105	77.32 285	94.33 115	87.66 322	91.20 120	92.99 211	95.13 198	75.40 294	98.28 203	77.86 299	99.19 80	97.99 148

tfpnnormal		94.27 116	94.87 91	92.48 196	97.71 99	80.88 227	94.55 110	95.41 224	93.70 57	96.67 70	97.72 49	91.40 124	98.18 214	87.45 200	99.18 82	98.36 118

FMVSNet1		94.84 92	95.13 84	93.97 140	97.60 108	84.29 182	95.99 51	96.56 177	92.38 75	97.03 55	98.53 21	90.12 155	98.98 112	88.78 176	99.16 83	98.65 92

ACMMPR		96.46 32	96.14 44	97.41 21	98.60 33	93.82 32	96.30 43	97.96 73	92.35 78	95.57 120	96.61 120	94.93 50	99.41 36	93.78 35	99.15 84	99.00 51

HFP-MVS		96.39 39	96.17 43	97.04 31	98.51 45	93.37 38	96.30 43	97.98 69	92.35 78	95.63 117	96.47 125	95.37 28	99.27 72	93.78 35	99.14 85	98.48 111

#test#		95.89 53	95.51 69	97.04 31	98.51 45	93.37 38	95.14 85	97.98 69	89.34 158	95.63 117	96.47 125	95.37 28	99.27 72	91.99 96	99.14 85	98.48 111

VDD-MVS		94.37 110	94.37 112	94.40 129	97.49 114	86.07 162	93.97 128	93.28 268	94.49 43	96.24 90	97.78 46	87.99 183	98.79 143	88.92 172	99.14 85	98.34 119

RRT_MVS		91.36 194	90.05 220	95.29 90	89.21 343	88.15 116	92.51 167	94.89 235	86.73 210	95.54 121	95.68 172	61.82 345	99.30 67	94.91 13	99.13 88	98.43 115

region2R		96.41 37	96.09 47	97.38 23	98.62 30	93.81 34	96.32 40	97.96 73	92.26 81	95.28 133	96.57 122	95.02 46	99.41 36	93.63 39	99.11 89	98.94 62

DROMVSNet		94.58 102	94.82 92	93.86 149	96.36 168	85.20 174	95.56 69	99.01 3	91.91 91	91.67 244	93.78 250	93.18 84	99.42 28	92.78 76	99.11 89	96.97 214

Gipuma		95.31 75	95.80 63	93.81 151	97.99 87	90.91 69	96.42 34	97.95 75	96.69 16	91.78 243	98.85 12	91.77 115	95.49 319	91.72 105	99.08 91	95.02 281
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
GST-MVS		96.24 44	95.99 53	97.00 34	98.65 28	92.71 47	95.69 64	98.01 66	92.08 86	95.74 113	96.28 143	95.22 37	99.42 28	93.17 65	99.06 92	98.88 71

OPM-MVS		95.61 63	95.45 71	96.08 53	98.49 53	91.00 67	92.65 160	97.33 126	90.05 144	96.77 67	96.85 101	95.04 44	98.56 181	92.77 77	99.06 92	98.70 91

VPNet		93.08 147	93.76 128	91.03 238	98.60 33	75.83 305	91.51 214	95.62 212	91.84 98	95.74 113	97.10 86	89.31 166	98.32 201	85.07 234	99.06 92	98.93 63

xxxxxxxxxxxxxcwj		95.03 81	94.93 88	95.33 86	97.46 117	88.05 119	92.04 189	98.42 13	87.63 196	96.36 80	96.68 115	94.37 63	99.32 65	92.41 88	99.05 95	98.64 96

SF-MVS		95.88 55	95.88 57	95.87 64	98.12 72	89.65 87	95.58 67	98.56 9	91.84 98	96.36 80	96.68 115	94.37 63	99.32 65	92.41 88	99.05 95	98.64 96

XVS		96.49 29	96.18 41	97.44 17	98.56 36	93.99 25	96.50 29	97.95 75	94.58 40	94.38 167	96.49 124	94.56 58	99.39 46	93.57 40	99.05 95	98.93 63

X-MVStestdata		90.70 206	88.45 246	97.44 17	98.56 36	93.99 25	96.50 29	97.95 75	94.58 40	94.38 167	26.89 365	94.56 58	99.39 46	93.57 40	99.05 95	98.93 63

test20.03		90.80 203	90.85 203	90.63 253	95.63 224	79.24 257	89.81 264	92.87 274	89.90 147	94.39 166	96.40 131	85.77 216	95.27 327	73.86 325	99.05 95	97.39 198

Anonymous20240529		95.50 66	95.83 61	94.50 122	97.33 123	85.93 164	95.19 84	96.77 167	96.64 18	97.61 34	98.05 34	93.23 81	98.79 143	88.60 181	99.04 100	98.78 81

IterMVS-LS		93.78 128	94.28 116	92.27 199	96.27 179	79.21 259	91.87 202	96.78 165	91.77 104	96.57 75	97.07 87	87.15 196	98.74 155	91.99 96	99.03 101	98.86 72
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ETH3D-3000-0.1		94.86 90	94.55 106	95.81 65	97.61 107	89.72 85	94.05 124	98.37 16	88.09 184	95.06 145	95.85 161	92.58 99	99.10 93	90.33 136	98.99 102	98.62 100

cl-mvsnet____		90.65 208	90.56 210	90.91 245	91.85 310	76.98 291	86.75 317	95.36 227	85.53 229	94.06 175	94.89 210	77.36 282	97.98 230	90.27 139	98.98 103	97.76 173

AllTest		94.88 89	94.51 109	96.00 55	98.02 82	92.17 50	95.26 79	98.43 11	90.48 136	95.04 146	96.74 110	92.54 101	97.86 239	85.11 232	98.98 103	97.98 149

TestCases				96.00 55	98.02 82	92.17 50		98.43 11	90.48 136	95.04 146	96.74 110	92.54 101	97.86 239	85.11 232	98.98 103	97.98 149

Patchmtry		90.11 224	89.92 222	90.66 252	90.35 331	77.00 289	92.96 150	92.81 275	90.25 142	94.74 158	96.93 96	67.11 316	97.52 260	85.17 227	98.98 103	97.46 191

cl-mvsnet1		90.65 208	90.56 210	90.91 245	91.85 310	76.99 290	86.75 317	95.36 227	85.52 231	94.06 175	94.89 210	77.37 281	97.99 229	90.28 138	98.97 107	97.76 173

9.14			94.81 93		97.49 114		94.11 122	98.37 16	87.56 199	95.38 127	96.03 155	94.66 55	99.08 95	90.70 125	98.97 107

D2MVS		89.93 231	89.60 229	90.92 243	94.03 273	78.40 269	88.69 289	94.85 236	78.96 294	93.08 207	95.09 200	74.57 295	96.94 283	88.19 186	98.96 109	97.41 194

PHI-MVS		94.34 113	93.80 126	95.95 57	95.65 222	91.67 61	94.82 96	97.86 80	87.86 189	93.04 210	94.16 235	91.58 120	98.78 147	90.27 139	98.96 109	97.41 194

ambc				92.98 173	96.88 142	83.01 203	95.92 56	96.38 187		96.41 77	97.48 62	88.26 176	97.80 244	89.96 150	98.93 111	98.12 137

EPNet		89.80 235	88.25 251	94.45 127	83.91 364	86.18 160	93.87 130	87.07 327	91.16 122	80.64 354	94.72 218	78.83 267	98.89 125	85.17 227	98.89 112	98.28 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPP-MVSNet		93.91 126	93.68 132	94.59 118	98.08 75	85.55 170	97.44 8	94.03 256	94.22 47	94.94 149	96.19 148	82.07 246	99.57 13	87.28 204	98.89 112	98.65 92

v1192		93.49 133	93.78 127	92.62 190	96.16 188	79.62 249	91.83 207	97.22 136	86.07 220	96.10 100	96.38 136	87.22 194	99.02 107	94.14 29	98.88 114	99.22 32

v1144		93.50 132	93.81 125	92.57 192	96.28 178	79.61 250	91.86 206	96.96 151	86.95 208	95.91 107	96.32 140	87.65 187	98.96 117	93.51 43	98.88 114	99.13 39

APD-MVS_3200maxsize		96.82 10	96.65 21	97.32 25	97.95 88	93.82 32	96.31 41	98.25 26	95.51 34	96.99 58	97.05 89	95.63 21	99.39 46	93.31 58	98.88 114	98.75 84

APD-MVS		95.00 83	94.69 99	95.93 60	97.38 120	90.88 70	94.59 104	97.81 87	89.22 163	95.46 125	96.17 151	93.42 76	99.34 59	89.30 161	98.87 117	97.56 187
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OMC-MVS		94.22 119	93.69 131	95.81 65	97.25 124	91.27 63	92.27 180	97.40 116	87.10 206	94.56 162	95.42 188	93.74 69	98.11 219	86.62 212	98.85 118	98.06 139

