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 3	98.67 1	85.39 37	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 16	85.07 57	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 46	97.23 2	95.32 2	99.01 2	97.26 6	80.16 133	98.99 1	95.15 1	99.14 2	96.47 30

LTVRE_ROB	86.10 1	93.04 4	93.44 3	91.82 22	93.73 64	85.72 34	96.79 1	95.51 9	88.86 16	95.63 10	96.99 10	84.81 72	93.16 135	91.10 2	97.53 72	96.58 28
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
TDRefinement		93.52 3	93.39 4	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 50	96.29 19	88.16 35	94.17 95	86.07 48	98.48 18	97.22 17

reproduce-ours		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 204

our_new_method		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 204

reproduce_model		92.89 5	93.18 7	92.01 13	94.20 49	88.23 9	92.87 13	94.32 21	90.25 11	95.65 9	95.74 30	87.75 41	95.72 36	89.60 4	98.27 26	92.08 193

RE-MVS-def			92.61 8		94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	90.64 10		87.16 32	97.60 66	92.73 158

HPM-MVS_fast		92.50 8	92.54 9	92.37 6	95.93 16	85.81 33	92.99 12	94.23 27	85.21 40	92.51 58	95.13 48	90.65 9	95.34 55	88.06 12	98.15 37	95.95 40

SR-MVS-dyc-post		92.41 9	92.41 10	92.39 5	94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	88.83 26	95.51 47	87.16 32	97.60 66	92.73 158

SR-MVS		92.23 10	92.34 11	91.91 17	94.89 38	87.85 10	92.51 24	93.87 51	88.20 23	93.24 42	94.02 94	90.15 16	95.67 38	86.82 36	97.34 76	92.19 189

APD-MVS_3200maxsize		92.05 12	92.24 12	91.48 25	93.02 80	85.17 39	92.47 26	95.05 14	87.65 27	93.21 43	94.39 77	90.09 17	95.08 66	86.67 38	97.60 66	94.18 95

HPM-MVS		92.13 11	92.20 13	91.91 17	95.58 26	84.67 46	93.51 8	94.85 15	82.88 64	91.77 70	93.94 102	90.55 12	95.73 35	88.50 10	98.23 31	95.33 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
COLMAP_ROB	83.01 3	91.97 13	91.95 14	92.04 11	93.68 65	86.15 24	93.37 10	95.10 13	90.28 10	92.11 63	95.03 50	89.75 20	94.93 70	79.95 113	98.27 26	95.04 63
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
APDe-MVS		91.22 25	91.92 15	89.14 66	92.97 82	78.04 93	92.84 16	94.14 36	83.33 58	93.90 28	95.73 31	88.77 27	96.41 3	87.60 21	97.98 45	92.98 152
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PS-CasMVS		90.06 43	91.92 15	84.47 149	96.56 6	58.83 309	89.04 88	92.74 96	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 121	98.74 6	99.00 2

DTE-MVSNet		89.98 47	91.91 17	84.21 158	96.51 7	57.84 317	88.93 90	92.84 93	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 124	98.57 15	98.80 6

PEN-MVS		90.03 45	91.88 18	84.48 148	96.57 5	58.88 306	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 127	98.72 9	98.97 3

ACMMP		91.91 14	91.87 19	92.03 12	95.53 27	85.91 28	93.35 11	94.16 32	82.52 67	92.39 61	94.14 89	89.15 25	95.62 39	87.35 27	98.24 30	94.56 76
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
LPG-MVS_test		91.47 21	91.68 20	90.82 37	94.75 41	81.69 63	90.00 62	94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 55	98.73 7	95.23 58

SED-MVS		90.46 37	91.64 21	86.93 99	94.18 50	72.65 145	90.47 55	93.69 56	83.77 52	94.11 26	94.27 79	90.28 14	95.84 24	86.03 49	97.92 49	92.29 183

MTAPA		91.52 18	91.60 22	91.29 30	96.59 4	86.29 21	92.02 33	91.81 125	84.07 49	92.00 66	94.40 76	86.63 54	95.28 58	88.59 9	98.31 24	92.30 182

CP-MVS		91.67 16	91.58 23	91.96 14	95.29 31	87.62 13	93.38 9	93.36 65	83.16 60	91.06 82	94.00 95	88.26 32	95.71 37	87.28 30	98.39 21	92.55 168

UA-Net		91.49 19	91.53 24	91.39 27	94.98 35	82.95 58	93.52 7	92.79 94	88.22 22	88.53 133	97.64 3	83.45 86	94.55 83	86.02 51	98.60 13	96.67 25

ACMH+	77.89 11	90.73 31	91.50 25	88.44 78	93.00 81	76.26 119	89.65 75	95.55 8	87.72 26	93.89 30	94.94 52	91.62 3	93.44 126	78.35 131	98.76 4	95.61 47

mPP-MVS		91.69 15	91.47 26	92.37 6	96.04 13	88.48 8	92.72 18	92.60 100	83.09 61	91.54 72	94.25 83	87.67 44	95.51 47	87.21 31	98.11 38	93.12 146

HFP-MVS		91.30 23	91.39 27	91.02 33	95.43 29	84.66 47	92.58 22	93.29 72	81.99 70	91.47 73	93.96 99	88.35 31	95.56 42	87.74 16	97.74 59	92.85 155

XVS		91.54 17	91.36 28	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	94.03 93	86.57 55	95.80 28	87.35 27	97.62 64	94.20 92

SteuartSystems-ACMMP		91.16 27	91.36 28	90.55 41	93.91 60	80.97 70	91.49 40	93.48 63	82.82 65	92.60 57	93.97 96	88.19 33	96.29 6	87.61 20	98.20 34	94.39 87
Skip Steuart: Steuart Systems R&D Blog.
ACMMPR		91.49 19	91.35 30	91.92 16	95.74 20	85.88 30	92.58 22	93.25 73	81.99 70	91.40 74	94.17 88	87.51 45	95.87 20	87.74 16	97.76 57	93.99 102

ZNCC-MVS		91.26 24	91.34 31	91.01 34	95.73 21	83.05 56	92.18 31	94.22 29	80.14 92	91.29 78	93.97 96	87.93 40	95.87 20	88.65 8	97.96 48	94.12 99

DVP-MVS		90.06 43	91.32 32	86.29 111	94.16 53	72.56 151	90.54 52	91.01 146	83.61 55	93.75 34	94.65 61	89.76 18	95.78 32	86.42 39	97.97 46	90.55 240
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
WR-MVS_H		89.91 50	91.31 33	85.71 126	96.32 9	62.39 262	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 119	95.90 17	80.94 102	98.80 3	98.84 5

region2R		91.44 22	91.30 34	91.87 19	95.75 19	85.90 29	92.63 21	93.30 71	81.91 72	90.88 88	94.21 84	87.75 41	95.87 20	87.60 21	97.71 60	93.83 111

