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

XVG-OURS-SEG-HR		95.38 75	95.00 95	96.51 46	98.10 81	94.07 20	92.46 183	98.13 46	90.69 134	93.75 191	96.25 162	98.03 2	97.02 281	92.08 94	95.55 283	98.45 117

pmmvs6		96.80 12	97.36 9	95.15 93	99.12 8	87.82 125	96.68 30	97.86 80	96.10 27	98.14 23	99.28 3	97.94 3	98.21 204	91.38 116	99.69 14	99.42 19

UniMVSNet_ETH3D		97.13 5	97.72 3	95.35 84	99.51 2	87.38 129	97.70 8	97.54 107	98.16 2	98.94 2	99.33 2	97.84 4	99.08 92	90.73 128	99.73 13	99.59 13

ACMH	88.36 12	96.59 27	97.43 5	94.07 134	98.56 42	85.33 178	96.33 47	98.30 23	94.66 40	98.72 8	98.30 32	97.51 5	98.00 222	94.87 18	99.59 28	98.86 74
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS_fast		97.01 6	96.89 14	97.39 21	99.12 8	93.92 28	97.16 14	98.17 41	93.11 69	96.48 84	97.36 82	96.92 6	99.34 61	94.31 27	99.38 57	98.92 68

ACMH+	88.43 11	96.48 30	96.82 15	95.47 81	98.54 48	89.06 98	95.65 79	98.61 11	96.10 27	98.16 22	97.52 70	96.90 7	98.62 167	90.30 142	99.60 26	98.72 92

HPM-MVS		96.81 11	96.62 22	97.36 23	98.89 20	93.53 38	97.51 10	98.44 13	92.35 82	95.95 109	96.41 145	96.71 8	99.42 32	93.99 34	99.36 58	99.13 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mvs_tets		96.83 8	96.71 18	97.17 27	98.83 25	92.51 48	96.58 33	97.61 102	87.57 201	98.80 7	98.90 9	96.50 9	99.59 13	96.15 7	99.47 41	99.40 21

SED-MVS		96.00 51	96.41 32	94.76 105	98.51 51	86.97 139	95.21 94	98.10 50	91.95 92	97.63 34	97.25 91	96.48 10	99.35 58	93.29 62	99.29 70	97.95 156

test_241102_ONE					98.51 51	86.97 139		98.10 50	91.85 98	97.63 34	97.03 107	96.48 10	98.95 112

LPG-MVS_test		96.38 39	96.23 39	96.84 38	98.36 66	92.13 52	95.33 90	98.25 27	91.78 105	97.07 59	97.22 95	96.38 12	99.28 70	92.07 95	99.59 28	99.11 44

LGP-MVS_train				96.84 38	98.36 66	92.13 52		98.25 27	91.78 105	97.07 59	97.22 95	96.38 12	99.28 70	92.07 95	99.59 28	99.11 44

ACMM	88.83 9	96.30 42	96.07 49	96.97 34	98.39 62	92.95 44	94.74 111	98.03 64	90.82 131	97.15 56	96.85 118	96.25 14	99.00 104	93.10 70	99.33 62	98.95 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
wuyk23d		87.83 269	90.79 201	78.96 353	90.46 340	88.63 107	92.72 170	90.67 315	91.65 113	98.68 11	97.64 63	96.06 15	77.53 374	59.84 369	99.41 54	70.73 372

testf1		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 18	94.96 36	97.30 51	97.93 48	96.05 16	97.90 229	89.32 167	99.23 82	98.19 133

APD_test2		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 18	94.96 36	97.30 51	97.93 48	96.05 16	97.90 229	89.32 167	99.23 82	98.19 133

ACMP	88.15 13	95.71 61	95.43 76	96.54 45	98.17 77	91.73 60	94.24 130	98.08 53	89.46 158	96.61 81	96.47 141	95.85 18	99.12 89	90.45 134	99.56 34	98.77 86
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TransMVSNet (Re)		95.27 84	96.04 51	92.97 169	98.37 65	81.92 218	95.07 101	96.76 171	93.97 52	97.77 30	98.57 20	95.72 19	97.90 229	88.89 184	99.23 82	99.08 48

ZNCC-MVS		96.42 35	96.20 41	97.07 30	98.80 30	92.79 46	96.08 61	98.16 44	91.74 109	95.34 137	96.36 153	95.68 20	99.44 28	94.41 25	99.28 75	98.97 60

ACMMP_NAP		96.21 44	96.12 46	96.49 48	98.90 19	91.42 63	94.57 119	98.03 64	90.42 142	96.37 87	97.35 85	95.68 20	99.25 73	94.44 24	99.34 60	98.80 82

APD-MVS_3200maxsize		96.82 9	96.65 20	97.32 25	97.95 95	93.82 33	96.31 50	98.25 27	95.51 34	96.99 66	97.05 106	95.63 22	99.39 48	93.31 61	98.88 121	98.75 87

DVP-MVS		95.82 57	96.18 42	94.72 107	98.51 51	86.69 147	95.20 96	97.00 150	91.85 98	97.40 49	97.35 85	95.58 23	99.34 61	93.44 55	99.31 65	98.13 138
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
test0726					98.51 51	86.69 147	95.34 89	98.18 37	91.85 98	97.63 34	97.37 79	95.58 23

MP-MVS-pluss		96.08 48	95.92 57	96.57 44	99.06 10	91.21 65	93.25 157	98.32 20	87.89 192	96.86 70	97.38 78	95.55 25	99.39 48	95.47 13	99.47 41	99.11 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
COLMAP_ROB	91.06 5	96.75 16	96.62 22	97.13 28	98.38 63	94.31 17	96.79 26	98.32 20	96.69 17	96.86 70	97.56 67	95.48 26	98.77 144	90.11 151	99.44 48	98.31 125
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SD-MVS		95.19 85	95.73 66	93.55 152	96.62 163	88.88 104	94.67 113	98.05 59	91.26 120	97.25 55	96.40 146	95.42 27	94.36 336	92.72 82	99.19 88	97.40 204
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
RE-MVS-def			96.66 19		98.07 83	95.27 9	96.37 44	98.12 47	95.66 32	97.00 64	97.03 107	95.40 28		93.49 49	98.84 126	98.00 148

test_241102_TWO								98.10 50	91.95 92	97.54 38	97.25 91	95.37 29	99.35 58	93.29 62	99.25 79	98.49 114

HFP-MVS		96.39 38	96.17 44	97.04 31	98.51 51	93.37 39	96.30 54	97.98 70	92.35 82	95.63 125	96.47 141	95.37 29	99.27 72	93.78 39	99.14 95	98.48 115

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 31	92.49 49	96.44 41	97.42 116	86.96 210	98.71 10	98.72 17	95.36 31	99.56 17	95.92 8	99.45 45	99.32 27

TranMVSNet+NR-MVSNet		96.07 49	96.26 38	95.50 80	98.26 71	87.69 126	93.75 146	97.86 80	95.96 31	97.48 44	97.14 101	95.33 32	99.44 28	90.79 126	99.76 10	99.38 22

PMVS	87.21 14	94.97 90	95.33 81	93.91 141	98.97 17	97.16 2	95.54 85	95.85 212	96.47 22	93.40 202	97.46 75	95.31 33	95.47 320	86.18 232	98.78 137	89.11 356
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pm-mvs1		95.43 71	95.94 54	93.93 140	98.38 63	85.08 181	95.46 87	97.12 143	91.84 101	97.28 53	98.46 27	95.30 34	97.71 251	90.17 149	99.42 50	98.99 55

PGM-MVS		96.32 40	95.94 54	97.43 18	98.59 41	93.84 32	95.33 90	98.30 23	91.40 118	95.76 118	96.87 117	95.26 35	99.45 26	92.77 78	99.21 86	99.00 53

PS-CasMVS		96.69 20	97.43 5	94.49 122	99.13 6	84.09 193	96.61 32	97.97 72	97.91 5	98.64 13	98.13 37	95.24 36	99.65 3	93.39 59	99.84 3	99.72 2

GST-MVS		96.24 43	95.99 53	97.00 33	98.65 34	92.71 47	95.69 78	98.01 67	92.08 90	95.74 120	96.28 159	95.22 37	99.42 32	93.17 68	99.06 99	98.88 73

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 26	98.81 28	93.86 31	99.07 2	98.98 6	97.01 13	98.92 4	98.78 14	95.22 37	98.61 168	96.85 2	99.77 9	99.31 28
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
DPE-MVS		95.89 54	95.88 58	95.92 64	97.93 96	89.83 85	93.46 153	98.30 23	92.37 80	97.75 31	96.95 111	95.14 39	99.51 20	91.74 105	99.28 75	98.41 119
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_one_0601					98.26 71	87.14 134		98.18 37	94.25 45	96.99 66	97.36 82	95.13 40

nrg030		96.32 40	96.55 25	95.62 76	97.83 99	88.55 111	95.77 74	98.29 26	92.68 73	98.03 25	97.91 52	95.13 40	98.95 112	93.85 37	99.49 40	99.36 24

APDe-MVS		96.46 31	96.64 21	95.93 62	97.68 112	89.38 95	96.90 22	98.41 16	92.52 77	97.43 46	97.92 51	95.11 42	99.50 21	94.45 23	99.30 67	98.92 68

ACMMP		96.61 24	96.34 34	97.43 18	98.61 38	93.88 29	96.95 21	98.18 37	92.26 85	96.33 89	96.84 120	95.10 43	99.40 45	93.47 52	99.33 62	99.02 52
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
SR-MVS		96.70 19	96.42 29	97.54 11	98.05 85	94.69 11	96.13 59	98.07 56	95.17 35	96.82 72	96.73 129	95.09 44	99.43 31	92.99 75	98.71 143	98.50 112

OPM-MVS		95.61 64	95.45 74	96.08 54	98.49 58	91.00 68	92.65 175	97.33 126	90.05 147	96.77 75	96.85 118	95.04 45	98.56 175	92.77 78	99.06 99	98.70 95
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DTE-MVSNet		96.74 17	97.43 5	94.67 109	99.13 6	84.68 184	96.51 35	97.94 78	98.14 3	98.67 12	98.32 31	95.04 45	99.69 2	93.27 64	99.82 7	99.62 10

region2R		96.41 36	96.09 47	97.38 22	98.62 36	93.81 35	96.32 49	97.96 73	92.26 85	95.28 141	96.57 138	95.02 47	99.41 38	93.63 43	99.11 97	98.94 63

PEN-MVS		96.69 20	97.39 8	94.61 112	99.16 4	84.50 185	96.54 34	98.05 59	98.06 4	98.64 13	98.25 33	95.01 48	99.65 3	92.95 76	99.83 5	99.68 4

SteuartSystems-ACMMP		96.40 37	96.30 36	96.71 40	98.63 35	91.96 55	95.70 76	98.01 67	93.34 65	96.64 79	96.57 138	94.99 49	99.36 57	93.48 51	99.34 60	98.82 78
Skip Steuart: Steuart Systems R&D Blog.
canonicalmvs		94.59 103	94.69 105	94.30 128	95.60 234	87.03 138	95.59 81	98.24 30	91.56 115	95.21 147	92.04 304	94.95 50	98.66 163	91.45 114	97.57 229	97.20 213