SR-MVS-dyc-post		96.84 8	96.60 25	97.56 10	98.07 76	95.27 8	96.37 36	98.12 43	95.66 32	97.00 56	97.03 90	94.85 51	99.42 28	93.49 44	98.84 119	98.00 145

RE-MVS-def			96.66 20		98.07 76	95.27 8	96.37 36	98.12 43	95.66 32	97.00 56	97.03 90	95.40 27		93.49 44	98.84 119	98.00 145

v144192		93.20 146	93.54 138	92.16 206	96.05 197	78.26 271	91.95 194	97.14 139	84.98 241	95.96 103	96.11 152	87.08 198	99.04 104	93.79 34	98.84 119	99.17 35

v1921920		93.26 141	93.61 134	92.19 202	96.04 201	78.31 270	91.88 201	97.24 134	85.17 234	96.19 96	96.19 148	86.76 206	99.05 101	94.18 28	98.84 119	99.22 32

DP-MVS		95.62 62	95.84 60	94.97 101	97.16 130	88.62 106	94.54 111	97.64 98	96.94 14	96.58 74	97.32 75	93.07 88	98.72 157	90.45 128	98.84 119	97.57 185

VDDNet		94.03 124	94.27 118	93.31 166	98.87 19	82.36 208	95.51 72	91.78 298	97.19 11	96.32 83	98.60 18	84.24 226	98.75 152	87.09 205	98.83 124	98.81 78

CPTT-MVS		94.74 96	94.12 121	96.60 44	98.15 71	93.01 42	95.84 59	97.66 97	89.21 164	93.28 199	95.46 185	88.89 169	98.98 112	89.80 152	98.82 125	97.80 170

ACMMP++_ref															98.82 125

test1172		96.79 15	96.52 27	97.60 9	98.03 81	94.87 10	96.07 50	98.06 56	95.76 31	96.89 60	96.85 101	94.85 51	99.42 28	93.35 57	98.81 127	98.53 107

v2v482		93.29 138	93.63 133	92.29 198	96.35 172	78.82 264	91.77 210	96.28 189	88.45 177	95.70 116	96.26 145	86.02 215	98.90 123	93.02 71	98.81 127	99.14 38

USDC		89.02 244	89.08 234	88.84 288	95.07 240	74.50 314	88.97 282	96.39 186	73.21 324	93.27 200	96.28 143	82.16 245	96.39 301	77.55 303	98.80 129	95.62 270

tttt0517		89.81 234	88.90 240	92.55 193	97.00 136	79.73 248	95.03 90	83.65 352	89.88 148	95.30 131	94.79 217	53.64 360	99.39 46	91.99 96	98.79 130	98.54 106

PMVS	87.21 14	94.97 84	95.33 76	93.91 145	98.97 14	97.16 2	95.54 70	95.85 207	96.47 20	93.40 195	97.46 63	95.31 33	95.47 320	86.18 221	98.78 131	89.11 347
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
TinyColmap		92.00 181	92.76 155	89.71 274	95.62 225	77.02 288	90.72 233	96.17 198	87.70 194	95.26 134	96.29 142	92.54 101	96.45 299	81.77 264	98.77 132	95.66 267

v1240		93.29 138	93.71 130	92.06 209	96.01 202	77.89 277	91.81 208	97.37 117	85.12 237	96.69 69	96.40 131	86.67 207	99.07 99	94.51 18	98.76 133	99.22 32

DeepPCF-MVS	90.46 6	94.20 120	93.56 137	96.14 51	95.96 204	92.96 43	89.48 270	97.46 113	85.14 235	96.23 91	95.42 188	93.19 82	98.08 220	90.37 132	98.76 133	97.38 200

Anonymous20231206		88.77 252	88.29 250	90.20 267	96.31 176	78.81 265	89.56 269	93.49 266	74.26 318	92.38 228	95.58 178	82.21 243	95.43 322	72.07 334	98.75 135	96.34 238

SR-MVS		96.70 19	96.42 29	97.54 11	98.05 78	94.69 11	96.13 47	98.07 53	95.17 36	96.82 64	96.73 112	95.09 43	99.43 27	92.99 73	98.71 136	98.50 109

UGNet		93.08 147	92.50 164	94.79 107	93.87 277	87.99 121	95.07 88	94.26 253	90.64 133	87.33 316	97.67 51	86.89 204	98.49 187	88.10 189	98.71 136	97.91 158
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
LFMVS		91.33 195	91.16 198	91.82 213	96.27 179	79.36 254	95.01 91	85.61 340	96.04 28	94.82 154	97.06 88	72.03 306	98.46 193	84.96 235	98.70 138	97.65 181

HPM-MVS++		95.02 82	94.39 111	96.91 38	97.88 90	93.58 36	94.09 123	96.99 150	91.05 123	92.40 227	95.22 195	91.03 138	99.25 74	92.11 91	98.69 139	97.90 159

miper_lstm_enhance		89.90 232	89.80 224	90.19 268	91.37 319	77.50 282	83.82 344	95.00 231	84.84 243	93.05 209	94.96 207	76.53 291	95.20 328	89.96 150	98.67 140	97.86 163

FMVSNet2		92.78 159	92.73 158	92.95 176	95.40 231	81.98 211	94.18 119	95.53 221	88.63 173	96.05 101	97.37 68	81.31 253	98.81 141	87.38 203	98.67 140	98.06 139

DeepC-MVS_fast	89.96 7	93.73 129	93.44 140	94.60 117	96.14 190	87.90 122	93.36 143	97.14 139	85.53 229	93.90 182	95.45 186	91.30 128	98.59 177	89.51 158	98.62 142	97.31 203
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				95.15 96	96.84 144	89.43 90	95.21 80				95.66 173	93.12 86	98.06 221	86.28 220	98.61 143	97.95 153

114514_t		90.51 210	89.80 224	92.63 189	98.00 84	82.24 209	93.40 142	97.29 130	65.84 352	89.40 285	94.80 216	86.99 199	98.75 152	83.88 245	98.61 143	96.89 218

CS-MVS		92.12 178	92.62 160	90.60 254	94.57 260	78.12 273	92.00 192	98.58 8	87.75 192	90.08 270	91.88 293	89.79 162	99.10 93	90.35 133	98.60 145	94.58 291

CDPH-MVS		92.67 163	91.83 177	95.18 95	96.94 139	88.46 112	90.70 234	97.07 145	77.38 303	92.34 232	95.08 201	92.67 98	98.88 126	85.74 223	98.57 146	98.20 131

cl_fuxian		91.32 196	91.42 188	91.00 241	92.29 301	76.79 294	87.52 303	96.42 184	85.76 226	94.72 160	93.89 246	82.73 238	98.16 216	90.93 122	98.55 147	98.04 142

test_prior3		93.29 138	92.85 152	94.61 113	95.95 205	87.23 131	90.21 248	97.36 122	89.33 159	90.77 257	94.81 213	90.41 150	98.68 167	88.21 183	98.55 147	97.93 155

test_prior2							90.21 248		89.33 159	90.77 257	94.81 213	90.41 150		88.21 183	98.55 147

LCM-MVSNet-Re		94.20 120	94.58 105	93.04 171	95.91 208	83.13 201	93.79 132	99.19 2	92.00 87	98.84 5	98.04 35	93.64 70	99.02 107	81.28 269	98.54 150	96.96 215

Patchmatch-RL test		88.81 251	88.52 244	89.69 275	95.33 236	79.94 241	86.22 325	92.71 279	78.46 298	95.80 110	94.18 234	66.25 324	95.33 325	89.22 167	98.53 151	93.78 310

Anonymous202405211		92.58 166	92.50 164	92.83 182	96.55 159	83.22 198	92.43 170	91.64 299	94.10 49	95.59 119	96.64 118	81.88 250	97.50 261	85.12 231	98.52 152	97.77 172

CNVR-MVS		94.58 102	94.29 115	95.46 82	96.94 139	89.35 94	91.81 208	96.80 164	89.66 151	93.90 182	95.44 187	92.80 95	98.72 157	92.74 79	98.52 152	98.32 120

HQP_MVS		94.26 117	93.93 123	95.23 93	97.71 99	88.12 117	94.56 108	97.81 87	91.74 106	93.31 196	95.59 175	86.93 201	98.95 119	89.26 165	98.51 154	98.60 103

plane_prior5								97.81 87					98.95 119	89.26 165	98.51 154	98.60 103

baseline		94.26 117	94.80 94	92.64 187	96.08 195	80.99 225	93.69 135	98.04 61	90.80 129	94.89 152	96.32 140	93.19 82	98.48 191	91.68 107	98.51 154	98.43 115

