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		95.70 1	96.40 1	93.61 2	98.67 1	85.39 32	95.54 3	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 12	85.07 49	99.27 1	99.54 1

TDRefinement		93.52 2	93.39 3	93.88 1	95.94 14	90.26 3	95.70 2	96.46 2	90.58 7	92.86 44	96.29 16	88.16 34	94.17 93	86.07 40	98.48 18	97.22 17

LTVRE_ROB	86.10 1	93.04 3	93.44 2	91.82 23	93.73 63	85.72 31	96.79 1	95.51 6	88.86 13	95.63 7	96.99 8	84.81 69	93.16 136	91.10 1	97.53 71	96.58 29
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
abl_6		93.02 4	93.16 4	92.60 4	94.73 42	88.99 7	93.26 10	94.19 29	89.11 11	94.43 15	95.27 36	91.86 3	95.09 60	87.54 18	98.02 38	93.71 108

HPM-MVS_fast		92.50 5	92.54 6	92.37 6	95.93 15	85.81 30	92.99 11	94.23 25	85.21 31	92.51 51	95.13 40	90.65 10	95.34 50	88.06 9	98.15 33	95.95 40

SR-MVS-dyc-post		92.41 6	92.41 7	92.39 5	94.13 53	88.95 8	92.87 12	94.16 30	88.75 15	93.79 28	94.43 61	88.83 24	95.51 41	87.16 25	97.60 64	92.73 144

test1172		92.40 7	92.41 7	92.37 6	94.68 43	89.04 6	91.98 29	93.62 54	90.14 10	93.63 35	94.16 76	88.83 24	95.51 41	87.11 27	97.54 70	92.54 154

SR-MVS		92.23 8	92.34 9	91.91 17	94.89 38	87.85 11	92.51 22	93.87 46	88.20 20	93.24 38	94.02 82	90.15 17	95.67 30	86.82 29	97.34 77	92.19 169

HPM-MVS		92.13 9	92.20 11	91.91 17	95.58 25	84.67 41	93.51 6	94.85 14	82.88 54	91.77 65	93.94 91	90.55 13	95.73 27	88.50 7	98.23 29	95.33 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS_3200maxsize		92.05 10	92.24 10	91.48 24	93.02 78	85.17 34	92.47 24	95.05 13	87.65 23	93.21 39	94.39 67	90.09 18	95.08 61	86.67 30	97.60 64	94.18 88

COLMAP_ROB	83.01 3	91.97 11	91.95 12	92.04 12	93.68 64	86.15 21	93.37 8	95.10 12	90.28 8	92.11 57	95.03 42	89.75 21	94.93 65	79.95 104	98.27 27	95.04 62
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMMP		91.91 12	91.87 17	92.03 13	95.53 26	85.91 25	93.35 9	94.16 30	82.52 58	92.39 54	94.14 77	89.15 23	95.62 31	87.35 20	98.24 28	94.56 72
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
mPP-MVS		91.69 13	91.47 24	92.37 6	96.04 12	88.48 10	92.72 16	92.60 96	83.09 51	91.54 67	94.25 73	87.67 42	95.51 41	87.21 24	98.11 34	93.12 129

CP-MVS		91.67 14	91.58 21	91.96 14	95.29 31	87.62 12	93.38 7	93.36 62	83.16 50	91.06 76	94.00 83	88.26 31	95.71 28	87.28 23	98.39 21	92.55 153

XVS		91.54 15	91.36 26	92.08 10	95.64 23	86.25 19	92.64 17	93.33 64	85.07 32	89.99 93	94.03 81	86.57 55	95.80 21	87.35 20	97.62 62	94.20 86

MTAPA		91.52 16	91.60 20	91.29 29	96.59 4	86.29 17	92.02 28	91.81 116	84.07 37	92.00 60	94.40 65	86.63 53	95.28 53	88.59 5	98.31 24	92.30 161

UA-Net		91.49 17	91.53 22	91.39 26	94.98 35	82.95 54	93.52 5	92.79 91	88.22 19	88.53 126	97.64 2	83.45 81	94.55 81	86.02 43	98.60 13	96.67 26

ACMMPR		91.49 17	91.35 28	91.92 16	95.74 19	85.88 27	92.58 20	93.25 72	81.99 63	91.40 70	94.17 75	87.51 43	95.87 15	87.74 11	97.76 54	93.99 94

LPG-MVS_test		91.47 19	91.68 18	90.82 38	94.75 40	81.69 59	90.00 51	94.27 22	82.35 60	93.67 33	94.82 48	91.18 5	95.52 39	85.36 47	98.73 7	95.23 58

region2R		91.44 20	91.30 32	91.87 19	95.75 18	85.90 26	92.63 19	93.30 69	81.91 65	90.88 81	94.21 74	87.75 40	95.87 15	87.60 16	97.71 58	93.83 101

HFP-MVS		91.30 21	91.39 25	91.02 33	95.43 28	84.66 42	92.58 20	93.29 70	81.99 63	91.47 68	93.96 87	88.35 29	95.56 34	87.74 11	97.74 56	92.85 139

zzz-MVS		91.27 22	91.26 33	91.29 29	96.59 4	86.29 17	88.94 76	91.81 116	84.07 37	92.00 60	94.40 65	86.63 53	95.28 53	88.59 5	98.31 24	92.30 161

ZNCC-MVS		91.26 23	91.34 29	91.01 35	95.73 20	83.05 52	92.18 26	94.22 26	80.14 85	91.29 73	93.97 84	87.93 39	95.87 15	88.65 4	97.96 45	94.12 91

APDe-MVS		91.22 24	91.92 13	89.14 64	92.97 80	78.04 90	92.84 14	94.14 34	83.33 48	93.90 24	95.73 25	88.77 26	96.41 1	87.60 16	97.98 42	92.98 134

PGM-MVS		91.20 25	90.95 41	91.93 15	95.67 22	85.85 28	90.00 51	93.90 43	80.32 82	91.74 66	94.41 64	88.17 33	95.98 9	86.37 33	97.99 40	93.96 96

SteuartSystems-ACMMP		91.16 26	91.36 26	90.55 42	93.91 59	80.97 66	91.49 35	93.48 60	82.82 55	92.60 50	93.97 84	88.19 32	96.29 4	87.61 15	98.20 32	94.39 81
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		91.14 27	90.91 42	91.83 21	96.18 11	86.88 14	92.20 25	93.03 82	82.59 57	88.52 127	94.37 68	86.74 52	95.41 47	86.32 34	98.21 30	93.19 127
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
GST-MVS		90.96 28	91.01 38	90.82 38	95.45 27	82.73 55	91.75 33	93.74 49	80.98 76	91.38 71	93.80 94	87.20 47	95.80 21	87.10 28	97.69 59	93.93 97

MP-MVS-pluss		90.81 29	91.08 35	89.99 51	95.97 13	79.88 72	88.13 90	94.51 20	75.79 137	92.94 41	94.96 43	88.36 28	95.01 63	90.70 2	98.40 20	95.09 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMH+	77.89 11	90.73 30	91.50 23	88.44 77	93.00 79	76.26 116	89.65 62	95.55 5	87.72 22	93.89 26	94.94 44	91.62 4	93.44 126	78.35 121	98.76 4	95.61 47

ACMMP_NAP		90.65 31	91.07 37	89.42 60	95.93 15	79.54 77	89.95 54	93.68 53	77.65 114	91.97 62	94.89 45	88.38 27	95.45 45	89.27 3	97.87 50	93.27 123

ACMM	79.39 9	90.65 31	90.99 39	89.63 56	95.03 34	83.53 47	89.62 63	93.35 63	79.20 96	93.83 27	93.60 101	90.81 8	92.96 142	85.02 51	98.45 19	92.41 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		90.60 33	90.34 49	91.38 27	89.03 175	84.23 45	93.58 4	94.68 17	90.65 6	90.33 88	93.95 90	84.50 71	95.37 48	80.87 94	95.50 138	94.53 75

ACMP	79.16 10	90.54 34	90.60 47	90.35 46	94.36 45	80.98 65	89.16 72	94.05 37	79.03 99	92.87 43	93.74 98	90.60 12	95.21 57	82.87 73	98.76 4	94.87 63
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DPE-MVS		90.53 35	91.08 35	88.88 66	93.38 70	78.65 86	89.15 73	94.05 37	84.68 35	93.90 24	94.11 79	88.13 35	96.30 3	84.51 57	97.81 52	91.70 184
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
#test#		90.49 36	90.31 50	91.02 33	95.43 28	84.66 42	90.65 41	93.29 70	77.00 121	91.47 68	93.96 87	88.35 29	95.56 34	84.88 52	97.74 56	92.85 139

SED-MVS		90.46 37	91.64 19	86.93 94	94.18 48	72.65 134	90.47 46	93.69 51	83.77 41	94.11 22	94.27 69	90.28 15	95.84 19	86.03 41	97.92 46	92.29 163

SMA-MVS		90.31 38	90.48 48	89.83 52	95.31 30	79.52 78	90.98 39	93.24 73	75.37 144	92.84 45	95.28 35	85.58 65	96.09 7	87.92 10	97.76 54	93.88 99
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		90.27 39	90.80 44	88.68 72	92.86 84	77.09 105	91.19 38	95.74 4	81.38 71	92.28 55	93.80 94	86.89 50	94.64 74	85.52 45	97.51 72	94.30 84

v7n		90.13 40	90.96 40	87.65 89	91.95 109	71.06 159	89.99 53	93.05 79	86.53 26	94.29 18	96.27 17	82.69 89	94.08 97	86.25 37	97.63 61	97.82 8

PMVS	80.48 6	90.08 41	90.66 46	88.34 80	96.71 3	92.97 1	90.31 48	89.57 175	88.51 18	90.11 90	95.12 41	90.98 7	88.92 243	77.55 135	97.07 84	83.13 308
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DVP-MVS		90.06 42	91.32 30	86.29 107	94.16 51	72.56 139	90.54 43	91.01 137	83.61 44	93.75 30	94.65 53	89.76 19	95.78 24	86.42 31	97.97 43	90.55 210
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
PS-CasMVS		90.06 42	91.92 13	84.47 145	96.56 7	58.83 277	89.04 74	92.74 93	91.40 4	96.12 3	96.06 22	87.23 46	95.57 33	79.42 112	98.74 6	99.00 2

PEN-MVS		90.03 44	91.88 16	84.48 144	96.57 6	58.88 274	88.95 75	93.19 74	91.62 3	96.01 5	96.16 20	87.02 48	95.60 32	78.69 117	98.72 9	98.97 3

OurMVSNet-221017-0		90.01 45	89.74 54	90.83 37	93.16 76	80.37 69	91.91 32	93.11 76	81.10 74	95.32 9	97.24 5	72.94 199	94.85 68	85.07 49	97.78 53	97.26 15

DTE-MVSNet		89.98 46	91.91 15	84.21 152	96.51 8	57.84 282	88.93 77	92.84 90	91.92 2	96.16 2	96.23 18	86.95 49	95.99 8	79.05 114	98.57 15	98.80 6