ACMMPR		96.46 31	96.14 45	97.41 20	98.60 39	93.82 33	96.30 54	97.96 73	92.35 82	95.57 127	96.61 136	94.93 51	99.41 38	93.78 39	99.15 94	99.00 53

tt0805		95.42 73	95.93 56	93.86 144	98.75 32	88.47 113	97.68 9	94.29 256	96.48 21	95.38 133	93.63 266	94.89 52	97.94 228	95.38 16	96.92 252	95.17 284

SR-MVS-dyc-post		96.84 7	96.60 24	97.56 10	98.07 83	95.27 9	96.37 44	98.12 47	95.66 32	97.00 64	97.03 107	94.85 53	99.42 32	93.49 49	98.84 126	98.00 148

casdiffmvs_mvg		95.10 87	95.62 69	93.53 155	96.25 192	83.23 202	92.66 174	98.19 35	93.06 70	97.49 42	97.15 100	94.78 54	98.71 156	92.27 90	98.72 142	98.65 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVS		96.44 34	96.08 48	97.54 11	98.29 68	94.62 14	96.80 25	98.08 53	92.67 75	95.08 152	96.39 150	94.77 55	99.42 32	93.17 68	99.44 48	98.58 109

test_0728_THIRD									93.26 66	97.40 49	97.35 85	94.69 56	99.34 61	93.88 35	99.42 50	98.89 71

9.14			94.81 99		97.49 123		94.11 135	98.37 17	87.56 202	95.38 133	96.03 172	94.66 57	99.08 92	90.70 129	98.97 113

GeoE		94.55 105	94.68 107	94.15 131	97.23 133	85.11 180	94.14 134	97.34 125	88.71 176	95.26 142	95.50 196	94.65 58	99.12 89	90.94 123	98.40 169	98.23 129

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 12	95.95 8	98.61 3	98.81 8	97.41 10	97.28 53	98.46 27	94.62 59	98.84 127	94.64 21	99.53 36	98.99 55

XVS		96.49 29	96.18 42	97.44 16	98.56 42	93.99 26	96.50 36	97.95 75	94.58 41	94.38 174	96.49 140	94.56 60	99.39 48	93.57 45	99.05 102	98.93 64

X-MVStestdata		90.70 201	88.45 246	97.44 16	98.56 42	93.99 26	96.50 36	97.95 75	94.58 41	94.38 174	26.89 375	94.56 60	99.39 48	93.57 45	99.05 102	98.93 64

mPP-MVS		96.46 31	96.05 50	97.69 4	98.62 36	94.65 13	96.45 39	97.74 93	92.59 76	95.47 129	96.68 132	94.50 62	99.42 32	93.10 70	99.26 78	98.99 55

DeepC-MVS	91.39 4	95.43 71	95.33 81	95.71 74	97.67 113	90.17 80	93.86 143	98.02 66	87.35 203	96.22 99	97.99 46	94.48 63	99.05 97	92.73 81	99.68 18	97.93 158
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		95.77 58	95.54 72	96.47 49	98.27 70	91.19 66	95.09 99	97.79 90	86.48 213	97.42 48	97.51 72	94.47 64	99.29 68	93.55 47	99.29 70	98.93 64
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
SF-MVS		95.88 55	95.88 58	95.87 68	98.12 79	89.65 87	95.58 83	98.56 12	91.84 101	96.36 88	96.68 132	94.37 65	99.32 67	92.41 88	99.05 102	98.64 103

MP-MVS		96.14 46	95.68 67	97.51 13	98.81 28	94.06 21	96.10 60	97.78 91	92.73 72	93.48 199	96.72 130	94.23 66	99.42 32	91.99 97	99.29 70	99.05 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
anonymousdsp		96.74 17	96.42 29	97.68 6	98.00 91	94.03 25	96.97 20	97.61 102	87.68 199	98.45 18	98.77 15	94.20 67	99.50 21	96.70 3	99.40 55	99.53 15

test_0402		95.73 60	96.22 40	94.26 129	98.19 76	85.77 172	93.24 158	97.24 134	96.88 16	97.69 32	97.77 58	94.12 68	99.13 86	91.54 113	99.29 70	97.88 164

Effi-MVS+		92.79 155	92.74 154	92.94 173	95.10 247	83.30 201	94.00 138	97.53 109	91.36 119	89.35 296	90.65 326	94.01 69	98.66 163	87.40 210	95.30 292	96.88 225

DROMVSNet		95.44 70	95.62 69	94.89 99	96.93 147	87.69 126	96.48 38	99.14 4	93.93 53	92.77 226	94.52 238	93.95 70	99.49 24	93.62 44	99.22 85	97.51 195

OMC-MVS		94.22 118	93.69 131	95.81 69	97.25 132	91.27 64	92.27 194	97.40 117	87.10 209	94.56 169	95.42 201	93.74 71	98.11 213	86.62 222	98.85 125	98.06 140

LCM-MVSNet-Re		94.20 119	94.58 110	93.04 166	95.91 216	83.13 206	93.79 145	99.19 3	92.00 91	98.84 5	98.04 43	93.64 72	99.02 102	81.28 279	98.54 160	96.96 221

CS-MVS		95.77 58	95.58 71	96.37 50	96.84 152	91.72 61	96.73 29	99.06 5	94.23 46	92.48 235	94.79 228	93.56 73	99.49 24	93.47 52	99.05 102	97.89 163

MTAPA		96.65 22	96.38 33	97.47 15	98.95 18	94.05 23	95.88 70	97.62 100	94.46 44	96.29 93	96.94 112	93.56 73	99.37 56	94.29 28	99.42 50	98.99 55

CS-MVS-test		95.32 78	95.10 92	95.96 58	96.86 151	90.75 74	96.33 47	99.20 2	93.99 50	91.03 267	93.73 264	93.52 75	99.55 18	91.81 103	99.45 45	97.58 189

UA-Net		97.35 4	97.24 11	97.69 4	98.22 74	93.87 30	98.42 6	98.19 35	96.95 14	95.46 131	99.23 4	93.45 76	99.57 14	95.34 17	99.89 2	99.63 9

MVS_111021_HR		93.63 130	93.42 141	94.26 129	96.65 159	86.96 141	89.30 281	96.23 197	88.36 185	93.57 197	94.60 235	93.45 76	97.77 246	90.23 147	98.38 173	98.03 146

cdsmvs_eth3d_5k		23.35 344	31.13 347	0.00 362	0.00 385	0.00 386	0.00 373	95.58 224	0.00 380	0.00 381	91.15 315	93.43 78	0.00 381	0.00 379	0.00 379	0.00 377

APD-MVS		95.00 89	94.69 105	95.93 62	97.38 128	90.88 71	94.59 116	97.81 86	89.22 165	95.46 131	96.17 167	93.42 79	99.34 61	89.30 169	98.87 124	97.56 192
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ANet_high		94.83 96	96.28 37	90.47 259	96.65 159	73.16 334	94.33 127	98.74 10	96.39 24	98.09 24	98.93 8	93.37 80	98.70 157	90.38 137	99.68 18	99.53 15

APD_test1		95.91 53	95.42 77	97.36 23	98.82 26	96.62 6	95.64 80	97.64 98	93.38 64	95.89 114	97.23 93	93.35 81	97.66 254	88.20 193	98.66 151	97.79 175

casdiffmvs		94.32 113	94.80 100	92.85 177	96.05 206	81.44 226	92.35 189	98.05 59	91.53 116	95.75 119	96.80 121	93.35 81	98.49 181	91.01 122	98.32 181	98.64 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_djsdf		96.62 23	96.49 26	97.01 32	98.55 45	91.77 59	97.15 15	97.37 118	88.98 169	98.26 21	98.86 10	93.35 81	99.60 9	96.41 4	99.45 45	99.66 6

VPA-MVSNet		95.14 86	95.67 68	93.58 151	97.76 103	83.15 205	94.58 118	97.58 104	93.39 63	97.05 62	98.04 43	93.25 84	98.51 180	89.75 161	99.59 28	99.08 48

Anonymous20240529		95.50 68	95.83 62	94.50 120	97.33 131	85.93 168	95.19 98	96.77 170	96.64 19	97.61 37	98.05 42	93.23 85	98.79 138	88.60 190	99.04 107	98.78 84

baseline		94.26 116	94.80 100	92.64 183	96.08 204	80.99 232	93.69 148	98.04 63	90.80 132	94.89 159	96.32 155	93.19 86	98.48 185	91.68 108	98.51 164	98.43 118

DeepPCF-MVS	90.46 6	94.20 119	93.56 137	96.14 52	95.96 213	92.96 43	89.48 275	97.46 113	85.14 236	96.23 98	95.42 201	93.19 86	98.08 214	90.37 138	98.76 139	97.38 207

Anonymous20231211		96.60 25	97.13 12	95.00 96	97.46 126	86.35 159	97.11 19	98.24 30	97.58 8	98.72 8	98.97 7	93.15 88	99.15 82	93.18 67	99.74 12	99.50 17

DVP-MVS++		95.93 52	96.34 34	94.70 108	96.54 168	86.66 149	98.45 4	98.22 32	93.26 66	97.54 38	97.36 82	93.12 89	99.38 54	93.88 35	98.68 147	98.04 143

OPU-MVS				95.15 93	96.84 152	89.43 92	95.21 94				95.66 190	93.12 89	98.06 215	86.28 231	98.61 153	97.95 156

LS3D		96.11 47	95.83 62	96.95 36	94.75 259	94.20 19	97.34 13	97.98 70	97.31 11	95.32 138	96.77 122	93.08 91	99.20 78	91.79 104	98.16 196	97.44 200

DP-MVS		95.62 63	95.84 61	94.97 97	97.16 137	88.62 108	94.54 123	97.64 98	96.94 15	96.58 82	97.32 88	93.07 92	98.72 150	90.45 134	98.84 126	97.57 190

EG-PatchMatch MVS		94.54 106	94.67 108	94.14 132	97.87 98	86.50 151	92.00 203	96.74 172	88.16 188	96.93 68	97.61 64	93.04 93	97.90 229	91.60 110	98.12 199	98.03 146

Fast-Effi-MVS+		91.28 193	90.86 198	92.53 190	95.45 238	82.53 211	89.25 284	96.52 185	85.00 240	89.91 286	88.55 346	92.94 94	98.84 127	84.72 250	95.44 287	96.22 250

PC_three_1452									75.31 318	95.87 115	95.75 187	92.93 95	96.34 305	87.18 213	98.68 147	98.04 143

v7n		96.82 9	97.31 10	95.33 86	98.54 48	86.81 143	96.83 23	98.07 56	96.59 20	98.46 17	98.43 29	92.91 96	99.52 19	96.25 6	99.76 10	99.65 8

XVG-ACMP-BASELINE		95.68 62	95.34 80	96.69 41	98.40 61	93.04 41	94.54 123	98.05 59	90.45 141	96.31 91	96.76 124	92.91 96	98.72 150	91.19 117	99.42 50	98.32 123

testgi		90.38 213	91.34 189	87.50 316	97.49 123	71.54 344	89.43 276	95.16 235	88.38 184	94.54 170	94.68 232	92.88 98	93.09 346	71.60 349	97.85 217	97.88 164

MVS_111021_LR		93.66 129	93.28 144	94.80 103	96.25 192	90.95 69	90.21 255	95.43 229	87.91 190	93.74 193	94.40 240	92.88 98	96.38 301	90.39 136	98.28 183	97.07 215

CNVR-MVS		94.58 104	94.29 115	95.46 82	96.94 145	89.35 96	91.81 215	96.80 167	89.66 154	93.90 189	95.44 200	92.80 100	98.72 150	92.74 80	98.52 162	98.32 123