ACMH	76.49 14	89.34 59	91.14 35	83.96 163	92.50 94	70.36 179	89.55 77	93.84 52	81.89 73	94.70 17	95.44 40	90.69 8	88.31 262	83.33 73	98.30 25	93.20 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS++		90.07 42	91.09 36	87.00 97	91.55 129	72.64 147	96.19 2	94.10 39	85.33 38	93.49 39	94.64 64	81.12 122	95.88 18	87.41 25	95.94 128	92.48 171

DPE-MVS		90.53 36	91.08 37	88.88 69	93.38 71	78.65 87	89.15 87	94.05 41	84.68 45	93.90 28	94.11 91	88.13 36	96.30 5	84.51 65	97.81 55	91.70 208
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		90.81 30	91.08 37	89.99 50	95.97 14	79.88 75	88.13 102	94.51 18	75.79 147	92.94 47	94.96 51	88.36 30	95.01 68	90.70 3	98.40 20	95.09 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		90.65 32	91.07 39	89.42 61	95.93 16	79.54 80	89.95 66	93.68 58	77.65 126	91.97 67	94.89 53	88.38 29	95.45 51	89.27 5	97.87 53	93.27 138

GST-MVS		90.96 29	91.01 40	90.82 37	95.45 28	82.73 59	91.75 38	93.74 54	80.98 83	91.38 75	93.80 106	87.20 49	95.80 28	87.10 34	97.69 61	93.93 105

ACMM	79.39 9	90.65 32	90.99 41	89.63 57	95.03 34	83.53 51	89.62 76	93.35 66	79.20 105	93.83 31	93.60 116	90.81 7	92.96 142	85.02 59	98.45 19	92.41 175
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v7n		90.13 40	90.96 42	87.65 91	91.95 112	71.06 173	89.99 64	93.05 83	86.53 31	94.29 22	96.27 20	82.69 93	94.08 98	86.25 45	97.63 63	97.82 8

PGM-MVS		91.20 26	90.95 43	91.93 15	95.67 23	85.85 31	90.00 62	93.90 48	80.32 89	91.74 71	94.41 75	88.17 34	95.98 13	86.37 41	97.99 43	93.96 104

MP-MVS		91.14 28	90.91 44	91.83 20	96.18 11	86.88 17	92.20 30	93.03 86	82.59 66	88.52 134	94.37 78	86.74 53	95.41 53	86.32 42	98.21 32	93.19 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVSNet		89.27 62	90.91 44	84.37 150	96.34 8	58.61 312	88.66 97	92.06 114	90.78 7	95.67 8	95.17 47	81.80 115	95.54 44	79.00 125	98.69 10	98.95 4

SF-MVS		90.27 39	90.80 46	88.68 76	92.86 86	77.09 108	91.19 44	95.74 6	81.38 78	92.28 62	93.80 106	86.89 52	94.64 78	85.52 54	97.51 73	94.30 91

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 156	97.00 2	64.33 237	89.67 74	88.38 205	88.84 17	94.29 22	97.57 4	90.48 13	91.26 187	72.57 209	97.65 62	97.34 14

PMVS	80.48 6	90.08 41	90.66 48	88.34 81	96.71 3	92.97 2	90.31 59	89.57 191	88.51 21	90.11 96	95.12 49	90.98 6	88.92 252	77.55 145	97.07 83	83.13 351
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMP	79.16 10	90.54 35	90.60 49	90.35 45	94.36 46	80.98 69	89.16 86	94.05 41	79.03 108	92.87 49	93.74 111	90.60 11	95.21 61	82.87 81	98.76 4	94.87 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SMA-MVS		90.31 38	90.48 50	89.83 54	95.31 30	79.52 81	90.98 47	93.24 74	75.37 154	92.84 51	95.28 44	85.58 67	96.09 8	87.92 14	97.76 57	93.88 108
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
LS3D		90.60 34	90.34 51	91.38 28	89.03 185	84.23 49	93.58 6	94.68 17	90.65 8	90.33 94	93.95 101	84.50 74	95.37 54	80.87 103	95.50 145	94.53 79

OPM-MVS		89.80 51	89.97 52	89.27 63	94.76 40	79.86 76	86.76 127	92.78 95	78.78 111	92.51 58	93.64 115	88.13 36	93.84 107	84.83 62	97.55 69	94.10 100
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SD-MVS		88.96 67	89.88 53	86.22 114	91.63 123	77.07 109	89.82 69	93.77 53	78.90 109	92.88 48	92.29 157	86.11 63	90.22 220	86.24 46	97.24 79	91.36 216
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
XVG-ACMP-BASELINE		89.98 47	89.84 54	90.41 43	94.91 37	84.50 48	89.49 81	93.98 43	79.68 97	92.09 64	93.89 104	83.80 81	93.10 138	82.67 85	98.04 39	93.64 123

tt0805		88.09 77	89.79 55	82.98 193	93.26 75	63.94 241	91.10 45	89.64 188	85.07 41	90.91 86	91.09 190	89.16 24	91.87 173	82.03 92	95.87 132	93.13 144

OurMVSNet-221017-0		90.01 46	89.74 56	90.83 36	93.16 78	80.37 72	91.91 36	93.11 79	81.10 81	95.32 14	97.24 7	72.94 214	94.85 72	85.07 57	97.78 56	97.26 15

3Dnovator+	83.92 2	89.97 49	89.66 57	90.92 35	91.27 138	81.66 66	91.25 42	94.13 37	88.89 15	88.83 126	94.26 82	77.55 156	95.86 23	84.88 60	95.87 132	95.24 57

APD-MVS		89.54 56	89.63 58	89.26 64	92.57 91	81.34 68	90.19 61	93.08 82	80.87 85	91.13 80	93.19 122	86.22 62	95.97 14	82.23 91	97.18 81	90.45 242
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Anonymous20231211		88.40 71	89.62 59	84.73 142	90.46 157	65.27 227	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 105	92.02 168	76.70 155	97.99 43	96.88 23

test_0402		88.65 69	89.58 60	85.88 122	92.55 92	72.22 159	84.01 176	89.44 193	88.63 20	94.38 21	95.77 29	86.38 61	93.59 118	79.84 114	95.21 154	91.82 202

XVG-OURS-SEG-HR		89.59 55	89.37 61	90.28 46	94.47 43	85.95 27	86.84 123	93.91 47	80.07 93	86.75 172	93.26 121	93.64 2	90.93 198	84.60 64	90.75 269	93.97 103