XVG-ACMP-BASELINE		89.98 46	89.84 53	90.41 44	94.91 37	84.50 44	89.49 68	93.98 39	79.68 89	92.09 58	93.89 92	83.80 77	93.10 140	82.67 75	98.04 35	93.64 113

3Dnovator+	83.92 2	89.97 48	89.66 55	90.92 36	91.27 132	81.66 62	91.25 36	94.13 35	88.89 12	88.83 121	94.26 72	77.55 146	95.86 18	84.88 52	95.87 125	95.24 57

WR-MVS_H		89.91 49	91.31 31	85.71 123	96.32 10	62.39 234	89.54 66	93.31 67	90.21 9	95.57 8	95.66 28	81.42 113	95.90 13	80.94 93	98.80 3	98.84 5

OPM-MVS		89.80 50	89.97 51	89.27 62	94.76 39	79.86 73	86.76 112	92.78 92	78.78 102	92.51 51	93.64 100	88.13 35	93.84 107	84.83 54	97.55 67	94.10 92

mvs_tets		89.78 51	89.27 62	91.30 28	93.51 66	84.79 39	89.89 56	90.63 145	70.00 212	94.55 14	96.67 11	87.94 38	93.59 118	84.27 59	95.97 121	95.52 48

anonymousdsp		89.73 52	88.88 69	92.27 9	89.82 166	86.67 15	90.51 45	90.20 162	69.87 213	95.06 10	96.14 21	84.28 73	93.07 141	87.68 13	96.34 109	97.09 19

test_djsdf		89.62 53	89.01 65	91.45 25	92.36 95	82.98 53	91.98 29	90.08 165	71.54 191	94.28 20	96.54 13	81.57 111	94.27 84	86.26 35	96.49 104	97.09 19

XVG-OURS-SEG-HR		89.59 54	89.37 60	90.28 47	94.47 44	85.95 24	86.84 108	93.91 42	80.07 86	86.75 158	93.26 104	93.64 2	90.93 199	84.60 56	90.75 251	93.97 95

APD-MVS		89.54 55	89.63 56	89.26 63	92.57 89	81.34 64	90.19 49	93.08 78	80.87 77	91.13 74	93.19 105	86.22 60	95.97 10	82.23 79	97.18 82	90.45 212
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
testtj		89.51 56	89.48 59	89.59 58	92.26 99	80.80 67	90.14 50	93.54 58	83.37 47	90.57 85	92.55 127	84.99 67	96.15 5	81.26 88	96.61 99	91.83 180

jajsoiax		89.41 57	88.81 71	91.19 32	93.38 70	84.72 40	89.70 58	90.29 159	69.27 216	94.39 16	96.38 15	86.02 63	93.52 122	83.96 61	95.92 123	95.34 52

CPTT-MVS		89.39 58	88.98 67	90.63 41	95.09 33	86.95 13	92.09 27	92.30 102	79.74 88	87.50 143	92.38 130	81.42 113	93.28 131	83.07 70	97.24 80	91.67 185

ACMH	76.49 14	89.34 59	91.14 34	83.96 158	92.50 92	70.36 164	89.55 64	93.84 47	81.89 66	94.70 12	95.44 33	90.69 9	88.31 253	83.33 68	98.30 26	93.20 126
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		89.27 60	90.91 42	84.37 146	96.34 9	58.61 279	88.66 85	92.06 107	90.78 5	95.67 6	95.17 39	81.80 109	95.54 38	79.00 115	98.69 10	98.95 4

XVG-OURS		89.18 61	88.83 70	90.23 48	94.28 46	86.11 23	85.91 123	93.60 57	80.16 84	89.13 117	93.44 102	83.82 76	90.98 197	83.86 63	95.30 146	93.60 115

DeepC-MVS	82.31 4	89.15 62	89.08 64	89.37 61	93.64 65	79.07 81	88.54 86	94.20 27	73.53 162	89.71 102	94.82 48	85.09 66	95.77 26	84.17 60	98.03 37	93.26 124
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
UniMVSNet_ETH3D		89.12 63	90.72 45	84.31 150	97.00 2	64.33 212	89.67 61	88.38 192	88.84 14	94.29 18	97.57 3	90.48 14	91.26 189	72.57 188	97.65 60	97.34 14

MSP-MVS		89.08 64	88.16 75	91.83 21	95.76 17	86.14 22	92.75 15	93.90 43	78.43 107	89.16 116	92.25 137	72.03 211	96.36 2	88.21 8	90.93 246	92.98 134
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
xxxxxxxxxxxxxcwj		89.04 65	89.13 63	88.79 68	93.75 61	77.44 98	86.31 120	95.27 10	70.80 200	92.28 55	93.80 94	86.89 50	94.64 74	85.52 45	97.51 72	94.30 84

SD-MVS		88.96 66	89.88 52	86.22 110	91.63 119	77.07 106	89.82 57	93.77 48	78.90 100	92.88 42	92.29 135	86.11 61	90.22 221	86.24 38	97.24 80	91.36 192
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
HPM-MVS++		88.93 67	88.45 74	90.38 45	94.92 36	85.85 28	89.70 58	91.27 130	78.20 109	86.69 161	92.28 136	80.36 124	95.06 62	86.17 39	96.49 104	90.22 215

ETH3D-3000-0.1		88.85 68	88.96 68	88.52 73	91.94 111	77.27 104	88.71 83	95.26 11	76.08 128	90.66 84	92.69 122	84.48 72	93.83 108	83.38 67	97.48 74	94.47 76

test_0402		88.65 69	89.58 58	85.88 119	92.55 90	72.22 147	84.01 153	89.44 177	88.63 17	94.38 17	95.77 24	86.38 59	93.59 118	79.84 105	95.21 147	91.82 181

DP-MVS		88.60 70	89.01 65	87.36 92	91.30 130	77.50 97	87.55 97	92.97 85	87.95 21	89.62 106	92.87 116	84.56 70	93.89 104	77.65 133	96.62 98	90.70 204

Anonymous20231211		88.40 71	89.62 57	84.73 140	90.46 154	65.27 203	88.86 79	93.02 83	87.15 24	93.05 40	97.10 6	82.28 97	92.02 169	76.70 143	97.99 40	96.88 23

PS-MVSNAJss		88.31 72	87.90 77	89.56 59	93.31 72	77.96 91	87.94 93	91.97 110	70.73 202	94.19 21	96.67 11	76.94 155	94.57 78	83.07 70	96.28 111	96.15 32

OMC-MVS		88.19 73	87.52 82	90.19 49	91.94 111	81.68 61	87.49 99	93.17 75	76.02 131	88.64 124	91.22 159	84.24 74	93.37 129	77.97 131	97.03 85	95.52 48

TSAR-MVS + MP.		88.14 74	87.82 78	89.09 65	95.72 21	76.74 110	92.49 23	91.19 133	67.85 234	86.63 162	94.84 47	79.58 130	95.96 11	87.62 14	94.50 170	94.56 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RPSCF		88.00 75	86.93 93	91.22 31	90.08 160	89.30 5	89.68 60	91.11 134	79.26 95	89.68 103	94.81 51	82.44 92	87.74 257	76.54 145	88.74 273	96.61 28

AllTest		87.97 76	87.40 85	89.68 54	91.59 120	83.40 48	89.50 67	95.44 7	79.47 91	88.00 136	93.03 108	82.66 90	91.47 181	70.81 197	96.14 117	94.16 89

TranMVSNet+NR-MVSNet		87.86 77	88.76 72	85.18 132	94.02 56	64.13 213	84.38 148	91.29 129	84.88 34	92.06 59	93.84 93	86.45 57	93.73 110	73.22 179	98.66 11	97.69 9

nrg030		87.85 78	88.49 73	85.91 117	90.07 162	69.73 167	87.86 94	94.20 27	74.04 156	92.70 49	94.66 52	85.88 64	91.50 180	79.72 106	97.32 78	96.50 30

ETH3D cwj APD-0.16		87.83 79	87.62 81	88.47 75	91.21 133	78.20 88	87.26 101	94.54 19	72.05 187	88.89 118	92.31 134	83.86 75	94.24 87	81.59 86	96.87 89	92.97 137

CNVR-MVS		87.81 80	87.68 80	88.21 82	92.87 82	77.30 103	85.25 133	91.23 131	77.31 118	87.07 151	91.47 156	82.94 86	94.71 71	84.67 55	96.27 113	92.62 151

HQP_MVS		87.75 81	87.43 84	88.70 71	93.45 67	76.42 114	89.45 69	93.61 55	79.44 93	86.55 163	92.95 113	74.84 174	95.22 55	80.78 96	95.83 126	94.46 77

NCCC		87.36 82	86.87 94	88.83 67	92.32 98	78.84 84	86.58 116	91.09 135	78.77 103	84.85 193	90.89 173	80.85 118	95.29 51	81.14 90	95.32 143	92.34 159

DeepPCF-MVS	81.24 5	87.28 83	86.21 103	90.49 43	91.48 127	84.90 37	83.41 173	92.38 101	70.25 208	89.35 114	90.68 180	82.85 88	94.57 78	79.55 108	95.95 122	92.00 174

SixPastTwentyTwo		87.20 84	87.45 83	86.45 103	92.52 91	69.19 176	87.84 95	88.05 198	81.66 68	94.64 13	96.53 14	65.94 239	94.75 70	83.02 72	96.83 92	95.41 50

test_part1		87.15 85	87.82 78	85.15 133	88.88 179	63.04 224	87.98 91	94.85 14	82.52 58	93.61 36	95.73 25	67.51 230	95.71 28	80.48 101	98.83 2	96.69 25

UniMVSNet (Re)		86.87 86	86.98 92	86.55 101	93.11 77	68.48 180	83.80 162	92.87 87	80.37 80	89.61 108	91.81 148	77.72 143	94.18 91	75.00 162	98.53 16	96.99 22

Vis-MVSNet		86.86 87	86.58 97	87.72 87	92.09 105	77.43 100	87.35 100	92.09 106	78.87 101	84.27 208	94.05 80	78.35 138	93.65 112	80.54 100	91.58 234	92.08 171
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_NR-MVSNet		86.84 88	87.06 88	86.17 114	92.86 84	67.02 191	82.55 196	91.56 120	83.08 52	90.92 78	91.82 147	78.25 139	93.99 99	74.16 167	98.35 22	97.49 13

DU-MVS		86.80 89	86.99 91	86.21 112	93.24 74	67.02 191	83.16 182	92.21 103	81.73 67	90.92 78	91.97 141	77.20 149	93.99 99	74.16 167	98.35 22	97.61 10

Regformer-2		86.74 90	86.08 105	88.73 69	84.18 265	79.20 80	83.52 168	89.33 179	83.33 48	89.92 97	85.07 275	83.23 84	93.16 136	83.39 66	92.72 213	93.83 101

DROMVSNet		86.66 91	87.04 90	85.54 126	88.38 188	68.42 181	88.88 78	96.08 3	77.93 112	83.41 219	88.62 217	82.91 87	95.35 49	81.39 87	95.75 131	92.86 138