ZD-MVS					97.23 133	90.32 78		97.54 107	84.40 247	94.78 163	95.79 182	92.76 101	99.39 48	88.72 188	98.40 169

XXY-MVS		92.58 162	93.16 147	90.84 250	97.75 104	79.84 250	91.87 211	96.22 199	85.94 222	95.53 128	97.68 60	92.69 102	94.48 332	83.21 260	97.51 230	98.21 131

CDPH-MVS		92.67 160	91.83 177	95.18 92	96.94 145	88.46 114	90.70 239	97.07 146	77.38 304	92.34 245	95.08 216	92.67 103	98.88 119	85.74 234	98.57 157	98.20 132

Fast-Effi-MVS+-dtu		92.77 157	92.16 167	94.58 118	94.66 265	88.25 116	92.05 200	96.65 176	89.62 155	90.08 282	91.23 314	92.56 104	98.60 170	86.30 230	96.27 269	96.90 223

AllTest		94.88 94	94.51 111	96.00 56	98.02 89	92.17 50	95.26 93	98.43 14	90.48 139	95.04 153	96.74 127	92.54 105	97.86 237	85.11 243	98.98 109	97.98 152

TestCases				96.00 56	98.02 89	92.17 50		98.43 14	90.48 139	95.04 153	96.74 127	92.54 105	97.86 237	85.11 243	98.98 109	97.98 152

TinyColmap		92.00 178	92.76 153	89.71 279	95.62 233	77.02 296	90.72 238	96.17 202	87.70 198	95.26 142	96.29 157	92.54 105	96.45 298	81.77 274	98.77 138	95.66 275

EGC-MVSNET		80.97 331	75.73 342	96.67 42	98.85 24	94.55 15	96.83 23	96.60 178	2.44 377	5.32 378	98.25 33	92.24 108	98.02 220	91.85 102	99.21 86	97.45 198

ETV-MVS		92.99 148	92.74 154	93.72 147	95.86 218	86.30 160	92.33 190	97.84 83	91.70 112	92.81 224	86.17 360	92.22 109	99.19 79	88.03 200	97.73 220	95.66 275

CLD-MVS		91.82 179	91.41 187	93.04 166	96.37 177	83.65 198	86.82 323	97.29 130	84.65 246	92.27 247	89.67 335	92.20 110	97.85 239	83.95 255	99.47 41	97.62 187
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
segment_acmp												92.14 111

Vis-MVSNet		95.50 68	95.48 73	95.56 79	98.11 80	89.40 94	95.35 88	98.22 32	92.36 81	94.11 177	98.07 41	92.02 112	99.44 28	93.38 60	97.67 225	97.85 168
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ITE_SJBPF				95.95 59	97.34 130	93.36 40		96.55 184	91.93 94	94.82 161	95.39 205	91.99 113	97.08 279	85.53 236	97.96 211	97.41 201

CP-MVSNet		96.19 45	96.80 16	94.38 127	98.99 16	83.82 196	96.31 50	97.53 109	97.60 7	98.34 19	97.52 70	91.98 114	99.63 6	93.08 72	99.81 8	99.70 3

CSCG		94.69 100	94.75 102	94.52 119	97.55 120	87.87 123	95.01 104	97.57 105	92.68 73	96.20 101	93.44 272	91.92 115	98.78 141	89.11 178	99.24 81	96.92 222

TSAR-MVS + MP.		94.96 91	94.75 102	95.57 78	98.86 22	88.69 105	96.37 44	96.81 166	85.23 233	94.75 164	97.12 102	91.85 116	99.40 45	93.45 54	98.33 179	98.62 106
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Gipuma		95.31 81	95.80 64	93.81 146	97.99 94	90.91 70	96.42 42	97.95 75	96.69 17	91.78 255	98.85 12	91.77 117	95.49 319	91.72 106	99.08 98	95.02 290
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WR-MVS_H		96.60 25	97.05 13	95.24 90	99.02 12	86.44 155	96.78 27	98.08 53	97.42 9	98.48 16	97.86 55	91.76 118	99.63 6	94.23 29	99.84 3	99.66 6

AdaColmap		91.63 184	91.36 188	92.47 192	95.56 235	86.36 158	92.24 197	96.27 194	88.88 173	89.90 287	92.69 290	91.65 119	98.32 195	77.38 317	97.64 226	92.72 339

PHI-MVS		94.34 112	93.80 126	95.95 59	95.65 230	91.67 62	94.82 109	97.86 80	87.86 193	93.04 217	94.16 249	91.58 120	98.78 141	90.27 144	98.96 115	97.41 201

xiu_mvs_v1_base_debu		91.47 188	91.52 182	91.33 229	95.69 227	81.56 222	89.92 265	96.05 206	83.22 255	91.26 262	90.74 321	91.55 121	98.82 129	89.29 170	95.91 275	93.62 326

xiu_mvs_v1_base		91.47 188	91.52 182	91.33 229	95.69 227	81.56 222	89.92 265	96.05 206	83.22 255	91.26 262	90.74 321	91.55 121	98.82 129	89.29 170	95.91 275	93.62 326

xiu_mvs_v1_base_debi		91.47 188	91.52 182	91.33 229	95.69 227	81.56 222	89.92 265	96.05 206	83.22 255	91.26 262	90.74 321	91.55 121	98.82 129	89.29 170	95.91 275	93.62 326

tfpnnormal		94.27 114	94.87 98	92.48 191	97.71 108	80.88 234	94.55 122	95.41 230	93.70 58	96.67 78	97.72 59	91.40 124	98.18 208	87.45 208	99.18 90	98.36 121

3Dnovator+	92.74 2	95.86 56	95.77 65	96.13 53	96.81 155	90.79 73	96.30 54	97.82 85	96.13 26	94.74 165	97.23 93	91.33 125	99.16 81	93.25 65	98.30 182	98.46 116

TEST9					96.45 175	89.46 90	90.60 242	96.92 157	79.09 294	90.49 273	94.39 241	91.31 126	98.88 119

DeepC-MVS_fast	89.96 7	93.73 128	93.44 140	94.60 115	96.14 200	87.90 122	93.36 156	97.14 140	85.53 230	93.90 189	95.45 199	91.30 127	98.59 172	89.51 164	98.62 152	97.31 210
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EI-MVSNet-Vis-set		94.36 110	94.28 116	94.61 112	92.55 306	85.98 167	92.44 184	94.69 248	93.70 58	96.12 105	95.81 181	91.24 128	98.86 124	93.76 42	98.22 191	98.98 59

MCST-MVS		92.91 150	92.51 161	94.10 133	97.52 121	85.72 173	91.36 225	97.13 142	80.33 280	92.91 222	94.24 245	91.23 129	98.72 150	89.99 155	97.93 213	97.86 166

RPSCF		95.58 66	94.89 97	97.62 7	97.58 118	96.30 7	95.97 66	97.53 109	92.42 78	93.41 200	97.78 56	91.21 130	97.77 246	91.06 119	97.06 244	98.80 82

train_agg		92.71 159	91.83 177	95.35 84	96.45 175	89.46 90	90.60 242	96.92 157	79.37 289	90.49 273	94.39 241	91.20 131	98.88 119	88.66 189	98.43 168	97.72 181

test_8					96.37 177	89.14 97	90.51 245	96.89 160	79.37 289	90.42 275	94.36 243	91.20 131	98.82 129

EI-MVSNet-UG-set		94.35 111	94.27 118	94.59 116	92.46 307	85.87 170	92.42 186	94.69 248	93.67 61	96.13 104	95.84 180	91.20 131	98.86 124	93.78 39	98.23 189	99.03 51

EIA-MVS		92.35 170	92.03 170	93.30 162	95.81 221	83.97 194	92.80 168	98.17 41	87.71 197	89.79 290	87.56 350	91.17 134	99.18 80	87.97 201	97.27 238	96.77 229

dcpmvs_2		93.96 124	95.01 94	90.82 251	97.60 116	74.04 329	93.68 149	98.85 7	89.80 152	97.82 28	97.01 110	91.14 135	99.21 76	90.56 132	98.59 155	99.19 36

xiu_mvs_v2_base		89.00 248	89.19 231	88.46 304	94.86 253	74.63 321	86.97 317	95.60 218	80.88 276	87.83 320	88.62 345	91.04 136	98.81 134	82.51 268	94.38 312	91.93 345

HPM-MVS++		95.02 88	94.39 112	96.91 37	97.88 97	93.58 37	94.09 136	96.99 152	91.05 126	92.40 240	95.22 210	91.03 137	99.25 73	92.11 92	98.69 146	97.90 161

TAPA-MVS	88.58 10	92.49 165	91.75 179	94.73 106	96.50 172	89.69 86	92.91 165	97.68 96	78.02 302	92.79 225	94.10 250	90.85 138	97.96 226	84.76 249	98.16 196	96.54 234
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pcd_1.5k_mvsjas		7.56 347	10.09 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	90.77 139	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		96.01 50	96.04 51	95.89 67	98.82 26	88.51 112	95.57 84	97.88 79	88.72 175	98.81 6	98.86 10	90.77 139	99.60 9	95.43 15	99.53 36	99.57 14

PS-MVSNAJ		88.86 253	88.99 237	88.48 303	94.88 251	74.71 319	86.69 326	95.60 218	80.88 276	87.83 320	87.37 353	90.77 139	98.82 129	82.52 267	94.37 313	91.93 345

MVS_Test		92.57 164	93.29 142	90.40 262	93.53 290	75.85 313	92.52 179	96.96 153	88.73 174	92.35 243	96.70 131	90.77 139	98.37 193	92.53 86	95.49 285	96.99 220

MIMVSNet1		95.52 67	95.45 74	95.72 73	99.14 5	89.02 99	96.23 57	96.87 162	93.73 57	97.87 27	98.49 26	90.73 143	99.05 97	86.43 228	99.60 26	99.10 47

ab-mvs		92.40 168	92.62 159	91.74 213	97.02 141	81.65 221	95.84 71	95.50 228	86.95 211	92.95 221	97.56 67	90.70 144	97.50 260	79.63 298	97.43 234	96.06 256

Test By Simon												90.61 145

3Dnovator	92.54 3	94.80 97	94.90 96	94.47 123	95.47 237	87.06 136	96.63 31	97.28 132	91.82 104	94.34 176	97.41 76	90.60 146	98.65 165	92.47 87	98.11 200	97.70 182

NCCC		94.08 122	93.54 138	95.70 75	96.49 173	89.90 83	92.39 188	96.91 159	90.64 136	92.33 246	94.60 235	90.58 147	98.96 110	90.21 148	97.70 223	98.23 129

UniMVSNet_NR-MVSNet		95.35 76	95.21 86	95.76 71	97.69 111	88.59 109	92.26 195	97.84 83	94.91 38	96.80 73	95.78 185	90.42 148	99.41 38	91.60 110	99.58 32	99.29 29

test_prior2							90.21 255		89.33 162	90.77 269	94.81 225	90.41 149		88.21 192	98.55 158

KD-MVS_self_test		94.10 121	94.73 104	92.19 198	97.66 114	79.49 260	94.86 108	97.12 143	89.59 157	96.87 69	97.65 62	90.40 150	98.34 194	89.08 179	99.35 59	98.75 87