9.14			89.29 62		91.84 119		88.80 93	95.32 12	75.14 156	91.07 81	92.89 136	87.27 47	93.78 108	83.69 72	97.55 69

mvs_tets		89.78 52	89.27 63	91.30 29	93.51 67	84.79 44	89.89 68	90.63 156	70.00 227	94.55 19	96.67 14	87.94 39	93.59 118	84.27 67	95.97 124	95.52 48

testf1		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 244	74.12 184	96.10 119	94.45 82

APD_test2		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 244	74.12 184	96.10 119	94.45 82

DeepC-MVS	82.31 4	89.15 64	89.08 66	89.37 62	93.64 66	79.07 83	88.54 98	94.20 30	73.53 173	89.71 107	94.82 56	85.09 68	95.77 34	84.17 68	98.03 41	93.26 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_djsdf		89.62 54	89.01 67	91.45 26	92.36 97	82.98 57	91.98 34	90.08 178	71.54 207	94.28 24	96.54 16	81.57 117	94.27 87	86.26 43	96.49 100	97.09 19

DP-MVS		88.60 70	89.01 67	87.36 93	91.30 136	77.50 101	87.55 109	92.97 89	87.95 25	89.62 111	92.87 137	84.56 73	93.89 104	77.65 143	96.62 95	90.70 234

CPTT-MVS		89.39 58	88.98 69	90.63 40	95.09 33	86.95 16	92.09 32	92.30 108	79.74 96	87.50 157	92.38 152	81.42 119	93.28 131	83.07 77	97.24 79	91.67 209

anonymousdsp		89.73 53	88.88 70	92.27 8	89.82 171	86.67 18	90.51 54	90.20 175	69.87 228	95.06 15	96.14 25	84.28 77	93.07 139	87.68 18	96.34 106	97.09 19

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 179	92.03 110	62.26 266	91.49 40	92.62 99	88.07 24	88.07 145	96.17 23	72.24 223	95.79 31	84.85 61	94.16 192	92.58 166

XVG-OURS		89.18 63	88.83 72	90.23 47	94.28 47	86.11 26	85.91 140	93.60 61	80.16 91	89.13 123	93.44 118	83.82 80	90.98 196	83.86 71	95.30 153	93.60 126

jajsoiax		89.41 57	88.81 73	91.19 32	93.38 71	84.72 45	89.70 71	90.29 172	69.27 231	94.39 20	96.38 18	86.02 65	93.52 122	83.96 69	95.92 130	95.34 52

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 134	94.02 58	64.13 238	84.38 170	91.29 138	84.88 44	92.06 65	93.84 105	86.45 58	93.73 109	73.22 200	98.66 11	97.69 9

nrg030		87.85 82	88.49 75	85.91 120	90.07 166	69.73 183	87.86 106	94.20 30	74.04 165	92.70 56	94.66 60	85.88 66	91.50 179	79.72 116	97.32 77	96.50 29

HPM-MVS++		88.93 68	88.45 76	90.38 44	94.92 36	85.85 31	89.70 71	91.27 139	78.20 118	86.69 175	92.28 158	80.36 131	95.06 67	86.17 47	96.49 100	90.22 246

EC-MVSNet		88.01 78	88.32 77	87.09 95	89.28 180	72.03 161	90.31 59	96.31 4	80.88 84	85.12 206	89.67 232	84.47 75	95.46 50	82.56 86	96.26 111	93.77 117

MSP-MVS		89.08 66	88.16 78	91.83 20	95.76 18	86.14 25	92.75 17	93.90 48	78.43 116	89.16 121	92.25 159	72.03 228	96.36 4	88.21 11	90.93 262	92.98 152
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
pmmvs6		86.52 99	88.06 79	81.90 214	92.22 103	62.28 265	84.66 163	89.15 196	83.54 57	89.85 104	97.32 5	88.08 38	86.80 281	70.43 226	97.30 78	96.62 26

APD_test1		88.40 71	87.91 80	89.88 51	89.50 175	86.65 20	89.98 65	91.91 120	84.26 47	90.87 89	93.92 103	82.18 106	89.29 248	73.75 192	94.81 173	93.70 119

PS-MVSNAJss		88.31 73	87.90 81	89.56 59	93.31 73	77.96 96	87.94 105	91.97 117	70.73 218	94.19 25	96.67 14	76.94 166	94.57 81	83.07 77	96.28 108	96.15 32

TSAR-MVS + MP.		88.14 75	87.82 82	89.09 67	95.72 22	76.74 112	92.49 25	91.19 142	67.85 251	86.63 176	94.84 55	79.58 138	95.96 15	87.62 19	94.50 181	94.56 76
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		87.81 83	87.68 83	88.21 83	92.87 84	77.30 107	85.25 153	91.23 140	77.31 131	87.07 166	91.47 179	82.94 91	94.71 75	84.67 63	96.27 110	92.62 165

CS-MVS		88.14 75	87.67 84	89.54 60	89.56 173	79.18 82	90.47 55	94.77 16	79.37 103	84.32 225	89.33 236	83.87 79	94.53 84	82.45 87	94.89 169	94.90 64

OMC-MVS		88.19 74	87.52 85	90.19 48	91.94 114	81.68 65	87.49 112	93.17 76	76.02 141	88.64 130	91.22 185	84.24 78	93.37 129	77.97 141	97.03 84	95.52 48

casdiffmvs_mvg		86.72 95	87.51 86	84.36 152	87.09 236	65.22 228	84.16 172	94.23 27	77.89 122	91.28 79	93.66 114	84.35 76	92.71 148	80.07 110	94.87 172	95.16 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SixPastTwentyTwo		87.20 89	87.45 87	86.45 108	92.52 93	69.19 192	87.84 107	88.05 212	81.66 75	94.64 18	96.53 17	65.94 258	94.75 74	83.02 79	96.83 89	95.41 50

HQP_MVS		87.75 84	87.43 88	88.70 75	93.45 68	76.42 116	89.45 82	93.61 59	79.44 101	86.55 177	92.95 134	74.84 187	95.22 59	80.78 105	95.83 134	94.46 80

AllTest		87.97 80	87.40 89	89.68 55	91.59 124	83.40 52	89.50 80	95.44 10	79.47 99	88.00 148	93.03 129	82.66 94	91.47 180	70.81 218	96.14 116	94.16 96

MM		87.64 85	87.15 90	89.09 67	89.51 174	76.39 118	88.68 96	86.76 233	84.54 46	83.58 242	93.78 108	73.36 210	96.48 2	87.98 13	96.21 112	94.41 86