ETH3D cwj APD-0.16		93.99 125	93.38 142	95.80 67	96.82 145	89.92 81	92.72 156	98.02 64	84.73 245	93.65 189	95.54 182	91.68 118	99.22 77	88.78 176	98.49 157	98.26 126

thisisatest0530		88.69 254	87.52 265	92.20 201	96.33 174	79.36 254	92.81 154	84.01 351	86.44 212	93.67 188	92.68 277	53.62 361	99.25 74	89.65 157	98.45 158	98.00 145

train_agg		92.71 162	91.83 177	95.35 84	96.45 164	89.46 88	90.60 236	96.92 155	79.37 287	90.49 262	94.39 227	91.20 133	98.88 126	88.66 180	98.43 159	97.72 176

GeoE		94.55 104	94.68 101	94.15 134	97.23 125	85.11 175	94.14 121	97.34 125	88.71 172	95.26 134	95.50 183	94.65 56	99.12 89	90.94 121	98.40 160	98.23 127

ZD-MVS					97.23 125	90.32 77		97.54 107	84.40 247	94.78 156	95.79 166	92.76 96	99.39 46	88.72 179	98.40 160

test9_res														88.16 188	98.40 160	97.83 166

ETH3 D test6400		91.91 182	91.25 194	93.89 146	96.59 155	84.41 181	92.10 186	97.72 95	78.52 297	91.82 242	93.78 250	88.70 170	99.13 87	83.61 246	98.39 163	98.14 134

TSAR-MVS + GP.		93.07 149	92.41 166	95.06 99	95.82 211	90.87 71	90.97 227	92.61 283	88.04 185	94.61 161	93.79 249	88.08 179	97.81 243	89.41 160	98.39 163	96.50 232

VNet		92.67 163	92.96 149	91.79 214	96.27 179	80.15 232	91.95 194	94.98 232	92.19 84	94.52 164	96.07 153	87.43 191	97.39 270	84.83 236	98.38 165	97.83 166

GBi-Net		93.21 144	92.96 149	93.97 140	95.40 231	84.29 182	95.99 51	96.56 177	88.63 173	95.10 141	98.53 21	81.31 253	98.98 112	86.74 208	98.38 165	98.65 92

test1		93.21 144	92.96 149	93.97 140	95.40 231	84.29 182	95.99 51	96.56 177	88.63 173	95.10 141	98.53 21	81.31 253	98.98 112	86.74 208	98.38 165	98.65 92

FMVSNet3		90.78 204	90.32 215	92.16 206	93.03 291	79.92 242	92.54 162	94.95 233	86.17 219	95.10 141	96.01 156	69.97 310	98.75 152	86.74 208	98.38 165	97.82 168

MVS_111021_HR		93.63 131	93.42 141	94.26 132	96.65 151	86.96 140	89.30 276	96.23 193	88.36 180	93.57 191	94.60 221	93.45 73	97.77 248	90.23 141	98.38 165	98.03 143

agg_prior1		92.60 165	91.76 180	95.10 98	96.20 184	88.89 100	90.37 243	96.88 159	79.67 284	90.21 267	94.41 225	91.30 128	98.78 147	88.46 182	98.37 170	97.64 182

agg_prior2														87.06 206	98.36 171	97.98 149

TSAR-MVS + MP.		94.96 85	94.75 96	95.57 78	98.86 20	88.69 103	96.37 36	96.81 163	85.23 232	94.75 157	97.12 85	91.85 114	99.40 41	93.45 49	98.33 172	98.62 100
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
pmmvs-eth3d		91.54 189	90.73 207	93.99 138	95.76 216	87.86 124	90.83 230	93.98 260	78.23 300	94.02 178	96.22 147	82.62 241	96.83 288	86.57 213	98.33 172	97.29 204

casdiffmvs		94.32 114	94.80 94	92.85 181	96.05 197	81.44 219	92.35 176	98.05 57	91.53 113	95.75 112	96.80 105	93.35 78	98.49 187	91.01 120	98.32 174	98.64 96

Regformer-1		94.55 104	94.33 114	95.19 94	92.83 294	88.54 110	91.87 202	95.84 208	93.99 50	95.95 104	95.04 203	92.00 110	98.79 143	93.14 67	98.31 175	98.23 127

Regformer-2		94.86 90	94.55 106	95.77 69	92.83 294	89.98 80	91.87 202	96.40 185	94.38 46	96.19 96	95.04 203	92.47 104	99.04 104	93.49 44	98.31 175	98.28 124

3Dnovator+	92.74 2	95.86 56	95.77 64	96.13 52	96.81 147	90.79 72	96.30 43	97.82 86	96.13 24	94.74 158	97.23 79	91.33 126	99.16 82	93.25 62	98.30 177	98.46 113

MVS_111021_LR		93.66 130	93.28 145	94.80 106	96.25 182	90.95 68	90.21 248	95.43 223	87.91 186	93.74 187	94.40 226	92.88 93	96.38 302	90.39 130	98.28 178	97.07 208

CANet		92.38 171	91.99 173	93.52 161	93.82 279	83.46 195	91.14 223	97.00 148	89.81 149	86.47 320	94.04 238	87.90 185	99.21 78	89.50 159	98.27 179	97.90 159

EI-MVSNet		92.99 151	93.26 147	92.19 202	92.12 306	79.21 259	92.32 178	94.67 246	91.77 104	95.24 137	95.85 161	87.14 197	98.49 187	91.99 96	98.26 180	98.86 72

RRT_test8_iter05		88.21 260	88.17 255	88.33 298	91.62 315	66.82 351	91.73 211	96.60 175	86.34 214	94.14 170	95.38 193	47.72 366	99.11 91	91.78 103	98.26 180	99.06 47

MVSTER		89.32 240	88.75 242	91.03 238	90.10 333	76.62 295	90.85 229	94.67 246	82.27 267	95.24 137	95.79 166	61.09 348	98.49 187	90.49 127	98.26 180	97.97 152

testtj		94.81 94	94.42 110	96.01 54	97.23 125	90.51 76	94.77 98	97.85 83	91.29 117	94.92 151	95.66 173	91.71 117	99.40 41	88.07 190	98.25 183	98.11 138

MSLP-MVS++		93.25 143	93.88 124	91.37 226	96.34 173	82.81 205	93.11 146	97.74 93	89.37 157	94.08 173	95.29 194	90.40 152	96.35 304	90.35 133	98.25 183	94.96 282

LF4IMVS		92.72 161	92.02 172	94.84 105	95.65 222	91.99 54	92.92 151	96.60 175	85.08 239	92.44 225	93.62 253	86.80 205	96.35 304	86.81 207	98.25 183	96.18 245

EI-MVSNet-UG-set		94.35 112	94.27 118	94.59 118	92.46 299	85.87 165	92.42 171	94.69 244	93.67 61	96.13 98	95.84 164	91.20 133	98.86 131	93.78 35	98.23 186	99.03 49

PM-MVS		93.33 137	92.67 159	95.33 86	96.58 156	94.06 19	92.26 181	92.18 289	85.92 223	96.22 92	96.61 120	85.64 220	95.99 312	90.35 133	98.23 186	95.93 254

EI-MVSNet-Vis-set		94.36 111	94.28 116	94.61 113	92.55 298	85.98 163	92.44 169	94.69 244	93.70 57	96.12 99	95.81 165	91.24 130	98.86 131	93.76 38	98.22 188	98.98 58

V42		93.43 135	93.58 135	92.97 174	95.34 235	81.22 222	92.67 159	96.49 182	87.25 202	96.20 94	96.37 137	87.32 193	98.85 133	92.39 90	98.21 189	98.85 75

TAMVS		90.16 223	89.05 235	93.49 162	96.49 162	86.37 154	90.34 245	92.55 284	80.84 276	92.99 211	94.57 223	81.94 249	98.20 211	73.51 326	98.21 189	95.90 257

K. test v3		93.37 136	93.27 146	93.66 153	98.05 78	82.62 206	94.35 114	86.62 329	96.05 27	97.51 38	98.85 12	76.59 290	99.65 3	93.21 63	98.20 191	98.73 89

DELS-MVS		92.05 180	92.16 168	91.72 217	94.44 262	80.13 234	87.62 297	97.25 133	87.34 201	92.22 235	93.18 265	89.54 165	98.73 156	89.67 156	98.20 191	96.30 240
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
TAPA-MVS	88.58 10	92.49 169	91.75 181	94.73 109	96.50 161	89.69 86	92.91 152	97.68 96	78.02 301	92.79 216	94.10 236	90.85 139	97.96 231	84.76 238	98.16 193	96.54 227
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		96.11 48	95.83 61	96.95 37	94.75 249	94.20 17	97.34 9	97.98 69	97.31 10	95.32 130	96.77 106	93.08 87	99.20 79	91.79 102	98.16 193	97.44 193

Regformer-3		94.28 115	94.23 120	94.46 126	92.78 296	86.28 158	92.39 173	94.70 243	93.69 60	95.97 102	95.56 180	91.34 125	98.48 191	93.45 49	98.14 195	98.62 100