MSLP-MVS++		93.25 141	93.88 124	91.37 227	96.34 183	82.81 209	93.11 159	97.74 93	89.37 161	94.08 179	95.29 209	90.40 150	96.35 303	90.35 139	98.25 187	94.96 291

UniMVSNet (Re)		95.32 78	95.15 89	95.80 70	97.79 102	88.91 102	92.91 165	98.07 56	93.46 62	96.31 91	95.97 175	90.14 152	99.34 61	92.11 92	99.64 24	99.16 38

Effi-MVS+-dtu		93.90 126	92.60 160	97.77 3	94.74 260	96.67 5	94.00 138	95.41 230	89.94 148	91.93 254	92.13 302	90.12 153	98.97 109	87.68 206	97.48 232	97.67 185

FMVSNet1		94.84 95	95.13 90	93.97 137	97.60 116	84.29 186	95.99 63	96.56 181	92.38 79	97.03 63	98.53 23	90.12 153	98.98 105	88.78 186	99.16 93	98.65 98

DU-MVS		95.28 82	95.12 91	95.75 72	97.75 104	88.59 109	92.58 177	97.81 86	93.99 50	96.80 73	95.90 176	90.10 155	99.41 38	91.60 110	99.58 32	99.26 30

NR-MVSNet		95.28 82	95.28 84	95.26 89	97.75 104	87.21 133	95.08 100	97.37 118	93.92 55	97.65 33	95.90 176	90.10 155	99.33 66	90.11 151	99.66 21	99.26 30

Baseline_NR-MVSNet		94.47 108	95.09 93	92.60 187	98.50 57	80.82 235	92.08 199	96.68 174	93.82 56	96.29 93	98.56 21	90.10 155	97.75 249	90.10 153	99.66 21	99.24 32

API-MVS		91.52 187	91.61 180	91.26 233	94.16 275	86.26 162	94.66 114	94.82 243	91.17 124	92.13 250	91.08 317	90.03 158	97.06 280	79.09 305	97.35 237	90.45 354

patch_mono-2		92.46 166	92.72 157	91.71 215	96.65 159	78.91 271	88.85 290	97.17 138	83.89 251	92.45 237	96.76 124	89.86 159	97.09 278	90.24 146	98.59 155	99.12 43

test12				94.43 125	95.95 214	86.75 145		96.24 196		89.76 291		89.79 160	98.79 138		97.95 212	97.75 180

旧先验1					96.20 195	84.17 191		94.82 243			95.57 195	89.57 161			97.89 215	96.32 246

DELS-MVS		92.05 177	92.16 167	91.72 214	94.44 270	80.13 241	87.62 304	97.25 133	87.34 204	92.22 248	93.18 279	89.54 162	98.73 149	89.67 162	98.20 194	96.30 247
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
VPNet		93.08 145	93.76 128	91.03 241	98.60 39	75.83 315	91.51 220	95.62 217	91.84 101	95.74 120	97.10 103	89.31 163	98.32 195	85.07 245	99.06 99	98.93 64

QAPM		92.88 152	92.77 152	93.22 164	95.82 219	83.31 200	96.45 39	97.35 124	83.91 250	93.75 191	96.77 122	89.25 164	98.88 119	84.56 251	97.02 246	97.49 196

MSDG		90.82 197	90.67 204	91.26 233	94.16 275	83.08 207	86.63 328	96.19 200	90.60 138	91.94 253	91.89 305	89.16 165	95.75 314	80.96 284	94.51 310	94.95 292

CPTT-MVS		94.74 98	94.12 121	96.60 43	98.15 78	93.01 42	95.84 71	97.66 97	89.21 166	93.28 206	95.46 198	88.89 166	98.98 105	89.80 158	98.82 132	97.80 174

DP-MVS Recon		92.31 171	91.88 175	93.60 150	97.18 136	86.87 142	91.10 230	97.37 118	84.92 242	92.08 251	94.08 251	88.59 167	98.20 205	83.50 257	98.14 198	95.73 270

FC-MVSNet-test		95.32 78	95.88 58	93.62 149	98.49 58	81.77 219	95.90 69	98.32 20	93.93 53	97.53 40	97.56 67	88.48 168	99.40 45	92.91 77	99.83 5	99.68 4

OpenMVS	89.45 8	92.27 173	92.13 169	92.68 182	94.53 269	84.10 192	95.70 76	97.03 148	82.44 268	91.14 266	96.42 144	88.47 169	98.38 190	85.95 233	97.47 233	95.55 279

F-COLMAP		92.28 172	91.06 195	95.95 59	97.52 121	91.90 56	93.53 151	97.18 137	83.98 249	88.70 308	94.04 252	88.41 170	98.55 177	80.17 291	95.99 274	97.39 205

ambc				92.98 168	96.88 149	83.01 208	95.92 68	96.38 191		96.41 86	97.48 74	88.26 171	97.80 242	89.96 156	98.93 118	98.12 139

v10		94.68 101	95.27 85	92.90 175	96.57 165	80.15 239	94.65 115	97.57 105	90.68 135	97.43 46	98.00 45	88.18 172	99.15 82	94.84 19	99.55 35	99.41 20

v8		94.65 102	95.29 83	92.74 180	96.65 159	79.77 254	94.59 116	97.17 138	91.86 97	97.47 45	97.93 48	88.16 173	99.08 92	94.32 26	99.47 41	99.38 22

TSAR-MVS + GP.		93.07 147	92.41 164	95.06 95	95.82 219	90.87 72	90.97 232	92.61 290	88.04 189	94.61 168	93.79 263	88.08 174	97.81 241	89.41 166	98.39 172	96.50 239

OurMVSNet-221017-0		96.80 12	96.75 17	96.96 35	99.03 11	91.85 57	97.98 7	98.01 67	94.15 48	98.93 3	99.07 5	88.07 175	99.57 14	95.86 9	99.69 14	99.46 18

diffmvs		91.74 181	91.93 174	91.15 239	93.06 298	78.17 281	88.77 293	97.51 112	86.28 216	92.42 239	93.96 257	88.04 176	97.46 263	90.69 130	96.67 261	97.82 172
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
原ACMM1				92.87 176	96.91 148	84.22 189		97.01 149	76.84 310	89.64 293	94.46 239	88.00 177	98.70 157	81.53 277	98.01 209	95.70 273

VDD-MVS		94.37 109	94.37 113	94.40 126	97.49 123	86.07 166	93.97 140	93.28 275	94.49 43	96.24 97	97.78 56	87.99 178	98.79 138	88.92 182	99.14 95	98.34 122

XVG-OURS		94.72 99	94.12 121	96.50 47	98.00 91	94.23 18	91.48 221	98.17 41	90.72 133	95.30 139	96.47 141	87.94 179	96.98 282	91.41 115	97.61 228	98.30 126

CANet		92.38 169	91.99 172	93.52 157	93.82 286	83.46 199	91.14 228	97.00 150	89.81 151	86.47 331	94.04 252	87.90 180	99.21 76	89.50 165	98.27 184	97.90 161

BH-untuned		90.68 202	90.90 196	90.05 273	95.98 212	79.57 258	90.04 261	94.94 240	87.91 190	94.07 180	93.00 281	87.76 181	97.78 245	79.19 304	95.17 295	92.80 338

FIs		94.90 93	95.35 79	93.55 152	98.28 69	81.76 220	95.33 90	98.14 45	93.05 71	97.07 59	97.18 98	87.65 182	99.29 68	91.72 106	99.69 14	99.61 11

v1144		93.50 131	93.81 125	92.57 188	96.28 188	79.61 257	91.86 213	96.96 153	86.95 211	95.91 112	96.32 155	87.65 182	98.96 110	93.51 48	98.88 121	99.13 41

mvs_anonymous		90.37 214	91.30 190	87.58 315	92.17 313	68.00 358	89.84 268	94.73 247	83.82 252	93.22 211	97.40 77	87.54 184	97.40 268	87.94 202	95.05 297	97.34 208

PCF-MVS	84.52 17	89.12 242	87.71 265	93.34 160	96.06 205	85.84 171	86.58 331	97.31 127	68.46 355	93.61 196	93.89 260	87.51 185	98.52 179	67.85 360	98.11 200	95.66 275
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		92.67 160	92.96 148	91.79 211	96.27 189	80.15 239	91.95 204	94.98 238	92.19 88	94.52 171	96.07 170	87.43 186	97.39 269	84.83 247	98.38 173	97.83 170

v148		92.87 153	93.29 142	91.62 219	96.25 192	77.72 288	91.28 226	95.05 236	89.69 153	95.93 111	96.04 171	87.34 187	98.38 190	90.05 154	97.99 210	98.78 84

V42		93.43 134	93.58 135	92.97 169	95.34 243	81.22 229	92.67 173	96.49 186	87.25 205	96.20 101	96.37 152	87.32 188	98.85 126	92.39 89	98.21 192	98.85 77

v1192		93.49 132	93.78 127	92.62 186	96.16 198	79.62 256	91.83 214	97.22 136	86.07 220	96.10 106	96.38 151	87.22 189	99.02 102	94.14 31	98.88 121	99.22 33

WR-MVS		93.49 132	93.72 129	92.80 179	97.57 119	80.03 245	90.14 258	95.68 216	93.70 58	96.62 80	95.39 205	87.21 190	99.04 100	87.50 207	99.64 24	99.33 26

IterMVS-LS		93.78 127	94.28 116	92.27 195	96.27 189	79.21 267	91.87 211	96.78 168	91.77 107	96.57 83	97.07 104	87.15 191	98.74 148	91.99 97	99.03 108	98.86 74
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		92.99 148	93.26 146	92.19 198	92.12 314	79.21 267	92.32 191	94.67 250	91.77 107	95.24 145	95.85 178	87.14 192	98.49 181	91.99 97	98.26 185	98.86 74

v144192		93.20 144	93.54 138	92.16 202	96.05 206	78.26 280	91.95 204	97.14 140	84.98 241	95.96 108	96.11 168	87.08 193	99.04 100	93.79 38	98.84 126	99.17 37

114514_t		90.51 206	89.80 224	92.63 185	98.00 91	82.24 215	93.40 155	97.29 130	65.84 362	89.40 295	94.80 227	86.99 194	98.75 145	83.88 256	98.61 153	96.89 224

新几何1				93.17 165	97.16 137	87.29 130		94.43 253	67.95 356	91.29 261	94.94 221	86.97 195	98.23 203	81.06 283	97.75 219	93.98 316

HQP_MVS		94.26 116	93.93 123	95.23 91	97.71 108	88.12 118	94.56 120	97.81 86	91.74 109	93.31 203	95.59 191	86.93 196	98.95 112	89.26 173	98.51 164	98.60 107

plane_prior6					97.21 135	88.23 117						86.93 196

UGNet		93.08 145	92.50 162	94.79 104	93.87 284	87.99 121	95.07 101	94.26 258	90.64 136	87.33 327	97.67 61	86.89 198	98.49 181	88.10 197	98.71 143	97.91 160
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
LF4IMVS		92.72 158	92.02 171	94.84 102	95.65 230	91.99 54	92.92 164	96.60 178	85.08 239	92.44 238	93.62 267	86.80 199	96.35 303	86.81 217	98.25 187	96.18 252

v1921920		93.26 139	93.61 134	92.19 198	96.04 210	78.31 279	91.88 210	97.24 134	85.17 235	96.19 103	96.19 164	86.76 200	99.05 97	94.18 30	98.84 126	99.22 33

v1240		93.29 137	93.71 130	92.06 205	96.01 211	77.89 285	91.81 215	97.37 118	85.12 237	96.69 77	96.40 146	86.67 201	99.07 96	94.51 22	98.76 139	99.22 33