IS-MVSNet		86.66 91	86.82 96	86.17 114	92.05 107	66.87 193	91.21 37	88.64 188	86.30 28	89.60 109	92.59 124	69.22 222	94.91 66	73.89 171	97.89 49	96.72 24

v10		86.54 93	87.10 87	84.84 137	88.16 194	63.28 221	86.64 115	92.20 104	75.42 143	92.81 47	94.50 57	74.05 184	94.06 98	83.88 62	96.28 111	97.17 18

pmmvs6		86.52 94	88.06 76	81.90 198	92.22 102	62.28 237	84.66 141	89.15 181	83.54 46	89.85 98	97.32 4	88.08 37	86.80 269	70.43 205	97.30 79	96.62 27

Regformer-4		86.41 95	85.71 113	88.52 73	84.27 261	77.57 96	84.07 151	88.00 200	82.82 55	89.84 99	85.48 263	82.06 101	92.77 148	83.83 64	91.04 240	95.22 60

PHI-MVS		86.38 96	85.81 110	88.08 83	88.44 187	77.34 101	89.35 71	93.05 79	73.15 173	84.76 194	87.70 230	78.87 134	94.18 91	80.67 98	96.29 110	92.73 144

test_prior3		86.31 97	86.31 100	86.32 105	90.59 151	71.99 149	83.37 174	92.85 88	75.43 141	84.58 197	91.57 152	81.92 107	94.17 93	79.54 109	96.97 86	92.80 141

CSCG		86.26 98	86.47 98	85.60 125	90.87 144	74.26 125	87.98 91	91.85 113	80.35 81	89.54 112	88.01 224	79.09 132	92.13 163	75.51 155	95.06 154	90.41 213

DeepC-MVS_fast	80.27 8	86.23 99	85.65 115	87.96 86	91.30 130	76.92 107	87.19 102	91.99 109	70.56 203	84.96 189	90.69 179	80.01 127	95.14 58	78.37 120	95.78 130	91.82 181
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v8		86.22 100	86.83 95	84.36 148	87.82 198	62.35 236	86.42 118	91.33 128	76.78 123	92.73 48	94.48 59	73.41 193	93.72 111	83.10 69	95.41 139	97.01 21

Anonymous20240529		86.20 101	87.13 86	83.42 170	90.19 158	64.55 210	84.55 143	90.71 142	85.85 29	89.94 96	95.24 38	82.13 99	90.40 216	69.19 216	96.40 107	95.31 54

CDPH-MVS		86.17 102	85.54 116	88.05 85	92.25 100	75.45 119	83.85 159	92.01 108	65.91 249	86.19 170	91.75 150	83.77 78	94.98 64	77.43 138	96.71 96	93.73 107

Regformer-1		86.00 103	85.50 117	87.49 90	84.18 265	76.90 108	83.52 168	87.94 202	82.18 62	89.19 115	85.07 275	82.28 97	91.89 173	82.40 77	92.72 213	93.69 109

NR-MVSNet		86.00 103	86.22 102	85.34 130	93.24 74	64.56 209	82.21 209	90.46 148	80.99 75	88.42 129	91.97 141	77.56 145	93.85 105	72.46 189	98.65 12	97.61 10

train_agg		85.98 105	85.28 120	88.07 84	92.34 96	79.70 75	83.94 155	90.32 153	65.79 250	84.49 199	90.97 169	81.93 105	93.63 114	81.21 89	96.54 102	90.88 199

FC-MVSNet-test		85.93 106	87.05 89	82.58 189	92.25 100	56.44 294	85.75 127	93.09 77	77.33 117	91.94 63	94.65 53	74.78 176	93.41 128	75.11 161	98.58 14	97.88 7

Effi-MVS+-dtu		85.82 107	83.38 153	93.14 3	87.13 213	91.15 2	87.70 96	88.42 190	74.57 151	83.56 216	85.65 260	78.49 136	94.21 89	72.04 191	92.88 208	94.05 93

agg_prior1		85.72 108	85.20 121	87.28 93	91.58 123	77.69 94	83.69 165	90.30 156	66.29 246	84.32 203	91.07 166	82.13 99	93.18 134	81.02 91	96.36 108	90.98 195

TAPA-MVS	77.73 12	85.71 109	84.83 127	88.37 79	88.78 181	79.72 74	87.15 104	93.50 59	69.17 217	85.80 180	89.56 201	80.76 119	92.13 163	73.21 184	95.51 137	93.25 125
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
canonicalmvs		85.50 110	86.14 104	83.58 167	87.97 195	67.13 189	87.55 97	94.32 21	73.44 164	88.47 128	87.54 233	86.45 57	91.06 196	75.76 154	93.76 185	92.54 154

EPP-MVSNet		85.47 111	85.04 123	86.77 98	91.52 126	69.37 170	91.63 34	87.98 201	81.51 70	87.05 152	91.83 146	66.18 238	95.29 51	70.75 200	96.89 88	95.64 45

GeoE		85.45 112	85.81 110	84.37 146	90.08 160	67.07 190	85.86 126	91.39 127	72.33 184	87.59 141	90.25 190	84.85 68	92.37 157	78.00 129	91.94 228	93.66 110

FIs		85.35 113	86.27 101	82.60 188	91.86 114	57.31 287	85.10 135	93.05 79	75.83 136	91.02 77	93.97 84	73.57 189	92.91 146	73.97 170	98.02 38	97.58 12

casdiffmvs		85.21 114	85.85 109	83.31 172	86.17 236	62.77 228	83.03 184	93.93 41	74.69 150	88.21 134	92.68 123	82.29 96	91.89 173	77.87 132	93.75 187	95.27 56

baseline		85.20 115	85.93 107	83.02 177	86.30 231	62.37 235	84.55 143	93.96 40	74.48 153	87.12 147	92.03 140	82.30 95	91.94 170	78.39 119	94.21 176	94.74 68

K. test v3		85.14 116	84.73 128	86.37 104	91.13 138	69.63 169	85.45 131	76.68 296	84.06 39	92.44 53	96.99 8	62.03 258	94.65 73	80.58 99	93.24 198	94.83 67

EI-MVSNet-Vis-set		85.12 117	84.53 136	86.88 95	84.01 268	72.76 133	83.91 158	85.18 240	80.44 79	88.75 122	85.49 262	80.08 126	91.92 171	82.02 80	90.85 249	95.97 38

ETH3 D test6400		85.09 118	84.87 126	85.75 122	90.80 146	69.34 171	85.90 124	93.31 67	65.43 256	86.11 173	89.95 196	80.92 117	94.86 67	75.90 153	95.57 136	93.05 131

Regformer-3		85.06 119	84.67 133	86.22 110	84.27 261	73.43 129	84.07 151	85.26 238	80.77 78	88.62 125	85.48 263	80.56 122	90.39 217	81.99 81	91.04 240	94.85 65

EI-MVSNet-UG-set		85.04 120	84.44 138	86.85 96	83.87 271	72.52 141	83.82 160	85.15 241	80.27 83	88.75 122	85.45 266	79.95 128	91.90 172	81.92 83	90.80 250	96.13 33

X-MVStestdata		85.04 120	82.70 163	92.08 10	95.64 23	86.25 19	92.64 17	93.33 64	85.07 32	89.99 93	16.05 365	86.57 55	95.80 21	87.35 20	97.62 62	94.20 86

MSLP-MVS++		85.00 122	86.03 106	81.90 198	91.84 115	71.56 157	86.75 113	93.02 83	75.95 134	87.12 147	89.39 202	77.98 140	89.40 239	77.46 136	94.78 163	84.75 285

F-COLMAP		84.97 123	83.42 152	89.63 56	92.39 94	83.40 48	88.83 80	91.92 112	73.19 172	80.18 266	89.15 208	77.04 153	93.28 131	65.82 243	92.28 219	92.21 168

3Dnovator	80.37 7	84.80 124	84.71 131	85.06 135	86.36 229	74.71 122	88.77 82	90.00 167	75.65 139	84.96 189	93.17 106	74.06 183	91.19 191	78.28 123	91.09 238	89.29 231

IterMVS-LS		84.73 125	84.98 124	83.96 158	87.35 208	63.66 216	83.25 178	89.88 169	76.06 129	89.62 106	92.37 133	73.40 195	92.52 153	78.16 126	94.77 165	95.69 43
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_111021_HR		84.63 126	84.34 142	85.49 129	90.18 159	75.86 118	79.23 254	87.13 212	73.35 165	85.56 184	89.34 203	83.60 80	90.50 214	76.64 144	94.05 181	90.09 220

HQP-MVS		84.61 127	84.06 145	86.27 108	91.19 134	70.66 161	84.77 137	92.68 94	73.30 168	80.55 259	90.17 194	72.10 207	94.61 76	77.30 139	94.47 171	93.56 117

v1192		84.57 128	84.69 132	84.21 152	87.75 200	62.88 226	83.02 185	91.43 124	69.08 219	89.98 95	90.89 173	72.70 203	93.62 117	82.41 76	94.97 158	96.13 33

mvs-test1		84.55 129	82.12 173	91.84 20	87.13 213	89.54 4	85.05 136	88.42 190	74.57 151	80.60 256	82.98 298	78.49 136	93.98 101	72.04 191	89.77 260	92.00 174

FMVSNet1		84.55 129	85.45 118	81.85 200	90.27 157	61.05 249	86.83 109	88.27 195	78.57 106	89.66 105	95.64 29	75.43 167	90.68 209	69.09 217	95.33 142	93.82 103

v1144		84.54 131	84.72 130	84.00 156	87.67 202	62.55 232	82.97 186	90.93 138	70.32 207	89.80 100	90.99 168	73.50 190	93.48 124	81.69 85	94.65 168	95.97 38

Gipuma		84.44 132	86.33 99	78.78 247	84.20 264	73.57 128	89.55 64	90.44 149	84.24 36	84.38 201	94.89 45	76.35 164	80.40 317	76.14 149	96.80 94	82.36 316
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MCST-MVS		84.36 133	83.93 148	85.63 124	91.59 120	71.58 156	83.52 168	92.13 105	61.82 277	83.96 210	89.75 200	79.93 129	93.46 125	78.33 122	94.34 174	91.87 179

VDDNet		84.35 134	85.39 119	81.25 208	95.13 32	59.32 267	85.42 132	81.11 270	86.41 27	87.41 144	96.21 19	73.61 188	90.61 212	66.33 237	96.85 90	93.81 106

ETV-MVS		84.31 135	83.91 149	85.52 127	88.58 183	70.40 163	84.50 147	93.37 61	78.76 104	84.07 209	78.72 335	80.39 123	95.13 59	73.82 173	92.98 206	91.04 194

v1240		84.30 136	84.51 137	83.65 165	87.65 203	61.26 245	82.85 189	91.54 121	67.94 232	90.68 83	90.65 182	71.71 213	93.64 113	82.84 74	94.78 163	96.07 35

MVS_111021_LR		84.28 137	83.76 150	85.83 121	89.23 172	83.07 51	80.99 228	83.56 255	72.71 178	86.07 174	89.07 210	81.75 110	86.19 279	77.11 141	93.36 193	88.24 244

hse-mvs3		84.25 138	82.76 162	88.72 70	91.82 117	82.60 56	84.00 154	84.98 247	71.27 193	86.70 159	90.55 184	63.04 254	93.92 103	78.26 124	94.20 177	89.63 222

v144192		84.24 139	84.41 139	83.71 164	87.59 205	61.57 241	82.95 187	91.03 136	67.82 235	89.80 100	90.49 185	73.28 196	93.51 123	81.88 84	94.89 161	96.04 37

v1921920		84.23 140	84.37 141	83.79 161	87.64 204	61.71 240	82.91 188	91.20 132	67.94 232	90.06 91	90.34 187	72.04 210	93.59 118	82.32 78	94.91 159	96.07 35