Regformer-4		94.90 87	94.67 102	95.59 76	92.78 296	89.02 97	92.39 173	95.91 204	94.50 42	96.41 77	95.56 180	92.10 108	99.01 109	94.23 26	98.14 195	98.74 87

DP-MVS Recon		92.31 173	91.88 176	93.60 155	97.18 129	86.87 141	91.10 225	97.37 117	84.92 242	92.08 238	94.08 237	88.59 172	98.20 211	83.50 247	98.14 195	95.73 263

EG-PatchMatch MVS		94.54 106	94.67 102	94.14 135	97.87 91	86.50 148	92.00 192	96.74 169	88.16 183	96.93 59	97.61 54	93.04 89	97.90 233	91.60 109	98.12 198	98.03 143

PCF-MVS	84.52 17	89.12 243	87.71 262	93.34 164	96.06 196	85.84 166	86.58 324	97.31 127	68.46 345	93.61 190	93.89 246	87.51 190	98.52 185	67.85 349	98.11 199	95.66 267
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	92.54 3	94.80 95	94.90 89	94.47 125	95.47 229	87.06 135	96.63 23	97.28 132	91.82 101	94.34 169	97.41 65	90.60 147	98.65 171	92.47 86	98.11 199	97.70 177

CS-MVS-test		91.17 198	91.31 192	90.74 249	94.24 267	79.99 240	91.46 216	98.39 15	86.29 215	87.43 314	89.06 332	88.63 171	99.07 99	88.20 185	98.09 201	93.17 321

PMMVS2		81.31 319	83.44 303	74.92 345	90.52 328	46.49 368	69.19 360	85.23 346	84.30 248	87.95 308	94.71 219	76.95 286	84.36 362	64.07 355	98.09 201	93.89 308

lessismore_v0				93.87 148	98.05 78	83.77 193		80.32 361		97.13 50	97.91 42	77.49 278	99.11 91	92.62 83	98.08 203	98.74 87

new-patchmatchnet		88.97 247	90.79 205	83.50 334	94.28 266	55.83 366	85.34 329	93.56 264	86.18 218	95.47 123	95.73 170	83.10 233	96.51 297	85.40 226	98.06 204	98.16 132

plane_prior						88.12 117	93.01 148		88.98 165						98.06 204

PVSNet_BlendedMVS		90.35 217	89.96 221	91.54 223	94.81 246	78.80 266	90.14 252	96.93 153	79.43 286	88.68 299	95.06 202	86.27 212	98.15 217	80.27 277	98.04 206	97.68 179

CL-MVSNet_2432*1600		90.04 229	89.90 223	90.47 257	95.24 237	77.81 278	86.60 323	92.62 282	85.64 228	93.25 203	93.92 244	83.84 228	96.06 310	79.93 284	98.03 207	97.53 189

FMVSNet5		87.82 267	86.56 282	91.62 220	92.31 300	79.81 246	93.49 139	94.81 240	83.26 253	91.36 248	96.93 96	52.77 362	97.49 263	76.07 314	98.03 207	97.55 188

原ACMM1				92.87 180	96.91 141	84.22 185		97.01 147	76.84 308	89.64 283	94.46 224	88.00 182	98.70 163	81.53 267	98.01 209	95.70 265

v148		92.87 156	93.29 143	91.62 220	96.25 182	77.72 280	91.28 221	95.05 230	89.69 150	95.93 106	96.04 154	87.34 192	98.38 196	90.05 148	97.99 210	98.78 81

ITE_SJBPF				95.95 57	97.34 122	93.36 40		96.55 180	91.93 90	94.82 154	95.39 191	91.99 111	97.08 279	85.53 225	97.96 211	97.41 194

test12				94.43 128	95.95 205	86.75 143		96.24 192		89.76 281		89.79 162	98.79 143		97.95 212	97.75 175

MCST-MVS		92.91 153	92.51 163	94.10 136	97.52 112	85.72 168	91.36 220	97.13 141	80.33 278	92.91 214	94.24 231	91.23 131	98.72 157	89.99 149	97.93 213	97.86 163

CDS-MVSNet		89.55 236	88.22 254	93.53 160	95.37 234	86.49 149	89.26 277	93.59 263	79.76 282	91.15 253	92.31 286	77.12 283	98.38 196	77.51 304	97.92 214	95.71 264
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
旧先验1					96.20 184	84.17 187		94.82 238			95.57 179	89.57 164			97.89 215	96.32 239

alignmvs		93.26 141	92.85 152	94.50 122	95.70 218	87.45 127	93.45 141	95.76 209	91.58 111	95.25 136	92.42 285	81.96 248	98.72 157	91.61 108	97.87 216	97.33 202

testgi		90.38 215	91.34 191	87.50 307	97.49 114	71.54 332	89.43 271	95.16 229	88.38 179	94.54 163	94.68 220	92.88 93	93.09 346	71.60 338	97.85 217	97.88 161

MVS_0304		90.96 201	90.15 218	93.37 163	93.17 286	87.06 135	93.62 137	92.43 287	89.60 153	82.25 345	95.50 183	82.56 242	97.83 242	84.41 242	97.83 218	95.22 275

新几何1				93.17 170	97.16 130	87.29 130		94.43 248	67.95 346	91.29 249	94.94 208	86.97 200	98.23 209	81.06 274	97.75 219	93.98 306

ETV-MVS		92.99 151	92.74 156	93.72 152	95.86 210	86.30 157	92.33 177	97.84 84	91.70 109	92.81 215	86.17 349	92.22 105	99.19 80	88.03 191	97.73 220	95.66 267

HQP3-MVS								97.31 127							97.73 220

HQP-MVS		92.09 179	91.49 187	93.88 147	96.36 168	84.89 177	91.37 217	97.31 127	87.16 203	88.81 292	93.40 259	84.76 223	98.60 175	86.55 214	97.73 220	98.14 134

1121		90.26 221	89.23 230	93.34 164	97.15 132	87.40 128	91.94 196	94.39 249	67.88 347	91.02 255	94.91 209	86.91 203	98.59 177	81.17 272	97.71 223	94.02 305

CANet_DTU		89.85 233	89.17 232	91.87 212	92.20 304	80.02 239	90.79 231	95.87 206	86.02 221	82.53 344	91.77 295	80.01 261	98.57 180	85.66 224	97.70 224	97.01 212

NCCC		94.08 123	93.54 138	95.70 74	96.49 162	89.90 83	92.39 173	96.91 157	90.64 133	92.33 233	94.60 221	90.58 148	98.96 117	90.21 142	97.70 224	98.23 127

Vis-MVSNet		95.50 66	95.48 70	95.56 79	98.11 73	89.40 92	95.35 74	98.22 31	92.36 77	94.11 171	98.07 33	92.02 109	99.44 23	93.38 56	97.67 226	97.85 165
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
AdaColmap		91.63 187	91.36 190	92.47 197	95.56 227	86.36 155	92.24 183	96.27 190	88.88 169	89.90 276	92.69 276	91.65 119	98.32 201	77.38 306	97.64 227	92.72 330

EPNet_dtu		85.63 294	84.37 297	89.40 279	86.30 358	74.33 316	91.64 212	88.26 316	84.84 243	72.96 363	89.85 317	71.27 308	97.69 254	76.60 311	97.62 228	96.18 245
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XVG-OURS		94.72 97	94.12 121	96.50 48	98.00 84	94.23 16	91.48 215	98.17 37	90.72 130	95.30 131	96.47 125	87.94 184	96.98 282	91.41 114	97.61 229	98.30 123

canonicalmvs		94.59 101	94.69 99	94.30 131	95.60 226	87.03 137	95.59 66	98.24 29	91.56 112	95.21 139	92.04 291	94.95 49	98.66 169	91.45 113	97.57 230	97.20 207

XXY-MVS		92.58 166	93.16 148	90.84 247	97.75 95	79.84 243	91.87 202	96.22 195	85.94 222	95.53 122	97.68 50	92.69 97	94.48 332	83.21 250	97.51 231	98.21 130

Effi-MVS+-dtu		93.90 127	92.60 162	97.77 4	94.74 251	96.67 3	94.00 126	95.41 224	89.94 145	91.93 241	92.13 289	90.12 155	98.97 116	87.68 197	97.48 232	97.67 180

OpenMVS	89.45 8	92.27 175	92.13 170	92.68 186	94.53 261	84.10 188	95.70 62	97.03 146	82.44 266	91.14 254	96.42 129	88.47 174	98.38 196	85.95 222	97.47 233	95.55 271

ab-mvs		92.40 170	92.62 160	91.74 216	97.02 135	81.65 215	95.84 59	95.50 222	86.95 208	92.95 213	97.56 56	90.70 145	97.50 261	79.63 287	97.43 234	96.06 249

thisisatest0515		84.72 299	82.99 307	89.90 272	92.96 292	75.33 308	84.36 338	83.42 353	77.37 304	88.27 304	86.65 344	53.94 359	98.72 157	82.56 256	97.40 235	95.67 266

test222					96.95 138	85.27 173	88.83 285	93.61 262	65.09 354	90.74 259	94.85 212	84.62 225			97.36 236	93.91 307