MAR-MVS		90.32 217	88.87 241	94.66 110	94.82 254	91.85 57	94.22 131	94.75 246	80.91 275	87.52 325	88.07 349	86.63 202	97.87 236	76.67 321	96.21 270	94.25 310
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
MSP-MVS		95.34 77	94.63 109	97.48 14	98.67 33	94.05 23	96.41 43	98.18 37	91.26 120	95.12 148	95.15 211	86.60 203	99.50 21	93.43 58	96.81 256	98.89 71
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
BH-RMVSNet		90.47 208	90.44 209	90.56 258	95.21 246	78.65 277	89.15 285	93.94 266	88.21 186	92.74 227	94.22 246	86.38 204	97.88 233	78.67 307	95.39 289	95.14 287

CNLPA		91.72 182	91.20 191	93.26 163	96.17 197	91.02 67	91.14 228	95.55 225	90.16 146	90.87 268	93.56 270	86.31 205	94.40 335	79.92 297	97.12 242	94.37 307

PVSNet_BlendedMVS		90.35 215	89.96 220	91.54 222	94.81 255	78.80 275	90.14 258	96.93 155	79.43 288	88.68 309	95.06 217	86.27 206	98.15 211	80.27 287	98.04 206	97.68 184

PVSNet_Blended		88.74 256	88.16 259	90.46 261	94.81 255	78.80 275	86.64 327	96.93 155	74.67 319	88.68 309	89.18 342	86.27 206	98.15 211	80.27 287	96.00 273	94.44 306

PAPR		87.65 274	86.77 284	90.27 265	92.85 302	77.38 292	88.56 298	96.23 197	76.82 311	84.98 339	89.75 334	86.08 208	97.16 276	72.33 344	93.35 327	96.26 249

v2v482		93.29 137	93.63 133	92.29 194	96.35 182	78.82 273	91.77 217	96.28 193	88.45 181	95.70 124	96.26 161	86.02 209	98.90 116	93.02 73	98.81 134	99.14 40

test20.03		90.80 198	90.85 199	90.63 256	95.63 232	79.24 265	89.81 269	92.87 281	89.90 149	94.39 173	96.40 146	85.77 210	95.27 327	73.86 336	99.05 102	97.39 205

PLC	85.34 15	90.40 210	88.92 238	94.85 101	96.53 171	90.02 81	91.58 219	96.48 187	80.16 281	86.14 333	92.18 300	85.73 211	98.25 202	76.87 320	94.61 309	96.30 247
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS		84.98 305	84.30 305	87.01 319	91.03 331	77.69 289	91.94 206	94.16 259	59.36 370	84.23 345	87.50 352	85.66 212	96.80 289	71.79 346	93.05 334	86.54 363

testdata				91.03 241	96.87 150	82.01 216		94.28 257	71.55 337	92.46 236	95.42 201	85.65 213	97.38 271	82.64 265	97.27 238	93.70 323

PM-MVS		93.33 136	92.67 158	95.33 86	96.58 164	94.06 21	92.26 195	92.18 296	85.92 223	96.22 99	96.61 136	85.64 214	95.99 312	90.35 139	98.23 189	95.93 261

MDA-MVSNet-bldmvs		91.04 194	90.88 197	91.55 221	94.68 264	80.16 238	85.49 336	92.14 299	90.41 143	94.93 157	95.79 182	85.10 215	96.93 285	85.15 240	94.19 319	97.57 190

PAPM_NR		91.03 195	90.81 200	91.68 217	96.73 157	81.10 231	93.72 147	96.35 192	88.19 187	88.77 306	92.12 303	85.09 216	97.25 273	82.40 269	93.90 320	96.68 232

HQP2-MVS												84.76 217

HQP-MVS		92.09 176	91.49 185	93.88 142	96.36 179	84.89 182	91.37 222	97.31 127	87.16 206	88.81 302	93.40 273	84.76 217	98.60 170	86.55 225	97.73 220	98.14 137

test222					96.95 144	85.27 179	88.83 291	93.61 267	65.09 364	90.74 270	94.85 224	84.62 219			97.36 236	93.91 317

VDDNet		94.03 123	94.27 118	93.31 161	98.87 21	82.36 214	95.51 86	91.78 305	97.19 12	96.32 90	98.60 19	84.24 220	98.75 145	87.09 215	98.83 131	98.81 80

PVSNet_Blended_VisFu		91.63 184	91.20 191	92.94 173	97.73 107	83.95 195	92.14 198	97.46 113	78.85 298	92.35 243	94.98 219	84.16 221	99.08 92	86.36 229	96.77 258	95.79 268

CL-MVSNet_self_test		90.04 228	89.90 222	90.47 259	95.24 245	77.81 286	86.60 330	92.62 289	85.64 228	93.25 210	93.92 258	83.84 222	96.06 310	79.93 295	98.03 207	97.53 194

mvsany_test3		89.11 243	88.21 257	91.83 209	91.30 329	90.25 79	88.09 301	78.76 371	76.37 312	96.43 85	98.39 30	83.79 223	90.43 359	86.57 223	94.20 317	94.80 296

mvsmamba		95.61 64	95.40 78	96.22 51	98.44 60	89.86 84	97.14 17	97.45 115	91.25 122	97.49 42	98.14 35	83.49 224	99.45 26	95.52 11	99.66 21	99.36 24

BH-w/o		87.21 285	87.02 280	87.79 314	94.77 258	77.27 294	87.90 302	93.21 278	81.74 273	89.99 285	88.39 348	83.47 225	96.93 285	71.29 350	92.43 341	89.15 355

PatchMatch-RL		89.18 240	88.02 262	92.64 183	95.90 217	92.87 45	88.67 297	91.06 310	80.34 279	90.03 284	91.67 309	83.34 226	94.42 334	76.35 324	94.84 303	90.64 353

DPM-MVS		89.35 238	88.40 247	92.18 201	96.13 202	84.20 190	86.96 318	96.15 203	75.40 317	87.36 326	91.55 312	83.30 227	98.01 221	82.17 272	96.62 262	94.32 309

OpenMVS_ROB	85.12 16	89.52 236	89.05 234	90.92 246	94.58 268	81.21 230	91.10 230	93.41 274	77.03 308	93.41 200	93.99 256	83.23 228	97.80 242	79.93 295	94.80 304	93.74 322

new-patchmatchnet		88.97 249	90.79 201	83.50 344	94.28 274	55.83 378	85.34 338	93.56 270	86.18 218	95.47 129	95.73 188	83.10 229	96.51 296	85.40 237	98.06 204	98.16 135

mvsany_test1		83.91 311	82.93 315	86.84 322	86.18 370	85.93 168	81.11 360	75.03 375	70.80 345	88.57 311	94.63 233	83.08 230	87.38 367	80.39 285	86.57 362	87.21 362

1314		86.46 295	86.33 292	86.87 321	91.65 324	74.54 322	91.94 206	94.10 260	74.28 322	84.78 341	87.33 354	83.03 231	95.00 329	78.72 306	91.16 350	91.06 351

IS-MVSNet		94.49 107	94.35 114	94.92 98	98.25 73	86.46 154	97.13 18	94.31 255	96.24 25	96.28 95	96.36 153	82.88 232	99.35 58	88.19 194	99.52 39	98.96 61

test_fmvs3		92.42 167	92.40 165	92.46 193	93.80 287	87.28 131	93.86 143	97.05 147	76.86 309	96.25 96	98.66 18	82.87 233	91.26 354	95.44 14	96.83 255	98.82 78

MG-MVS		89.54 235	89.80 224	88.76 295	94.88 251	72.47 341	89.60 272	92.44 293	85.82 224	89.48 294	95.98 174	82.85 234	97.74 250	81.87 273	95.27 293	96.08 255

TR-MVS		87.70 271	87.17 275	89.27 287	94.11 277	79.26 264	88.69 295	91.86 304	81.94 272	90.69 271	89.79 332	82.82 235	97.42 266	72.65 343	91.98 345	91.14 350

c3_l		91.32 192	91.42 186	91.00 244	92.29 309	76.79 303	87.52 310	96.42 189	85.76 226	94.72 167	93.89 260	82.73 236	98.16 210	90.93 124	98.55 158	98.04 143

YYNet1		88.17 264	88.24 254	87.93 311	92.21 311	73.62 331	80.75 361	88.77 321	82.51 267	94.99 155	95.11 214	82.70 237	93.70 341	83.33 258	93.83 321	96.48 240

MDA-MVSNet_test_wron		88.16 265	88.23 255	87.93 311	92.22 310	73.71 330	80.71 362	88.84 320	82.52 266	94.88 160	95.14 212	82.70 237	93.61 342	83.28 259	93.80 322	96.46 241

pmmvs-eth3d		91.54 186	90.73 203	93.99 135	95.76 224	87.86 124	90.83 235	93.98 265	78.23 301	94.02 184	96.22 163	82.62 239	96.83 288	86.57 223	98.33 179	97.29 211

MVS_0304		90.96 196	90.15 217	93.37 159	93.17 295	87.06 136	93.62 150	92.43 294	89.60 156	82.25 356	95.50 196	82.56 240	97.83 240	84.41 253	97.83 218	95.22 283

Anonymous20231206		88.77 255	88.29 251	90.20 269	96.31 186	78.81 274	89.56 274	93.49 272	74.26 323	92.38 241	95.58 194	82.21 241	95.43 322	72.07 345	98.75 141	96.34 245

miper_ehance_all_eth		90.48 207	90.42 210	90.69 254	91.62 325	76.57 306	86.83 322	96.18 201	83.38 253	94.06 181	92.66 292	82.20 242	98.04 216	89.79 159	97.02 246	97.45 198

USDC		89.02 245	89.08 233	88.84 294	95.07 248	74.50 324	88.97 287	96.39 190	73.21 329	93.27 207	96.28 159	82.16 243	96.39 300	77.55 314	98.80 135	95.62 278

EPP-MVSNet		93.91 125	93.68 132	94.59 116	98.08 82	85.55 175	97.44 12	94.03 261	94.22 47	94.94 156	96.19 164	82.07 244	99.57 14	87.28 212	98.89 119	98.65 98

UnsupCasMVSNet_eth		90.33 216	90.34 212	90.28 264	94.64 267	80.24 237	89.69 271	95.88 210	85.77 225	93.94 188	95.69 189	81.99 245	92.98 347	84.21 254	91.30 348	97.62 187

alignmvs		93.26 139	92.85 151	94.50 120	95.70 226	87.45 128	93.45 154	95.76 213	91.58 114	95.25 144	92.42 298	81.96 246	98.72 150	91.61 109	97.87 216	97.33 209

TAMVS		90.16 221	89.05 234	93.49 158	96.49 173	86.37 157	90.34 252	92.55 291	80.84 278	92.99 218	94.57 237	81.94 247	98.20 205	73.51 337	98.21 192	95.90 264

Anonymous202405211		92.58 162	92.50 162	92.83 178	96.55 167	83.22 203	92.43 185	91.64 307	94.10 49	95.59 126	96.64 134	81.88 248	97.50 260	85.12 242	98.52 162	97.77 177