Anonymous20240529		86.20 104	87.13 91	83.42 181	90.19 162	64.55 235	84.55 165	90.71 153	85.85 36	89.94 103	95.24 46	82.13 107	90.40 216	69.19 239	96.40 105	95.31 54

v10		86.54 98	87.10 92	84.84 138	88.16 209	63.28 248	86.64 130	92.20 110	75.42 153	92.81 53	94.50 68	74.05 198	94.06 99	83.88 70	96.28 108	97.17 18

UniMVSNet_NR-MVSNet		86.84 93	87.06 93	86.17 117	92.86 86	67.02 211	82.55 220	91.56 128	83.08 62	90.92 84	91.82 169	78.25 147	93.99 100	74.16 182	98.35 22	97.49 13

FC-MVSNet-test		85.93 109	87.05 94	82.58 204	92.25 101	56.44 328	85.75 145	93.09 81	77.33 130	91.94 68	94.65 61	74.78 189	93.41 128	75.11 176	98.58 14	97.88 7

DU-MVS		86.80 94	86.99 95	86.21 115	93.24 76	67.02 211	83.16 203	92.21 109	81.73 74	90.92 84	91.97 163	77.20 160	93.99 100	74.16 182	98.35 22	97.61 10

UniMVSNet (Re)		86.87 91	86.98 96	86.55 106	93.11 79	68.48 197	83.80 185	92.87 91	80.37 87	89.61 113	91.81 170	77.72 153	94.18 93	75.00 177	98.53 16	96.99 22

RPSCF		88.00 79	86.93 97	91.22 31	90.08 164	89.30 5	89.68 73	91.11 143	79.26 104	89.68 108	94.81 59	82.44 97	87.74 266	76.54 157	88.74 297	96.61 27

NCCC		87.36 87	86.87 98	88.83 70	92.32 100	78.84 86	86.58 131	91.09 144	78.77 112	84.85 214	90.89 199	80.85 125	95.29 56	81.14 100	95.32 150	92.34 180

v8		86.22 103	86.83 99	84.36 152	87.82 215	62.35 264	86.42 134	91.33 137	76.78 135	92.73 55	94.48 70	73.41 207	93.72 110	83.10 76	95.41 146	97.01 21

IS-MVSNet		86.66 97	86.82 100	86.17 117	92.05 109	66.87 214	91.21 43	88.64 202	86.30 33	89.60 114	92.59 145	69.22 242	94.91 71	73.89 189	97.89 52	96.72 24

Vis-MVSNet		86.86 92	86.58 101	87.72 89	92.09 107	77.43 104	87.35 113	92.09 113	78.87 110	84.27 230	94.05 92	78.35 146	93.65 111	80.54 109	91.58 250	92.08 193
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsmconf0.01_n		86.68 96	86.52 102	87.18 94	85.94 263	78.30 89	86.93 120	92.20 110	65.94 263	89.16 121	93.16 124	83.10 89	89.89 233	87.81 15	94.43 184	93.35 133

CSCG		86.26 101	86.47 103	85.60 128	90.87 149	74.26 131	87.98 104	91.85 121	80.35 88	89.54 117	88.01 255	79.09 140	92.13 164	75.51 170	95.06 161	90.41 243

SPE-MVS-test		87.00 90	86.43 104	88.71 74	89.46 176	77.46 102	89.42 84	95.73 7	77.87 124	81.64 278	87.25 273	82.43 98	94.53 84	77.65 143	96.46 102	94.14 98

Gipuma		84.44 138	86.33 105	78.78 262	84.20 292	73.57 135	89.55 77	90.44 161	84.24 48	84.38 222	94.89 53	76.35 177	80.40 345	76.14 164	96.80 91	82.36 361
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FIs		85.35 118	86.27 106	82.60 203	91.86 116	57.31 321	85.10 157	93.05 83	75.83 146	91.02 83	93.97 96	73.57 203	92.91 146	73.97 188	98.02 42	97.58 12

NR-MVSNet		86.00 107	86.22 107	85.34 132	93.24 76	64.56 234	82.21 232	90.46 160	80.99 82	88.42 137	91.97 163	77.56 155	93.85 105	72.46 210	98.65 12	97.61 10

DeepPCF-MVS	81.24 5	87.28 88	86.21 108	90.49 42	91.48 133	84.90 42	83.41 194	92.38 105	70.25 224	89.35 119	90.68 208	82.85 92	94.57 81	79.55 118	95.95 127	92.00 197

sasdasda		85.50 113	86.14 109	83.58 175	87.97 211	67.13 208	87.55 109	94.32 21	73.44 176	88.47 135	87.54 266	86.45 58	91.06 194	75.76 168	93.76 201	92.54 169

canonicalmvs		85.50 113	86.14 109	83.58 175	87.97 211	67.13 208	87.55 109	94.32 21	73.44 176	88.47 135	87.54 266	86.45 58	91.06 194	75.76 168	93.76 201	92.54 169

MSLP-MVS++		85.00 128	86.03 111	81.90 214	91.84 119	71.56 170	86.75 128	93.02 87	75.95 144	87.12 161	89.39 234	77.98 148	89.40 247	77.46 146	94.78 174	84.75 323

MGCFI-Net		85.04 125	85.95 112	82.31 210	87.52 224	63.59 244	86.23 138	93.96 44	73.46 174	88.07 145	87.83 261	86.46 57	90.87 203	76.17 163	93.89 199	92.47 173

baseline		85.20 121	85.93 113	83.02 191	86.30 253	62.37 263	84.55 165	93.96 44	74.48 162	87.12 161	92.03 162	82.30 103	91.94 169	78.39 129	94.21 189	94.74 73

Baseline_NR-MVSNet		84.00 153	85.90 114	78.29 273	91.47 134	53.44 351	82.29 228	87.00 232	79.06 107	89.55 115	95.72 32	77.20 160	86.14 295	72.30 211	98.51 17	95.28 55

test_fmvsmconf0.1_n		86.18 105	85.88 115	87.08 96	85.26 272	78.25 90	85.82 144	91.82 123	65.33 277	88.55 132	92.35 156	82.62 96	89.80 235	86.87 35	94.32 187	93.18 143

casdiffmvs		85.21 120	85.85 116	83.31 184	86.17 258	62.77 255	83.03 205	93.93 46	74.69 160	88.21 142	92.68 144	82.29 104	91.89 172	77.87 142	93.75 204	95.27 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		85.45 116	85.81 117	84.37 150	90.08 164	67.07 210	85.86 143	91.39 135	72.33 200	87.59 155	90.25 220	84.85 71	92.37 158	78.00 139	91.94 243	93.66 120

