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.

TDRefinement		86.32 2	86.33 2	86.29 1	88.64 33	81.19 5	88.84 4	90.72 1	78.27 9	87.95 15	92.53 13	79.37 13	84.79 67	74.51 51	96.15 2	92.88 7

FOURS1					89.19 25	77.84 16	91.64 1	89.11 2	84.05 2	91.57 2

AllTest		77.66 77	77.43 82	78.35 71	79.19 156	70.81 60	78.60 93	88.64 3	65.37 83	80.09 117	88.17 111	70.33 81	78.43 180	55.60 195	90.90 116	85.81 75

TestCases				78.35 71	79.19 156	70.81 60		88.64 3	65.37 83	80.09 117	88.17 111	70.33 81	78.43 180	55.60 195	90.90 116	85.81 75

xxxxxxxxxxxxxcwj		80.31 54	80.94 54	78.42 70	87.00 43	67.23 90	79.24 85	88.61 5	56.65 166	84.29 67	89.18 90	73.73 59	83.22 94	76.01 39	93.77 62	84.81 96

SF-MVS		80.72 48	81.80 46	77.48 80	82.03 123	64.40 115	83.41 49	88.46 6	65.28 85	84.29 67	89.18 90	73.73 59	83.22 94	76.01 39	93.77 62	84.81 96

COLMAP_ROB	72.78 3	83.75 13	84.11 17	82.68 14	82.97 109	74.39 36	87.18 11	88.18 7	78.98 7	86.11 39	91.47 29	79.70 12	85.76 42	66.91 108	95.46 11	87.89 47
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	66.64 10	81.20 40	82.48 43	77.35 84	81.16 135	62.39 127	80.51 67	87.80 8	73.02 28	87.57 21	91.08 36	80.28 10	82.44 107	64.82 120	96.10 4	87.21 56

LTVRE_ROB	75.46 1	84.22 8	84.98 9	81.94 23	84.82 77	75.40 30	91.60 3	87.80 8	73.52 26	88.90 11	93.06 6	71.39 75	81.53 121	81.53 3	92.15 89	88.91 37
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
LCM-MVSNet		86.90 1	88.67 1	81.57 25	91.50 1	63.30 123	84.80 34	87.77 10	86.18 1	96.26 1	96.06 1	90.32 1	84.49 70	68.08 93	97.05 1	96.93 1

9.14			80.22 59		80.68 137		80.35 72	87.69 11	59.90 132	83.00 80	88.20 110	74.57 51	81.75 119	73.75 56	93.78 61

ETH3D-3000-0.1		79.14 63	79.80 63	77.16 87	80.67 138	64.57 112	80.26 74	87.60 12	60.74 127	82.47 88	88.03 115	71.73 70	81.81 117	73.12 59	93.61 65	85.09 87

DROMVSNet		77.08 82	77.39 83	76.14 99	76.86 189	56.87 172	80.32 73	87.52 13	63.45 106	74.66 195	84.52 178	69.87 86	84.94 62	69.76 84	89.59 144	86.60 65

APD-MVS_3200maxsize		83.57 15	84.33 14	81.31 33	82.83 112	73.53 44	85.50 28	87.45 14	74.11 21	86.45 34	90.52 53	80.02 11	84.48 71	77.73 30	94.34 49	85.93 73

test_part1		76.97 83	78.21 77	73.25 136	77.87 173	45.76 251	78.27 99	87.26 15	66.69 71	85.31 52	91.43 31	55.95 213	84.24 78	65.71 113	95.43 12	89.75 22

HPM-MVS		84.12 10	84.63 11	82.60 15	88.21 39	74.40 35	85.24 29	87.21 16	70.69 48	85.14 54	90.42 57	78.99 16	86.62 14	80.83 6	94.93 24	86.79 62
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DeepC-MVS	72.44 4	81.00 45	80.83 56	81.50 26	86.70 49	70.03 69	82.06 58	87.00 17	59.89 133	80.91 108	90.53 51	72.19 65	88.56 1	73.67 57	94.52 36	85.92 74
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		84.59 6	85.10 8	83.06 6	88.60 34	75.83 27	86.27 25	86.89 18	73.69 25	86.17 36	91.70 24	78.23 20	85.20 58	79.45 13	94.91 25	88.15 45

CS-MVS-test		73.63 118	73.74 120	73.30 135	75.80 202	51.70 199	77.02 116	86.83 19	61.29 121	68.47 265	79.23 243	65.42 129	85.14 61	64.04 125	85.55 196	83.07 151

LPG-MVS_test		83.47 18	84.33 14	80.90 38	87.00 43	70.41 65	82.04 59	86.35 20	69.77 53	87.75 16	91.13 34	81.83 3	86.20 25	77.13 37	95.96 5	86.08 69

LGP-MVS_train				80.90 38	87.00 43	70.41 65		86.35 20	69.77 53	87.75 16	91.13 34	81.83 3	86.20 25	77.13 37	95.96 5	86.08 69

MP-MVS-pluss		82.54 29	83.46 28	79.76 47	88.88 32	68.44 82	81.57 62	86.33 22	63.17 110	85.38 51	91.26 33	76.33 32	84.67 69	83.30 1	94.96 23	86.17 68
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SR-MVS-dyc-post		84.75 5	85.26 7	83.21 3	86.19 54	79.18 9	87.23 9	86.27 23	77.51 11	87.65 19	90.73 45	79.20 14	85.58 48	78.11 25	94.46 38	84.89 92

RE-MVS-def			85.50 4		86.19 54	79.18 9	87.23 9	86.27 23	77.51 11	87.65 19	90.73 45	81.38 7		78.11 25	94.46 38	84.89 92

RPMNet		65.77 218	65.08 228	67.84 219	66.37 298	48.24 224	70.93 186	86.27 23	54.66 187	61.35 305	86.77 133	33.29 320	85.67 46	55.93 192	70.17 327	69.62 305

3Dnovator+	73.19 2	81.08 44	80.48 57	82.87 9	81.41 132	72.03 49	84.38 37	86.23 26	77.28 16	80.65 110	90.18 73	59.80 176	87.58 4	73.06 60	91.34 102	89.01 33

ETH3D cwj APD-0.16		78.38 74	78.72 72	77.38 82	80.09 143	66.16 100	79.08 88	86.13 27	57.55 156	80.93 106	87.76 118	71.98 69	82.73 104	72.11 71	92.83 77	83.25 144

abl_6		84.92 3	85.70 3	82.57 17	86.72 48	79.27 8	87.56 7	86.08 28	77.48 13	88.12 14	91.53 27	81.18 8	84.31 76	78.12 24	94.47 37	84.15 120

ACMP	69.50 8	82.64 28	83.38 29	80.40 43	86.50 50	69.44 73	82.30 56	86.08 28	66.80 69	86.70 32	89.99 75	81.64 6	85.95 32	74.35 52	96.11 3	85.81 75
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ZNCC-MVS		83.12 22	83.68 23	81.45 29	89.14 26	73.28 46	86.32 24	85.97 30	67.39 64	84.02 71	90.39 61	74.73 48	86.46 16	80.73 7	94.43 42	84.60 105

ACMMP		84.22 8	84.84 10	82.35 20	89.23 23	76.66 26	87.65 6	85.89 31	71.03 45	85.85 41	90.58 49	78.77 17	85.78 41	79.37 16	95.17 17	84.62 102
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
LS3D		80.99 46	80.85 55	81.41 30	78.37 165	71.37 55	87.45 8	85.87 32	77.48 13	81.98 91	89.95 77	69.14 90	85.26 54	66.15 109	91.24 104	87.61 51

test_one_0601					85.84 66	61.45 134		85.63 33	75.27 19	85.62 47	90.38 63	76.72 29

XVG-ACMP-BASELINE		80.54 49	81.06 53	78.98 61	87.01 42	72.91 47	80.23 76	85.56 34	66.56 73	85.64 44	89.57 82	69.12 91	80.55 143	72.51 65	93.37 69	83.48 136

DVP-MVS++.		81.24 39	82.74 40	76.76 88	83.14 102	60.90 141	91.64 1	85.49 35	74.03 23	84.93 56	90.38 63	66.82 113	85.90 37	77.43 33	90.78 120	83.49 134

test_0728_SECOND				76.57 91	86.20 53	60.57 146	83.77 42	85.49 35					85.90 37	75.86 42	94.39 43	83.25 144

HQP_MVS		78.77 67	78.78 71	78.72 64	85.18 71	65.18 107	82.74 53	85.49 35	65.45 80	78.23 136	89.11 94	60.83 167	86.15 28	71.09 74	90.94 112	84.82 94

plane_prior5								85.49 35					86.15 28	71.09 74	90.94 112	84.82 94

PGM-MVS		83.07 23	83.25 33	82.54 18	89.57 14	77.21 24	82.04 59	85.40 39	67.96 62	84.91 60	90.88 39	75.59 38	86.57 15	78.16 23	94.71 32	83.82 124

XVG-OURS-SEG-HR		79.62 58	79.99 61	78.49 68	86.46 51	74.79 34	77.15 113	85.39 40	66.73 70	80.39 114	88.85 101	74.43 54	78.33 185	74.73 49	85.79 194	82.35 171

SD-MVS		80.28 55	81.55 52	76.47 94	83.57 96	67.83 86	83.39 50	85.35 41	64.42 95	86.14 38	87.07 123	74.02 55	80.97 134	77.70 31	92.32 87	80.62 203
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
SR-MVS		84.51 7	85.27 6	82.25 21	88.52 35	77.71 17	86.81 17	85.25 42	77.42 15	86.15 37	90.24 70	81.69 5	85.94 33	77.77 29	93.58 67	83.09 148

test1172		84.85 4	85.39 5	83.21 3	88.34 38	80.50 6	85.12 30	85.22 43	81.06 3	87.20 28	90.28 69	79.20 14	85.58 48	78.04 27	94.08 56	83.55 132

GST-MVS		82.79 27	83.27 32	81.34 32	88.99 28	73.29 45	85.94 26	85.13 44	68.58 60	84.14 70	90.21 72	73.37 61	86.41 17	79.09 19	93.98 60	84.30 118

APDe-MVS		82.88 26	84.14 16	79.08 57	84.80 79	66.72 95	86.54 21	85.11 45	72.00 41	86.65 33	91.75 23	78.20 21	87.04 9	77.93 28	94.32 50	83.47 137

test0726					86.16 56	60.78 143	83.81 41	85.10 46	72.48 34	85.27 53	89.96 76	78.57 18

MSP-MVS		80.49 50	79.67 65	82.96 7	89.70 12	77.46 23	87.16 12	85.10 46	64.94 90	81.05 104	88.38 106	57.10 204	87.10 8	79.75 8	83.87 224	84.31 116
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
DPE-MVS		82.00 34	83.02 36	78.95 62	85.36 70	67.25 89	82.91 52	84.98 48	73.52 26	85.43 50	90.03 74	76.37 31	86.97 11	74.56 50	94.02 59	82.62 164
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMMP_NAP		82.33 31	83.28 31	79.46 53	89.28 19	69.09 80	83.62 44	84.98 48	64.77 91	83.97 72	91.02 37	75.53 41	85.93 36	82.00 2	94.36 47	83.35 142