VDD-MVS		84.23 140	84.58 135	83.20 174	91.17 137	65.16 205	83.25 178	84.97 248	79.79 87	87.18 146	94.27 69	74.77 177	90.89 202	69.24 213	96.54 102	93.55 119

v2v482		84.09 142	84.24 143	83.62 166	87.13 213	61.40 242	82.71 192	89.71 171	72.19 186	89.55 110	91.41 157	70.70 218	93.20 133	81.02 91	93.76 185	96.25 31

EG-PatchMatch MVS		84.08 143	84.11 144	83.98 157	92.22 102	72.61 138	82.20 211	87.02 217	72.63 179	88.86 119	91.02 167	78.52 135	91.11 194	73.41 178	91.09 238	88.21 245

DP-MVS Recon		84.05 144	83.22 155	86.52 102	91.73 118	75.27 120	83.23 180	92.40 99	72.04 188	82.04 237	88.33 220	77.91 142	93.95 102	66.17 238	95.12 152	90.34 214

TransMVSNet (Re)		84.02 145	85.74 112	78.85 246	91.00 141	55.20 304	82.29 205	87.26 208	79.65 90	88.38 131	95.52 32	83.00 85	86.88 267	67.97 228	96.60 100	94.45 79

Baseline_NR-MVSNet		84.00 146	85.90 108	78.29 258	91.47 128	53.44 313	82.29 205	87.00 220	79.06 98	89.55 110	95.72 27	77.20 149	86.14 280	72.30 190	98.51 17	95.28 55

TSAR-MVS + GP.		83.95 147	82.69 164	87.72 87	89.27 171	81.45 63	83.72 164	81.58 269	74.73 149	85.66 181	86.06 255	72.56 205	92.69 150	75.44 157	95.21 147	89.01 239

alignmvs		83.94 148	83.98 147	83.80 160	87.80 199	67.88 186	84.54 145	91.42 126	73.27 171	88.41 130	87.96 225	72.33 206	90.83 204	76.02 152	94.11 179	92.69 148

Effi-MVS+		83.90 149	84.01 146	83.57 168	87.22 211	65.61 202	86.55 117	92.40 99	78.64 105	81.34 250	84.18 287	83.65 79	92.93 144	74.22 166	87.87 283	92.17 170

CANet		83.79 150	82.85 161	86.63 99	86.17 236	72.21 148	83.76 163	91.43 124	77.24 119	74.39 310	87.45 235	75.36 168	95.42 46	77.03 142	92.83 209	92.25 167

pm-mvs1		83.69 151	84.95 125	79.91 232	90.04 164	59.66 264	82.43 200	87.44 205	75.52 140	87.85 138	95.26 37	81.25 115	85.65 286	68.74 221	96.04 120	94.42 80

AdaColmap		83.66 152	83.69 151	83.57 168	90.05 163	72.26 146	86.29 122	90.00 167	78.19 110	81.65 245	87.16 240	83.40 82	94.24 87	61.69 268	94.76 166	84.21 290

MIMVSNet1		83.63 153	84.59 134	80.74 219	94.06 55	62.77 228	82.72 191	84.53 251	77.57 116	90.34 87	95.92 23	76.88 161	85.83 284	61.88 266	97.42 75	93.62 114

WR-MVS		83.56 154	84.40 140	81.06 214	93.43 69	54.88 305	78.67 261	85.02 245	81.24 72	90.74 82	91.56 154	72.85 200	91.08 195	68.00 227	98.04 35	97.23 16

CNLPA		83.55 155	83.10 159	84.90 136	89.34 170	83.87 46	84.54 145	88.77 185	79.09 97	83.54 217	88.66 216	74.87 173	81.73 311	66.84 234	92.29 218	89.11 233

LCM-MVSNet-Re		83.48 156	85.06 122	78.75 248	85.94 239	55.75 299	80.05 238	94.27 22	76.47 124	96.09 4	94.54 56	83.31 83	89.75 234	59.95 280	94.89 161	90.75 202

hse-mvs2		83.47 157	81.81 178	88.47 75	91.03 140	82.27 57	82.61 193	83.69 253	71.27 193	86.70 159	86.05 256	63.04 254	92.41 155	78.26 124	93.62 191	90.71 203

V42		83.47 157	83.37 154	83.75 163	83.16 277	63.33 220	81.31 222	90.23 161	69.51 215	90.91 80	90.81 176	74.16 182	92.29 161	80.06 102	90.22 257	95.62 46

VPA-MVSNet		83.47 157	84.73 128	79.69 237	90.29 156	57.52 286	81.30 224	88.69 187	76.29 125	87.58 142	94.44 60	80.60 121	87.20 262	66.60 236	96.82 93	94.34 83

RRT_MVS		83.25 160	81.08 190	89.74 53	80.55 305	79.32 79	86.41 119	86.69 221	72.33 184	87.00 153	91.08 164	44.98 339	95.55 37	84.47 58	96.24 114	94.36 82

PAPM_NR		83.23 161	83.19 157	83.33 171	90.90 143	65.98 199	88.19 89	90.78 141	78.13 111	80.87 254	87.92 228	73.49 192	92.42 154	70.07 207	88.40 274	91.60 187

CLD-MVS		83.18 162	82.64 165	84.79 138	89.05 174	67.82 187	77.93 269	92.52 97	68.33 226	85.07 188	81.54 316	82.06 101	92.96 142	69.35 212	97.91 48	93.57 116
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ANet_high		83.17 163	85.68 114	75.65 285	81.24 292	45.26 352	79.94 240	92.91 86	83.83 40	91.33 72	96.88 10	80.25 125	85.92 282	68.89 219	95.89 124	95.76 42

114514_t		83.10 164	82.54 169	84.77 139	92.90 81	69.10 178	86.65 114	90.62 146	54.66 317	81.46 247	90.81 176	76.98 154	94.38 83	72.62 187	96.18 115	90.82 201

UGNet		82.78 165	81.64 180	86.21 112	86.20 235	76.24 117	86.86 107	85.68 232	77.07 120	73.76 313	92.82 117	69.64 219	91.82 176	69.04 218	93.69 188	90.56 209
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		82.75 166	81.93 177	85.19 131	82.08 283	80.15 71	85.53 130	88.76 186	68.01 229	85.58 183	87.75 229	71.80 212	86.85 268	74.02 169	93.87 184	88.58 242

EI-MVSNet		82.61 167	82.42 171	83.20 174	83.25 275	63.66 216	83.50 171	85.07 242	76.06 129	86.55 163	85.10 272	73.41 193	90.25 218	78.15 128	90.67 253	95.68 44

QAPM		82.59 168	82.59 168	82.58 189	86.44 224	66.69 195	89.94 55	90.36 152	67.97 231	84.94 191	92.58 126	72.71 202	92.18 162	70.63 203	87.73 285	88.85 240

Fast-Effi-MVS+-dtu		82.54 169	81.41 185	85.90 118	85.60 241	76.53 113	83.07 183	89.62 174	73.02 175	79.11 274	83.51 292	80.74 120	90.24 220	68.76 220	89.29 264	90.94 197

MVS_Test		82.47 170	83.22 155	80.22 228	82.62 282	57.75 284	82.54 197	91.96 111	71.16 198	82.89 226	92.52 129	77.41 147	90.50 214	80.04 103	87.84 284	92.40 158

v148		82.31 171	82.48 170	81.81 203	85.59 242	59.66 264	81.47 220	86.02 228	72.85 176	88.05 135	90.65 182	70.73 217	90.91 201	75.15 160	91.79 229	94.87 63

API-MVS		82.28 172	82.61 167	81.30 207	86.29 232	69.79 165	88.71 83	87.67 204	78.42 108	82.15 236	84.15 288	77.98 140	91.59 179	65.39 245	92.75 210	82.51 315

MVSFormer		82.23 173	81.57 183	84.19 154	85.54 243	69.26 173	91.98 29	90.08 165	71.54 191	76.23 294	85.07 275	58.69 279	94.27 84	86.26 35	88.77 271	89.03 237

EIA-MVS		82.19 174	81.23 188	85.10 134	87.95 196	69.17 177	83.22 181	93.33 64	70.42 204	78.58 277	79.77 332	77.29 148	94.20 90	71.51 194	88.96 269	91.93 178

PCF-MVS	74.62 15	82.15 175	80.92 193	85.84 120	89.43 168	72.30 145	80.53 233	91.82 115	57.36 306	87.81 139	89.92 198	77.67 144	93.63 114	58.69 285	95.08 153	91.58 188
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PLC	73.85 16	82.09 176	80.31 199	87.45 91	90.86 145	80.29 70	85.88 125	90.65 144	68.17 228	76.32 293	86.33 250	73.12 198	92.61 152	61.40 272	90.02 259	89.44 226
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CS-MVS		82.02 177	82.63 166	80.19 229	84.80 251	57.56 285	82.39 202	94.72 16	71.24 196	80.22 265	84.89 279	75.85 165	94.56 80	76.08 150	93.49 192	88.46 243

GBi-Net		82.02 177	82.07 174	81.85 200	86.38 226	61.05 249	86.83 109	88.27 195	72.43 180	86.00 175	95.64 29	63.78 248	90.68 209	65.95 239	93.34 194	93.82 103

test1		82.02 177	82.07 174	81.85 200	86.38 226	61.05 249	86.83 109	88.27 195	72.43 180	86.00 175	95.64 29	63.78 248	90.68 209	65.95 239	93.34 194	93.82 103

OpenMVS	76.72 13	81.98 180	82.00 176	81.93 197	84.42 257	68.22 183	88.50 87	89.48 176	66.92 241	81.80 243	91.86 143	72.59 204	90.16 223	71.19 196	91.25 237	87.40 258

DIV-MVS_2432*1600		81.93 181	83.14 158	78.30 257	84.75 252	52.75 317	80.37 235	89.42 178	70.24 209	90.26 89	93.39 103	74.55 181	86.77 270	68.61 223	96.64 97	95.38 51

tfpnnormal		81.79 182	82.95 160	78.31 256	88.93 178	55.40 300	80.83 231	82.85 259	76.81 122	85.90 179	94.14 77	74.58 180	86.51 274	66.82 235	95.68 135	93.01 133

cl_fuxian		81.64 183	81.59 182	81.79 204	80.86 298	59.15 271	78.61 262	90.18 163	68.36 225	87.20 145	87.11 242	69.39 220	91.62 178	78.16 126	94.43 173	94.60 71

PVSNet_Blended_VisFu		81.55 184	80.49 197	84.70 142	91.58 123	73.24 131	84.21 149	91.67 119	62.86 270	80.94 252	87.16 240	67.27 232	92.87 147	69.82 209	88.94 270	87.99 249