PHI-MVS		86.38 100	85.81 117	88.08 84	88.44 203	77.34 105	89.35 85	93.05 83	73.15 186	84.76 215	87.70 263	78.87 142	94.18 93	80.67 107	96.29 107	92.73 158

mmtdpeth		85.13 123	85.78 119	83.17 189	84.65 282	74.71 127	85.87 142	90.35 166	77.94 121	83.82 237	96.96 12	77.75 151	80.03 348	78.44 128	96.21 112	94.79 72

TransMVSNet (Re)		84.02 152	85.74 120	78.85 261	91.00 146	55.20 340	82.29 228	87.26 220	79.65 98	88.38 139	95.52 37	83.00 90	86.88 279	67.97 254	96.60 96	94.45 82

ANet_high		83.17 171	85.68 121	75.65 308	81.24 331	45.26 394	79.94 259	92.91 90	83.83 51	91.33 76	96.88 13	80.25 132	85.92 298	68.89 243	95.89 131	95.76 42

DeepC-MVS_fast	80.27 8	86.23 102	85.65 122	87.96 87	91.30 136	76.92 110	87.19 115	91.99 116	70.56 219	84.96 210	90.69 207	80.01 135	95.14 64	78.37 130	95.78 138	91.82 202
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		86.17 106	85.54 123	88.05 86	92.25 101	75.45 124	83.85 182	92.01 115	65.91 265	86.19 186	91.75 173	83.77 82	94.98 69	77.43 148	96.71 93	93.73 118

test_fmvsmconf_n		85.88 110	85.51 124	86.99 98	84.77 280	78.21 91	85.40 152	91.39 135	65.32 278	87.72 153	91.81 170	82.33 101	89.78 236	86.68 37	94.20 190	92.99 151

FMVSNet1		84.55 136	85.45 125	81.85 216	90.27 161	61.05 280	86.83 124	88.27 209	78.57 115	89.66 110	95.64 34	75.43 180	90.68 209	69.09 240	95.33 149	93.82 112

balanced_conf03		84.80 130	85.40 126	83.00 192	88.95 188	61.44 273	90.42 58	92.37 106	71.48 209	88.72 129	93.13 125	70.16 238	95.15 63	79.26 123	94.11 193	92.41 175

VDDNet		84.35 140	85.39 127	81.25 227	95.13 32	59.32 299	85.42 151	81.11 298	86.41 32	87.41 158	96.21 22	73.61 202	90.61 212	66.33 264	96.85 87	93.81 115

test_fmvsmvis_n_1920		85.22 119	85.36 128	84.81 139	85.80 265	76.13 122	85.15 156	92.32 107	61.40 307	91.33 76	90.85 202	83.76 83	86.16 294	84.31 66	93.28 213	92.15 191

train_agg		85.98 108	85.28 129	88.07 85	92.34 98	79.70 78	83.94 178	90.32 167	65.79 267	84.49 219	90.97 194	81.93 111	93.63 113	81.21 99	96.54 98	90.88 228

dcpmvs_2		84.23 146	85.14 130	81.50 224	88.61 198	61.98 270	82.90 211	93.11 79	68.66 240	92.77 54	92.39 151	78.50 144	87.63 268	76.99 154	92.30 231	94.90 64

LCM-MVSNet-Re		83.48 165	85.06 131	78.75 263	85.94 263	55.75 334	80.05 257	94.27 24	76.47 136	96.09 6	94.54 67	83.31 88	89.75 239	59.95 317	94.89 169	90.75 231

EPP-MVSNet		85.47 115	85.04 132	86.77 103	91.52 132	69.37 187	91.63 39	87.98 214	81.51 77	87.05 167	91.83 168	66.18 257	95.29 56	70.75 221	96.89 86	95.64 45

IterMVS-LS		84.73 132	84.98 133	83.96 163	87.35 227	63.66 242	83.25 199	89.88 183	76.06 139	89.62 111	92.37 155	73.40 209	92.52 153	78.16 136	94.77 176	95.69 43
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
pm-mvs1		83.69 159	84.95 134	79.91 248	90.04 168	59.66 296	82.43 224	87.44 217	75.52 151	87.85 150	95.26 45	81.25 121	85.65 305	68.74 246	96.04 121	94.42 85

TAPA-MVS	77.73 12	85.71 112	84.83 135	88.37 80	88.78 194	79.72 77	87.15 117	93.50 62	69.17 232	85.80 195	89.56 233	80.76 126	92.13 164	73.21 205	95.51 144	93.25 140
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		83.47 166	84.73 136	79.69 252	90.29 160	57.52 320	81.30 244	88.69 201	76.29 137	87.58 156	94.44 71	80.60 129	87.20 273	66.60 262	96.82 90	94.34 89

K. test v3		85.14 122	84.73 136	86.37 109	91.13 143	69.63 185	85.45 150	76.68 327	84.06 50	92.44 60	96.99 10	62.03 280	94.65 77	80.58 108	93.24 214	94.83 71

v1144		84.54 137	84.72 138	84.00 161	87.67 220	62.55 259	82.97 208	90.93 149	70.32 223	89.80 105	90.99 193	73.50 204	93.48 124	81.69 98	94.65 179	95.97 38

3Dnovator	80.37 7	84.80 130	84.71 139	85.06 136	86.36 251	74.71 127	88.77 94	90.00 180	75.65 149	84.96 210	93.17 123	74.06 197	91.19 189	78.28 133	91.09 256	89.29 265

v1192		84.57 135	84.69 140	84.21 158	87.75 217	62.88 252	83.02 206	91.43 132	69.08 234	89.98 102	90.89 199	72.70 218	93.62 116	82.41 88	94.97 166	96.13 33

MIMVSNet1		83.63 161	84.59 141	80.74 236	94.06 57	62.77 255	82.72 214	84.53 271	77.57 128	90.34 93	95.92 28	76.88 172	85.83 303	61.88 304	97.42 74	93.62 124

MVS_0304		85.37 117	84.58 142	87.75 88	85.28 271	73.36 136	86.54 133	85.71 248	77.56 129	81.78 276	92.47 150	70.29 236	96.02 11	85.59 53	95.96 125	93.87 109

VDD-MVS		84.23 146	84.58 142	83.20 187	91.17 142	65.16 230	83.25 199	84.97 265	79.79 95	87.18 160	94.27 79	74.77 190	90.89 201	69.24 236	96.54 98	93.55 131

mvs5depth		83.82 157	84.54 144	81.68 221	82.23 319	68.65 196	86.89 121	89.90 182	80.02 94	87.74 152	97.86 2	64.19 267	82.02 333	76.37 159	95.63 143	94.35 88