XVG-OURS		79.51 59	79.82 62	78.58 67	86.11 61	74.96 33	76.33 123	84.95 50	66.89 66	82.75 85	88.99 98	66.82 113	78.37 183	74.80 47	90.76 123	82.40 170

test_241102_TWO								84.80 51	72.61 32	84.93 56	89.70 80	77.73 23	85.89 39	75.29 45	94.22 55	83.25 144

SteuartSystems-ACMMP		83.07 23	83.64 24	81.35 31	85.14 73	71.00 59	85.53 27	84.78 52	70.91 46	85.64 44	90.41 58	75.55 40	87.69 3	79.75 8	95.08 20	85.36 82
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		82.12 32	82.68 42	80.43 42	88.90 31	69.52 71	85.12 30	84.76 53	63.53 104	84.23 69	91.47 29	72.02 67	87.16 7	79.74 10	94.36 47	84.61 103
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
OMC-MVS		79.41 61	78.79 70	81.28 34	80.62 139	70.71 63	80.91 65	84.76 53	62.54 114	81.77 94	86.65 140	71.46 73	83.53 88	67.95 98	92.44 84	89.60 23

SED-MVS		81.78 35	83.48 27	76.67 89	86.12 58	61.06 137	83.62 44	84.72 55	72.61 32	87.38 25	89.70 80	77.48 24	85.89 39	75.29 45	94.39 43	83.08 149

test_241102_ONE					86.12 58	61.06 137		84.72 55	72.64 31	87.38 25	89.47 83	77.48 24	85.74 43

ETV-MVS		72.72 141	72.16 148	74.38 118	76.90 187	55.95 175	73.34 154	84.67 57	62.04 117	72.19 227	70.81 320	65.90 124	85.24 56	58.64 171	84.96 209	81.95 178

XVS		83.51 17	83.73 22	82.85 10	89.43 16	77.61 18	86.80 18	84.66 58	72.71 29	82.87 82	90.39 61	73.86 56	86.31 20	78.84 20	94.03 57	84.64 100

X-MVStestdata		76.81 84	74.79 103	82.85 10	89.43 16	77.61 18	86.80 18	84.66 58	72.71 29	82.87 82	9.95 367	73.86 56	86.31 20	78.84 20	94.03 57	84.64 100

testtj		81.19 41	81.70 49	79.67 51	83.95 92	69.77 70	83.58 47	84.63 60	72.13 38	82.85 84	88.36 107	75.00 46	86.79 12	71.99 72	92.84 76	82.44 169

DP-MVS		78.44 73	79.29 67	75.90 101	81.86 126	65.33 105	79.05 89	84.63 60	74.83 20	80.41 113	86.27 151	71.68 71	83.45 90	62.45 143	92.40 85	78.92 224

ETH3 D test6400		75.73 92	76.00 94	74.92 111	81.75 127	56.93 170	78.31 97	84.60 62	52.83 212	77.15 151	85.14 173	68.59 95	84.03 79	65.44 116	90.20 129	83.82 124

CS-MVS		69.29 179	69.70 174	68.07 216	70.59 264	42.36 279	69.70 200	84.56 63	53.13 208	67.96 268	76.74 270	59.41 178	83.56 86	60.33 157	84.84 211	78.28 232

ACMM	69.25 9	82.11 33	83.31 30	78.49 68	88.17 40	73.96 38	83.11 51	84.52 64	66.40 74	87.45 23	89.16 93	81.02 9	80.52 144	74.27 53	95.73 7	80.98 192
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVS		84.12 10	84.55 12	82.80 12	89.42 18	79.74 7	88.19 5	84.43 65	71.96 42	84.70 62	90.56 50	77.12 26	86.18 27	79.24 18	95.36 13	82.49 168

baseline		73.10 128	73.96 115	70.51 176	71.46 257	46.39 247	72.08 164	84.40 66	55.95 172	76.62 166	86.46 147	67.20 108	78.03 192	64.22 124	87.27 178	87.11 59

test_prior3		76.71 86	77.19 85	75.27 108	82.15 121	59.85 152	75.57 130	84.33 67	58.92 141	76.53 170	86.78 131	67.83 105	83.39 91	69.81 82	92.76 80	82.58 165

test_prior				75.27 108	82.15 121	59.85 152		84.33 67					83.39 91			82.58 165

HFP-MVS		83.39 19	84.03 18	81.48 27	89.25 21	75.69 28	87.01 15	84.27 69	70.23 49	84.47 65	90.43 55	76.79 27	85.94 33	79.58 11	94.23 53	82.82 158

#test#		82.40 30	82.71 41	81.48 27	89.25 21	75.69 28	84.47 36	84.27 69	64.45 94	84.47 65	90.43 55	76.79 27	85.94 33	76.01 39	94.23 53	82.82 158

casdiffmvs		73.06 131	73.84 116	70.72 172	71.32 258	46.71 243	70.93 186	84.26 71	55.62 175	77.46 149	87.10 120	67.09 109	77.81 195	63.95 127	86.83 184	87.64 50

MSLP-MVS++		74.48 109	75.78 96	70.59 174	84.66 80	62.40 126	78.65 92	84.24 72	60.55 129	77.71 146	81.98 208	63.12 142	77.64 199	62.95 140	88.14 159	71.73 287

region2R		83.54 16	83.86 21	82.58 16	89.82 10	77.53 20	87.06 14	84.23 73	70.19 51	83.86 73	90.72 47	75.20 42	86.27 22	79.41 15	94.25 52	83.95 123

ACMMPR		83.62 14	83.93 19	82.69 13	89.78 11	77.51 22	87.01 15	84.19 74	70.23 49	84.49 64	90.67 48	75.15 43	86.37 19	79.58 11	94.26 51	84.18 119

HQP3-MVS								84.12 75							89.16 149

HQP-MVS		75.24 98	75.01 102	75.94 100	82.37 116	58.80 162	77.32 109	84.12 75	59.08 137	71.58 232	85.96 163	58.09 192	85.30 53	67.38 104	89.16 149	83.73 130

DeepPCF-MVS	71.07 5	78.48 72	77.14 87	82.52 19	84.39 88	77.04 25	76.35 121	84.05 77	56.66 165	80.27 115	85.31 171	68.56 96	87.03 10	67.39 103	91.26 103	83.50 133

TAPA-MVS	65.27 12	75.16 99	74.29 111	77.77 77	74.86 212	68.08 83	77.89 104	84.04 78	55.15 179	76.19 177	83.39 191	66.91 111	80.11 154	60.04 163	90.14 133	85.13 86
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OPM-MVS		80.99 46	81.63 51	79.07 58	86.86 47	69.39 74	79.41 84	84.00 79	65.64 78	85.54 48	89.28 86	76.32 33	83.47 89	74.03 54	93.57 68	84.35 115
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DeepC-MVS_fast	69.89 7	77.17 81	76.33 92	79.70 50	83.90 94	67.94 84	80.06 79	83.75 80	56.73 164	74.88 189	85.32 170	65.54 126	87.79 2	65.61 115	91.14 108	83.35 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APD-MVS		81.13 43	81.73 48	79.36 55	84.47 84	70.53 64	83.85 40	83.70 81	69.43 55	83.67 75	88.96 99	75.89 36	86.41 17	72.62 64	92.95 74	81.14 187
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMH	63.62 14	77.50 79	80.11 60	69.68 190	79.61 147	56.28 174	78.81 90	83.62 82	63.41 108	87.14 31	90.23 71	76.11 34	73.32 240	67.58 100	94.44 41	79.44 218
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MP-MVS		83.19 20	83.54 26	82.14 22	90.54 5	79.00 11	86.42 23	83.59 83	71.31 43	81.26 102	90.96 38	74.57 51	84.69 68	78.41 22	94.78 28	82.74 162
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		77.33 80	77.06 88	78.14 74	84.21 89	63.98 118	76.07 126	83.45 84	54.20 195	77.68 147	87.18 119	69.98 84	85.37 51	68.01 95	92.72 82	85.08 89

CLD-MVS		72.88 138	72.36 144	74.43 116	77.03 183	54.30 186	68.77 215	83.43 85	52.12 218	76.79 164	74.44 289	69.54 88	83.91 80	55.88 193	93.25 72	85.09 87
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
canonicalmvs		72.29 148	73.38 127	69.04 198	74.23 225	47.37 237	73.93 152	83.18 86	54.36 192	76.61 167	81.64 214	72.03 66	75.34 224	57.12 180	87.28 177	84.40 113

PHI-MVS		74.92 103	74.36 110	76.61 90	76.40 192	62.32 128	80.38 70	83.15 87	54.16 197	73.23 213	80.75 221	62.19 152	83.86 81	68.02 94	90.92 115	83.65 131

MCST-MVS		73.42 122	73.34 129	73.63 129	81.28 133	59.17 158	74.80 141	83.13 88	45.50 275	72.84 216	83.78 188	65.15 131	80.99 132	64.54 121	89.09 154	80.73 201

F-COLMAP		75.29 97	73.99 114	79.18 56	81.73 128	71.90 50	81.86 61	82.98 89	59.86 134	72.27 224	84.00 185	64.56 137	83.07 99	51.48 225	87.19 180	82.56 167

DP-MVS Recon		73.57 120	72.69 140	76.23 97	82.85 111	63.39 121	74.32 148	82.96 90	57.75 150	70.35 248	81.98 208	64.34 138	84.41 75	49.69 239	89.95 137	80.89 194

v10		75.69 93	76.20 93	74.16 121	74.44 224	48.69 218	75.84 129	82.93 91	59.02 140	85.92 40	89.17 92	58.56 187	82.74 103	70.73 76	89.14 152	91.05 13

mPP-MVS		84.01 12	84.39 13	82.88 8	90.65 4	81.38 4	87.08 13	82.79 92	72.41 36	85.11 55	90.85 41	76.65 30	84.89 64	79.30 17	94.63 34	82.35 171

Effi-MVS+		72.10 149	72.28 145	71.58 164	74.21 229	50.33 207	74.72 144	82.73 93	62.62 113	70.77 244	76.83 269	69.96 85	80.97 134	60.20 158	78.43 281	83.45 139

test11								82.71 94

PEN-MVS		80.46 51	82.91 37	73.11 139	89.83 9	39.02 302	77.06 115	82.61 95	80.04 5	90.60 6	92.85 9	74.93 47	85.21 57	63.15 139	95.15 18	95.09 2

nrg030		74.87 106	75.99 95	71.52 166	74.90 211	49.88 214	74.10 151	82.58 96	54.55 190	83.50 77	89.21 89	71.51 72	75.74 220	61.24 149	92.34 86	88.94 36

v7n		79.37 62	80.41 58	76.28 96	78.67 164	55.81 177	79.22 87	82.51 97	70.72 47	87.54 22	92.44 14	68.00 104	81.34 122	72.84 61	91.72 91	91.69 10

WR-MVS_H		80.22 56	82.17 45	74.39 117	89.46 15	42.69 275	78.24 100	82.24 98	78.21 10	89.57 9	92.10 18	68.05 102	85.59 47	66.04 111	95.62 9	94.88 5

DELS-MVS		68.83 185	68.31 191	70.38 177	70.55 268	48.31 222	63.78 279	82.13 99	54.00 199	68.96 260	75.17 281	58.95 184	80.06 155	58.55 172	82.74 234	82.76 160
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
OurMVSNet-221017-0		78.57 69	78.53 75	78.67 65	80.48 140	64.16 116	80.24 75	82.06 100	61.89 118	88.77 12	93.32 4	57.15 202	82.60 106	70.08 80	92.80 78	89.25 27