CS-MVS-test		81.45 185	81.56 184	81.13 212	85.28 246	61.14 247	81.92 213	94.59 18	70.05 211	77.34 288	81.92 311	75.32 169	94.52 82	74.28 165	93.32 197	87.74 255

DELS-MVS		81.44 186	81.25 186	82.03 196	84.27 261	62.87 227	76.47 291	92.49 98	70.97 199	81.64 246	83.83 289	75.03 171	92.70 149	74.29 164	92.22 222	90.51 211
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
FMVSNet2		81.31 187	81.61 181	80.41 225	86.38 226	58.75 278	83.93 157	86.58 223	72.43 180	87.65 140	92.98 110	63.78 248	90.22 221	66.86 232	93.92 183	92.27 165

TinyColmap		81.25 188	82.34 172	77.99 263	85.33 245	60.68 256	82.32 204	88.33 193	71.26 195	86.97 154	92.22 139	77.10 152	86.98 266	62.37 261	95.17 149	86.31 269

AUN-MVS		81.18 189	78.78 216	88.39 78	90.93 142	82.14 58	82.51 198	83.67 254	64.69 264	80.29 262	85.91 259	51.07 309	92.38 156	76.29 148	93.63 190	90.65 207

tttt0517		81.07 190	79.58 211	85.52 127	88.99 177	66.45 197	87.03 106	75.51 304	73.76 160	88.32 133	90.20 191	37.96 355	94.16 96	79.36 113	95.13 150	95.93 41

Fast-Effi-MVS+		81.04 191	80.57 194	82.46 193	87.50 206	63.22 222	78.37 265	89.63 173	68.01 229	81.87 239	82.08 310	82.31 94	92.65 151	67.10 231	88.30 279	91.51 190

BH-untuned		80.96 192	80.99 191	80.84 218	88.55 184	68.23 182	80.33 236	88.46 189	72.79 177	86.55 163	86.76 245	74.72 178	91.77 177	61.79 267	88.99 268	82.52 314

1121		80.86 193	79.81 210	84.02 155	93.93 58	78.70 85	81.64 217	80.18 277	55.43 314	83.67 213	91.15 162	71.29 215	91.41 186	67.95 229	93.06 203	81.96 320

eth_miper_zixun_eth		80.84 194	80.22 203	82.71 186	81.41 290	60.98 252	77.81 271	90.14 164	67.31 239	86.95 155	87.24 239	64.26 244	92.31 159	75.23 159	91.61 232	94.85 65

xiu_mvs_v1_base_debu		80.84 194	80.14 205	82.93 180	88.31 189	71.73 152	79.53 245	87.17 209	65.43 256	79.59 268	82.73 305	76.94 155	90.14 226	73.22 179	88.33 275	86.90 264

xiu_mvs_v1_base		80.84 194	80.14 205	82.93 180	88.31 189	71.73 152	79.53 245	87.17 209	65.43 256	79.59 268	82.73 305	76.94 155	90.14 226	73.22 179	88.33 275	86.90 264

xiu_mvs_v1_base_debi		80.84 194	80.14 205	82.93 180	88.31 189	71.73 152	79.53 245	87.17 209	65.43 256	79.59 268	82.73 305	76.94 155	90.14 226	73.22 179	88.33 275	86.90 264

IterMVS-SCA-FT		80.64 198	79.41 212	84.34 149	83.93 269	69.66 168	76.28 293	81.09 271	72.43 180	86.47 169	90.19 192	60.46 264	93.15 138	77.45 137	86.39 296	90.22 215

BH-RMVSNet		80.53 199	80.22 203	81.49 206	87.19 212	66.21 198	77.79 272	86.23 225	74.21 155	83.69 212	88.50 218	73.25 197	90.75 206	63.18 258	87.90 282	87.52 256

Anonymous202405211		80.51 200	81.19 189	78.49 253	88.48 185	57.26 288	76.63 287	82.49 261	81.21 73	84.30 206	92.24 138	67.99 228	86.24 278	62.22 262	95.13 150	91.98 177

cl-mvsnet1		80.43 201	80.23 201	81.02 215	79.99 308	59.25 268	77.07 282	87.02 217	67.38 237	86.19 170	89.22 205	63.09 252	90.16 223	76.32 146	95.80 128	93.66 110

cl-mvsnet____		80.42 202	80.23 201	81.02 215	79.99 308	59.25 268	77.07 282	87.02 217	67.37 238	86.18 172	89.21 206	63.08 253	90.16 223	76.31 147	95.80 128	93.65 112

diffmvs		80.40 203	80.48 198	80.17 230	79.02 320	60.04 260	77.54 276	90.28 160	66.65 244	82.40 231	87.33 238	73.50 190	87.35 261	77.98 130	89.62 262	93.13 128

EPNet		80.37 204	78.41 222	86.23 109	76.75 331	73.28 130	87.18 103	77.45 291	76.24 127	68.14 333	88.93 212	65.41 241	93.85 105	69.47 211	96.12 119	91.55 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		80.34 205	80.04 208	81.24 210	79.82 310	58.95 273	77.66 273	89.66 172	65.75 253	85.99 178	85.11 271	68.29 227	91.42 185	76.03 151	92.03 224	93.33 120

MG-MVS		80.32 206	80.94 192	78.47 254	88.18 192	52.62 320	82.29 205	85.01 246	72.01 189	79.24 273	92.54 128	69.36 221	93.36 130	70.65 202	89.19 267	89.45 225

VPNet		80.25 207	81.68 179	75.94 284	92.46 93	47.98 344	76.70 286	81.67 268	73.45 163	84.87 192	92.82 117	74.66 179	86.51 274	61.66 269	96.85 90	93.33 120

MAR-MVS		80.24 208	78.74 218	84.73 140	86.87 223	78.18 89	85.75 127	87.81 203	65.67 255	77.84 282	78.50 336	73.79 187	90.53 213	61.59 271	90.87 248	85.49 278
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
PM-MVS		80.20 209	79.00 215	83.78 162	88.17 193	86.66 16	81.31 222	66.81 347	69.64 214	88.33 132	90.19 192	64.58 242	83.63 303	71.99 193	90.03 258	81.06 334

Anonymous20240521		80.18 210	81.25 186	76.95 272	83.15 278	60.84 254	82.46 199	85.99 229	68.76 223	86.78 156	93.73 99	59.13 276	77.44 324	73.71 174	97.55 67	92.56 152

LFMVS		80.15 211	80.56 195	78.89 245	89.19 173	55.93 296	85.22 134	73.78 316	82.96 53	84.28 207	92.72 121	57.38 288	90.07 230	63.80 253	95.75 131	90.68 205

DPM-MVS		80.10 212	79.18 214	82.88 183	90.71 149	69.74 166	78.87 258	90.84 139	60.29 291	75.64 302	85.92 258	67.28 231	93.11 139	71.24 195	91.79 229	85.77 275

MSDG		80.06 213	79.99 209	80.25 227	83.91 270	68.04 185	77.51 277	89.19 180	77.65 114	81.94 238	83.45 294	76.37 163	86.31 277	63.31 257	86.59 293	86.41 267

ab-mvs		79.67 214	80.56 195	76.99 271	88.48 185	56.93 290	84.70 140	86.06 227	68.95 221	80.78 255	93.08 107	75.30 170	84.62 295	56.78 294	90.90 247	89.43 227

VNet		79.31 215	80.27 200	76.44 279	87.92 197	53.95 309	75.58 299	84.35 252	74.39 154	82.23 234	90.72 178	72.84 201	84.39 297	60.38 279	93.98 182	90.97 196

bset_n11_16_dypcd		79.19 216	77.97 226	82.86 184	85.81 240	66.85 194	75.02 304	79.31 281	66.07 247	83.50 218	83.37 297	55.04 302	92.10 166	78.63 118	94.99 157	89.63 222

thisisatest0530		79.07 217	77.33 233	84.26 151	87.13 213	64.58 208	83.66 166	75.95 299	68.86 222	85.22 187	87.36 237	38.10 353	93.57 121	75.47 156	94.28 175	94.62 69

cl-mvsnet2		78.97 218	78.21 224	81.24 210	77.74 324	59.01 272	77.46 279	87.13 212	65.79 250	84.32 203	85.10 272	58.96 278	90.88 203	75.36 158	92.03 224	93.84 100

RPMNet		78.88 219	78.28 223	80.68 222	79.58 311	62.64 230	82.58 194	94.16 30	74.80 148	75.72 300	92.59 124	48.69 315	95.56 34	73.48 177	82.91 323	83.85 295

PAPR		78.84 220	78.10 225	81.07 213	85.17 247	60.22 259	82.21 209	90.57 147	62.51 272	75.32 305	84.61 283	74.99 172	92.30 160	59.48 283	88.04 281	90.68 205

PVSNet_BlendedMVS		78.80 221	77.84 227	81.65 205	84.43 255	63.41 218	79.49 248	90.44 149	61.70 280	75.43 303	87.07 243	69.11 223	91.44 183	60.68 277	92.24 220	90.11 219

FMVSNet3		78.80 221	78.55 219	79.57 239	82.89 281	56.89 292	81.76 214	85.77 231	69.04 220	86.00 175	90.44 186	51.75 307	90.09 229	65.95 239	93.34 194	91.72 183

test_yl		78.71 223	78.51 220	79.32 242	84.32 259	58.84 275	78.38 263	85.33 236	75.99 132	82.49 229	86.57 246	58.01 282	90.02 231	62.74 259	92.73 211	89.10 234

DCV-MVSNet		78.71 223	78.51 220	79.32 242	84.32 259	58.84 275	78.38 263	85.33 236	75.99 132	82.49 229	86.57 246	58.01 282	90.02 231	62.74 259	92.73 211	89.10 234

pmmvs-eth3d		78.42 225	77.04 236	82.57 191	87.44 207	74.41 124	80.86 230	79.67 280	55.68 312	84.69 195	90.31 189	60.91 262	85.42 287	62.20 263	91.59 233	87.88 252

MVS_0304		78.17 226	77.23 234	80.99 217	84.13 267	69.07 179	81.39 221	80.81 273	76.28 126	67.53 338	89.11 209	62.87 256	86.77 270	60.90 276	92.01 227	87.13 261

mvs_anonymous		78.13 227	78.76 217	76.23 283	79.24 317	50.31 338	78.69 260	84.82 249	61.60 281	83.09 225	92.82 117	73.89 186	87.01 263	68.33 226	86.41 295	91.37 191

RRT_test8_iter05		78.08 228	77.52 229	79.75 235	80.84 299	52.54 321	80.61 232	88.96 183	67.77 236	84.62 196	89.29 204	33.89 360	92.10 166	77.59 134	94.15 178	94.62 69

TAMVS		78.08 228	76.36 242	83.23 173	90.62 150	72.87 132	79.08 255	80.01 279	61.72 279	81.35 249	86.92 244	63.96 247	88.78 247	50.61 327	93.01 205	88.04 248

miper_enhance_ethall		77.83 230	76.93 237	80.51 223	76.15 337	58.01 281	75.47 301	88.82 184	58.05 300	83.59 215	80.69 320	64.41 243	91.20 190	73.16 185	92.03 224	92.33 160