EI-MVSNet-Vis-set		85.12 124	84.53 145	86.88 100	84.01 294	72.76 144	83.91 181	85.18 257	80.44 86	88.75 127	85.49 300	80.08 134	91.92 170	82.02 93	90.85 267	95.97 38

v1240		84.30 142	84.51 146	83.65 172	87.65 221	61.26 277	82.85 212	91.54 129	67.94 249	90.68 91	90.65 211	71.71 230	93.64 112	82.84 82	94.78 174	96.07 35

EI-MVSNet-UG-set		85.04 125	84.44 147	86.85 101	83.87 298	72.52 153	83.82 183	85.15 258	80.27 90	88.75 127	85.45 302	79.95 136	91.90 171	81.92 96	90.80 268	96.13 33

v144192		84.24 145	84.41 148	83.71 171	87.59 223	61.57 272	82.95 209	91.03 145	67.82 252	89.80 105	90.49 214	73.28 211	93.51 123	81.88 97	94.89 169	96.04 37

WR-MVS		83.56 163	84.40 149	81.06 232	93.43 70	54.88 341	78.67 281	85.02 262	81.24 79	90.74 90	91.56 177	72.85 215	91.08 193	68.00 253	98.04 39	97.23 16

v1921920		84.23 146	84.37 150	83.79 167	87.64 222	61.71 271	82.91 210	91.20 141	67.94 249	90.06 97	90.34 217	72.04 227	93.59 118	82.32 89	94.91 167	96.07 35

MVS_111021_HR		84.63 133	84.34 151	85.49 131	90.18 163	75.86 123	79.23 273	87.13 224	73.35 178	85.56 200	89.34 235	83.60 85	90.50 214	76.64 156	94.05 196	90.09 252

v2v482		84.09 149	84.24 152	83.62 173	87.13 232	61.40 274	82.71 215	89.71 186	72.19 203	89.55 115	91.41 180	70.70 235	93.20 133	81.02 101	93.76 201	96.25 31

EG-PatchMatch MVS		84.08 150	84.11 153	83.98 162	92.22 103	72.61 150	82.20 234	87.02 229	72.63 194	88.86 124	91.02 192	78.52 143	91.11 192	73.41 197	91.09 256	88.21 280

HQP-MVS		84.61 134	84.06 154	86.27 112	91.19 139	70.66 175	84.77 158	92.68 97	73.30 181	80.55 292	90.17 224	72.10 224	94.61 79	77.30 150	94.47 182	93.56 129

Effi-MVS+		83.90 156	84.01 155	83.57 177	87.22 230	65.61 226	86.55 132	92.40 103	78.64 114	81.34 283	84.18 321	83.65 84	92.93 144	74.22 181	87.87 311	92.17 190

alignmvs		83.94 155	83.98 156	83.80 166	87.80 216	67.88 204	84.54 167	91.42 134	73.27 184	88.41 138	87.96 256	72.33 221	90.83 204	76.02 166	94.11 193	92.69 162

MCST-MVS		84.36 139	83.93 157	85.63 127	91.59 124	71.58 168	83.52 191	92.13 112	61.82 300	83.96 235	89.75 231	79.93 137	93.46 125	78.33 132	94.34 186	91.87 201

ETV-MVS		84.31 141	83.91 158	85.52 129	88.58 199	70.40 178	84.50 169	93.37 64	78.76 113	84.07 233	78.72 374	80.39 130	95.13 65	73.82 191	92.98 221	91.04 222

MVS_111021_LR		84.28 143	83.76 159	85.83 124	89.23 182	83.07 55	80.99 248	83.56 278	72.71 193	86.07 189	89.07 241	81.75 116	86.19 293	77.11 152	93.36 209	88.24 279

AdaColmap		83.66 160	83.69 160	83.57 177	90.05 167	72.26 158	86.29 136	90.00 180	78.19 119	81.65 277	87.16 275	83.40 87	94.24 90	61.69 306	94.76 177	84.21 333

RRT-MVS		82.97 174	83.44 161	81.57 223	85.06 275	58.04 315	87.20 114	90.37 164	77.88 123	88.59 131	93.70 113	63.17 274	93.05 140	76.49 158	88.47 299	93.62 124

F-COLMAP		84.97 129	83.42 162	89.63 57	92.39 96	83.40 52	88.83 92	91.92 119	73.19 185	80.18 300	89.15 240	77.04 164	93.28 131	65.82 271	92.28 234	92.21 188

Effi-MVS+-dtu		85.82 111	83.38 163	93.14 4	87.13 232	91.15 3	87.70 108	88.42 204	74.57 161	83.56 243	85.65 297	78.49 145	94.21 91	72.04 212	92.88 223	94.05 101

V42		83.47 166	83.37 164	83.75 169	83.16 313	63.33 247	81.31 242	90.23 174	69.51 230	90.91 86	90.81 204	74.16 196	92.29 162	80.06 111	90.22 277	95.62 46

MVS_Test		82.47 181	83.22 165	80.22 245	82.62 318	57.75 319	82.54 221	91.96 118	71.16 214	82.89 254	92.52 149	77.41 157	90.50 214	80.04 112	87.84 312	92.40 177

DP-MVS Recon		84.05 151	83.22 165	86.52 107	91.73 122	75.27 125	83.23 201	92.40 103	72.04 204	82.04 267	88.33 251	77.91 150	93.95 102	66.17 265	95.12 159	90.34 245

PAPM_NR		83.23 169	83.19 167	83.33 183	90.90 148	65.98 222	88.19 101	90.78 152	78.13 120	80.87 288	87.92 259	73.49 206	92.42 155	70.07 229	88.40 300	91.60 211

SDMVSNet		81.90 196	83.17 168	78.10 276	88.81 192	62.45 261	76.08 322	86.05 243	73.67 170	83.41 245	93.04 127	82.35 100	80.65 342	70.06 230	95.03 162	91.21 218

KD-MVS_self_test		81.93 194	83.14 169	78.30 272	84.75 281	52.75 355	80.37 254	89.42 194	70.24 225	90.26 95	93.39 119	74.55 194	86.77 282	68.61 248	96.64 94	95.38 51

CNLPA		83.55 164	83.10 170	84.90 137	89.34 179	83.87 50	84.54 167	88.77 199	79.09 106	83.54 244	88.66 248	74.87 186	81.73 335	66.84 259	92.29 233	89.11 267