CPTT-MVS		81.51 38	81.76 47	80.76 40	89.20 24	78.75 12	86.48 22	82.03 101	68.80 56	80.92 107	88.52 103	72.00 68	82.39 108	74.80 47	93.04 73	81.14 187

CSCG		74.12 112	74.39 108	73.33 133	79.35 151	61.66 133	77.45 108	81.98 102	62.47 116	79.06 127	80.19 230	61.83 154	78.79 170	59.83 165	87.35 174	79.54 217

PVSNet_Blended_VisFu		70.04 166	68.88 184	73.53 131	82.71 113	63.62 120	74.81 139	81.95 103	48.53 257	67.16 275	79.18 246	51.42 233	78.38 182	54.39 209	79.72 271	78.60 226

DTE-MVSNet		80.35 53	82.89 38	72.74 151	89.84 8	37.34 317	77.16 112	81.81 104	80.45 4	90.92 3	92.95 7	74.57 51	86.12 30	63.65 131	94.68 33	94.76 6

v1192		73.40 123	73.42 125	73.32 134	74.65 221	48.67 219	72.21 163	81.73 105	52.76 213	81.85 92	84.56 177	57.12 203	82.24 113	68.58 88	87.33 175	89.06 32

原ACMM1				73.90 124	85.90 62	65.15 109		81.67 106	50.97 233	74.25 200	86.16 156	61.60 157	83.54 87	56.75 182	91.08 110	73.00 273

test12				76.51 92	82.28 119	60.94 140		81.64 107		73.60 206		64.88 133	85.19 59		90.42 127	83.38 140

CNVR-MVS		78.49 71	78.59 74	78.16 73	85.86 65	67.40 88	78.12 103	81.50 108	63.92 99	77.51 148	86.56 144	68.43 99	84.82 66	73.83 55	91.61 96	82.26 174

PCF-MVS	63.80 13	72.70 142	71.69 152	75.72 103	78.10 168	60.01 151	73.04 155	81.50 108	45.34 279	79.66 120	84.35 181	65.15 131	82.65 105	48.70 247	89.38 148	84.50 111
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		75.07 101	75.64 98	73.35 132	73.42 236	47.46 236	75.20 134	81.45 110	60.05 131	85.64 44	89.26 87	58.08 194	81.80 118	69.71 85	87.97 164	90.79 17

PAPM_NR		73.91 113	74.16 112	73.16 138	81.90 125	53.50 192	81.28 63	81.40 111	66.17 75	73.30 212	83.31 196	59.96 172	83.10 98	58.45 173	81.66 248	82.87 156

TSAR-MVS + MP.		79.05 64	78.81 69	79.74 48	88.94 29	67.52 87	86.61 20	81.38 112	51.71 223	77.15 151	91.42 32	65.49 127	87.20 6	79.44 14	87.17 181	84.51 110
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EIA-MVS		68.59 190	67.16 209	72.90 146	75.18 207	55.64 179	69.39 203	81.29 113	52.44 215	64.53 286	70.69 321	60.33 170	82.30 111	54.27 211	76.31 292	80.75 200

PS-CasMVS		80.41 52	82.86 39	73.07 140	89.93 7	39.21 299	77.15 113	81.28 114	79.74 6	90.87 4	92.73 11	75.03 45	84.93 63	63.83 130	95.19 16	95.07 3

PLC	62.01 16	71.79 152	70.28 170	76.33 95	80.31 142	68.63 81	78.18 102	81.24 115	54.57 189	67.09 276	80.63 223	59.44 177	81.74 120	46.91 262	84.17 219	78.63 225
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
DPM-MVS		69.98 168	69.22 180	72.26 161	82.69 114	58.82 161	70.53 190	81.23 116	47.79 264	64.16 290	80.21 228	51.32 234	83.12 97	60.14 161	84.95 210	74.83 260

MVS_Test		69.84 170	70.71 166	67.24 225	67.49 292	43.25 271	69.87 197	81.22 117	52.69 214	71.57 235	86.68 137	62.09 153	74.51 234	66.05 110	78.74 277	83.96 122

v1240		73.06 131	73.14 132	72.84 148	74.74 215	47.27 239	71.88 172	81.11 118	51.80 222	82.28 90	84.21 182	56.22 211	82.34 110	68.82 86	87.17 181	88.91 37

PAPR		69.20 181	68.66 190	70.82 171	75.15 208	47.77 231	75.31 133	81.11 118	49.62 248	66.33 278	79.27 242	61.53 158	82.96 100	48.12 253	81.50 250	81.74 181

ZD-MVS					83.91 93	69.36 75		81.09 120	58.91 143	82.73 86	89.11 94	75.77 37	86.63 13	72.73 62	92.93 75

v1144		73.29 126	73.39 126	73.01 141	74.12 230	48.11 226	72.01 166	81.08 121	53.83 203	81.77 94	84.68 175	58.07 195	81.91 115	68.10 92	86.86 183	88.99 35

UniMVSNet (Re)		75.00 102	75.48 100	73.56 130	83.14 102	47.92 229	70.41 193	81.04 122	63.67 102	79.54 121	86.37 149	62.83 143	81.82 116	57.10 181	95.25 15	90.94 15

NCCC		78.25 75	78.04 79	78.89 63	85.61 67	69.45 72	79.80 81	80.99 123	65.77 77	75.55 181	86.25 153	67.42 107	85.42 50	70.10 79	90.88 118	81.81 180

AdaColmap		74.22 111	74.56 105	73.20 137	81.95 124	60.97 139	79.43 82	80.90 124	65.57 79	72.54 221	81.76 212	70.98 78	85.26 54	47.88 255	90.00 135	73.37 270

MSC_two_6792asdad				79.02 59	83.14 102	67.03 92		80.75 125					86.24 23	77.27 35	94.85 26	83.78 127

No_MVS				79.02 59	83.14 102	67.03 92		80.75 125					86.24 23	77.27 35	94.85 26	83.78 127

v1921920		72.96 137	72.98 137	72.89 147	74.67 218	47.58 234	71.92 170	80.69 127	51.70 224	81.69 98	83.89 186	56.58 209	82.25 112	68.34 90	87.36 173	88.82 39

zzz-MVS		83.01 25	83.63 25	81.13 35	91.16 2	78.16 14	82.72 55	80.63 128	72.08 39	84.93 56	90.79 42	74.65 49	84.42 73	80.98 4	94.75 29	80.82 196

MTGPA								80.63 128

MTAPA		83.19 20	83.87 20	81.13 35	91.16 2	78.16 14	84.87 32	80.63 128	72.08 39	84.93 56	90.79 42	74.65 49	84.42 73	80.98 4	94.75 29	80.82 196

DVP-MVS		81.15 42	83.12 35	75.24 110	86.16 56	60.78 143	83.77 42	80.58 131	72.48 34	85.83 42	90.41 58	78.57 18	85.69 44	75.86 42	94.39 43	79.24 220
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
ITE_SJBPF				80.35 44	76.94 185	73.60 42		80.48 132	66.87 67	83.64 76	86.18 154	70.25 83	79.90 156	61.12 152	88.95 155	87.56 52

CP-MVSNet		79.48 60	81.65 50	72.98 143	89.66 13	39.06 301	76.76 117	80.46 133	78.91 8	90.32 7	91.70 24	68.49 97	84.89 64	63.40 136	95.12 19	95.01 4

v144192		72.99 135	73.06 135	72.77 149	74.58 222	47.48 235	71.90 171	80.44 134	51.57 225	81.46 100	84.11 184	58.04 196	82.12 114	67.98 96	87.47 171	88.70 42

IU-MVS					86.12 58	60.90 141		80.38 135	45.49 277	81.31 101				75.64 44	94.39 43	84.65 99

CANet		73.00 134	71.84 150	76.48 93	75.82 200	61.28 135	74.81 139	80.37 136	63.17 110	62.43 301	80.50 225	61.10 165	85.16 60	64.00 126	84.34 218	83.01 153

V42		71.06 156	70.83 165	71.72 163	67.25 293	47.14 240	65.94 252	80.35 137	51.35 228	83.40 78	83.23 198	59.25 181	78.80 169	65.91 112	80.81 258	89.23 28

Anonymous20231211		75.54 94	77.19 85	70.59 174	77.67 178	45.70 253	74.73 143	80.19 138	68.80 56	82.95 81	92.91 8	66.26 120	76.76 211	58.41 174	92.77 79	89.30 26

HPM-MVS++		79.89 57	79.80 63	80.18 45	89.02 27	78.44 13	83.49 48	80.18 139	64.71 93	78.11 139	88.39 105	65.46 128	83.14 96	77.64 32	91.20 105	78.94 223

DU-MVS		74.91 104	75.57 99	72.93 145	83.50 97	45.79 249	69.47 202	80.14 140	65.22 86	81.74 96	87.08 121	61.82 155	81.07 130	56.21 190	94.98 21	91.93 8

114514_t		73.40 123	73.33 130	73.64 128	84.15 91	57.11 169	78.20 101	80.02 141	43.76 289	72.55 220	86.07 161	64.00 139	83.35 93	60.14 161	91.03 111	80.45 206

UA-Net		81.56 37	82.28 44	79.40 54	88.91 30	69.16 78	84.67 35	80.01 142	75.34 17	79.80 119	94.91 2	69.79 87	80.25 149	72.63 63	94.46 38	88.78 41

FIs		72.56 144	73.80 117	68.84 206	78.74 163	37.74 313	71.02 184	79.83 143	56.12 170	80.88 109	89.45 84	58.18 189	78.28 186	56.63 183	93.36 70	90.51 19

alignmvs		70.54 162	71.00 163	69.15 197	73.50 234	48.04 228	69.85 198	79.62 144	53.94 202	76.54 169	82.00 207	59.00 183	74.68 232	57.32 179	87.21 179	84.72 98

LCM-MVSNet-Re		69.10 183	71.57 157	61.70 272	70.37 269	34.30 337	61.45 295	79.62 144	56.81 162	89.59 8	88.16 113	68.44 98	72.94 243	42.30 282	87.33 175	77.85 240

c3_l		69.82 171	69.89 172	69.61 191	66.24 301	43.48 267	68.12 225	79.61 146	51.43 227	77.72 145	80.18 231	54.61 218	78.15 191	63.62 132	87.50 170	87.20 57

PS-MVSNAJss		77.54 78	77.35 84	78.13 75	84.88 76	66.37 98	78.55 94	79.59 147	53.48 206	86.29 35	92.43 15	62.39 149	80.25 149	67.90 99	90.61 124	87.77 48

GeoE		73.14 127	73.77 119	71.26 169	78.09 169	52.64 197	74.32 148	79.56 148	56.32 169	76.35 175	83.36 195	70.76 79	77.96 193	63.32 137	81.84 243	83.18 147

FC-MVSNet-test		73.32 125	74.78 104	68.93 203	79.21 155	36.57 319	71.82 173	79.54 149	57.63 155	82.57 87	90.38 63	59.38 180	78.99 166	57.91 177	94.56 35	91.23 12

RPSCF		75.76 91	74.37 109	79.93 46	74.81 213	77.53 20	77.53 107	79.30 150	59.44 136	78.88 128	89.80 79	71.26 76	73.09 242	57.45 178	80.89 256	89.17 30