Vis-MVSNet (Re-imp)		77.82 231	77.79 228	77.92 264	88.82 180	51.29 331	83.28 176	71.97 329	74.04 156	82.23 234	89.78 199	57.38 288	89.41 238	57.22 293	95.41 139	93.05 131

CANet_DTU		77.81 232	77.05 235	80.09 231	81.37 291	59.90 262	83.26 177	88.29 194	69.16 218	67.83 336	83.72 290	60.93 261	89.47 235	69.22 215	89.70 261	90.88 199

OpenMVS_ROB	70.19 17	77.77 233	77.46 230	78.71 249	84.39 258	61.15 246	81.18 226	82.52 260	62.45 274	83.34 220	87.37 236	66.20 237	88.66 249	64.69 249	85.02 307	86.32 268

MDA-MVSNet-bldmvs		77.47 234	76.90 238	79.16 244	79.03 319	64.59 207	66.58 340	75.67 302	73.15 173	88.86 119	88.99 211	66.94 233	81.23 313	64.71 248	88.22 280	91.64 186

jason		77.42 235	75.75 248	82.43 194	87.10 217	69.27 172	77.99 268	81.94 266	51.47 336	77.84 282	85.07 275	60.32 266	89.00 241	70.74 201	89.27 266	89.03 237
jason: jason.
CDS-MVSNet		77.32 236	75.40 251	83.06 176	89.00 176	72.48 142	77.90 270	82.17 264	60.81 286	78.94 275	83.49 293	59.30 274	88.76 248	54.64 311	92.37 217	87.93 251
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		77.19 237	76.75 239	78.52 252	87.01 219	61.30 244	75.55 300	87.12 215	61.24 283	74.45 309	78.79 334	77.20 149	90.93 199	64.62 251	84.80 313	83.32 304

MVSTER		77.09 238	75.70 249	81.25 208	75.27 344	61.08 248	77.49 278	85.07 242	60.78 287	86.55 163	88.68 215	43.14 345	90.25 218	73.69 175	90.67 253	92.42 156

PS-MVSNAJ		77.04 239	76.53 241	78.56 251	87.09 218	61.40 242	75.26 302	87.13 212	61.25 282	74.38 311	77.22 343	76.94 155	90.94 198	64.63 250	84.83 312	83.35 303

IterMVS		76.91 240	76.34 243	78.64 250	80.91 296	64.03 214	76.30 292	79.03 284	64.88 263	83.11 223	89.16 207	59.90 270	84.46 296	68.61 223	85.15 306	87.42 257
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
D2MVS		76.84 241	75.67 250	80.34 226	80.48 306	62.16 239	73.50 314	84.80 250	57.61 304	82.24 233	87.54 233	51.31 308	87.65 258	70.40 206	93.19 200	91.23 193

CL-MVSNet_2432*1600		76.81 242	77.38 232	75.12 288	86.90 221	51.34 329	73.20 317	80.63 275	68.30 227	81.80 243	88.40 219	66.92 234	80.90 314	55.35 305	94.90 160	93.12 129

TR-MVS		76.77 243	75.79 247	79.72 236	86.10 238	65.79 201	77.14 280	83.02 257	65.20 261	81.40 248	82.10 309	66.30 236	90.73 208	55.57 302	85.27 304	82.65 310

USDC		76.63 244	76.73 240	76.34 281	83.46 273	57.20 289	80.02 239	88.04 199	52.14 332	83.65 214	91.25 158	63.24 251	86.65 273	54.66 310	94.11 179	85.17 280

BH-w/o		76.57 245	76.07 246	78.10 261	86.88 222	65.92 200	77.63 274	86.33 224	65.69 254	80.89 253	79.95 329	68.97 225	90.74 207	53.01 319	85.25 305	77.62 340

Patchmtry		76.56 246	77.46 230	73.83 294	79.37 316	46.60 349	82.41 201	76.90 293	73.81 159	85.56 184	92.38 130	48.07 317	83.98 300	63.36 256	95.31 145	90.92 198

PVSNet_Blended		76.49 247	75.40 251	79.76 234	84.43 255	63.41 218	75.14 303	90.44 149	57.36 306	75.43 303	78.30 337	69.11 223	91.44 183	60.68 277	87.70 286	84.42 288

miper_lstm_enhance		76.45 248	76.10 245	77.51 268	76.72 332	60.97 253	64.69 343	85.04 244	63.98 266	83.20 222	88.22 221	56.67 291	78.79 322	73.22 179	93.12 201	92.78 143

lupinMVS		76.37 249	74.46 259	82.09 195	85.54 243	69.26 173	76.79 284	80.77 274	50.68 342	76.23 294	82.82 303	58.69 279	88.94 242	69.85 208	88.77 271	88.07 246

cascas		76.29 250	74.81 255	80.72 221	84.47 254	62.94 225	73.89 312	87.34 206	55.94 311	75.16 307	76.53 346	63.97 246	91.16 192	65.00 246	90.97 245	88.06 247

thres600view7		75.97 251	75.35 253	77.85 266	87.01 219	51.84 327	80.45 234	73.26 320	75.20 145	83.10 224	86.31 252	45.54 330	89.05 240	55.03 308	92.24 220	92.66 149

GA-MVS		75.83 252	74.61 256	79.48 241	81.87 285	59.25 268	73.42 315	82.88 258	68.68 224	79.75 267	81.80 313	50.62 311	89.46 236	66.85 233	85.64 301	89.72 221

MVP-Stereo		75.81 253	73.51 268	82.71 186	89.35 169	73.62 127	80.06 237	85.20 239	60.30 290	73.96 312	87.94 226	57.89 286	89.45 237	52.02 322	74.87 349	85.06 282
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
thres100view900		75.45 254	75.05 254	76.66 278	87.27 209	51.88 326	81.07 227	73.26 320	75.68 138	83.25 221	86.37 249	45.54 330	88.80 244	51.98 323	90.99 242	89.31 229

ET-MVSNet_ETH3D		75.28 255	72.77 274	82.81 185	83.03 280	68.11 184	77.09 281	76.51 297	60.67 289	77.60 286	80.52 324	38.04 354	91.15 193	70.78 199	90.68 252	89.17 232

thres400		75.14 256	74.23 261	77.86 265	86.24 233	52.12 323	79.24 252	73.87 314	73.34 166	81.82 241	84.60 284	46.02 324	88.80 244	51.98 323	90.99 242	92.66 149

wuyk23d		75.13 257	79.30 213	62.63 333	75.56 340	75.18 121	80.89 229	73.10 322	75.06 147	94.76 11	95.32 34	87.73 41	52.85 361	34.16 360	97.11 83	59.85 357

EU-MVSNet		75.12 258	74.43 260	77.18 270	83.11 279	59.48 266	85.71 129	82.43 262	39.76 360	85.64 182	88.76 213	44.71 341	87.88 256	73.86 172	85.88 300	84.16 291

HyFIR lowres test		75.12 258	72.66 276	82.50 192	91.44 129	65.19 204	72.47 319	87.31 207	46.79 348	80.29 262	84.30 286	52.70 306	92.10 166	51.88 326	86.73 292	90.22 215

CMPMVS	59.41 20	75.12 258	73.57 266	79.77 233	75.84 339	67.22 188	81.21 225	82.18 263	50.78 340	76.50 290	87.66 231	55.20 300	82.99 305	62.17 265	90.64 256	89.09 236
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		74.92 261	72.98 273	80.73 220	84.95 248	71.71 155	76.23 294	77.59 290	52.83 326	77.73 285	86.38 248	56.35 294	84.97 291	57.72 292	87.05 290	85.51 277

tfpn200view9		74.86 262	74.23 261	76.74 277	86.24 233	52.12 323	79.24 252	73.87 314	73.34 166	81.82 241	84.60 284	46.02 324	88.80 244	51.98 323	90.99 242	89.31 229

1112_ss		74.82 263	73.74 264	78.04 262	89.57 167	60.04 260	76.49 290	87.09 216	54.31 318	73.66 314	79.80 330	60.25 267	86.76 272	58.37 286	84.15 316	87.32 259

ppachtmachnet_test		74.73 264	74.00 263	76.90 274	80.71 302	56.89 292	71.53 323	78.42 286	58.24 298	79.32 272	82.92 302	57.91 285	84.26 298	65.60 244	91.36 236	89.56 224

Patchmatch-RL test		74.48 265	73.68 265	76.89 275	84.83 250	66.54 196	72.29 320	69.16 340	57.70 302	86.76 157	86.33 250	45.79 329	82.59 306	69.63 210	90.65 255	81.54 325

PatchMatch-RL		74.48 265	73.22 270	78.27 259	87.70 201	85.26 33	75.92 296	70.09 337	64.34 265	76.09 296	81.25 318	65.87 240	78.07 323	53.86 313	83.82 317	71.48 348

XXY-MVS		74.44 267	76.19 244	69.21 314	84.61 253	52.43 322	71.70 322	77.18 292	60.73 288	80.60 256	90.96 171	75.44 166	69.35 342	56.13 298	88.33 275	85.86 274

CR-MVSNet		74.00 268	73.04 272	76.85 276	79.58 311	62.64 230	82.58 194	76.90 293	50.50 343	75.72 300	92.38 130	48.07 317	84.07 299	68.72 222	82.91 323	83.85 295

Test_1112_low_res		73.90 269	73.08 271	76.35 280	90.35 155	55.95 295	73.40 316	86.17 226	50.70 341	73.14 315	85.94 257	58.31 281	85.90 283	56.51 296	83.22 320	87.20 260

test20.03		73.75 270	74.59 258	71.22 307	81.11 294	51.12 333	70.15 328	72.10 328	70.42 204	80.28 264	91.50 155	64.21 245	74.72 334	46.96 343	94.58 169	87.82 254

SCA		73.32 271	72.57 278	75.58 286	81.62 287	55.86 297	78.89 257	71.37 334	61.73 278	74.93 308	83.42 295	60.46 264	87.01 263	58.11 290	82.63 327	83.88 292

baseline1		73.26 272	73.54 267	72.43 303	84.92 249	47.79 345	79.89 241	74.00 312	65.93 248	78.81 276	86.28 253	56.36 293	81.63 312	56.63 295	79.04 340	87.87 253

1314		73.22 273	72.56 279	75.20 287	80.41 307	57.84 282	81.64 217	85.36 235	51.68 335	73.10 316	76.65 345	61.45 260	85.19 289	63.54 254	79.21 339	82.59 311

MVS		73.21 274	72.59 277	75.06 289	80.97 295	60.81 255	81.64 217	85.92 230	46.03 351	71.68 322	77.54 339	68.47 226	89.77 233	55.70 301	85.39 302	74.60 345

HY-MVS	64.64 18	73.03 275	72.47 280	74.71 290	83.36 274	54.19 307	82.14 212	81.96 265	56.76 310	69.57 330	86.21 254	60.03 268	84.83 294	49.58 332	82.65 325	85.11 281

thisisatest0515		73.00 276	70.52 291	80.46 224	81.45 289	59.90 262	73.16 318	74.31 311	57.86 301	76.08 297	77.78 338	37.60 356	92.12 165	65.00 246	91.45 235	89.35 228