FA-MVS(test-final)		83.13 172	83.02 171	83.43 180	86.16 260	66.08 221	88.00 103	88.36 206	75.55 150	85.02 208	92.75 142	65.12 262	92.50 154	74.94 178	91.30 254	91.72 206

tfpnnormal		81.79 197	82.95 172	78.31 271	88.93 189	55.40 336	80.83 251	82.85 284	76.81 134	85.90 194	94.14 89	74.58 193	86.51 286	66.82 260	95.68 142	93.01 150

test_fmvsm_n_1920		83.60 162	82.89 173	85.74 125	85.22 273	77.74 99	84.12 174	90.48 159	59.87 326	86.45 185	91.12 189	75.65 178	85.89 301	82.28 90	90.87 265	93.58 127

CANet		83.79 158	82.85 174	86.63 104	86.17 258	72.21 160	83.76 186	91.43 132	77.24 132	74.39 351	87.45 269	75.36 181	95.42 52	77.03 153	92.83 224	92.25 187

h-mvs33		84.25 144	82.76 175	88.72 73	91.82 121	82.60 60	84.00 177	84.98 264	71.27 210	86.70 173	90.55 213	63.04 277	93.92 103	78.26 134	94.20 190	89.63 257

X-MVStestdata		85.04 125	82.70 176	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 419	86.57 55	95.80 28	87.35 27	97.62 64	94.20 92

TSAR-MVS + GP.		83.95 154	82.69 177	87.72 89	89.27 181	81.45 67	83.72 187	81.58 296	74.73 159	85.66 196	86.06 292	72.56 220	92.69 150	75.44 172	95.21 154	89.01 273

CLD-MVS		83.18 170	82.64 178	84.79 140	89.05 184	67.82 205	77.93 289	92.52 101	68.33 242	85.07 207	81.54 350	82.06 108	92.96 142	69.35 235	97.91 51	93.57 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
API-MVS		82.28 183	82.61 179	81.30 226	86.29 254	69.79 181	88.71 95	87.67 216	78.42 117	82.15 266	84.15 322	77.98 148	91.59 178	65.39 274	92.75 225	82.51 360

QAPM		82.59 178	82.59 180	82.58 204	86.44 246	66.69 215	89.94 67	90.36 165	67.97 248	84.94 212	92.58 147	72.71 217	92.18 163	70.63 224	87.73 313	88.85 274

114514_t		83.10 173	82.54 181	84.77 141	92.90 83	69.10 194	86.65 129	90.62 157	54.66 358	81.46 280	90.81 204	76.98 165	94.38 86	72.62 208	96.18 114	90.82 230

v148		82.31 182	82.48 182	81.81 219	85.59 267	59.66 296	81.47 241	86.02 244	72.85 189	88.05 147	90.65 211	70.73 234	90.91 200	75.15 175	91.79 244	94.87 66

EI-MVSNet		82.61 177	82.42 183	83.20 187	83.25 310	63.66 242	83.50 192	85.07 259	76.06 139	86.55 177	85.10 308	73.41 207	90.25 217	78.15 138	90.67 271	95.68 44

TinyColmap		81.25 203	82.34 184	77.99 279	85.33 270	60.68 287	82.32 227	88.33 207	71.26 212	86.97 168	92.22 161	77.10 163	86.98 277	62.37 298	95.17 156	86.31 306

GBi-Net		82.02 191	82.07 185	81.85 216	86.38 248	61.05 280	86.83 124	88.27 209	72.43 195	86.00 190	95.64 34	63.78 270	90.68 209	65.95 267	93.34 210	93.82 112

test1		82.02 191	82.07 185	81.85 216	86.38 248	61.05 280	86.83 124	88.27 209	72.43 195	86.00 190	95.64 34	63.78 270	90.68 209	65.95 267	93.34 210	93.82 112

OpenMVS	76.72 13	81.98 193	82.00 187	81.93 213	84.42 287	68.22 199	88.50 99	89.48 192	66.92 258	81.80 274	91.86 165	72.59 219	90.16 222	71.19 217	91.25 255	87.40 295

fmvsm_s_conf0.1_n_a		82.58 179	81.93 188	84.50 147	87.68 219	73.35 137	86.14 139	77.70 316	61.64 305	85.02 208	91.62 175	77.75 151	86.24 290	82.79 83	87.07 320	93.91 107

LF4IMVS		82.75 176	81.93 188	85.19 133	82.08 320	80.15 74	85.53 148	88.76 200	68.01 246	85.58 199	87.75 262	71.80 229	86.85 280	74.02 187	93.87 200	88.58 276

hse-mvs2		83.47 166	81.81 190	88.47 77	91.03 145	82.27 61	82.61 216	83.69 276	71.27 210	86.70 173	86.05 293	63.04 277	92.41 156	78.26 134	93.62 208	90.71 233

VPNet		80.25 222	81.68 191	75.94 306	92.46 95	47.98 381	76.70 309	81.67 294	73.45 175	84.87 213	92.82 138	74.66 192	86.51 286	61.66 307	96.85 87	93.33 134

SSC-MVS		77.55 251	81.64 192	65.29 377	90.46 157	20.33 423	73.56 346	68.28 380	85.44 37	88.18 144	94.64 64	70.93 233	81.33 337	71.25 215	92.03 239	94.20 92

UGNet		82.78 175	81.64 192	86.21 115	86.20 257	76.24 120	86.86 122	85.68 249	77.07 133	73.76 355	92.82 138	69.64 239	91.82 175	69.04 242	93.69 205	90.56 239
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
FMVSNet2		81.31 202	81.61 194	80.41 242	86.38 248	58.75 310	83.93 180	86.58 235	72.43 195	87.65 154	92.98 131	63.78 270	90.22 220	66.86 257	93.92 198	92.27 185

fmvsm_s_conf0.1_n		82.17 187	81.59 195	83.94 165	86.87 242	71.57 169	85.19 155	77.42 319	62.27 299	84.47 221	91.33 182	76.43 174	85.91 299	83.14 74	87.14 318	94.33 90

c3_l		81.64 198	81.59 195	81.79 220	80.86 337	59.15 303	78.61 282	90.18 176	68.36 241	87.20 159	87.11 277	69.39 240	91.62 177	78.16 136	94.43 184	94.60 75

MVSFormer		82.23 184	81.57 197	84.19 160	85.54 268	69.26 189	91.98 34	90.08 178	71.54 207	76.23 332	85.07 311	58.69 302	94.27 87	86.26 43	88.77 295	89.03 271

fmvsm_l_conf0.5_n		82.06 190	81.54 198	83.60 174	83.94 295	73.90 133	83.35 196	86.10 240	58.97 328	83.80 238	90.36 216	74.23 195	86.94 278	82.90 80	90.22 277	89.94 254

fmvsm_s_conf0.5_n_a		82.21 185	81.51 199	84.32 155	86.56 244	73.35 137	85.46 149	77.30 320	61.81 301	84.51 218	90.88 201	77.36 158	86.21 292	82.72 84	86.97 325	93.38 132