PMVS	70.70 6	81.70 36	83.15 34	77.36 83	90.35 6	82.82 2	82.15 57	79.22 151	74.08 22	87.16 30	91.97 19	84.80 2	76.97 205	64.98 119	93.61 65	72.28 282
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
v2v482		72.55 146	72.58 141	72.43 157	72.92 248	46.72 242	71.41 177	79.13 152	55.27 177	81.17 103	85.25 172	55.41 214	81.13 127	67.25 107	85.46 197	89.43 25

Vis-MVSNet		74.85 107	74.56 105	75.72 103	81.63 130	64.64 111	76.35 121	79.06 153	62.85 112	73.33 211	88.41 104	62.54 147	79.59 160	63.94 129	82.92 232	82.94 154
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PVSNet_BlendedMVS		65.38 220	64.30 230	68.61 208	69.81 272	49.36 215	65.60 260	78.96 154	45.50 275	59.98 314	78.61 252	51.82 229	78.20 188	44.30 272	84.11 220	78.27 233

PVSNet_Blended		62.90 246	61.64 251	66.69 233	69.81 272	49.36 215	61.23 298	78.96 154	42.04 300	59.98 314	68.86 338	51.82 229	78.20 188	44.30 272	77.77 288	72.52 278

miper_ehance_all_eth		68.36 192	68.16 198	68.98 200	65.14 312	43.34 269	67.07 240	78.92 156	49.11 252	76.21 176	77.72 262	53.48 222	77.92 194	61.16 151	84.59 214	85.68 81

eth_miper_zixun_eth		69.42 176	68.73 189	71.50 167	67.99 286	46.42 245	67.58 230	78.81 157	50.72 236	78.13 138	80.34 227	50.15 240	80.34 146	60.18 159	84.65 212	87.74 49

UniMVSNet_NR-MVSNet		74.90 105	75.65 97	72.64 154	83.04 107	45.79 249	69.26 205	78.81 157	66.66 72	81.74 96	86.88 127	63.26 141	81.07 130	56.21 190	94.98 21	91.05 13

QAPM		69.18 182	69.26 178	68.94 202	71.61 256	52.58 198	80.37 71	78.79 159	49.63 247	73.51 207	85.14 173	53.66 221	79.12 164	55.11 200	75.54 297	75.11 258

TEST9					85.47 68	69.32 76	76.42 119	78.69 160	53.73 204	76.97 154	86.74 134	66.84 112	81.10 128

train_agg		76.38 87	76.55 89	75.86 102	85.47 68	69.32 76	76.42 119	78.69 160	54.00 199	76.97 154	86.74 134	66.60 116	81.10 128	72.50 66	91.56 97	77.15 243

test_8					85.09 74	67.89 85	76.26 124	78.66 162	54.00 199	76.89 159	86.72 136	66.60 116	80.89 139

agg_prior1		75.89 89	76.41 90	74.31 119	84.44 86	66.02 101	76.12 125	78.62 163	54.40 191	76.95 156	86.85 128	66.44 119	80.34 146	72.45 67	91.42 100	76.57 247

agg_prior					84.44 86	66.02 101		78.62 163		76.95 156			80.34 146

CNLPA		73.44 121	73.03 136	74.66 112	78.27 166	75.29 31	75.99 127	78.49 165	65.39 82	75.67 179	83.22 200	61.23 163	66.77 296	53.70 215	85.33 201	81.92 179

IterMVS-LS		73.01 133	73.12 134	72.66 153	73.79 233	49.90 211	71.63 174	78.44 166	58.22 145	80.51 111	86.63 141	58.15 191	79.62 158	62.51 141	88.20 158	88.48 43
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		68.81 186	68.30 192	70.35 178	74.66 220	48.61 220	66.06 251	78.32 167	50.62 237	71.48 238	75.54 277	68.75 94	79.59 160	50.55 234	78.73 278	82.86 157

3Dnovator	65.95 11	71.50 154	71.22 161	72.34 159	73.16 240	63.09 124	78.37 96	78.32 167	57.67 153	72.22 226	84.61 176	54.77 215	78.47 177	60.82 155	81.07 253	75.45 254

TranMVSNet+NR-MVSNet		76.13 88	77.66 81	71.56 165	84.61 82	42.57 277	70.98 185	78.29 169	68.67 59	83.04 79	89.26 87	72.99 63	80.75 140	55.58 198	95.47 10	91.35 11

MSDG		67.47 205	67.48 206	67.46 223	70.70 263	54.69 184	66.90 243	78.17 170	60.88 126	70.41 247	74.76 283	61.22 164	73.18 241	47.38 258	76.87 289	74.49 262

Fast-Effi-MVS+-dtu		70.00 167	68.74 188	73.77 126	73.47 235	64.53 113	71.36 178	78.14 171	55.81 174	68.84 263	74.71 286	65.36 130	75.75 219	52.00 222	79.00 275	81.03 189

IS-MVSNet		75.10 100	75.42 101	74.15 122	79.23 154	48.05 227	79.43 82	78.04 172	70.09 52	79.17 126	88.02 116	53.04 223	83.60 85	58.05 176	93.76 64	90.79 17

miper_enhance_ethall		65.86 216	65.05 229	68.28 214	61.62 330	42.62 276	64.74 267	77.97 173	42.52 298	73.42 210	72.79 305	49.66 241	77.68 198	58.12 175	84.59 214	84.54 106

save fliter					87.00 43	67.23 90	79.24 85	77.94 174	56.65 166

ambc				70.10 185	77.74 176	50.21 209	74.28 150	77.93 175		79.26 125	88.29 109	54.11 220	79.77 157	64.43 122	91.10 109	80.30 208

Effi-MVS+-dtu		75.43 95	72.28 145	84.91 2	77.05 181	83.58 1	78.47 95	77.70 176	57.68 151	74.89 188	78.13 259	64.80 134	84.26 77	56.46 187	85.32 202	86.88 61

mvs-test1		73.81 115	70.69 167	83.18 5	77.05 181	81.39 3	75.39 132	77.70 176	57.68 151	71.19 241	74.72 285	64.80 134	83.66 84	56.46 187	81.19 252	84.50 111

Regformer-2		75.32 96	74.47 107	77.88 76	74.22 226	66.65 96	72.77 158	77.54 178	68.47 61	80.44 112	72.08 308	70.60 80	80.97 134	70.08 80	84.02 222	86.01 72

BH-untuned		69.39 177	69.46 175	69.18 196	77.96 172	56.88 171	68.47 222	77.53 179	56.77 163	77.79 144	79.63 237	60.30 171	80.20 152	46.04 266	80.65 259	70.47 296

MAR-MVS		67.72 201	66.16 216	72.40 158	74.45 223	64.99 110	74.87 137	77.50 180	48.67 255	65.78 282	68.58 340	57.01 206	77.79 196	46.68 264	81.92 241	74.42 263
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
OpenMVS	62.51 15	68.76 187	68.75 187	68.78 207	70.56 267	53.91 189	78.29 98	77.35 181	48.85 254	70.22 250	83.52 189	52.65 226	76.93 206	55.31 199	81.99 240	75.49 253

NR-MVSNet		73.62 119	74.05 113	72.33 160	83.50 97	43.71 264	65.65 258	77.32 182	64.32 96	75.59 180	87.08 121	62.45 148	81.34 122	54.90 201	95.63 8	91.93 8

EPP-MVSNet		73.86 114	73.38 127	75.31 107	78.19 167	53.35 194	80.45 68	77.32 182	65.11 88	76.47 172	86.80 129	49.47 242	83.77 82	53.89 213	92.72 82	88.81 40

Anonymous20240529		72.56 144	73.79 118	68.86 205	76.89 188	45.21 255	68.80 214	77.25 184	67.16 65	76.89 159	90.44 54	65.95 123	74.19 237	50.75 231	90.00 135	87.18 58

diffmvs		67.42 206	67.50 205	67.20 226	62.26 326	45.21 255	64.87 266	77.04 185	48.21 258	71.74 229	79.70 236	58.40 188	71.17 264	64.99 118	80.27 263	85.22 83

API-MVS		70.97 158	71.51 158	69.37 192	75.20 206	55.94 176	80.99 64	76.84 186	62.48 115	71.24 239	77.51 265	61.51 159	80.96 138	52.04 221	85.76 195	71.22 291

ANet_high		67.08 208	69.94 171	58.51 296	57.55 350	27.09 359	58.43 313	76.80 187	63.56 103	82.40 89	91.93 20	59.82 175	64.98 304	50.10 237	88.86 156	83.46 138

PAPM		61.79 256	60.37 262	66.05 237	76.09 197	41.87 281	69.30 204	76.79 188	40.64 310	53.80 340	79.62 238	44.38 269	82.92 101	29.64 348	73.11 313	73.36 271

mvs_tets		78.93 65	78.67 73	79.72 49	84.81 78	73.93 39	80.65 66	76.50 189	51.98 221	87.40 24	91.86 21	76.09 35	78.53 175	68.58 88	90.20 129	86.69 64

cl22		67.14 207	66.51 214	69.03 199	63.20 322	43.46 268	66.88 244	76.25 190	49.22 250	74.48 197	77.88 261	45.49 262	77.40 201	60.64 156	84.59 214	86.24 67

anonymousdsp		78.60 68	77.80 80	81.00 37	78.01 171	74.34 37	80.09 77	76.12 191	50.51 238	89.19 10	90.88 39	71.45 74	77.78 197	73.38 58	90.60 125	90.90 16

jajsoiax		78.51 70	78.16 78	79.59 52	84.65 81	73.83 41	80.42 69	76.12 191	51.33 229	87.19 29	91.51 28	73.79 58	78.44 179	68.27 91	90.13 134	86.49 66

Gipuma		69.55 174	72.83 139	59.70 288	63.63 321	53.97 188	80.08 78	75.93 193	64.24 97	73.49 208	88.93 100	57.89 198	62.46 313	59.75 166	91.55 98	62.67 340
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LF4IMVS		67.50 203	67.31 208	68.08 215	58.86 345	61.93 129	71.43 176	75.90 194	44.67 284	72.42 223	80.20 229	57.16 201	70.44 270	58.99 170	86.12 191	71.88 285

MVSFormer		69.93 169	69.03 182	72.63 155	74.93 209	59.19 156	83.98 38	75.72 195	52.27 216	63.53 297	76.74 270	43.19 276	80.56 141	72.28 68	78.67 279	78.14 235

test_djsdf		78.88 66	78.27 76	80.70 41	81.42 131	71.24 57	83.98 38	75.72 195	52.27 216	87.37 27	92.25 16	68.04 103	80.56 141	72.28 68	91.15 107	90.32 20

SixPastTwentyTwo		75.77 90	76.34 91	74.06 123	81.69 129	54.84 182	76.47 118	75.49 197	64.10 98	87.73 18	92.24 17	50.45 238	81.30 124	67.41 102	91.46 99	86.04 71

Regformer-1		74.28 110	73.63 123	76.21 98	74.22 226	64.12 117	72.77 158	75.46 198	66.86 68	79.27 124	72.08 308	69.29 89	78.74 171	68.73 87	84.02 222	85.77 80

Regformer-4		74.64 108	73.67 121	77.55 78	74.74 215	64.49 114	72.91 156	75.42 199	67.45 63	80.24 116	72.07 310	68.98 92	80.19 153	70.29 78	80.91 254	87.98 46