API-MVS		91.52 190	91.61 182	91.26 230	94.16 268	86.26 159	94.66 102	94.82 238	91.17 121	92.13 237	91.08 305	90.03 161	97.06 280	79.09 294	97.35 237	90.45 345

EIA-MVS		92.35 172	92.03 171	93.30 167	95.81 213	83.97 190	92.80 155	98.17 37	87.71 193	89.79 280	87.56 339	91.17 136	99.18 81	87.97 192	97.27 238	96.77 223

testdata				91.03 238	96.87 143	82.01 210		94.28 252	71.55 331	92.46 224	95.42 188	85.65 219	97.38 272	82.64 255	97.27 238	93.70 313

N_pmnet		88.90 249	87.25 269	93.83 150	94.40 264	93.81 34	84.73 333	87.09 326	79.36 289	93.26 201	92.43 284	79.29 265	91.68 351	77.50 305	97.22 240	96.00 251

ppachtmachnet_test		88.61 255	88.64 243	88.50 294	91.76 312	70.99 335	84.59 336	92.98 272	79.30 291	92.38 228	93.53 257	79.57 263	97.45 265	86.50 216	97.17 241	97.07 208

CNLPA		91.72 185	91.20 195	93.26 168	96.17 187	91.02 66	91.14 223	95.55 220	90.16 143	90.87 256	93.56 256	86.31 211	94.40 335	79.92 286	97.12 242	94.37 296

jason		89.17 242	88.32 248	91.70 218	95.73 217	80.07 235	88.10 294	93.22 269	71.98 330	90.09 269	92.79 273	78.53 272	98.56 181	87.43 201	97.06 243	96.46 234
jason: jason.
RPSCF		95.58 64	94.89 90	97.62 8	97.58 109	96.30 4	95.97 54	97.53 109	92.42 74	93.41 193	97.78 46	91.21 132	97.77 248	91.06 117	97.06 243	98.80 79

cl-mvsnet2		89.02 244	88.50 245	90.59 255	89.76 335	76.45 297	86.62 322	94.03 256	82.98 260	92.65 219	92.49 279	72.05 305	97.53 259	88.93 171	97.02 245	97.78 171

miper_ehance_all_eth		90.48 211	90.42 213	90.69 251	91.62 315	76.57 296	86.83 315	96.18 197	83.38 252	94.06 175	92.66 278	82.20 244	98.04 222	89.79 153	97.02 245	97.45 192

miper_enhance_ethall		88.42 257	87.87 260	90.07 269	88.67 348	75.52 306	85.10 330	95.59 217	75.68 310	92.49 223	89.45 327	78.96 266	97.88 235	87.86 195	97.02 245	96.81 221

eth_miper_zixun_eth		90.72 205	90.61 209	91.05 237	92.04 308	76.84 293	86.91 312	96.67 172	85.21 233	94.41 165	93.92 244	79.53 264	98.26 207	89.76 154	97.02 245	98.06 139

QAPM		92.88 155	92.77 154	93.22 169	95.82 211	83.31 196	96.45 31	97.35 124	83.91 250	93.75 185	96.77 106	89.25 167	98.88 126	84.56 240	97.02 245	97.49 190

thres600view7		87.66 270	87.10 274	89.36 280	96.05 197	73.17 322	92.72 156	85.31 343	91.89 93	93.29 198	90.97 306	63.42 338	98.39 194	73.23 328	96.99 250	96.51 229

test_yl		90.11 224	89.73 227	91.26 230	94.09 271	79.82 244	90.44 240	92.65 280	90.90 124	93.19 205	93.30 261	73.90 297	98.03 223	82.23 260	96.87 251	95.93 254

DCV-MVSNet		90.11 224	89.73 227	91.26 230	94.09 271	79.82 244	90.44 240	92.65 280	90.90 124	93.19 205	93.30 261	73.90 297	98.03 223	82.23 260	96.87 251	95.93 254

MSP-MVS		95.34 72	94.63 104	97.48 14	98.67 27	94.05 21	96.41 35	98.18 34	91.26 118	95.12 140	95.15 196	86.60 209	99.50 19	93.43 53	96.81 253	98.89 69
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
pmmvs5		87.87 265	87.14 272	90.07 269	93.26 285	76.97 292	88.89 284	92.18 289	73.71 322	88.36 302	93.89 246	76.86 289	96.73 291	80.32 276	96.81 253	96.51 229

PVSNet_Blended_VisFu		91.63 187	91.20 195	92.94 177	97.73 98	83.95 191	92.14 185	97.46 113	78.85 296	92.35 230	94.98 206	84.16 227	99.08 95	86.36 218	96.77 255	95.79 261

MVSFormer		92.18 177	92.23 167	92.04 210	94.74 251	80.06 236	97.15 11	97.37 117	88.98 165	88.83 290	92.79 273	77.02 284	99.60 8	96.41 4	96.75 256	96.46 234

lupinMVS		88.34 259	87.31 267	91.45 224	94.74 251	80.06 236	87.23 305	92.27 288	71.10 334	88.83 290	91.15 303	77.02 284	98.53 184	86.67 211	96.75 256	95.76 262

diffmvs		91.74 184	91.93 175	91.15 236	93.06 289	78.17 272	88.77 287	97.51 112	86.28 216	92.42 226	93.96 243	88.04 181	97.46 264	90.69 126	96.67 258	97.82 168

DPM-MVS		89.35 239	88.40 247	92.18 205	96.13 193	84.20 186	86.96 311	96.15 199	75.40 314	87.36 315	91.55 300	83.30 231	98.01 226	82.17 262	96.62 259	94.32 298

thres100view900		87.35 278	86.89 276	88.72 290	96.14 190	73.09 324	93.00 149	85.31 343	92.13 85	93.26 201	90.96 307	63.42 338	98.28 203	71.27 340	96.54 260	94.79 285

tfpn200view9		87.05 286	86.52 284	88.67 291	95.77 214	72.94 325	91.89 199	86.00 335	90.84 126	92.61 220	89.80 319	63.93 335	98.28 203	71.27 340	96.54 260	94.79 285

thres400		87.20 282	86.52 284	89.24 284	95.77 214	72.94 325	91.89 199	86.00 335	90.84 126	92.61 220	89.80 319	63.93 335	98.28 203	71.27 340	96.54 260	96.51 229

CMPMVS	68.83 22	87.28 279	85.67 292	92.09 208	88.77 347	85.42 171	90.31 246	94.38 250	70.02 340	88.00 307	93.30 261	73.78 299	94.03 340	75.96 316	96.54 260	96.83 220
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		88.95 248	87.70 263	92.70 185	94.30 265	85.60 169	87.22 306	92.16 291	74.62 316	89.75 282	94.19 233	77.97 276	96.41 300	82.71 254	96.36 264	96.09 247

Fast-Effi-MVS+-dtu		92.77 160	92.16 168	94.58 120	94.66 257	88.25 114	92.05 188	96.65 173	89.62 152	90.08 270	91.23 302	92.56 100	98.60 175	86.30 219	96.27 265	96.90 217

MAR-MVS		90.32 219	88.87 241	94.66 112	94.82 245	91.85 57	94.22 118	94.75 241	80.91 273	87.52 313	88.07 338	86.63 208	97.87 238	76.67 310	96.21 266	94.25 299
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
AUN-MVS		90.05 228	88.30 249	95.32 89	96.09 194	90.52 75	92.42 171	92.05 295	82.08 269	88.45 301	92.86 270	65.76 326	98.69 165	88.91 173	96.07 267	96.75 225

hse-mvs2		92.24 176	91.20 195	95.38 83	96.16 188	90.65 73	92.52 163	92.01 296	89.23 161	93.95 179	92.99 268	76.88 287	98.69 165	91.02 118	96.03 268	96.81 221

PVSNet_Blended		88.74 253	88.16 257	90.46 259	94.81 246	78.80 266	86.64 320	96.93 153	74.67 315	88.68 299	89.18 330	86.27 212	98.15 217	80.27 277	96.00 269	94.44 295