SixPastTwentyTwo		94.91 92	95.21 86	93.98 136	98.52 50	83.19 204	95.93 67	94.84 242	94.86 39	98.49 15	98.74 16	81.45 249	99.60 9	94.69 20	99.39 56	99.15 39

cascas		87.02 291	86.28 293	89.25 288	91.56 326	76.45 307	84.33 348	96.78 168	71.01 342	86.89 330	85.91 361	81.35 250	96.94 283	83.09 261	95.60 282	94.35 308

GBi-Net		93.21 142	92.96 148	93.97 137	95.40 239	84.29 186	95.99 63	96.56 181	88.63 177	95.10 149	98.53 23	81.31 251	98.98 105	86.74 218	98.38 173	98.65 98

test1		93.21 142	92.96 148	93.97 137	95.40 239	84.29 186	95.99 63	96.56 181	88.63 177	95.10 149	98.53 23	81.31 251	98.98 105	86.74 218	98.38 173	98.65 98

FMVSNet2		92.78 156	92.73 156	92.95 171	95.40 239	81.98 217	94.18 132	95.53 227	88.63 177	96.05 107	97.37 79	81.31 251	98.81 134	87.38 211	98.67 149	98.06 140

MVE	59.87 23	73.86 341	72.65 344	77.47 354	87.00 368	74.35 325	61.37 371	60.93 379	67.27 357	69.69 374	86.49 358	81.24 254	72.33 375	56.45 372	83.45 367	85.74 364
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
RRT_MVS		95.41 74	95.20 88	96.05 55	98.86 22	88.92 101	97.49 11	94.48 252	93.12 68	97.94 26	98.54 22	81.19 255	99.63 6	95.48 12	99.69 14	99.60 12

MVP-Stereo		90.07 226	88.92 238	93.54 154	96.31 186	86.49 152	90.93 233	95.59 222	79.80 282	91.48 258	95.59 191	80.79 256	97.39 269	78.57 308	91.19 349	96.76 230
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UnsupCasMVSNet_bld		88.50 260	88.03 261	89.90 275	95.52 236	78.88 272	87.39 311	94.02 263	79.32 292	93.06 215	94.02 254	80.72 257	94.27 337	75.16 330	93.08 333	96.54 234

MS-PatchMatch		88.05 266	87.75 264	88.95 291	93.28 292	77.93 283	87.88 303	92.49 292	75.42 316	92.57 233	93.59 269	80.44 258	94.24 339	81.28 279	92.75 336	94.69 302

Anonymous20240521		92.86 154	93.57 136	90.74 253	96.57 165	75.50 317	94.15 133	95.60 218	89.38 160	95.90 113	97.90 54	80.39 259	97.96 226	92.60 85	99.68 18	98.75 87

CANet_DTU		89.85 231	89.17 232	91.87 208	92.20 312	80.02 246	90.79 236	95.87 211	86.02 221	82.53 355	91.77 307	80.01 260	98.57 174	85.66 235	97.70 223	97.01 219

PMMVS		83.00 316	81.11 324	88.66 298	83.81 377	86.44 155	82.24 357	85.65 345	61.75 369	82.07 358	85.64 362	79.75 261	91.59 353	75.99 326	93.09 332	87.94 361

ppachtmachnet_test		88.61 259	88.64 243	88.50 302	91.76 322	70.99 348	84.59 345	92.98 279	79.30 293	92.38 241	93.53 271	79.57 262	97.45 264	86.50 227	97.17 241	97.07 215

eth_miper_zixun_eth		90.72 200	90.61 205	91.05 240	92.04 317	76.84 302	86.91 319	96.67 175	85.21 234	94.41 172	93.92 258	79.53 263	98.26 201	89.76 160	97.02 246	98.06 140

test_vis1_rt		85.58 300	84.58 302	88.60 299	87.97 360	86.76 144	85.45 337	93.59 268	66.43 359	87.64 322	89.20 341	79.33 264	85.38 370	81.59 276	89.98 355	93.66 324

N_pmnet		88.90 252	87.25 273	93.83 145	94.40 272	93.81 35	84.73 342	87.09 334	79.36 291	93.26 208	92.43 297	79.29 265	91.68 352	77.50 316	97.22 240	96.00 258

miper_enhance_ethall		88.42 261	87.87 263	90.07 271	88.67 358	75.52 316	85.10 339	95.59 222	75.68 313	92.49 234	89.45 338	78.96 266	97.88 233	87.86 204	97.02 246	96.81 227

EPNet		89.80 233	88.25 253	94.45 124	83.91 376	86.18 163	93.87 142	87.07 335	91.16 125	80.64 364	94.72 230	78.83 267	98.89 118	85.17 238	98.89 119	98.28 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		87.23 284	86.82 282	88.46 304	93.96 281	77.94 282	86.84 321	92.78 285	77.59 303	87.61 324	91.83 306	78.75 268	91.92 351	77.84 311	94.20 317	95.52 280

bld_raw_dy_0_64		94.27 114	94.15 120	94.65 111	98.55 45	86.28 161	95.80 73	95.55 225	88.41 183	97.09 58	98.08 40	78.69 269	98.87 123	95.63 10	99.53 36	98.81 80

IterMVS-SCA-FT		91.65 183	91.55 181	91.94 207	93.89 283	79.22 266	87.56 307	93.51 271	91.53 116	95.37 135	96.62 135	78.65 270	98.90 116	91.89 101	94.95 299	97.70 182

SCA		87.43 280	87.21 274	88.10 309	92.01 318	71.98 343	89.43 276	88.11 329	82.26 270	88.71 307	92.83 285	78.65 270	97.59 256	79.61 299	93.30 328	94.75 299

our_test_3		87.55 277	87.59 267	87.44 317	91.76 322	70.48 349	83.83 351	90.55 316	79.79 283	92.06 252	92.17 301	78.63 272	95.63 315	84.77 248	94.73 305	96.22 250

jason		89.17 241	88.32 249	91.70 216	95.73 225	80.07 242	88.10 300	93.22 276	71.98 336	90.09 281	92.79 287	78.53 273	98.56 175	87.43 209	97.06 244	96.46 241
jason: jason.
IterMVS		90.18 220	90.16 214	90.21 268	93.15 296	75.98 312	87.56 307	92.97 280	86.43 215	94.09 178	96.40 146	78.32 274	97.43 265	87.87 203	94.69 307	97.23 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		87.19 287	85.92 296	91.00 244	97.13 139	79.41 261	84.51 346	95.60 218	64.14 365	90.07 283	94.81 225	78.26 275	97.14 277	73.34 338	95.38 290	96.46 241

WTY-MVS		86.93 292	86.50 291	88.24 307	94.96 249	74.64 320	87.19 314	92.07 301	78.29 300	88.32 314	91.59 311	78.06 276	94.27 337	74.88 331	93.15 331	95.80 267

pmmvs4		88.95 250	87.70 266	92.70 181	94.30 273	85.60 174	87.22 313	92.16 298	74.62 320	89.75 292	94.19 247	77.97 277	96.41 299	82.71 264	96.36 268	96.09 254

DSMNet-mixed		82.21 321	81.56 320	84.16 341	89.57 350	70.00 354	90.65 241	77.66 374	54.99 373	83.30 351	97.57 66	77.89 278	90.50 358	66.86 363	95.54 284	91.97 344

FA-MVS(test-final)		91.81 180	91.85 176	91.68 217	94.95 250	79.99 247	96.00 62	93.44 273	87.80 194	94.02 184	97.29 89	77.60 279	98.45 187	88.04 199	97.49 231	96.61 233

lessismore_v0				93.87 143	98.05 85	83.77 197		80.32 368		97.13 57	97.91 52	77.49 280	99.11 91	92.62 84	98.08 203	98.74 90

HY-MVS	82.50 18	86.81 293	85.93 295	89.47 281	93.63 288	77.93 283	94.02 137	91.58 308	75.68 313	83.64 348	93.64 265	77.40 281	97.42 266	71.70 348	92.07 344	93.05 335

1112_ss		88.42 261	87.41 269	91.45 225	96.69 158	80.99 232	89.72 270	96.72 173	73.37 327	87.00 329	90.69 324	77.38 282	98.20 205	81.38 278	93.72 323	95.15 286

DIV-MVS_self_test		90.65 203	90.56 207	90.91 248	91.85 320	76.99 298	86.75 324	95.36 233	85.52 232	94.06 181	94.89 222	77.37 283	97.99 224	90.28 143	98.97 113	97.76 178

cl____		90.65 203	90.56 207	90.91 248	91.85 320	76.98 299	86.75 324	95.36 233	85.53 230	94.06 181	94.89 222	77.36 284	97.98 225	90.27 144	98.98 109	97.76 178

CDS-MVSNet		89.55 234	88.22 256	93.53 155	95.37 242	86.49 152	89.26 282	93.59 268	79.76 284	91.15 265	92.31 299	77.12 285	98.38 190	77.51 315	97.92 214	95.71 271
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_vis3_rt		90.40 210	90.03 219	91.52 223	92.58 304	88.95 100	90.38 250	97.72 95	73.30 328	97.79 29	97.51 72	77.05 286	87.10 368	89.03 180	94.89 300	98.50 112

MVSFormer		92.18 175	92.23 166	92.04 206	94.74 260	80.06 243	97.15 15	97.37 118	88.98 169	88.83 300	92.79 287	77.02 287	99.60 9	96.41 4	96.75 259	96.46 241

lupinMVS		88.34 263	87.31 270	91.45 225	94.74 260	80.06 243	87.23 312	92.27 295	71.10 341	88.83 300	91.15 315	77.02 287	98.53 178	86.67 221	96.75 259	95.76 269

PMMVS2		81.31 327	83.44 310	74.92 355	90.52 338	46.49 380	69.19 369	85.23 353	84.30 248	87.95 319	94.71 231	76.95 289	84.36 372	64.07 366	98.09 202	93.89 318

h-mvs33		92.89 151	91.99 172	95.58 77	96.97 143	90.55 76	93.94 141	94.01 264	89.23 163	93.95 186	96.19 164	76.88 290	99.14 84	91.02 120	95.71 280	97.04 218

hse-mvs2		92.24 174	91.20 191	95.38 83	96.16 198	90.65 75	92.52 179	92.01 303	89.23 163	93.95 186	92.99 282	76.88 290	98.69 159	91.02 120	96.03 272	96.81 227

pmmvs5		87.87 268	87.14 276	90.07 271	93.26 294	76.97 300	88.89 289	92.18 296	73.71 326	88.36 313	93.89 260	76.86 292	96.73 291	80.32 286	96.81 256	96.51 236

test_vis1_n_1920		89.45 237	89.85 223	88.28 306	93.59 289	76.71 304	90.67 240	97.78 91	79.67 286	90.30 279	96.11 168	76.62 293	92.17 350	90.31 141	93.57 325	95.96 259

K. test v3		93.37 135	93.27 145	93.66 148	98.05 85	82.62 210	94.35 126	86.62 337	96.05 29	97.51 41	98.85 12	76.59 294	99.65 3	93.21 66	98.20 194	98.73 91

miper_lstm_enhance		89.90 230	89.80 224	90.19 270	91.37 328	77.50 290	83.82 352	95.00 237	84.84 244	93.05 216	94.96 220	76.53 295	95.20 328	89.96 156	98.67 149	97.86 166