RRT_test8_iter05		65.80 217	65.13 224	67.80 221	67.02 296	40.85 289	67.13 239	75.33 200	49.73 245	72.69 218	81.32 215	24.45 362	77.37 202	61.69 147	86.82 185	85.18 85

KD-MVS_self_test		66.38 214	67.51 204	62.97 264	61.76 328	34.39 336	58.11 315	75.30 201	50.84 235	77.12 153	85.42 169	56.84 207	69.44 275	51.07 229	91.16 106	85.08 89

TinyColmap		67.98 197	69.28 177	64.08 250	67.98 287	46.82 241	70.04 194	75.26 202	53.05 209	77.36 150	86.79 130	59.39 179	72.59 250	45.64 268	88.01 163	72.83 275

BH-w/o		64.81 226	64.29 231	66.36 235	76.08 198	54.71 183	65.61 259	75.23 203	50.10 242	71.05 243	71.86 315	54.33 219	79.02 165	38.20 308	76.14 293	65.36 328

MG-MVS		70.47 163	71.34 160	67.85 218	79.26 153	40.42 294	74.67 146	75.15 204	58.41 144	68.74 264	88.14 114	56.08 212	83.69 83	59.90 164	81.71 247	79.43 219

RRT_MVS		73.80 116	71.19 162	81.60 24	71.04 259	70.33 67	78.78 91	74.91 205	56.96 160	77.83 143	85.56 168	32.82 323	87.39 5	71.16 73	91.68 93	87.07 60

cl____		68.26 196	68.26 193	68.29 212	64.98 313	43.67 265	65.89 253	74.67 206	50.04 243	76.86 161	82.42 204	48.74 249	75.38 222	60.92 154	89.81 139	85.80 79

DIV-MVS_self_test		68.27 195	68.26 193	68.29 212	64.98 313	43.67 265	65.89 253	74.67 206	50.04 243	76.86 161	82.43 203	48.74 249	75.38 222	60.94 153	89.81 139	85.81 75

test_0402		78.17 76	79.48 66	74.24 120	83.50 97	59.15 159	72.52 160	74.60 208	75.34 17	88.69 13	91.81 22	75.06 44	82.37 109	65.10 117	88.68 157	81.20 185

CANet_DTU		64.04 236	63.83 233	64.66 245	68.39 280	42.97 273	73.45 153	74.50 209	52.05 220	54.78 334	75.44 280	43.99 271	70.42 271	53.49 217	78.41 282	80.59 204

USDC		62.80 247	63.10 242	61.89 271	65.19 309	43.30 270	67.42 233	74.20 210	35.80 332	72.25 225	84.48 179	45.67 260	71.95 258	37.95 310	84.97 206	70.42 298

MVS		60.62 264	59.97 264	62.58 267	68.13 285	47.28 238	68.59 217	73.96 211	32.19 347	59.94 316	68.86 338	50.48 237	77.64 199	41.85 286	75.74 294	62.83 338

EG-PatchMatch MVS		70.70 160	70.88 164	70.16 182	82.64 115	58.80 162	71.48 175	73.64 212	54.98 180	76.55 168	81.77 211	61.10 165	78.94 167	54.87 202	80.84 257	72.74 277

BH-RMVSNet		68.69 189	68.20 197	70.14 183	76.40 192	53.90 190	64.62 269	73.48 213	58.01 147	73.91 205	81.78 210	59.09 182	78.22 187	48.59 248	77.96 286	78.31 230

GBi-Net		68.30 193	68.79 185	66.81 230	73.14 241	40.68 290	71.96 167	73.03 214	54.81 181	74.72 192	90.36 66	48.63 251	75.20 226	47.12 259	85.37 198	84.54 106

test1		68.30 193	68.79 185	66.81 230	73.14 241	40.68 290	71.96 167	73.03 214	54.81 181	74.72 192	90.36 66	48.63 251	75.20 226	47.12 259	85.37 198	84.54 106

FMVSNet1		71.06 156	72.48 142	66.81 230	77.65 179	40.68 290	71.96 167	73.03 214	61.14 123	79.45 123	90.36 66	60.44 169	75.20 226	50.20 236	88.05 161	84.54 106

test_yl		65.11 222	65.09 226	65.18 242	70.59 264	40.86 287	63.22 287	72.79 217	57.91 148	68.88 261	79.07 249	42.85 279	74.89 230	45.50 269	84.97 206	79.81 213

DCV-MVSNet		65.11 222	65.09 226	65.18 242	70.59 264	40.86 287	63.22 287	72.79 217	57.91 148	68.88 261	79.07 249	42.85 279	74.89 230	45.50 269	84.97 206	79.81 213

MVS_111021_HR		72.98 136	72.97 138	72.99 142	80.82 136	65.47 104	68.81 212	72.77 219	57.67 153	75.76 178	82.38 205	71.01 77	77.17 203	61.38 148	86.15 190	76.32 248

v148		69.38 178	69.39 176	69.36 193	69.14 279	44.56 258	68.83 211	72.70 220	54.79 184	78.59 130	84.12 183	54.69 216	76.74 212	59.40 168	82.20 238	86.79 62

1314		59.83 269	58.86 272	62.74 266	65.71 306	44.78 257	68.59 217	72.63 221	33.54 345	61.05 309	67.29 346	43.62 274	71.26 263	49.49 241	67.84 338	72.19 283

pmmvs6		71.82 151	73.66 122	66.31 236	75.94 199	42.01 280	66.99 241	72.53 222	63.45 106	76.43 173	92.78 10	72.95 64	69.69 274	51.41 226	90.46 126	87.22 55

UGNet		70.20 165	69.05 181	73.65 127	76.24 194	63.64 119	75.87 128	72.53 222	61.48 120	60.93 311	86.14 157	52.37 227	77.12 204	50.67 232	85.21 203	80.17 211
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
PS-MVSNAJ		64.27 234	63.73 235	65.90 239	77.82 175	51.42 202	63.33 284	72.33 224	45.09 282	61.60 303	68.04 341	62.39 149	73.95 238	49.07 243	73.87 310	72.34 280

xiu_mvs_v2_base		64.43 231	63.96 232	65.85 240	77.72 177	51.32 203	63.63 281	72.31 225	45.06 283	61.70 302	69.66 330	62.56 145	73.93 239	49.06 244	73.91 309	72.31 281

HyFIR lowres test		63.01 244	60.47 261	70.61 173	83.04 107	54.10 187	59.93 306	72.24 226	33.67 343	69.00 258	75.63 276	38.69 303	76.93 206	36.60 319	75.45 299	80.81 199

Regformer-3		72.86 139	72.28 145	74.62 113	74.74 215	60.18 149	72.91 156	71.76 227	64.74 92	78.42 134	72.07 310	67.00 110	76.28 215	67.97 97	80.91 254	87.39 53

UniMVSNet_ETH3D		76.74 85	79.02 68	69.92 189	89.27 20	43.81 263	74.47 147	71.70 228	72.33 37	85.50 49	93.65 3	77.98 22	76.88 208	54.60 205	91.64 94	89.08 31

cascas		64.59 227	62.77 245	70.05 186	75.27 205	50.02 210	61.79 294	71.61 229	42.46 299	63.68 295	68.89 337	49.33 244	80.35 145	47.82 256	84.05 221	79.78 215

MVP-Stereo		61.56 257	59.22 268	68.58 209	79.28 152	60.44 147	69.20 206	71.57 230	43.58 292	56.42 328	78.37 255	39.57 300	76.46 214	34.86 329	60.16 351	68.86 312
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EI-MVSNet-Vis-set		72.78 140	71.87 149	75.54 105	74.77 214	59.02 160	72.24 162	71.56 231	63.92 99	78.59 130	71.59 316	66.22 121	78.60 173	67.58 100	80.32 262	89.00 34

EI-MVSNet-UG-set		72.63 143	71.68 153	75.47 106	74.67 218	58.64 165	72.02 165	71.50 232	63.53 104	78.58 132	71.39 319	65.98 122	78.53 175	67.30 106	80.18 264	89.23 28

VPA-MVSNet		68.71 188	70.37 169	63.72 254	76.13 196	38.06 311	64.10 274	71.48 233	56.60 168	74.10 202	88.31 108	64.78 136	69.72 273	47.69 257	90.15 132	83.37 141

hse-mvs2		72.32 147	70.66 168	77.31 85	83.10 106	71.77 51	69.19 207	71.45 234	54.28 193	77.89 140	78.26 256	49.04 245	79.23 162	63.62 132	89.13 153	80.92 193

AUN-MVS		70.22 164	67.88 201	77.22 86	82.96 110	71.61 52	69.08 208	71.39 235	49.17 251	71.70 230	78.07 260	37.62 310	79.21 163	61.81 144	89.15 151	80.82 196

EI-MVSNet		69.61 173	69.01 183	71.41 168	73.94 231	49.90 211	71.31 180	71.32 236	58.22 145	75.40 184	70.44 322	58.16 190	75.85 216	62.51 141	79.81 268	88.48 43

MVSTER		63.29 241	61.60 253	68.36 210	59.77 342	46.21 248	60.62 301	71.32 236	41.83 301	75.40 184	79.12 247	30.25 344	75.85 216	56.30 189	79.81 268	83.03 152

TransMVSNet (Re)		69.62 172	71.63 154	63.57 255	76.51 191	35.93 325	65.75 257	71.29 238	61.05 124	75.02 186	89.90 78	65.88 125	70.41 272	49.79 238	89.48 146	84.38 114

xiu_mvs_v1_base_debu		67.87 198	67.07 210	70.26 179	79.13 158	61.90 130	67.34 234	71.25 239	47.98 260	67.70 270	74.19 295	61.31 160	72.62 247	56.51 184	78.26 283	76.27 249

xiu_mvs_v1_base		67.87 198	67.07 210	70.26 179	79.13 158	61.90 130	67.34 234	71.25 239	47.98 260	67.70 270	74.19 295	61.31 160	72.62 247	56.51 184	78.26 283	76.27 249

xiu_mvs_v1_base_debi		67.87 198	67.07 210	70.26 179	79.13 158	61.90 130	67.34 234	71.25 239	47.98 260	67.70 270	74.19 295	61.31 160	72.62 247	56.51 184	78.26 283	76.27 249

FMVSNet2		67.48 204	68.21 196	65.29 241	73.14 241	38.94 303	68.81 212	71.21 242	54.81 181	76.73 165	86.48 146	48.63 251	74.60 233	47.98 254	86.11 192	82.35 171

h-mvs33		73.08 129	71.61 155	77.48 80	83.89 95	72.89 48	70.47 191	71.12 243	54.28 193	77.89 140	83.41 190	49.04 245	80.98 133	63.62 132	90.77 122	78.58 227

miper_lstm_enhance		61.97 253	61.63 252	62.98 263	60.04 338	45.74 252	47.53 343	70.95 244	44.04 286	73.06 214	78.84 251	39.72 298	60.33 319	55.82 194	84.64 213	82.88 155

无先验							74.82 138	70.94 245	47.75 265				76.85 209	54.47 206		72.09 284

Baseline_NR-MVSNet		70.62 161	73.19 131	62.92 265	76.97 184	34.44 335	68.84 210	70.88 246	60.25 130	79.50 122	90.53 51	61.82 155	69.11 278	54.67 204	95.27 14	85.22 83