F-COLMAP		92.28 174	91.06 199	95.95 57	97.52 112	91.90 56	93.53 138	97.18 137	83.98 249	88.70 298	94.04 238	88.41 175	98.55 183	80.17 280	95.99 270	97.39 198

xiu_mvs_v1_base_debu		91.47 191	91.52 184	91.33 227	95.69 219	81.56 216	89.92 259	96.05 201	83.22 254	91.26 250	90.74 309	91.55 121	98.82 136	89.29 162	95.91 271	93.62 315

xiu_mvs_v1_base		91.47 191	91.52 184	91.33 227	95.69 219	81.56 216	89.92 259	96.05 201	83.22 254	91.26 250	90.74 309	91.55 121	98.82 136	89.29 162	95.91 271	93.62 315

xiu_mvs_v1_base_debi		91.47 191	91.52 184	91.33 227	95.69 219	81.56 216	89.92 259	96.05 201	83.22 254	91.26 250	90.74 309	91.55 121	98.82 136	89.29 162	95.91 271	93.62 315

thres200		85.85 293	85.18 294	87.88 304	94.44 262	72.52 328	89.08 281	86.21 331	88.57 176	91.44 247	88.40 336	64.22 333	98.00 227	68.35 348	95.88 274	93.12 322

Patchmatch-test		86.10 292	86.01 289	86.38 317	90.63 326	74.22 318	89.57 268	86.69 328	85.73 227	89.81 279	92.83 271	65.24 330	91.04 353	77.82 302	95.78 275	93.88 309

hse-mvs3		92.89 154	91.99 173	95.58 77	96.97 137	90.55 74	93.94 129	94.01 259	89.23 161	93.95 179	96.19 148	76.88 287	99.14 85	91.02 118	95.71 276	97.04 211

mvs-test1		93.07 149	91.80 179	96.89 39	94.74 251	95.83 6	92.17 184	95.41 224	89.94 145	89.85 277	90.59 315	90.12 155	98.88 126	87.68 197	95.66 277	95.97 252

cascas		87.02 287	86.28 288	89.25 283	91.56 317	76.45 297	84.33 339	96.78 165	71.01 335	86.89 319	85.91 350	81.35 252	96.94 283	83.09 251	95.60 278	94.35 297

XVG-OURS-SEG-HR		95.38 70	95.00 87	96.51 47	98.10 74	94.07 18	92.46 168	98.13 42	90.69 131	93.75 185	96.25 146	98.03 2	97.02 281	92.08 93	95.55 279	98.45 114

DSMNet-mixed		82.21 313	81.56 312	84.16 331	89.57 339	70.00 341	90.65 235	77.66 364	54.99 363	83.30 340	97.57 55	77.89 277	90.50 355	66.86 352	95.54 280	91.97 335

MVS_Test		92.57 168	93.29 143	90.40 260	93.53 281	75.85 303	92.52 163	96.96 151	88.73 170	92.35 230	96.70 114	90.77 140	98.37 199	92.53 85	95.49 281	96.99 213

MIMVSNet		87.13 285	86.54 283	88.89 287	96.05 197	76.11 300	94.39 113	88.51 314	81.37 272	88.27 304	96.75 109	72.38 303	95.52 317	65.71 354	95.47 282	95.03 280

Fast-Effi-MVS+		91.28 197	90.86 202	92.53 194	95.45 230	82.53 207	89.25 279	96.52 181	85.00 240	89.91 275	88.55 335	92.94 90	98.84 134	84.72 239	95.44 283	96.22 243

ET-MVSNet_ETH3D		86.15 291	84.27 299	91.79 214	93.04 290	81.28 221	87.17 308	86.14 332	79.57 285	83.65 336	88.66 333	57.10 353	98.18 214	87.74 196	95.40 284	95.90 257

BH-RMVSNet		90.47 212	90.44 212	90.56 256	95.21 238	78.65 268	89.15 280	93.94 261	88.21 181	92.74 217	94.22 232	86.38 210	97.88 235	78.67 296	95.39 285	95.14 278

CHOSEN 1792x2688		87.19 283	85.92 291	91.00 241	97.13 133	79.41 253	84.51 337	95.60 213	64.14 355	90.07 272	94.81 213	78.26 274	97.14 278	73.34 327	95.38 286	96.46 234

Effi-MVS+		92.79 158	92.74 156	92.94 177	95.10 239	83.30 197	94.00 126	97.53 109	91.36 116	89.35 286	90.65 314	94.01 68	98.66 169	87.40 202	95.30 287	96.88 219

MG-MVS		89.54 237	89.80 224	88.76 289	94.88 242	72.47 329	89.60 267	92.44 286	85.82 224	89.48 284	95.98 157	82.85 236	97.74 252	81.87 263	95.27 288	96.08 248

HyFIR lowres test		87.19 283	85.51 293	92.24 200	97.12 134	80.51 229	85.03 331	96.06 200	66.11 351	91.66 245	92.98 269	70.12 309	99.14 85	75.29 318	95.23 289	97.07 208

BH-untuned		90.68 207	90.90 200	90.05 271	95.98 203	79.57 251	90.04 255	94.94 234	87.91 186	94.07 174	93.00 267	87.76 186	97.78 247	79.19 293	95.17 290	92.80 328

pmmvs3		80.83 323	78.96 331	86.45 314	87.23 354	77.48 283	84.87 332	82.31 355	63.83 356	85.03 327	89.50 326	49.66 363	93.10 345	73.12 330	95.10 291	88.78 350

mvs_anonymous		90.37 216	91.30 193	87.58 306	92.17 305	68.00 345	89.84 263	94.73 242	83.82 251	93.22 204	97.40 66	87.54 189	97.40 269	87.94 193	95.05 292	97.34 201

IterMVS-SCA-FT		91.65 186	91.55 183	91.94 211	93.89 276	79.22 258	87.56 300	93.51 265	91.53 113	95.37 128	96.62 119	78.65 269	98.90 123	91.89 101	94.95 293	97.70 177

test-LLR		83.58 304	83.17 305	84.79 327	89.68 337	66.86 349	83.08 345	84.52 348	83.07 258	82.85 342	84.78 353	62.86 341	93.49 343	82.85 252	94.86 294	94.03 303

test-mter		81.21 321	80.01 328	84.79 327	89.68 337	66.86 349	83.08 345	84.52 348	73.85 321	82.85 342	84.78 353	43.66 370	93.49 343	82.85 252	94.86 294	94.03 303

PatchMatch-RL		89.18 241	88.02 259	92.64 187	95.90 209	92.87 45	88.67 291	91.06 302	80.34 277	90.03 273	91.67 297	83.34 230	94.42 334	76.35 313	94.84 296	90.64 344

OpenMVS_ROB	85.12 16	89.52 238	89.05 235	90.92 243	94.58 259	81.21 223	91.10 225	93.41 267	77.03 307	93.41 193	93.99 242	83.23 232	97.80 244	79.93 284	94.80 297	93.74 312

our_test_3		87.55 273	87.59 264	87.44 308	91.76 312	70.48 336	83.83 343	90.55 307	79.79 281	92.06 239	92.17 288	78.63 271	95.63 315	84.77 237	94.73 298	96.22 243

CHOSEN 280x420		80.04 328	77.97 334	86.23 318	90.13 332	74.53 313	72.87 358	89.59 310	66.38 350	76.29 360	85.32 352	56.96 354	95.36 323	69.49 347	94.72 299	88.79 349

IterMVS		90.18 222	90.16 216	90.21 266	93.15 287	75.98 302	87.56 300	92.97 273	86.43 213	94.09 172	96.40 131	78.32 273	97.43 266	87.87 194	94.69 300	97.23 205
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EMVS		80.35 327	80.28 326	80.54 340	84.73 363	69.07 343	72.54 359	80.73 359	87.80 190	81.66 351	81.73 358	62.89 340	89.84 356	75.79 317	94.65 301	82.71 357

PLC	85.34 15	90.40 214	88.92 238	94.85 104	96.53 160	90.02 79	91.58 213	96.48 183	80.16 279	86.14 322	92.18 287	85.73 217	98.25 208	76.87 309	94.61 302	96.30 240
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		90.82 202	90.67 208	91.26 230	94.16 268	83.08 202	86.63 321	96.19 196	90.60 135	91.94 240	91.89 292	89.16 168	95.75 314	80.96 275	94.51 303	94.95 283

xiu_mvs_v2_base		89.00 246	89.19 231	88.46 296	94.86 244	74.63 311	86.97 310	95.60 213	80.88 274	87.83 309	88.62 334	91.04 137	98.81 141	82.51 258	94.38 304	91.93 336

PS-MVSNAJ		88.86 250	88.99 237	88.48 295	94.88 242	74.71 309	86.69 319	95.60 213	80.88 274	87.83 309	87.37 342	90.77 140	98.82 136	82.52 257	94.37 305	91.93 336

EU-MVSNet		87.39 277	86.71 280	89.44 277	93.40 282	76.11 300	94.93 94	90.00 309	57.17 361	95.71 115	97.37 68	64.77 332	97.68 255	92.67 82	94.37 305	94.52 293

E-PMN		80.72 325	80.86 320	80.29 341	85.11 361	68.77 344	72.96 357	81.97 356	87.76 191	83.25 341	83.01 357	62.22 344	89.17 358	77.15 308	94.31 307	82.93 356