EPNet_dtu		72.87 277	71.33 289	77.49 269	77.72 325	60.55 257	82.35 203	75.79 300	66.49 245	58.39 361	81.06 319	53.68 304	85.98 281	53.55 314	92.97 207	85.95 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		72.62 278	71.41 288	76.28 282	83.25 275	60.34 258	83.50 171	79.02 285	37.77 361	76.33 292	85.10 272	49.60 314	87.41 260	70.54 204	77.54 345	81.08 332

CHOSEN 1792x2688		72.45 279	70.56 290	78.13 260	90.02 165	63.08 223	68.72 332	83.16 256	42.99 357	75.92 298	85.46 265	57.22 290	85.18 290	49.87 331	81.67 328	86.14 270

testgi		72.36 280	74.61 256	65.59 327	80.56 304	42.82 358	68.29 333	73.35 319	66.87 242	81.84 240	89.93 197	72.08 209	66.92 350	46.05 345	92.54 215	87.01 263

thres200		72.34 281	71.55 287	74.70 291	83.48 272	51.60 328	75.02 304	73.71 317	70.14 210	78.56 278	80.57 323	46.20 322	88.20 254	46.99 342	89.29 264	84.32 289

FPMVS		72.29 282	72.00 282	73.14 297	88.63 182	85.00 35	74.65 308	67.39 341	71.94 190	77.80 284	87.66 231	50.48 312	75.83 330	49.95 329	79.51 335	58.58 359

FMVSNet5		72.10 283	71.69 284	73.32 295	81.57 288	53.02 316	76.77 285	78.37 287	63.31 267	76.37 291	91.85 144	36.68 357	78.98 320	47.87 339	92.45 216	87.95 250

our_test_3		71.85 284	71.59 285	72.62 301	80.71 302	53.78 310	69.72 330	71.71 333	58.80 295	78.03 279	80.51 325	56.61 292	78.84 321	62.20 263	86.04 299	85.23 279

PAPM		71.77 285	70.06 296	76.92 273	86.39 225	53.97 308	76.62 288	86.62 222	53.44 323	63.97 351	84.73 282	57.79 287	92.34 158	39.65 355	81.33 331	84.45 287

IB-MVS	62.13 19	71.64 286	68.97 300	79.66 238	80.80 301	62.26 238	73.94 311	76.90 293	63.27 268	68.63 332	76.79 344	33.83 361	91.84 175	59.28 284	87.26 288	84.88 283
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
UnsupCasMVSNet_eth		71.63 287	72.30 281	69.62 312	76.47 334	52.70 319	70.03 329	80.97 272	59.18 294	79.36 271	88.21 222	60.50 263	69.12 343	58.33 288	77.62 344	87.04 262

Anonymous20231206		71.38 288	71.88 283	69.88 310	86.31 230	54.37 306	70.39 327	74.62 307	52.57 328	76.73 289	88.76 213	59.94 269	72.06 336	44.35 348	93.23 199	83.23 306

MIMVSNet		71.09 289	71.59 285	69.57 313	87.23 210	50.07 339	78.91 256	71.83 330	60.20 292	71.26 323	91.76 149	55.08 301	76.09 328	41.06 353	87.02 291	82.54 313

MS-PatchMatch		70.93 290	70.22 294	73.06 298	81.85 286	62.50 233	73.82 313	77.90 288	52.44 329	75.92 298	81.27 317	55.67 297	81.75 310	55.37 304	77.70 343	74.94 344

pmmvs5		70.73 291	70.07 295	72.72 299	77.03 330	52.73 318	74.14 309	75.65 303	50.36 344	72.17 320	85.37 269	55.42 299	80.67 316	52.86 320	87.59 287	84.77 284

PatchT		70.52 292	72.76 275	63.79 332	79.38 315	33.53 364	77.63 274	65.37 349	73.61 161	71.77 321	92.79 120	44.38 342	75.65 331	64.53 252	85.37 303	82.18 318

N_pmnet		70.20 293	68.80 302	74.38 292	80.91 296	84.81 38	59.12 353	76.45 298	55.06 315	75.31 306	82.36 308	55.74 296	54.82 360	47.02 341	87.24 289	83.52 299

tpmvs		70.16 294	69.56 298	71.96 305	74.71 348	48.13 342	79.63 243	75.45 305	65.02 262	70.26 327	81.88 312	45.34 335	85.68 285	58.34 287	75.39 348	82.08 319

new-patchmatchnet		70.10 295	73.37 269	60.29 340	81.23 293	16.95 368	59.54 351	74.62 307	62.93 269	80.97 251	87.93 227	62.83 257	71.90 337	55.24 306	95.01 156	92.00 174

YYNet1		70.06 296	70.44 292	68.90 315	73.76 350	53.42 314	58.99 354	67.20 343	58.42 297	87.10 149	85.39 268	59.82 271	67.32 347	59.79 281	83.50 319	85.96 271

MDA-MVSNet_test_wron		70.05 297	70.44 292	68.88 316	73.84 349	53.47 312	58.93 355	67.28 342	58.43 296	87.09 150	85.40 267	59.80 272	67.25 348	59.66 282	83.54 318	85.92 273

CostFormer		69.98 298	68.68 303	73.87 293	77.14 328	50.72 336	79.26 251	74.51 309	51.94 334	70.97 326	84.75 281	45.16 338	87.49 259	55.16 307	79.23 338	83.40 302

baseline2		69.77 299	66.89 309	78.41 255	79.51 313	58.09 280	76.23 294	69.57 339	57.50 305	64.82 349	77.45 341	46.02 324	88.44 250	53.08 316	77.83 342	88.70 241

PatchmatchNet		69.71 300	68.83 301	72.33 304	77.66 326	53.60 311	79.29 250	69.99 338	57.66 303	72.53 318	82.93 301	46.45 321	80.08 319	60.91 275	72.09 352	83.31 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
JIA-IIPM		69.41 301	66.64 313	77.70 267	73.19 352	71.24 158	75.67 297	65.56 348	70.42 204	65.18 345	92.97 112	33.64 362	83.06 304	53.52 315	69.61 358	78.79 339

UnsupCasMVSNet_bld		69.21 302	69.68 297	67.82 321	79.42 314	51.15 332	67.82 337	75.79 300	54.15 319	77.47 287	85.36 270	59.26 275	70.64 339	48.46 336	79.35 337	81.66 323

gg-mvs-nofinetune		68.96 303	69.11 299	68.52 320	76.12 338	45.32 351	83.59 167	55.88 362	86.68 25	64.62 350	97.01 7	30.36 365	83.97 301	44.78 347	82.94 322	76.26 342

tpm2		68.45 304	66.83 310	73.30 296	78.93 321	48.50 341	79.76 242	71.76 331	47.50 347	69.92 329	83.60 291	42.07 347	88.40 251	48.44 337	79.51 335	83.01 309

tpm		67.95 305	68.08 306	67.55 322	78.74 322	43.53 356	75.60 298	67.10 346	54.92 316	72.23 319	88.10 223	42.87 346	75.97 329	52.21 321	80.95 334	83.15 307

WTY-MVS		67.91 306	68.35 304	66.58 325	80.82 300	48.12 343	65.96 341	72.60 324	53.67 322	71.20 324	81.68 315	58.97 277	69.06 344	48.57 335	81.67 328	82.55 312

test-LLR		67.21 307	66.74 311	68.63 318	76.45 335	55.21 302	67.89 334	67.14 344	62.43 275	65.08 346	72.39 351	43.41 343	69.37 340	61.00 273	84.89 310	81.31 327

sss		66.92 308	67.26 308	65.90 326	77.23 327	51.10 334	64.79 342	71.72 332	52.12 333	70.13 328	80.18 327	57.96 284	65.36 355	50.21 328	81.01 333	81.25 329

KD-MVS_2432*1600		66.87 309	65.81 314	70.04 308	67.50 361	47.49 346	62.56 347	79.16 282	61.21 284	77.98 280	80.61 321	25.29 371	82.48 307	53.02 317	84.92 308	80.16 337

miper_refine_blended		66.87 309	65.81 314	70.04 308	67.50 361	47.49 346	62.56 347	79.16 282	61.21 284	77.98 280	80.61 321	25.29 371	82.48 307	53.02 317	84.92 308	80.16 337

tpm cat1		66.76 311	65.21 317	71.42 306	77.09 329	50.62 337	78.01 267	73.68 318	44.89 353	68.64 331	79.00 333	45.51 332	82.42 309	49.91 330	70.15 355	81.23 331

DWT-MVSNet_test		66.43 312	64.37 318	72.63 300	74.86 347	50.86 335	76.52 289	72.74 323	54.06 320	65.50 343	68.30 357	32.13 363	84.84 293	61.63 270	73.59 350	82.19 317

PVSNet	58.17 21	66.41 313	65.63 316	68.75 317	81.96 284	49.88 340	62.19 349	72.51 326	51.03 338	68.04 334	75.34 349	50.84 310	74.77 332	45.82 346	82.96 321	81.60 324

tpmrst		66.28 314	66.69 312	65.05 330	72.82 356	39.33 359	78.20 266	70.69 336	53.16 325	67.88 335	80.36 326	48.18 316	74.75 333	58.13 289	70.79 354	81.08 332

Patchmatch-test		65.91 315	67.38 307	61.48 338	75.51 341	43.21 357	68.84 331	63.79 351	62.48 273	72.80 317	83.42 295	44.89 340	59.52 359	48.27 338	86.45 294	81.70 322

ADS-MVSNet2		65.87 316	63.64 321	72.55 302	73.16 353	56.92 291	67.10 338	74.81 306	49.74 345	66.04 341	82.97 299	46.71 319	77.26 325	42.29 350	69.96 356	83.46 300

test-mter		65.00 317	63.79 320	68.63 318	76.45 335	55.21 302	67.89 334	67.14 344	50.98 339	65.08 346	72.39 351	28.27 368	69.37 340	61.00 273	84.89 310	81.31 327

test0.0.03 1		64.66 318	64.36 319	65.57 328	75.03 346	46.89 348	64.69 343	61.58 356	62.43 275	71.18 325	77.54 339	43.41 343	68.47 345	40.75 354	82.65 325	81.35 326

pmmvs3		62.47 319	60.02 331	69.80 311	71.58 359	64.00 215	70.52 326	58.44 360	39.77 359	66.05 340	75.84 347	27.10 370	72.28 335	46.15 344	84.77 314	73.11 346

EPMVS		62.47 319	62.63 323	62.01 334	70.63 360	38.74 360	74.76 306	52.86 364	53.91 321	67.71 337	80.01 328	39.40 351	66.60 351	55.54 303	68.81 359	80.68 336

ADS-MVSNet		61.90 321	62.19 324	61.03 339	73.16 353	36.42 362	67.10 338	61.75 354	49.74 345	66.04 341	82.97 299	46.71 319	63.21 357	42.29 350	69.96 356	83.46 300

PMMVS		61.65 322	60.38 328	65.47 329	65.40 365	69.26 173	63.97 345	61.73 355	36.80 362	60.11 356	68.43 355	59.42 273	66.35 352	48.97 334	78.57 341	60.81 356

E-PMN		61.59 323	61.62 325	61.49 337	66.81 363	55.40 300	53.77 357	60.34 357	66.80 243	58.90 359	65.50 358	40.48 350	66.12 353	55.72 300	86.25 297	62.95 355