Test_1112_low_res		87.50 279	86.58 286	90.25 266	96.80 156	77.75 287	87.53 309	96.25 195	69.73 351	86.47 331	93.61 268	75.67 296	97.88 233	79.95 293	93.20 329	95.11 288

test_fmvs2		90.62 205	90.40 211	91.29 232	91.93 319	85.46 176	92.70 172	96.48 187	74.44 321	94.91 158	97.59 65	75.52 297	90.57 356	93.44 55	96.56 263	97.84 169

Vis-MVSNet (Re-imp)		90.42 209	90.16 214	91.20 237	97.66 114	77.32 293	94.33 127	87.66 331	91.20 123	92.99 218	95.13 213	75.40 298	98.28 197	77.86 310	99.19 88	97.99 151

test_vis1_n		89.01 247	89.01 236	89.03 290	92.57 305	82.46 213	92.62 176	96.06 204	73.02 331	90.40 276	95.77 186	74.86 299	89.68 361	90.78 127	94.98 298	94.95 292

D2MVS		89.93 229	89.60 229	90.92 246	94.03 280	78.40 278	88.69 295	94.85 241	78.96 296	93.08 214	95.09 215	74.57 300	96.94 283	88.19 194	98.96 115	97.41 201

PVSNet	76.22 20	82.89 317	82.37 317	84.48 339	93.96 281	64.38 371	78.60 364	88.61 322	71.50 338	84.43 344	86.36 359	74.27 301	94.60 331	69.87 357	93.69 324	94.46 305

test_yl		90.11 223	89.73 227	91.26 233	94.09 278	79.82 251	90.44 246	92.65 287	90.90 127	93.19 212	93.30 275	73.90 302	98.03 217	82.23 270	96.87 253	95.93 261

DCV-MVSNet		90.11 223	89.73 227	91.26 233	94.09 278	79.82 251	90.44 246	92.65 287	90.90 127	93.19 212	93.30 275	73.90 302	98.03 217	82.23 270	96.87 253	95.93 261

CMPMVS	68.83 22	87.28 283	85.67 297	92.09 204	88.77 357	85.42 177	90.31 253	94.38 254	70.02 349	88.00 318	93.30 275	73.78 304	94.03 340	75.96 327	96.54 264	96.83 226
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline1		87.62 275	87.31 270	88.54 300	94.71 263	74.27 327	93.10 160	88.20 327	86.20 217	92.18 249	93.04 280	73.21 305	95.52 317	79.32 302	85.82 363	95.83 266

PVSNet_0	70.34 21	74.58 340	72.96 343	79.47 352	90.63 336	66.24 364	73.26 365	83.40 361	63.67 367	78.02 368	78.35 371	72.53 306	89.59 362	56.68 371	60.05 375	82.57 369

MIMVSNet		87.13 289	86.54 288	88.89 293	96.05 206	76.11 310	94.39 125	88.51 323	81.37 274	88.27 315	96.75 126	72.38 307	95.52 317	65.71 365	95.47 286	95.03 289

PAPM		81.91 325	80.11 335	87.31 318	93.87 284	72.32 342	84.02 350	93.22 276	69.47 352	76.13 371	89.84 329	72.15 308	97.23 274	53.27 373	89.02 356	92.37 342

cl22		89.02 245	88.50 245	90.59 257	89.76 346	76.45 307	86.62 329	94.03 261	82.98 261	92.65 229	92.49 293	72.05 309	97.53 258	88.93 181	97.02 246	97.78 176

LFMVS		91.33 191	91.16 194	91.82 210	96.27 189	79.36 262	95.01 104	85.61 347	96.04 30	94.82 161	97.06 105	72.03 310	98.46 186	84.96 246	98.70 145	97.65 186

MVS-HIRNet		78.83 339	80.60 331	73.51 356	93.07 297	47.37 379	87.10 316	78.00 373	68.94 353	77.53 369	97.26 90	71.45 311	94.62 330	63.28 368	88.74 357	78.55 371

EPNet_dtu		85.63 299	84.37 304	89.40 284	86.30 369	74.33 326	91.64 218	88.26 325	84.84 244	72.96 373	89.85 328	71.27 312	97.69 252	76.60 322	97.62 227	96.18 252
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test1111		90.39 212	90.61 205	89.74 278	98.04 88	71.50 345	95.59 81	79.72 370	89.41 159	95.94 110	98.14 35	70.79 313	98.81 134	88.52 191	99.32 64	98.90 70

ECVR-MVS		90.12 222	90.16 214	90.00 274	97.81 100	72.68 339	95.76 75	78.54 372	89.04 167	95.36 136	98.10 38	70.51 314	98.64 166	87.10 214	99.18 90	98.67 96

HyFIR lowres test		87.19 287	85.51 298	92.24 196	97.12 140	80.51 236	85.03 340	96.06 204	66.11 361	91.66 257	92.98 283	70.12 315	99.14 84	75.29 329	95.23 294	97.07 215

FMVSNet3		90.78 199	90.32 213	92.16 202	93.03 300	79.92 249	92.54 178	94.95 239	86.17 219	95.10 149	96.01 173	69.97 316	98.75 145	86.74 218	98.38 173	97.82 172

test_f		86.65 294	87.13 277	85.19 334	90.28 342	86.11 165	86.52 332	91.66 306	69.76 350	95.73 122	97.21 97	69.51 317	81.28 373	89.15 177	94.40 311	88.17 360

RPMNet		90.31 218	90.14 218	90.81 252	91.01 332	78.93 269	92.52 179	98.12 47	91.91 95	89.10 297	96.89 116	68.84 318	99.41 38	90.17 149	92.70 337	94.08 311

test_fmvs1_n		88.73 257	88.38 248	89.76 277	92.06 316	82.53 211	92.30 193	96.59 180	71.14 340	92.58 232	95.41 204	68.55 319	89.57 363	91.12 118	95.66 281	97.18 214

test_fmvs1		87.59 276	87.27 272	88.54 300	88.32 359	81.26 228	90.43 249	95.72 215	70.55 346	91.70 256	94.63 233	68.13 320	89.42 364	90.59 131	95.34 291	94.94 294

ADS-MVSNet2		84.01 310	82.20 319	89.41 283	89.04 354	76.37 309	87.57 305	90.98 312	72.71 334	84.46 342	92.45 294	68.08 321	96.48 297	70.58 355	83.97 365	95.38 281

ADS-MVSNet		82.25 320	81.55 321	84.34 340	89.04 354	65.30 365	87.57 305	85.13 354	72.71 334	84.46 342	92.45 294	68.08 321	92.33 349	70.58 355	83.97 365	95.38 281

CVMVSNet		85.16 303	84.72 300	86.48 323	92.12 314	70.19 350	92.32 191	88.17 328	56.15 372	90.64 272	95.85 178	67.97 323	96.69 292	88.78 186	90.52 352	92.56 340

new_pmnet		81.22 328	81.01 327	81.86 348	90.92 334	70.15 351	84.03 349	80.25 369	70.83 343	85.97 334	89.78 333	67.93 324	84.65 371	67.44 361	91.90 346	90.78 352

CR-MVSNet		87.89 267	87.12 278	90.22 267	91.01 332	78.93 269	92.52 179	92.81 282	73.08 330	89.10 297	96.93 113	67.11 325	97.64 255	88.80 185	92.70 337	94.08 311

Patchmtry		90.11 223	89.92 221	90.66 255	90.35 341	77.00 297	92.96 163	92.81 282	90.25 145	94.74 165	96.93 113	67.11 325	97.52 259	85.17 238	98.98 109	97.46 197

PatchmatchNet		85.22 302	84.64 301	86.98 320	89.51 351	69.83 355	90.52 244	87.34 333	78.87 297	87.22 328	92.74 289	66.91 327	96.53 294	81.77 274	86.88 361	94.58 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GA-MVS		87.70 271	86.82 282	90.31 263	93.27 293	77.22 295	84.72 344	92.79 284	85.11 238	89.82 288	90.07 327	66.80 328	97.76 248	84.56 251	94.27 316	95.96 259

MDTV_nov1_ep13_2view						42.48 381	88.45 299		67.22 358	83.56 349		66.80 328		72.86 342		94.06 313

tpmrst		82.85 318	82.93 315	82.64 346	87.65 361	58.99 376	90.14 258	87.90 330	75.54 315	83.93 346	91.63 310	66.79 330	95.36 323	81.21 281	81.54 370	93.57 329

sam_mvs1												66.64 331				94.75 299

sam_mvs												66.41 332

Patchmatch-RL test		88.81 254	88.52 244	89.69 280	95.33 244	79.94 248	86.22 333	92.71 286	78.46 299	95.80 117	94.18 248	66.25 333	95.33 325	89.22 175	98.53 161	93.78 320

patchmatchnet-post											91.71 308	66.22 334	97.59 256

AUN-MVS		90.05 227	88.30 250	95.32 88	96.09 203	90.52 77	92.42 186	92.05 302	82.08 271	88.45 312	92.86 284	65.76 335	98.69 159	88.91 183	96.07 271	96.75 231

test_post											6.07 378	65.74 336	95.84 313

test_post1							90.21 255				5.85 379	65.36 337	96.00 311	79.61 299

MDTV_nov1_ep13			83.88 309		89.42 352	61.52 374	88.74 294	87.41 332	73.99 324	84.96 340	94.01 255	65.25 338	95.53 316	78.02 309	93.16 330

Patchmatch-test		86.10 297	86.01 294	86.38 327	90.63 336	74.22 328	89.57 273	86.69 336	85.73 227	89.81 289	92.83 285	65.24 339	91.04 355	77.82 313	95.78 279	93.88 319

tpmvs		84.22 309	83.97 308	84.94 335	87.09 366	65.18 366	91.21 227	88.35 324	82.87 262	85.21 336	90.96 319	65.24 339	96.75 290	79.60 301	85.25 364	92.90 337

EU-MVSNet		87.39 281	86.71 285	89.44 282	93.40 291	76.11 310	94.93 107	90.00 318	57.17 371	95.71 123	97.37 79	64.77 341	97.68 253	92.67 83	94.37 313	94.52 304

thres200		85.85 298	85.18 299	87.88 313	94.44 270	72.52 340	89.08 286	86.21 339	88.57 180	91.44 259	88.40 347	64.22 342	98.00 222	68.35 359	95.88 278	93.12 332

PatchT		87.51 278	88.17 258	85.55 330	90.64 335	66.91 360	92.02 202	86.09 341	92.20 87	89.05 299	97.16 99	64.15 343	96.37 302	89.21 176	92.98 335	93.37 330

tfpn200view9		87.05 290	86.52 289	88.67 297	95.77 222	72.94 336	91.89 208	86.00 342	90.84 129	92.61 230	89.80 330	63.93 344	98.28 197	71.27 351	96.54 264	94.79 297

thres400		87.20 286	86.52 289	89.24 289	95.77 222	72.94 336	91.89 208	86.00 342	90.84 129	92.61 230	89.80 330	63.93 344	98.28 197	71.27 351	96.54 264	96.51 236

FPMVS		84.50 307	83.28 311	88.16 308	96.32 185	94.49 16	85.76 334	85.47 348	83.09 258	85.20 337	94.26 244	63.79 346	86.58 369	63.72 367	91.88 347	83.40 366

thres100view900		87.35 282	86.89 281	88.72 296	96.14 200	73.09 335	93.00 162	85.31 350	92.13 89	93.26 208	90.96 319	63.42 347	98.28 197	71.27 351	96.54 264	94.79 297

thres600view7		87.66 273	87.10 279	89.36 285	96.05 206	73.17 333	92.72 170	85.31 350	91.89 96	93.29 205	90.97 318	63.42 347	98.39 188	73.23 339	96.99 251	96.51 236