GA-MVS		87.70 268	86.82 277	90.31 261	93.27 284	77.22 287	84.72 335	92.79 277	85.11 238	89.82 278	90.07 316	66.80 319	97.76 250	84.56 240	94.27 308	95.96 253

sss		87.23 280	86.82 277	88.46 296	93.96 274	77.94 274	86.84 314	92.78 278	77.59 302	87.61 312	91.83 294	78.75 268	91.92 350	77.84 300	94.20 309	95.52 272

MDA-MVSNet-bldmvs		91.04 199	90.88 201	91.55 222	94.68 256	80.16 231	85.49 328	92.14 292	90.41 140	94.93 150	95.79 166	85.10 221	96.93 285	85.15 229	94.19 310	97.57 185

PAPM_NR		91.03 200	90.81 204	91.68 219	96.73 149	81.10 224	93.72 134	96.35 188	88.19 182	88.77 296	92.12 290	85.09 222	97.25 274	82.40 259	93.90 311	96.68 226

YYNet1		88.17 261	88.24 252	87.93 302	92.21 303	73.62 320	80.75 352	88.77 312	82.51 265	94.99 148	95.11 199	82.70 239	93.70 341	83.33 248	93.83 312	96.48 233

MDA-MVSNet_test_wron		88.16 262	88.23 253	87.93 302	92.22 302	73.71 319	80.71 353	88.84 311	82.52 264	94.88 153	95.14 197	82.70 239	93.61 342	83.28 249	93.80 313	96.46 234

1112_ss		88.42 257	87.41 266	91.45 224	96.69 150	80.99 225	89.72 265	96.72 170	73.37 323	87.00 318	90.69 312	77.38 280	98.20 211	81.38 268	93.72 314	95.15 277

PVSNet	76.22 20	82.89 309	82.37 309	84.48 329	93.96 274	64.38 359	78.60 355	88.61 313	71.50 332	84.43 333	86.36 348	74.27 296	94.60 331	69.87 346	93.69 315	94.46 294

TESTMET0.1,1		79.09 330	78.04 333	82.25 337	87.52 351	64.03 360	83.08 345	80.62 360	70.28 339	80.16 355	83.22 356	44.13 369	90.56 354	79.95 282	93.36 316	92.15 334

PAPR		87.65 271	86.77 279	90.27 263	92.85 293	77.38 284	88.56 292	96.23 193	76.82 309	84.98 328	89.75 323	86.08 214	97.16 277	72.33 333	93.35 317	96.26 242

SCA		87.43 276	87.21 270	88.10 301	92.01 309	71.98 331	89.43 271	88.11 320	82.26 268	88.71 297	92.83 271	78.65 269	97.59 257	79.61 288	93.30 318	94.75 287

Test_1112_low_res		87.50 275	86.58 281	90.25 264	96.80 148	77.75 279	87.53 302	96.25 191	69.73 341	86.47 320	93.61 254	75.67 293	97.88 235	79.95 282	93.20 319	95.11 279

MDTV_nov1_ep13			83.88 302		89.42 341	61.52 362	88.74 288	87.41 324	73.99 320	84.96 329	94.01 241	65.25 329	95.53 316	78.02 298	93.16 320

WTY-MVS		86.93 288	86.50 286	88.24 299	94.96 241	74.64 310	87.19 307	92.07 294	78.29 299	88.32 303	91.59 299	78.06 275	94.27 337	74.88 320	93.15 321	95.80 260

PMMVS		83.00 308	81.11 316	88.66 292	83.81 365	86.44 152	82.24 349	85.65 338	61.75 359	82.07 347	85.64 351	79.75 262	91.59 352	75.99 315	93.09 322	87.94 351

UnsupCasMVSNet_bld		88.50 256	88.03 258	89.90 272	95.52 228	78.88 263	87.39 304	94.02 258	79.32 290	93.06 208	94.02 240	80.72 258	94.27 337	75.16 319	93.08 323	96.54 227

MVS		84.98 298	84.30 298	87.01 310	91.03 321	77.69 281	91.94 196	94.16 254	59.36 360	84.23 334	87.50 341	85.66 218	96.80 289	71.79 335	93.05 324	86.54 352

PatchT		87.51 274	88.17 255	85.55 320	90.64 325	66.91 347	92.02 191	86.09 333	92.20 83	89.05 289	97.16 83	64.15 334	96.37 303	89.21 168	92.98 325	93.37 319

MS-PatchMatch		88.05 263	87.75 261	88.95 285	93.28 283	77.93 275	87.88 296	92.49 285	75.42 313	92.57 222	93.59 255	80.44 259	94.24 339	81.28 269	92.75 326	94.69 290

CR-MVSNet		87.89 264	87.12 273	90.22 265	91.01 322	78.93 261	92.52 163	92.81 275	73.08 325	89.10 287	96.93 96	67.11 316	97.64 256	88.80 175	92.70 327	94.08 300

RPMNet		90.31 220	90.14 219	90.81 248	91.01 322	78.93 261	92.52 163	98.12 43	91.91 91	89.10 287	96.89 99	68.84 311	99.41 36	90.17 143	92.70 327	94.08 300

KD-MVS_2432*1600		82.17 314	80.75 321	86.42 315	82.04 366	70.09 339	81.75 350	90.80 304	82.56 262	90.37 265	89.30 328	42.90 371	96.11 308	74.47 321	92.55 329	93.06 323

miper_refine_blended		82.17 314	80.75 321	86.42 315	82.04 366	70.09 339	81.75 350	90.80 304	82.56 262	90.37 265	89.30 328	42.90 371	96.11 308	74.47 321	92.55 329	93.06 323

BH-w/o		87.21 281	87.02 275	87.79 305	94.77 248	77.27 286	87.90 295	93.21 271	81.74 271	89.99 274	88.39 337	83.47 229	96.93 285	71.29 339	92.43 331	89.15 346

IB-MVS	77.21 19	83.11 306	81.05 317	89.29 281	91.15 320	75.85 303	85.66 327	86.00 335	79.70 283	82.02 349	86.61 345	48.26 365	98.39 194	77.84 300	92.22 332	93.63 314
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
gg-mvs-nofinetune		82.10 316	81.02 318	85.34 323	87.46 353	71.04 333	94.74 99	67.56 366	96.44 21	79.43 357	98.99 6	45.24 367	96.15 306	67.18 351	92.17 333	88.85 348

HY-MVS	82.50 18	86.81 289	85.93 290	89.47 276	93.63 280	77.93 275	94.02 125	91.58 300	75.68 310	83.64 337	93.64 252	77.40 279	97.42 267	71.70 337	92.07 334	93.05 325

TR-MVS		87.70 268	87.17 271	89.27 282	94.11 270	79.26 256	88.69 289	91.86 297	81.94 270	90.69 260	89.79 321	82.82 237	97.42 267	72.65 332	91.98 335	91.14 341

new_pmnet		81.22 320	81.01 319	81.86 338	90.92 324	70.15 338	84.03 341	80.25 362	70.83 336	85.97 323	89.78 322	67.93 315	84.65 361	67.44 350	91.90 336	90.78 343

FPMVS		84.50 300	83.28 304	88.16 300	96.32 175	94.49 14	85.76 326	85.47 341	83.09 257	85.20 326	94.26 230	63.79 337	86.58 360	63.72 356	91.88 337	83.40 355

UnsupCasMVSNet_eth		90.33 218	90.34 214	90.28 262	94.64 258	80.24 230	89.69 266	95.88 205	85.77 225	93.94 181	95.69 171	81.99 247	92.98 347	84.21 243	91.30 338	97.62 183

MVP-Stereo		90.07 227	88.92 238	93.54 159	96.31 176	86.49 149	90.93 228	95.59 217	79.80 280	91.48 246	95.59 175	80.79 257	97.39 270	78.57 297	91.19 339	96.76 224
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		86.46 290	86.33 287	86.87 312	91.65 314	74.54 312	91.94 196	94.10 255	74.28 317	84.78 330	87.33 343	83.03 234	95.00 329	78.72 295	91.16 340	91.06 342

tpm		84.38 301	84.08 300	85.30 324	90.47 329	63.43 361	89.34 274	85.63 339	77.24 306	87.62 311	95.03 205	61.00 349	97.30 273	79.26 292	91.09 341	95.16 276

CVMVSNet		85.16 296	84.72 295	86.48 313	92.12 306	70.19 337	92.32 178	88.17 319	56.15 362	90.64 261	95.85 161	67.97 314	96.69 292	88.78 176	90.52 342	92.56 331

test0.0.03 1		82.48 311	81.47 315	85.48 321	89.70 336	73.57 321	84.73 333	81.64 357	83.07 258	88.13 306	86.61 345	62.86 341	89.10 359	66.24 353	90.29 343	93.77 311

baseline2		83.38 305	81.54 314	88.90 286	91.38 318	72.84 327	88.78 286	81.22 358	78.97 293	79.82 356	87.56 339	61.73 346	97.80 244	74.30 323	90.05 344	96.05 250