TESTMET0.1,1		61.29 324	60.32 329	64.19 331	72.06 357	51.30 330	67.89 334	62.09 352	45.27 352	60.65 355	69.01 354	27.93 369	64.74 356	56.31 297	81.65 330	76.53 341

MVS-HIRNet		61.16 325	62.92 322	55.87 343	79.09 318	35.34 363	71.83 321	57.98 361	46.56 349	59.05 358	91.14 163	49.95 313	76.43 327	38.74 356	71.92 353	55.84 360

EMVS		61.10 326	60.81 327	61.99 335	65.96 364	55.86 297	53.10 358	58.97 359	67.06 240	56.89 362	63.33 359	40.98 348	67.03 349	54.79 309	86.18 298	63.08 354

DSMNet-mixed		60.98 327	61.61 326	59.09 342	72.88 355	45.05 353	74.70 307	46.61 367	26.20 363	65.34 344	90.32 188	55.46 298	63.12 358	41.72 352	81.30 332	69.09 352

dp		60.70 328	60.29 330	61.92 336	72.04 358	38.67 361	70.83 324	64.08 350	51.28 337	60.75 354	77.28 342	36.59 358	71.58 338	47.41 340	62.34 361	75.52 343

CHOSEN 280x420		59.08 329	56.52 334	66.76 324	76.51 333	64.39 211	49.62 359	59.00 358	43.86 355	55.66 363	68.41 356	35.55 359	68.21 346	43.25 349	76.78 347	67.69 353

PVSNet_0	51.08 22	56.10 330	54.97 335	59.48 341	75.12 345	53.28 315	55.16 356	61.89 353	44.30 354	59.16 357	62.48 360	54.22 303	65.91 354	35.40 359	47.01 362	59.25 358

new_pmnet		55.69 331	57.66 333	49.76 345	75.47 342	30.59 365	59.56 350	51.45 365	43.62 356	62.49 352	75.48 348	40.96 349	49.15 363	37.39 358	72.52 351	69.55 351

PMMVS2		55.64 332	59.27 332	44.74 346	64.30 366	12.32 369	40.60 360	49.79 366	53.19 324	65.06 348	84.81 280	53.60 305	49.76 362	32.68 362	89.41 263	72.15 347

MVE	40.22 23	51.82 333	50.47 336	55.87 343	62.66 367	51.91 325	31.61 362	39.28 368	40.65 358	50.76 364	74.98 350	56.24 295	44.67 364	33.94 361	64.11 360	71.04 350
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		30.46 334	29.60 337	33.06 347	17.99 369	3.84 371	13.62 363	73.92 313	2.79 365	18.29 367	53.41 362	28.53 367	43.25 365	22.56 363	35.27 364	52.11 361

cdsmvs_eth3d_5k		20.81 335	27.75 338	0.00 352	0.00 373	0.00 374	0.00 364	85.44 234	0.00 369	0.00 370	82.82 303	81.46 112	0.00 370	0.00 368	0.00 368	0.00 366

tmp_tt		20.25 336	24.50 339	7.49 349	4.47 370	8.70 370	34.17 361	25.16 370	1.00 366	32.43 366	18.49 364	39.37 352	9.21 367	21.64 364	43.75 363	4.57 363

ab-mvs-re		6.65 337	8.87 340	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	79.80 330	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		6.41 338	8.55 341	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	76.94 155	0.00 370	0.00 368	0.00 368	0.00 366

test123		6.27 339	8.08 342	0.84 350	1.11 372	0.57 372	62.90 346	0.82 372	0.54 367	1.07 369	2.75 369	1.26 373	0.30 368	1.04 366	1.26 367	1.66 364

testmvs		5.91 340	7.65 343	0.72 351	1.20 371	0.37 373	59.14 352	0.67 373	0.49 368	1.11 368	2.76 368	0.94 374	0.24 369	1.02 367	1.47 366	1.55 365

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

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

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

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

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

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

eth-test2					0.00 373

eth-test					0.00 373

ZD-MVS					92.22 102	80.48 68		91.85 113	71.22 197	90.38 86	92.98 110	86.06 62	96.11 6	81.99 81	96.75 95

RE-MVS-def			92.61 5		94.13 53	88.95 8	92.87 12	94.16 30	88.75 15	93.79 28	94.43 61	90.64 11		87.16 25	97.60 64	92.73 144

IU-MVS					94.18 48	72.64 136		90.82 140	56.98 308	89.67 104				85.78 44	97.92 46	93.28 122

OPU-MVS				88.27 81	91.89 113	77.83 92	90.47 46				91.22 159	81.12 116	94.68 72	74.48 163	95.35 141	92.29 163

test_241102_TWO								93.71 50	83.77 41	93.49 37	94.27 69	89.27 22	95.84 19	86.03 41	97.82 51	92.04 172

test_241102_ONE					94.18 48	72.65 134		93.69 51	83.62 43	94.11 22	93.78 97	90.28 15	95.50 44

9.14			89.29 61		91.84 115		88.80 81	95.32 9	75.14 146	91.07 75	92.89 115	87.27 45	93.78 109	83.69 65	97.55 67

save fliter					93.75 61	77.44 98	86.31 120	89.72 170	70.80 200

test_0728_THIRD									85.33 30	93.75 30	94.65 53	87.44 44	95.78 24	87.41 19	98.21 30	92.98 134

test_0728_SECOND				86.79 97	94.25 47	72.45 143	90.54 43	94.10 36					95.88 14	86.42 31	97.97 43	92.02 173

test0726					94.16 51	72.56 139	90.63 42	93.90 43	83.61 44	93.75 30	94.49 58	89.76 19

GSMVS																83.88 292

test_part2					93.86 60	77.77 93				92.84 45

sam_mvs1												46.11 323				83.88 292

sam_mvs												45.92 328

ambc				82.98 178	90.55 153	64.86 206	88.20 88	89.15 181		89.40 113	93.96 87	71.67 214	91.38 188	78.83 116	96.55 101	92.71 147

MTGPA								91.81 116

test_post1							78.85 259				3.13 366	45.19 337	80.13 318	58.11 290

test_post											3.10 367	45.43 333	77.22 326

patchmatchnet-post											81.71 314	45.93 327	87.01 263

GG-mvs-BLEND				67.16 323	73.36 351	46.54 350	84.15 150	55.04 363		58.64 360	61.95 361	29.93 366	83.87 302	38.71 357	76.92 346	71.07 349

MTMP							90.66 40	33.14 369

gm-plane-assit					75.42 343	44.97 354			52.17 330		72.36 353		87.90 255	54.10 312

test9_res														80.83 95	96.45 106	90.57 208

TEST9					92.34 96	79.70 75	83.94 155	90.32 153	65.41 260	84.49 199	90.97 169	82.03 103	93.63 114

test_8					92.09 105	78.87 83	83.82 160	90.31 155	65.79 250	84.36 202	90.96 171	81.93 105	93.44 126

agg_prior2														79.68 107	96.16 116	90.22 215

agg_prior					91.58 123	77.69 94		90.30 156		84.32 203			93.18 134

TestCases				89.68 54	91.59 120	83.40 48		95.44 7	79.47 91	88.00 136	93.03 108	82.66 90	91.47 181	70.81 197	96.14 117	94.16 89

test_prior4						78.97 82	84.59 142

test_prior2							83.37 174		75.43 141	84.58 197	91.57 152	81.92 107		79.54 109	96.97 86

test_prior				86.32 105	90.59 151	71.99 149		92.85 88					94.17 93			92.80 141

旧先验2							81.73 215		56.88 309	86.54 168			84.90 292	72.81 186

新几何2							81.72 216

新几何1				82.95 179	93.96 57	78.56 87		80.24 276	55.45 313	83.93 211	91.08 164	71.19 216	88.33 252	65.84 242	93.07 202	81.95 321

旧先验1					91.97 108	71.77 151		81.78 267			91.84 145	73.92 185			93.65 189	83.61 298

无先验							82.81 190	85.62 233	58.09 299				91.41 186	67.95 229		84.48 286

原ACMM2							82.26 208

原ACMM1				84.60 143	92.81 87	74.01 126		91.50 122	62.59 271	82.73 228	90.67 181	76.53 162	94.25 86	69.24 213	95.69 134	85.55 276

test222					93.31 72	76.54 111	79.38 249	77.79 289	52.59 327	82.36 232	90.84 175	66.83 235			91.69 231	81.25 329

testdata2													86.43 276	63.52 255

segment_acmp												81.94 104

testdata				79.54 240	92.87 82	72.34 144		80.14 278	59.91 293	85.47 186	91.75 150	67.96 229	85.24 288	68.57 225	92.18 223	81.06 334

testdata1							79.62 244		73.95 158

test12				86.57 100	90.74 147	72.63 137		90.69 143		82.76 227		79.20 131	94.80 69		95.32 143	92.27 165

plane_prior7					93.45 67	77.31 102

plane_prior6					92.61 88	76.54 111						74.84 174

plane_prior5								93.61 55					95.22 55	80.78 96	95.83 126	94.46 77

plane_prior4											92.95 113

plane_prior3						76.85 109			77.79 113	86.55 163

plane_prior2							89.45 69		79.44 93

plane_prior1					92.83 86

plane_prior						76.42 114	87.15 104		75.94 135						95.03 155

n2								0.00 374

nn								0.00 374

door-mid								74.45 310

lessismore_v0				85.95 116	91.10 139	70.99 160		70.91 335		91.79 64	94.42 63	61.76 259	92.93 144	79.52 111	93.03 204	93.93 97

LGP-MVS_train				90.82 38	94.75 40	81.69 59		94.27 22	82.35 60	93.67 33	94.82 48	91.18 5	95.52 39	85.36 47	98.73 7	95.23 58

test11								91.46 123

door								72.57 325

HQP5-MVS						70.66 161

HQP-NCC					91.19 134		84.77 137		73.30 168	80.55 259

ACMP_Plane					91.19 134		84.77 137		73.30 168	80.55 259

BP-MVS														77.30 139

HQP4-MVS										80.56 258			94.61 76			93.56 117

HQP3-MVS								92.68 94							94.47 171

HQP2-MVS												72.10 207

NP-MVS					91.95 109	74.55 123					90.17 194

MDTV_nov1_ep13_2view						27.60 367	70.76 325		46.47 350	61.27 353		45.20 336		49.18 333		83.75 297

MDTV_nov1_ep13			68.29 305		78.03 323	43.87 355	74.12 310	72.22 327	52.17 330	67.02 339	85.54 261	45.36 334	80.85 315	55.73 299	84.42 315

ACMMP++_ref															95.74 133

ACMMP++															97.35 76

Test By Simon												79.09 132

ITE_SJBPF				90.11 50	90.72 148	84.97 36		90.30 156	81.56 69	90.02 92	91.20 161	82.40 93	90.81 205	73.58 176	94.66 167	94.56 72

DeepMVS_CX				24.13 348	32.95 368	29.49 366		21.63 371	12.07 364	37.95 365	45.07 363	30.84 364	19.21 366	17.94 365	33.06 365	23.69 362

High-resolution multi-view benchmark