VDD-MVS		70.81 159	71.44 159	68.91 204	79.07 161	46.51 244	67.82 228	70.83 247	61.23 122	74.07 203	88.69 102	59.86 174	75.62 221	51.11 228	90.28 128	84.61 103

pm-mvs1		68.40 191	69.85 173	64.04 252	73.10 244	39.94 296	64.61 270	70.50 248	55.52 176	73.97 204	89.33 85	63.91 140	68.38 282	49.68 240	88.02 162	83.81 126

FMVSNet3		65.00 225	65.16 221	64.52 247	69.47 275	37.56 316	66.63 246	70.38 249	51.55 226	74.72 192	83.27 197	37.89 309	74.44 235	47.12 259	85.37 198	81.57 183

TR-MVS		64.59 227	63.54 237	67.73 222	75.75 203	50.83 205	63.39 283	70.29 250	49.33 249	71.55 236	74.55 287	50.94 235	78.46 178	40.43 294	75.69 295	73.89 267

cdsmvs_eth3d_5k		17.71 336	23.62 338	0.00 355	0.00 378	0.00 379	0.00 366	70.17 251	0.00 373	0.00 374	74.25 293	68.16 101	0.00 374	0.00 372	0.00 372	0.00 370

mvs_anonymous		65.08 224	65.49 220	63.83 253	63.79 319	37.60 315	66.52 248	69.82 252	43.44 293	73.46 209	86.08 160	58.79 186	71.75 261	51.90 223	75.63 296	82.15 175

D2MVS		62.58 249	61.05 257	67.20 226	63.85 318	47.92 229	56.29 320	69.58 253	39.32 313	70.07 251	78.19 257	34.93 316	72.68 245	53.44 218	83.74 226	81.00 191

TSAR-MVS + GP.		73.08 129	71.60 156	77.54 79	78.99 162	70.73 62	74.96 136	69.38 254	60.73 128	74.39 199	78.44 254	57.72 199	82.78 102	60.16 160	89.60 143	79.11 222

GA-MVS		62.91 245	61.66 250	66.66 234	67.09 295	44.49 259	61.18 299	69.36 255	51.33 229	69.33 256	74.47 288	36.83 311	74.94 229	50.60 233	74.72 304	80.57 205

Anonymous20240521		63.55 238	66.07 217	55.99 303	66.18 303	44.04 262	68.77 215	68.80 256	46.99 269	72.57 219	85.84 165	39.87 297	50.22 335	53.40 219	92.23 88	73.71 269

ab-mvs		64.11 235	65.13 224	61.05 279	71.99 254	38.03 312	67.59 229	68.79 257	49.08 253	65.32 283	86.26 152	58.02 197	66.85 294	39.33 298	79.79 270	78.27 233

WR-MVS		71.20 155	72.48 142	67.36 224	84.98 75	35.70 327	64.43 272	68.66 258	65.05 89	81.49 99	86.43 148	57.57 200	76.48 213	50.36 235	93.32 71	89.90 21

bset_n11_16_dypcd		66.91 211	65.84 219	70.12 184	72.95 247	53.54 191	63.64 280	68.65 259	48.54 256	72.54 221	74.28 292	40.58 293	78.54 174	63.52 135	87.82 166	78.29 231

1112_ss		59.48 271	58.99 271	60.96 281	77.84 174	42.39 278	61.42 296	68.45 260	37.96 322	59.93 317	67.46 343	45.11 265	65.07 303	40.89 292	71.81 318	75.41 255

EU-MVSNet		60.82 261	60.80 259	60.86 282	68.37 281	41.16 284	72.27 161	68.27 261	26.96 361	69.08 257	75.71 275	32.09 329	67.44 288	55.59 197	78.90 276	73.97 265

CMPMVS	48.73 20	61.54 258	60.89 258	63.52 256	61.08 333	51.55 201	68.07 226	68.00 262	33.88 340	65.87 280	81.25 217	37.91 308	67.71 285	49.32 242	82.60 235	71.31 290
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
OpenMVS_ROB	54.93 17	63.23 242	63.28 239	63.07 262	69.81 272	45.34 254	68.52 220	67.14 263	43.74 290	70.61 246	79.22 244	47.90 255	72.66 246	48.75 246	73.84 311	71.21 292

VNet		64.01 237	65.15 223	60.57 283	73.28 239	35.61 328	57.60 317	67.08 264	54.61 188	66.76 277	83.37 193	56.28 210	66.87 292	42.19 283	85.20 204	79.23 221

Test_1112_low_res		58.78 276	58.69 273	59.04 293	79.41 150	38.13 310	57.62 316	66.98 265	34.74 336	59.62 318	77.56 264	42.92 278	63.65 310	38.66 303	70.73 324	75.35 257

MVS_111021_LR		72.10 149	71.82 151	72.95 144	79.53 149	73.90 40	70.45 192	66.64 266	56.87 161	76.81 163	81.76 212	68.78 93	71.76 260	61.81 144	83.74 226	73.18 272

VDDNet		71.60 153	73.13 133	67.02 229	86.29 52	41.11 285	69.97 195	66.50 267	68.72 58	74.74 191	91.70 24	59.90 173	75.81 218	48.58 249	91.72 91	84.15 120

Anonymous202405211		66.02 215	66.89 213	63.43 258	74.22 226	38.14 309	59.00 310	66.13 268	63.33 109	69.76 254	85.95 164	51.88 228	70.50 269	44.23 274	87.52 169	81.64 182

jason		64.47 230	62.84 244	69.34 195	76.91 186	59.20 155	67.15 238	65.67 269	35.29 333	65.16 284	76.74 270	44.67 267	70.68 266	54.74 203	79.28 274	78.14 235
jason: jason.
CDS-MVSNet		64.33 233	62.66 246	69.35 194	80.44 141	58.28 166	65.26 262	65.66 270	44.36 285	67.30 274	75.54 277	43.27 275	71.77 259	37.68 311	84.44 217	78.01 238
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 1792x2688		58.09 279	56.30 290	63.45 257	79.95 144	50.93 204	54.07 328	65.59 271	28.56 358	61.53 304	74.33 290	41.09 289	66.52 298	33.91 333	67.69 339	72.92 274

IterMVS-SCA-FT		67.68 202	66.07 217	72.49 156	73.34 238	58.20 167	63.80 278	65.55 272	48.10 259	76.91 158	82.64 202	45.20 263	78.84 168	61.20 150	77.89 287	80.44 207

HY-MVS	49.31 19	57.96 280	57.59 281	59.10 292	66.85 297	36.17 322	65.13 264	65.39 273	39.24 315	54.69 336	78.14 258	44.28 270	67.18 291	33.75 334	70.79 323	73.95 266

IB-MVS	49.67 18	59.69 270	56.96 285	67.90 217	68.19 284	50.30 208	61.42 296	65.18 274	47.57 266	55.83 331	67.15 347	23.77 363	79.60 159	43.56 278	79.97 266	73.79 268
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
tfpnnormal		66.48 213	67.93 199	62.16 270	73.40 237	36.65 318	63.45 282	64.99 275	55.97 171	72.82 217	87.80 117	57.06 205	69.10 279	48.31 252	87.54 168	80.72 202

CL-MVSNet_self_test		62.44 251	63.40 238	59.55 290	72.34 251	32.38 344	56.39 319	64.84 276	51.21 231	67.46 273	81.01 220	50.75 236	63.51 311	38.47 306	88.12 160	82.75 161

KD-MVS_2432*1600		52.05 307	51.58 309	53.44 308	52.11 366	31.20 349	44.88 350	64.83 277	41.53 303	64.37 287	70.03 327	15.61 374	64.20 305	36.25 321	74.61 305	64.93 332

miper_refine_blended		52.05 307	51.58 309	53.44 308	52.11 366	31.20 349	44.88 350	64.83 277	41.53 303	64.37 287	70.03 327	15.61 374	64.20 305	36.25 321	74.61 305	64.93 332

CVMVSNet		59.21 273	58.44 276	61.51 274	73.94 231	47.76 232	71.31 180	64.56 279	26.91 362	60.34 313	70.44 322	36.24 313	67.65 286	53.57 216	68.66 335	69.12 310

lupinMVS		63.36 239	61.49 254	68.97 201	74.93 209	59.19 156	65.80 256	64.52 280	34.68 338	63.53 297	74.25 293	43.19 276	70.62 267	53.88 214	78.67 279	77.10 244

ET-MVSNet_ETH3D		63.32 240	60.69 260	71.20 170	70.15 271	55.66 178	65.02 265	64.32 281	43.28 297	68.99 259	72.05 314	25.46 358	78.19 190	54.16 212	82.80 233	79.74 216

thisisatest0530		67.05 210	65.16 221	72.73 152	73.10 244	50.55 206	71.26 182	63.91 282	50.22 240	74.46 198	80.75 221	26.81 351	80.25 149	59.43 167	86.50 188	87.37 54

旧先验1					84.55 83	60.36 148		63.69 283			87.05 124	54.65 217			83.34 229	69.66 304

EPNet		69.10 183	67.32 207	74.46 114	68.33 283	61.27 136	77.56 106	63.57 284	60.95 125	56.62 327	82.75 201	51.53 232	81.24 125	54.36 210	90.20 129	80.88 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TAMVS		65.31 221	63.75 234	69.97 188	82.23 120	59.76 154	66.78 245	63.37 285	45.20 280	69.79 253	79.37 241	47.42 257	72.17 253	34.48 330	85.15 205	77.99 239

tttt0517		69.46 175	67.79 202	74.46 114	75.34 204	52.72 196	75.05 135	63.27 286	54.69 186	78.87 129	84.37 180	26.63 352	81.15 126	63.95 127	87.93 165	89.51 24

MS-PatchMatch		55.59 289	54.89 297	57.68 298	69.18 277	49.05 217	61.00 300	62.93 287	35.98 330	58.36 321	68.93 336	36.71 312	66.59 297	37.62 313	63.30 347	57.39 349

MVS_0304		62.51 250	62.27 248	63.25 259	69.39 276	48.47 221	64.05 276	62.48 288	59.69 135	54.10 339	81.04 219	45.71 259	66.31 299	41.38 289	82.58 236	74.96 259

IterMVS		63.12 243	62.48 247	65.02 244	66.34 300	52.86 195	63.81 277	62.25 289	46.57 272	71.51 237	80.40 226	44.60 268	66.82 295	51.38 227	75.47 298	75.38 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thisisatest0515		60.48 265	57.86 279	68.34 211	67.25 293	46.42 245	60.58 302	62.14 290	40.82 308	63.58 296	69.12 333	26.28 354	78.34 184	48.83 245	82.13 239	80.26 209

VPNet		65.58 219	67.56 203	59.65 289	79.72 146	30.17 353	60.27 304	62.14 290	54.19 196	71.24 239	86.63 141	58.80 185	67.62 287	44.17 275	90.87 119	81.18 186

新几何1				69.99 187	88.37 36	71.34 56		62.08 292	43.85 287	74.99 187	86.11 159	52.85 225	70.57 268	50.99 230	83.23 231	68.05 314

1121		69.23 180	68.26 193	72.12 162	88.36 37	71.40 54	68.59 217	62.06 293	43.80 288	74.75 190	86.18 154	52.92 224	76.85 209	54.47 206	83.27 230	68.12 313

pmmvs-eth3d		64.41 232	63.27 240	67.82 220	75.81 201	60.18 149	69.49 201	62.05 294	38.81 318	74.13 201	82.23 206	43.76 273	68.65 280	42.53 281	80.63 261	74.63 261