PAPM		81.91 317	80.11 327	87.31 309	93.87 277	72.32 330	84.02 342	93.22 269	69.47 342	76.13 361	89.84 318	72.15 304	97.23 275	53.27 362	89.02 345	92.37 333

MVS-HIRNet		78.83 331	80.60 323	73.51 346	93.07 288	47.37 367	87.10 309	78.00 363	68.94 343	77.53 359	97.26 76	71.45 307	94.62 330	63.28 357	88.74 346	78.55 360

tpm2		81.46 318	80.35 325	84.80 326	89.90 334	65.14 355	90.44 240	85.36 342	65.82 353	82.05 348	92.44 283	57.94 352	96.69 292	70.71 343	88.49 347	92.56 331

CostFormer		83.09 307	82.21 310	85.73 319	89.27 342	67.01 346	90.35 244	86.47 330	70.42 338	83.52 339	93.23 264	61.18 347	96.85 287	77.21 307	88.26 348	93.34 320

GG-mvs-BLEND				83.24 335	85.06 362	71.03 334	94.99 93	65.55 367		74.09 362	75.51 362	44.57 368	94.46 333	59.57 359	87.54 349	84.24 354

PatchmatchNet		85.22 295	84.64 296	86.98 311	89.51 340	69.83 342	90.52 238	87.34 325	78.87 295	87.22 317	92.74 275	66.91 318	96.53 295	81.77 264	86.88 350	94.58 291
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
baseline1		87.62 272	87.31 267	88.54 293	94.71 255	74.27 317	93.10 147	88.20 318	86.20 217	92.18 236	93.04 266	73.21 300	95.52 317	79.32 291	85.82 351	95.83 259

tpmvs		84.22 302	83.97 301	84.94 325	87.09 355	65.18 354	91.21 222	88.35 315	82.87 261	85.21 325	90.96 307	65.24 330	96.75 290	79.60 290	85.25 352	92.90 327

ADS-MVSNet2		84.01 303	82.20 311	89.41 278	89.04 344	76.37 299	87.57 298	90.98 303	72.71 328	84.46 331	92.45 281	68.08 312	96.48 298	70.58 344	83.97 353	95.38 273

ADS-MVSNet		82.25 312	81.55 313	84.34 330	89.04 344	65.30 353	87.57 298	85.13 347	72.71 328	84.46 331	92.45 281	68.08 312	92.33 349	70.58 344	83.97 353	95.38 273

JIA-IIPM		85.08 297	83.04 306	91.19 235	87.56 350	86.14 161	89.40 273	84.44 350	88.98 165	82.20 346	97.95 39	56.82 355	96.15 306	76.55 312	83.45 355	91.30 340

MVE	59.87 23	73.86 333	72.65 336	77.47 344	87.00 357	74.35 315	61.37 362	60.93 368	67.27 348	69.69 364	86.49 347	81.24 256	72.33 364	56.45 361	83.45 355	85.74 353
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DWT-MVSNet_test		80.74 324	79.18 330	85.43 322	87.51 352	66.87 348	89.87 262	86.01 334	74.20 319	80.86 353	80.62 359	48.84 364	96.68 294	81.54 266	83.14 357	92.75 329

EPMVS		81.17 322	80.37 324	83.58 333	85.58 360	65.08 356	90.31 246	71.34 365	77.31 305	85.80 324	91.30 301	59.38 350	92.70 348	79.99 281	82.34 358	92.96 326

tpmrst		82.85 310	82.93 308	82.64 336	87.65 349	58.99 364	90.14 252	87.90 321	75.54 312	83.93 335	91.63 298	66.79 321	95.36 323	81.21 271	81.54 359	93.57 318

tpm cat1		80.61 326	79.46 329	84.07 332	88.78 346	65.06 357	89.26 277	88.23 317	62.27 358	81.90 350	89.66 325	62.70 343	95.29 326	71.72 336	80.60 360	91.86 338

dp		79.28 329	78.62 332	81.24 339	85.97 359	56.45 365	86.91 312	85.26 345	72.97 326	81.45 352	89.17 331	56.01 357	95.45 321	73.19 329	76.68 361	91.82 339

DeepMVS_CX				53.83 348	70.38 368	64.56 358		48.52 370	33.01 364	65.50 365	74.21 363	56.19 356	46.64 366	38.45 365	70.07 362	50.30 362

tmp_tt		37.97 335	44.33 338	18.88 349	11.80 370	21.54 370	63.51 361	45.66 371	4.23 366	51.34 366	50.48 364	59.08 351	22.11 367	44.50 364	68.35 363	13.00 363

PVSNet_0	70.34 21	74.58 332	72.96 335	79.47 342	90.63 326	66.24 352	73.26 356	83.40 354	63.67 357	78.02 358	78.35 361	72.53 302	89.59 357	56.68 360	60.05 364	82.57 358

test_method		50.44 334	48.94 337	54.93 347	39.68 369	12.38 371	28.59 363	90.09 308	6.82 365	41.10 367	78.41 360	54.41 358	70.69 365	50.12 363	51.26 365	81.72 359

test123		9.49 337	12.01 340	1.91 350	2.87 371	1.30 372	82.38 348	1.34 373	1.36 367	2.84 368	6.56 367	2.45 373	0.97 368	2.73 366	5.56 366	3.47 364

testmvs		9.02 338	11.42 341	1.81 351	2.77 372	1.13 373	79.44 354	1.90 372	1.18 368	2.65 369	6.80 366	1.95 374	0.87 369	2.62 367	3.45 367	3.44 365

uanet_test		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

cdsmvs_eth3d_5k		23.35 336	31.13 339	0.00 352	0.00 373	0.00 374	0.00 364	95.58 219	0.00 369	0.00 370	91.15 303	93.43 75	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		7.56 339	10.09 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	90.77 140	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

ab-mvs-re		7.56 339	10.08 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	90.69 312	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

test_241102_ONE					98.51 45	86.97 138		98.10 46	91.85 95	97.63 31	97.03 90	96.48 11	98.95 119

save fliter					97.46 117	88.05 119	92.04 189	97.08 144	87.63 196

test0726					98.51 45	86.69 145	95.34 75	98.18 34	91.85 95	97.63 31	97.37 68	95.58 22

GSMVS																94.75 287

test_part2					98.21 68	89.41 91				96.72 68

sam_mvs1												66.64 322				94.75 287

sam_mvs												66.41 323

MTGPA								97.62 99

test_post1							90.21 248				5.85 369	65.36 328	96.00 311	79.61 288

test_post											6.07 368	65.74 327	95.84 313

patchmatchnet-post											91.71 296	66.22 325	97.59 257

MTMP							94.82 96	54.62 369

gm-plane-assit					87.08 356	59.33 363			71.22 333		83.58 355		97.20 276	73.95 324

TEST9					96.45 164	89.46 88	90.60 236	96.92 155	79.09 292	90.49 262	94.39 227	91.31 127	98.88 126

test_8					96.37 166	89.14 95	90.51 239	96.89 158	79.37 287	90.42 264	94.36 229	91.20 133	98.82 136

agg_prior					96.20 184	88.89 100		96.88 159		90.21 267			98.78 147

test_prior4						89.91 82	90.74 232

test_prior				94.61 113	95.95 205	87.23 131		97.36 122					98.68 167			97.93 155

旧先验2							90.00 257		68.65 344	92.71 218			96.52 296	85.15 229

新几何2							90.02 256

无先验							89.94 258	95.75 210	70.81 337				98.59 177	81.17 272		94.81 284

原ACMM2							89.34 274

testdata2													98.03 223	80.24 279

segment_acmp												92.14 107

testdata1							88.96 283		88.44 178

plane_prior7					97.71 99	88.68 104

plane_prior6					97.21 128	88.23 115						86.93 201

plane_prior4											95.59 175

plane_prior3						88.43 113			90.35 141	93.31 196

plane_prior2							94.56 108		91.74 106

plane_prior1					97.38 120

n2								0.00 374

nn								0.00 374

door-mid								92.13 293

test11								96.65 173

door								91.26 301

HQP5-MVS						84.89 177

HQP-NCC					96.36 168		91.37 217		87.16 203	88.81 292

ACMP_Plane					96.36 168		91.37 217		87.16 203	88.81 292

BP-MVS														86.55 214

HQP4-MVS										88.81 292			98.61 173			98.15 133

HQP2-MVS												84.76 223

NP-MVS					96.82 145	87.10 134					93.40 259

MDTV_nov1_ep13_2view						42.48 369	88.45 293		67.22 349	83.56 338		66.80 319		72.86 331		94.06 302

Test By Simon												90.61 146

High-resolution multi-view benchmark