EMVS		80.35 335	80.28 334	80.54 350	84.73 375	69.07 356	72.54 368	80.73 366	87.80 194	81.66 362	81.73 369	62.89 349	89.84 360	75.79 328	94.65 308	82.71 368

test-LLR		83.58 312	83.17 312	84.79 337	89.68 348	66.86 361	83.08 353	84.52 355	83.07 259	82.85 353	84.78 364	62.86 350	93.49 343	82.85 262	94.86 301	94.03 314

test0.0.03 1		82.48 319	81.47 323	85.48 331	89.70 347	73.57 332	84.73 342	81.64 364	83.07 259	88.13 317	86.61 356	62.86 350	89.10 366	66.24 364	90.29 353	93.77 321

tpm cat1		80.61 334	79.46 337	84.07 342	88.78 356	65.06 369	89.26 282	88.23 326	62.27 368	81.90 361	89.66 336	62.70 352	95.29 326	71.72 347	80.60 371	91.86 347

E-PMN		80.72 333	80.86 328	80.29 351	85.11 373	68.77 357	72.96 366	81.97 363	87.76 196	83.25 352	83.01 368	62.22 353	89.17 365	77.15 319	94.31 315	82.93 367

baseline2		83.38 313	81.54 322	88.90 292	91.38 327	72.84 338	88.78 292	81.22 365	78.97 295	79.82 366	87.56 350	61.73 354	97.80 242	74.30 334	90.05 354	96.05 257

CostFormer		83.09 315	82.21 318	85.73 329	89.27 353	67.01 359	90.35 251	86.47 338	70.42 347	83.52 350	93.23 278	61.18 355	96.85 287	77.21 318	88.26 359	93.34 331

MVSTER		89.32 239	88.75 242	91.03 241	90.10 344	76.62 305	90.85 234	94.67 250	82.27 269	95.24 145	95.79 182	61.09 356	98.49 181	90.49 133	98.26 185	97.97 155

tpm		84.38 308	84.08 307	85.30 333	90.47 339	63.43 373	89.34 279	85.63 346	77.24 307	87.62 323	95.03 218	61.00 357	97.30 272	79.26 303	91.09 351	95.16 285

FE-MVS		89.06 244	88.29 251	91.36 228	94.78 257	79.57 258	96.77 28	90.99 311	84.87 243	92.96 220	96.29 157	60.69 358	98.80 137	80.18 290	97.11 243	95.71 271

EPMVS		81.17 330	80.37 332	83.58 343	85.58 372	65.08 368	90.31 253	71.34 376	77.31 306	85.80 335	91.30 313	59.38 359	92.70 348	79.99 292	82.34 369	92.96 336

tmp_tt		37.97 343	44.33 346	18.88 359	11.80 382	21.54 382	63.51 370	45.66 383	4.23 376	51.34 376	50.48 374	59.08 360	22.11 378	44.50 375	68.35 374	13.00 374

tpm2		81.46 326	80.35 333	84.80 336	89.90 345	65.14 367	90.44 246	85.36 349	65.82 363	82.05 359	92.44 296	57.94 361	96.69 292	70.71 354	88.49 358	92.56 340

ET-MVSNet_ETH3D		86.15 296	84.27 306	91.79 211	93.04 299	81.28 227	87.17 315	86.14 340	79.57 287	83.65 347	88.66 344	57.10 362	98.18 208	87.74 205	95.40 288	95.90 264

CHOSEN 280x420		80.04 336	77.97 341	86.23 328	90.13 343	74.53 323	72.87 367	89.59 319	66.38 360	76.29 370	85.32 363	56.96 363	95.36 323	69.49 358	94.72 306	88.79 358

JIA-IIPM		85.08 304	83.04 313	91.19 238	87.56 362	86.14 164	89.40 278	84.44 357	88.98 169	82.20 357	97.95 47	56.82 364	96.15 306	76.55 323	83.45 367	91.30 349

DeepMVS_CX				53.83 358	70.38 380	64.56 370		48.52 382	33.01 374	65.50 375	74.21 373	56.19 365	46.64 377	38.45 376	70.07 373	50.30 373

dp		79.28 337	78.62 339	81.24 349	85.97 371	56.45 377	86.91 319	85.26 352	72.97 332	81.45 363	89.17 343	56.01 366	95.45 321	73.19 340	76.68 372	91.82 348

iter_conf_final		90.23 219	89.32 230	92.95 171	94.65 266	81.46 225	94.32 129	95.40 232	85.61 229	92.84 223	95.37 207	54.58 367	99.13 86	92.16 91	98.94 117	98.25 128

test_method		50.44 342	48.94 345	54.93 357	39.68 381	12.38 383	28.59 372	90.09 317	6.82 375	41.10 377	78.41 370	54.41 368	70.69 376	50.12 374	51.26 376	81.72 370

thisisatest0515		84.72 306	82.99 314	89.90 275	92.96 301	75.33 318	84.36 347	83.42 360	77.37 305	88.27 315	86.65 355	53.94 369	98.72 150	82.56 266	97.40 235	95.67 274

tttt0517		89.81 232	88.90 240	92.55 189	97.00 142	79.73 255	95.03 103	83.65 359	89.88 150	95.30 139	94.79 228	53.64 370	99.39 48	91.99 97	98.79 136	98.54 110

thisisatest0530		88.69 258	87.52 268	92.20 197	96.33 184	79.36 262	92.81 167	84.01 358	86.44 214	93.67 194	92.68 291	53.62 371	99.25 73	89.65 163	98.45 167	98.00 148

FMVSNet5		87.82 270	86.56 287	91.62 219	92.31 308	79.81 253	93.49 152	94.81 245	83.26 254	91.36 260	96.93 113	52.77 372	97.49 262	76.07 325	98.03 207	97.55 193

pmmvs3		80.83 332	78.96 338	86.45 324	87.23 365	77.48 291	84.87 341	82.31 362	63.83 366	85.03 338	89.50 337	49.66 373	93.10 345	73.12 341	95.10 296	88.78 359

iter_conf05		88.94 251	88.09 260	91.50 224	92.74 303	76.97 300	92.80 168	95.92 209	82.82 263	93.65 195	95.37 207	49.41 374	99.13 86	90.82 125	99.28 75	98.40 120

IB-MVS	77.21 19	83.11 314	81.05 325	89.29 286	91.15 330	75.85 313	85.66 335	86.00 342	79.70 285	82.02 360	86.61 356	48.26 375	98.39 188	77.84 311	92.22 342	93.63 325
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		82.10 324	81.02 326	85.34 332	87.46 364	71.04 346	94.74 111	67.56 377	96.44 23	79.43 367	98.99 6	45.24 376	96.15 306	67.18 362	92.17 343	88.85 357

GG-mvs-BLEND				83.24 345	85.06 374	71.03 347	94.99 106	65.55 378		74.09 372	75.51 372	44.57 377	94.46 333	59.57 370	87.54 360	84.24 365

TESTMET0.1,1		79.09 338	78.04 340	82.25 347	87.52 363	64.03 372	83.08 353	80.62 367	70.28 348	80.16 365	83.22 367	44.13 378	90.56 357	79.95 293	93.36 326	92.15 343

test-mter		81.21 329	80.01 336	84.79 337	89.68 348	66.86 361	83.08 353	84.52 355	73.85 325	82.85 353	84.78 364	43.66 379	93.49 343	82.85 262	94.86 301	94.03 314

KD-MVS_2432*1600		82.17 322	80.75 329	86.42 325	82.04 378	70.09 352	81.75 358	90.80 313	82.56 264	90.37 277	89.30 339	42.90 380	96.11 308	74.47 332	92.55 339	93.06 333

miper_refine_blended		82.17 322	80.75 329	86.42 325	82.04 378	70.09 352	81.75 358	90.80 313	82.56 264	90.37 277	89.30 339	42.90 380	96.11 308	74.47 332	92.55 339	93.06 333

test2506		85.42 301	84.57 303	87.96 310	97.81 100	66.53 363	96.14 58	56.35 380	89.04 167	93.55 198	98.10 38	42.88 382	98.68 161	88.09 198	99.18 90	98.67 96

test123		9.49 345	12.01 348	1.91 360	2.87 383	1.30 384	82.38 356	1.34 385	1.36 378	2.84 379	6.56 377	2.45 383	0.97 379	2.73 377	5.56 377	3.47 375

testmvs		9.02 346	11.42 349	1.81 361	2.77 384	1.13 385	79.44 363	1.90 384	1.18 379	2.65 380	6.80 376	1.95 384	0.87 380	2.62 378	3.45 378	3.44 376

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		7.56 347	10.08 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	90.69 324	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.21 3	94.68 12	98.45 4	98.81 8	97.73 6	98.27 20

MSC_two_6792asdad				95.90 65	96.54 168	89.57 88		96.87 162					99.41 38	94.06 32	99.30 67	98.72 92

No_MVS				95.90 65	96.54 168	89.57 88		96.87 162					99.41 38	94.06 32	99.30 67	98.72 92

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					98.51 51	86.66 149		96.83 165	72.74 333	95.83 116				93.00 74	99.29 70	98.64 103

save fliter					97.46 126	88.05 120	92.04 201	97.08 145	87.63 200

test_0728_SECOND				94.88 100	98.55 45	86.72 146	95.20 96	98.22 32					99.38 54	93.44 55	99.31 65	98.53 111

GSMVS																94.75 299

test_part2					98.21 75	89.41 93				96.72 76

MTGPA								97.62 100

MTMP							94.82 109	54.62 381

gm-plane-assit					87.08 367	59.33 375			71.22 339		83.58 366		97.20 275	73.95 335

test9_res														88.16 196	98.40 169	97.83 170

agg_prior2														87.06 216	98.36 178	97.98 152

agg_prior					96.20 195	88.89 103		96.88 161		90.21 280			98.78 141

test_prior4						89.91 82	90.74 237

test_prior				94.61 112	95.95 214	87.23 132		97.36 123					98.68 161			97.93 158

旧先验2							90.00 263		68.65 354	92.71 228			96.52 295	85.15 240

新几何2							90.02 262

无先验							89.94 264	95.75 214	70.81 344				98.59 172	81.17 282		94.81 295

原ACMM2							89.34 279

testdata2													98.03 217	80.24 289

testdata1							88.96 288		88.44 182

plane_prior7					97.71 108	88.68 106

plane_prior5								97.81 86					98.95 112	89.26 173	98.51 164	98.60 107

plane_prior4											95.59 191

plane_prior3						88.43 115			90.35 144	93.31 203

plane_prior2							94.56 120		91.74 109

plane_prior1					97.38 128

plane_prior						88.12 118	93.01 161		88.98 169						98.06 204

n2								0.00 386

nn								0.00 386

door-mid								92.13 300

test11								96.65 176

door								91.26 309

HQP5-MVS						84.89 182

HQP-NCC					96.36 179		91.37 222		87.16 206	88.81 302

ACMP_Plane					96.36 179		91.37 222		87.16 206	88.81 302

BP-MVS														86.55 225

HQP4-MVS										88.81 302			98.61 168			98.15 136

HQP3-MVS								97.31 127							97.73 220

NP-MVS					96.82 154	87.10 135					93.40 273

ACMMP++_ref															98.82 132

ACMMP++															99.25 79

High-resolution multi-view benchmark