K. test v3		73.67 117	73.61 124	73.87 125	79.78 145	55.62 180	74.69 145	62.04 295	66.16 76	84.76 61	93.23 5	49.47 242	80.97 134	65.66 114	86.67 187	85.02 91

testdata				64.13 249	85.87 64	63.34 122		61.80 296	47.83 263	76.42 174	86.60 143	48.83 248	62.31 315	54.46 208	81.26 251	66.74 323

N_pmnet		52.06 306	51.11 314	54.92 305	59.64 343	71.03 58	37.42 359	61.62 297	33.68 342	57.12 323	72.10 307	37.94 307	31.03 365	29.13 352	71.35 319	62.70 339

ppachtmachnet_test		60.26 267	59.61 267	62.20 269	67.70 290	44.33 260	58.18 314	60.96 298	40.75 309	65.80 281	72.57 306	41.23 286	63.92 308	46.87 263	82.42 237	78.33 229

pmmvs4		60.78 262	59.04 270	66.00 238	73.06 246	57.67 168	64.53 271	60.22 299	36.91 327	65.96 279	77.27 266	39.66 299	68.54 281	38.87 301	74.89 303	71.80 286

CostFormer		57.35 283	56.14 291	60.97 280	63.76 320	38.43 305	67.50 231	60.22 299	37.14 326	59.12 319	76.34 273	32.78 324	71.99 257	39.12 300	69.27 332	72.47 279

LFMVS		67.06 209	67.89 200	64.56 246	78.02 170	38.25 308	70.81 189	59.60 301	65.18 87	71.06 242	86.56 144	43.85 272	75.22 225	46.35 265	89.63 142	80.21 210

test222					87.30 41	69.15 79	67.85 227	59.59 302	41.06 306	73.05 215	85.72 167	48.03 254			80.65 259	66.92 319

tpmvs		55.84 286	55.45 296	57.01 300	60.33 337	33.20 342	65.89 253	59.29 303	47.52 267	56.04 329	73.60 298	31.05 339	68.06 284	40.64 293	64.64 343	69.77 303

UnsupCasMVSNet_eth		52.26 305	53.29 303	49.16 322	55.08 360	33.67 340	50.03 336	58.79 304	37.67 323	63.43 299	74.75 284	41.82 284	45.83 342	38.59 305	59.42 353	67.98 315

EPNet_dtu		58.93 275	58.52 274	60.16 287	67.91 288	47.70 233	69.97 195	58.02 305	49.73 245	47.28 355	73.02 304	38.14 305	62.34 314	36.57 320	85.99 193	70.43 297
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DWT-MVSNet_test		53.04 300	51.12 313	58.77 294	61.23 331	38.67 304	62.16 292	57.74 306	38.24 319	51.76 344	59.07 357	21.36 365	67.40 289	44.80 271	63.76 346	70.25 299

MIMVSNet1		66.57 212	69.23 179	58.59 295	81.26 134	37.73 314	64.06 275	57.62 307	57.02 159	78.40 135	90.75 44	62.65 144	58.10 326	41.77 287	89.58 145	79.95 212

tfpn200view9		60.35 266	59.97 264	61.51 274	70.78 261	35.35 329	63.27 285	57.47 308	53.00 210	68.31 266	77.09 267	32.45 327	72.09 254	35.61 326	81.73 244	77.08 245

thres400		60.77 263	59.97 264	63.15 260	70.78 261	35.35 329	63.27 285	57.47 308	53.00 210	68.31 266	77.09 267	32.45 327	72.09 254	35.61 326	81.73 244	82.02 176

lessismore_v0				72.75 150	79.60 148	56.83 173		57.37 310		83.80 74	89.01 97	47.45 256	78.74 171	64.39 123	86.49 189	82.69 163

tpm cat1		54.02 297	52.63 305	58.19 297	64.85 315	39.86 297	66.26 250	57.28 311	32.16 348	56.90 325	70.39 324	32.75 325	65.30 302	34.29 331	58.79 354	69.41 307

thres200		57.55 282	57.02 284	59.17 291	67.89 289	34.93 332	58.91 312	57.25 312	50.24 239	64.01 291	71.46 318	32.49 326	71.39 262	31.31 340	79.57 272	71.19 293

MDA-MVSNet-bldmvs		62.34 252	61.73 249	64.16 248	61.64 329	49.90 211	48.11 341	57.24 313	53.31 207	80.95 105	79.39 240	49.00 247	61.55 317	45.92 267	80.05 265	81.03 189

thres100view900		61.17 259	61.09 256	61.39 276	72.14 253	35.01 331	65.42 261	56.99 314	55.23 178	70.71 245	79.90 233	32.07 330	72.09 254	35.61 326	81.73 244	77.08 245

thres600view7		61.82 255	61.38 255	63.12 261	71.81 255	34.93 332	64.64 268	56.99 314	54.78 185	70.33 249	79.74 235	32.07 330	72.42 252	38.61 304	83.46 228	82.02 176

tpm2		56.12 285	54.64 298	60.55 284	66.24 301	36.01 323	68.14 224	56.77 316	33.60 344	58.25 322	75.52 279	30.25 344	74.33 236	33.27 335	69.76 331	71.32 289

CR-MVSNet		58.96 274	58.49 275	60.36 285	66.37 298	48.24 224	70.93 186	56.40 317	32.87 346	61.35 305	86.66 138	33.19 321	63.22 312	48.50 250	70.17 327	69.62 305

Patchmtry		60.91 260	63.01 243	54.62 306	66.10 304	26.27 362	67.47 232	56.40 317	54.05 198	72.04 228	86.66 138	33.19 321	60.17 320	43.69 276	87.45 172	77.42 241

MDTV_nov1_ep13			54.05 300		65.54 307	29.30 355	59.00 310	55.22 319	35.96 331	52.44 342	75.98 274	30.77 341	59.62 321	38.21 307	73.33 312

baseline1		57.82 281	58.36 277	56.19 302	69.17 278	30.76 352	62.94 289	55.21 320	46.04 274	63.83 293	78.47 253	41.20 287	63.68 309	39.44 297	68.99 333	74.13 264

door-mid								55.02 321

ADS-MVSNet2		48.76 315	47.25 323	53.29 310	55.90 357	40.54 293	47.34 344	54.99 322	31.41 354	50.48 348	72.06 312	31.23 335	54.26 331	25.93 356	55.93 359	65.07 330

baseline2		55.57 290	52.74 304	64.05 251	65.26 308	44.11 261	62.38 290	54.43 323	39.03 316	51.21 345	67.35 345	33.66 319	72.45 251	37.14 316	64.22 345	75.60 252

Vis-MVSNet (Re-imp)		62.74 248	63.21 241	61.34 277	72.19 252	31.56 348	67.31 237	53.87 324	53.60 205	69.88 252	83.37 193	40.52 294	70.98 265	41.40 288	86.78 186	81.48 184

pmmvs5		52.49 304	52.58 306	52.21 314	54.99 361	32.38 344	55.45 324	53.84 325	32.15 349	55.49 333	74.81 282	38.08 306	57.37 327	34.02 332	74.40 307	66.88 320

XXY-MVS		55.19 291	57.40 283	48.56 325	64.45 316	34.84 334	51.54 334	53.59 326	38.99 317	63.79 294	79.43 239	56.59 208	45.57 343	36.92 318	71.29 320	65.25 329

PVSNet	43.83 21	51.56 309	51.17 312	52.73 311	68.34 282	38.27 307	48.22 340	53.56 327	36.41 328	54.29 337	64.94 350	34.60 317	54.20 332	30.34 343	69.87 329	65.71 327

test_method		19.26 335	19.12 339	19.71 350	9.09 374	1.91 376	7.79 365	53.44 328	1.42 369	10.27 371	35.80 365	17.42 371	25.11 369	12.44 367	24.38 368	32.10 365

SCA		58.57 278	58.04 278	60.17 286	70.17 270	41.07 286	65.19 263	53.38 329	43.34 296	61.00 310	73.48 299	45.20 263	69.38 276	40.34 295	70.31 326	70.05 300

UnsupCasMVSNet_bld		50.01 313	51.03 315	46.95 326	58.61 346	32.64 343	48.31 339	53.27 330	34.27 339	60.47 312	71.53 317	41.40 285	47.07 340	30.68 342	60.78 350	61.13 344

wuyk23d		61.97 253	66.25 215	49.12 323	58.19 349	60.77 145	66.32 249	52.97 331	55.93 173	90.62 5	86.91 126	73.07 62	35.98 363	20.63 365	91.63 95	50.62 354

door								52.91 332

FMVSNet5		55.08 292	55.54 295	53.71 307	65.80 305	33.50 341	56.22 321	52.50 333	43.72 291	61.06 308	83.38 192	25.46 358	54.87 329	30.11 345	81.64 249	72.75 276

our_test_3		56.46 284	56.51 288	56.30 301	67.70 290	39.66 298	55.36 325	52.34 334	40.57 311	63.85 292	69.91 329	40.04 296	58.22 325	43.49 279	75.29 302	71.03 295

PatchmatchNet		54.60 293	54.27 299	55.59 304	65.17 311	39.08 300	66.92 242	51.80 335	39.89 312	58.39 320	73.12 303	31.69 332	58.33 324	43.01 280	58.38 357	69.38 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FPMVS		59.43 272	60.07 263	57.51 299	77.62 180	71.52 53	62.33 291	50.92 336	57.40 157	69.40 255	80.00 232	39.14 301	61.92 316	37.47 314	66.36 340	39.09 363

Anonymous20231206		54.13 295	55.82 293	49.04 324	70.89 260	35.96 324	51.73 333	50.87 337	34.86 334	62.49 300	79.22 244	42.52 282	44.29 351	27.95 353	81.88 242	66.88 320

new-patchmatchnet		52.89 301	55.76 294	44.26 338	59.94 340	6.31 373	37.36 360	50.76 338	41.10 305	64.28 289	79.82 234	44.77 266	48.43 338	36.24 323	87.61 167	78.03 237

tpmrst		50.15 312	51.38 311	46.45 330	56.05 355	24.77 364	64.40 273	49.98 339	36.14 329	53.32 341	69.59 331	35.16 315	48.69 337	39.24 299	58.51 356	65.89 325

WTY-MVS		49.39 314	50.31 317	46.62 329	61.22 332	32.00 347	46.61 346	49.77 340	33.87 341	54.12 338	69.55 332	41.96 283	45.40 345	31.28 341	64.42 344	62.47 341

testgi		54.00 298	56.86 286	45.45 333	58.20 348	25.81 363	49.05 337	49.50 341	45.43 278	67.84 269	81.17 218	51.81 231	43.20 355	29.30 349	79.41 273	67.34 318

test20.03		55.74 288	57.51 282	50.42 316	59.89 341	32.09 346	50.63 335	49.01 342	50.11 241	65.07 285	83.23 198	45.61 261	48.11 339	30.22 344	83.82 225	71.07 294

PatchMatch-RL		58.68 277	57.72 280	61.57 273	76.21 195	73.59 43	61.83 293	49.00 343	47.30 268	61.08 307	68.97 335	50.16 239	59.01 323	36.06 325	68.84 334	52.10 353

sss		47.59 319	48.32 319	45.40 334	56.73 354	33.96 338	45.17 349	48.51 344	32.11 351	52.37 343	65.79 348	40.39 295	41.91 359	31.85 338	61.97 348	60.35 345

MIMVSNet		54.39 294	56.12 292	49.20 321	72.57 249	30.91 351	59.98 305	48.43 345	41.66 302	55.94 330	83.86 187	41.19 288	50.42 334	26.05 355	75.38 300	66.27 324

JIA-IIPM		54.03 296	51.62 308	61.25 278	59.14 344	55.21 181	59.10 309	47.72 346	50.85 234	50.31 351	85.81 166	20.10 368	63.97 307	36.16 324	55.41 362	64.55 335

Patchmatch-RL test		59.95 268	59.12 269	62.44 268	72.46 250	54.61 185	59.63 307	47.51 347	41.05 307	74.58 196	74.30 291	31.06 338	65.31 301	51.61 224	79.85 267	67.39 316

MDA-MVSNet_test_wron		52.57 303	53.49 302	49.81 318	54.24 363	36.47 320	40.48 355	46.58 348	38.13 320	75.47 183	73.32 301	41.05 291	43.85 353	40.98 291	71.20 321	69.10 311

YYNet1		52.58 302	53.50 301	49.85 317	54.15 364	36.45 321	40.53 354	46.55 349	38.09 321	75.52 182	73.31 302	41.08 290	43.88 352	41.10 290	71.14 322	69.21 309

test-LLR		50.43 311	50.69 316	49.64 319	60.76 334	41.87 281	53.18 330	45.48 350	43.41 294	49.41 352	60.47 355	29.22 349	44.73 349	42.09 284	72.14 316	62.33 342

test-mter		48.56 316	48.20 321	49.64 319	60.76 334	41.87 281	53.18 330	45.48 350	31.91 352	49.41 352	60.47 355	18.34 369	44.73 349	42.09 284	72.14 316	62.33 342

tpm		50.60 310	52.42 307	45.14 335	65.18 310	26.29 361	60.30 303	43.50 352	37.41 324	57.01 324	79.09 248	30.20 346	42.32 356	32.77 337	66.36 340	66.81 322

PatchT		53.35 299	56.47 289	43.99 339	64.19 317	17.46 370	59.15 308	43.10 353	52.11 219	54.74 335	86.95 125	29.97 347	49.98 336	43.62 277	74.40 307	64.53 336

PM-MVS		64.49 229	63.61 236	67.14 228	76.68 190	75.15 32	68.49 221	42.85 354	51.17 232	77.85 142	80.51 224	45.76 258	66.31 299	52.83 220	76.35 291	59.96 346

GG-mvs-BLEND				52.24 313	60.64 336	29.21 356	69.73 199	42.41 355		45.47 357	52.33 361	20.43 367	68.16 283	25.52 359	65.42 342	59.36 347

PMMVS		44.69 325	43.95 332	46.92 327	50.05 369	53.47 193	48.08 342	42.40 356	22.36 366	44.01 363	53.05 360	42.60 281	45.49 344	31.69 339	61.36 349	41.79 361

dp		44.09 328	44.88 329	41.72 344	58.53 347	23.18 366	54.70 327	42.38 357	34.80 335	44.25 362	65.61 349	24.48 361	44.80 348	29.77 347	49.42 364	57.18 350

E-PMN		45.17 323	45.36 326	44.60 337	50.07 368	42.75 274	38.66 357	42.29 358	46.39 273	39.55 365	51.15 362	26.00 355	45.37 346	37.68 311	76.41 290	45.69 360

PVSNet_0	36.71 22	41.12 331	40.78 334	42.14 341	59.97 339	40.13 295	40.97 353	42.24 359	30.81 356	44.86 360	49.41 363	40.70 292	45.12 347	23.15 362	34.96 366	41.16 362

TESTMET0.1,1		45.17 323	44.93 328	45.89 332	56.02 356	38.31 306	53.18 330	41.94 360	27.85 359	44.86 360	56.47 358	17.93 370	41.50 360	38.08 309	68.06 336	57.85 348

Patchmatch-test		47.93 317	49.96 318	41.84 342	57.42 351	24.26 365	48.75 338	41.49 361	39.30 314	56.79 326	73.48 299	30.48 343	33.87 364	29.29 350	72.61 314	67.39 316

gg-mvs-nofinetune		55.75 287	56.75 287	52.72 312	62.87 323	28.04 358	68.92 209	41.36 362	71.09 44	50.80 347	92.63 12	20.74 366	66.86 293	29.97 346	72.41 315	63.25 337

test0.0.03 1		47.72 318	48.31 320	45.93 331	55.53 359	29.39 354	46.40 347	41.21 363	43.41 294	55.81 332	67.65 342	29.22 349	43.77 354	25.73 358	69.87 329	64.62 334

EMVS		44.61 327	44.45 331	45.10 336	48.91 370	43.00 272	37.92 358	41.10 364	46.75 271	38.00 367	48.43 364	26.42 353	46.27 341	37.11 317	75.38 300	46.03 359

ADS-MVSNet		44.62 326	45.58 325	41.73 343	55.90 357	20.83 368	47.34 344	39.94 365	31.41 354	50.48 348	72.06 312	31.23 335	39.31 361	25.93 356	55.93 359	65.07 330

pmmvs3		46.71 320	45.09 327	51.55 315	56.76 353	48.25 223	55.78 323	39.53 366	24.13 365	50.35 350	63.40 351	15.90 373	51.08 333	29.29 350	70.69 325	55.33 352

MVS-HIRNet		45.53 322	47.29 322	40.24 345	62.29 325	26.82 360	56.02 322	37.41 367	29.74 357	43.69 364	81.27 216	33.96 318	55.48 328	24.46 361	56.79 358	38.43 364

CHOSEN 280x420		41.62 330	39.89 335	46.80 328	61.81 327	51.59 200	33.56 361	35.74 368	27.48 360	37.64 368	53.53 359	23.24 364	42.09 357	27.39 354	58.64 355	46.72 358

EPMVS		45.74 321	46.53 324	43.39 340	54.14 365	22.33 367	55.02 326	35.00 369	34.69 337	51.09 346	70.20 326	25.92 356	42.04 358	37.19 315	55.50 361	65.78 326

new_pmnet		37.55 333	39.80 336	30.79 348	56.83 352	16.46 371	39.35 356	30.65 370	25.59 363	45.26 358	61.60 354	24.54 360	28.02 367	21.60 363	52.80 363	47.90 357

PMMVS2		37.74 332	40.87 333	28.36 349	42.41 372	5.35 374	24.61 362	27.75 371	32.15 349	47.85 354	70.27 325	35.85 314	29.51 366	19.08 366	67.85 337	50.22 355

DSMNet-mixed		43.18 329	44.66 330	38.75 347	54.75 362	28.88 357	57.06 318	27.42 372	13.47 367	47.27 356	77.67 263	38.83 302	39.29 362	25.32 360	60.12 352	48.08 356

MVE	27.91 23	36.69 334	35.64 337	39.84 346	43.37 371	35.85 326	19.49 363	24.61 373	24.68 364	39.05 366	62.63 353	38.67 304	27.10 368	21.04 364	47.25 365	56.56 351
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MTMP							84.83 33	19.26 374

tmp_tt		11.98 337	14.73 340	3.72 352	2.28 375	4.62 375	19.44 364	14.50 375	0.47 370	21.55 369	9.58 368	25.78 357	4.57 371	11.61 368	27.37 367	1.96 367

DeepMVS_CX				11.83 351	15.51 373	13.86 372		11.25 376	5.76 368	20.85 370	26.46 366	17.06 372	9.22 370	9.69 369	13.82 369	12.42 366

test123		4.43 340	5.78 343	0.39 354	0.97 376	0.28 377	46.33 348	0.45 377	0.31 371	0.62 372	1.50 371	0.61 377	0.11 373	0.56 370	0.63 370	0.77 369

testmvs		4.06 341	5.28 344	0.41 353	0.64 377	0.16 378	42.54 352	0.31 378	0.26 372	0.50 373	1.40 372	0.77 376	0.17 372	0.56 370	0.55 371	0.90 368

test_blank		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet_test		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

pcd_1.5k_mvsjas		5.20 339	6.93 342	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	62.39 149	0.00 374	0.00 372	0.00 372	0.00 370

sosnet-low-res		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

sosnet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uncertanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

Regformer		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

n2								0.00 379

nn								0.00 379

ab-mvs-re		5.62 338	7.50 341	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	67.46 343	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

uanet		0.00 342	0.00 345	0.00 355	0.00 378	0.00 379	0.00 366	0.00 379	0.00 373	0.00 374	0.00 373	0.00 378	0.00 374	0.00 372	0.00 372	0.00 370

PC_three_1452									46.98 270	81.83 93	86.28 150	66.55 118	84.47 72	63.31 138	90.78 120	83.49 134

eth-test2					0.00 378

eth-test					0.00 378

OPU-MVS				78.65 66	83.44 100	66.85 94	83.62 44				86.12 158	66.82 113	86.01 31	61.72 146	89.79 141	83.08 149

test_0728_THIRD									74.03 23	85.83 42	90.41 58	75.58 39	85.69 44	77.43 33	94.74 31	84.31 116

GSMVS																70.05 300

test_part2					85.90 62	66.44 97				84.61 63

sam_mvs1												31.41 333				70.05 300

sam_mvs												31.21 337

test_post1							66.63 246				2.08 369	30.66 342	59.33 322	40.34 295

test_post											1.99 370	30.91 340	54.76 330

patchmatchnet-post											68.99 334	31.32 334	69.38 276

gm-plane-assit					62.51 324	33.91 339			37.25 325		62.71 352		72.74 244	38.70 302

test9_res														72.12 70	91.37 101	77.40 242

agg_prior2														70.70 77	90.93 114	78.55 228

test_prior4						70.14 68	77.57 105

test_prior2							75.57 130		58.92 141	76.53 170	86.78 131	67.83 105		69.81 82	92.76 80

旧先验2							71.17 183		45.11 281	78.54 133			61.28 318	59.19 169

新几何2							71.33 179

原ACMM2							74.78 142

testdata2													67.30 290	48.34 251

segment_acmp												68.30 100

testdata1							68.34 223		57.24 158

plane_prior7					85.18 71	66.21 99

plane_prior6					84.18 90	65.31 106						60.83 167

plane_prior4											89.11 94

plane_prior3						65.67 103			63.82 101	78.23 136

plane_prior2							82.74 53		65.45 80

plane_prior1					84.46 85

plane_prior						65.18 107	80.06 79		61.88 119						89.91 138

HQP5-MVS						58.80 162

HQP-NCC					82.37 116		77.32 109		59.08 137	71.58 232

ACMP_Plane					82.37 116		77.32 109		59.08 137	71.58 232

BP-MVS														67.38 104

HQP4-MVS										71.59 231			85.31 52			83.74 129

HQP2-MVS												58.09 192

NP-MVS					83.34 101	63.07 125					85.97 162

MDTV_nov1_ep13_2view						18.41 369	53.74 329		31.57 353	44.89 359		29.90 348		32.93 336		71.48 288

ACMMP++_ref															89.47 147

ACMMP++															91.96 90

Test By Simon												62.56 145

High-resolution multi-view benchmark