Fast-Effi-MVS+-dtu		82.54 180	81.41 200	85.90 121	85.60 266	76.53 115	83.07 204	89.62 190	73.02 188	79.11 310	83.51 326	80.74 127	90.24 219	68.76 245	89.29 288	90.94 225

sd_testset		79.95 230	81.39 201	75.64 309	88.81 192	58.07 314	76.16 321	82.81 285	73.67 170	83.41 245	93.04 127	80.96 124	77.65 358	58.62 323	95.03 162	91.21 218

fmvsm_s_conf0.5_n		81.91 195	81.30 202	83.75 169	86.02 262	71.56 170	84.73 161	77.11 323	62.44 296	84.00 234	90.68 208	76.42 175	85.89 301	83.14 74	87.11 319	93.81 115

Anonymous20240521		80.18 225	81.25 203	76.95 292	83.15 314	60.84 285	82.46 223	85.99 245	68.76 238	86.78 170	93.73 112	59.13 299	77.44 359	73.71 193	97.55 69	92.56 167

DELS-MVS		81.44 201	81.25 203	82.03 212	84.27 291	62.87 253	76.47 316	92.49 102	70.97 216	81.64 278	83.83 323	75.03 184	92.70 149	74.29 180	92.22 237	90.51 241
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
EIA-MVS		82.19 186	81.23 205	85.10 135	87.95 213	69.17 193	83.22 202	93.33 67	70.42 220	78.58 314	79.77 366	77.29 159	94.20 92	71.51 214	88.96 293	91.93 200

Anonymous202405211		80.51 214	81.19 206	78.49 268	88.48 201	57.26 322	76.63 311	82.49 287	81.21 80	84.30 228	92.24 160	67.99 248	86.24 290	62.22 299	95.13 157	91.98 199

BH-untuned		80.96 207	80.99 207	80.84 235	88.55 200	68.23 198	80.33 255	88.46 203	72.79 192	86.55 177	86.76 281	74.72 191	91.77 176	61.79 305	88.99 292	82.52 359

MG-MVS		80.32 220	80.94 208	78.47 269	88.18 207	52.62 358	82.29 228	85.01 263	72.01 205	79.24 309	92.54 148	69.36 241	93.36 130	70.65 223	89.19 291	89.45 259

PCF-MVS	74.62 15	82.15 188	80.92 209	85.84 123	89.43 177	72.30 157	80.53 252	91.82 123	57.36 342	87.81 151	89.92 228	77.67 154	93.63 113	58.69 322	95.08 160	91.58 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_l_conf0.5_n_a		81.46 200	80.87 210	83.25 185	83.73 300	73.21 142	83.00 207	85.59 251	58.22 334	82.96 253	90.09 226	72.30 222	86.65 284	81.97 95	89.95 281	89.88 255

Fast-Effi-MVS+		81.04 206	80.57 211	82.46 208	87.50 225	63.22 249	78.37 285	89.63 189	68.01 246	81.87 270	82.08 344	82.31 102	92.65 151	67.10 256	88.30 306	91.51 214

LFMVS		80.15 226	80.56 212	78.89 260	89.19 183	55.93 330	85.22 154	73.78 347	82.96 63	84.28 229	92.72 143	57.38 311	90.07 229	63.80 289	95.75 139	90.68 235

ab-mvs		79.67 231	80.56 212	76.99 291	88.48 201	56.93 324	84.70 162	86.06 242	68.95 236	80.78 289	93.08 126	75.30 182	84.62 313	56.78 332	90.90 263	89.43 261

PVSNet_Blended_VisFu		81.55 199	80.49 214	84.70 144	91.58 127	73.24 141	84.21 171	91.67 127	62.86 290	80.94 286	87.16 275	67.27 251	92.87 147	69.82 232	88.94 294	87.99 286

diffmvs		80.40 217	80.48 215	80.17 246	79.02 358	60.04 291	77.54 296	90.28 173	66.65 261	82.40 261	87.33 272	73.50 204	87.35 271	77.98 140	89.62 285	93.13 144
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PLC	73.85 16	82.09 189	80.31 216	87.45 92	90.86 150	80.29 73	85.88 141	90.65 155	68.17 245	76.32 331	86.33 287	73.12 213	92.61 152	61.40 309	90.02 280	89.44 260
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VNet		79.31 232	80.27 217	76.44 300	87.92 214	53.95 347	75.58 328	84.35 272	74.39 163	82.23 264	90.72 206	72.84 216	84.39 317	60.38 315	93.98 197	90.97 224

cl____		80.42 216	80.23 218	81.02 233	79.99 345	59.25 300	77.07 304	87.02 229	67.37 254	86.18 188	89.21 238	63.08 276	90.16 222	76.31 161	95.80 136	93.65 122

DIV-MVS_self_test		80.43 215	80.23 218	81.02 233	79.99 345	59.25 300	77.07 304	87.02 229	67.38 253	86.19 186	89.22 237	63.09 275	90.16 222	76.32 160	95.80 136	93.66 120

eth_miper_zixun_eth		80.84 208	80.22 220	82.71 201	81.41 329	60.98 283	77.81 291	90.14 177	67.31 256	86.95 169	87.24 274	64.26 265	92.31 160	75.23 174	91.61 248	94.85 70

BH-RMVSNet		80.53 213	80.22 220	81.49 225	87.19 231	66.21 220	77.79 292	86.23 238	74.21 164	83.69 239	88.50 249	73.25 212	90.75 206	63.18 295	87.90 310	87.52 293

xiu_mvs_v1_base_debu		80.84 208	80.14 222	82.93 196	88.31 204	71.73 164	79.53 264	87.17 221	65.43 273	79.59 302	82.73 338	76.94 166	90.14 225	73.22 200	88.33 302	86.90 300

xiu_mvs_v1_base		80.84 208	80.14 222	82.93 196	88.31 204	71.73 164	79.53 264	87.17 221	65.43 273	79.59 302	82.73 338	76.94 166	90.14 225	73.22 200	88.33 302	86.90 300

xiu_mvs_v1_base_debi		80.84 208	80.14 222	82.93 196	88.31 204	71.73 164	79.53 264	87.17 221	65.43 273	79.59 302	82.73 338	76.94 166	90.14 225	73.22 200	88.33 302	86.90 300

miper_ehance_all_eth		80.34 219	80.04 225	81.24 229	79.82 348	58.95 305	77.66 293	89.66 187	65.75 270	85.99 193	85.11 307	68.29 247	91.42 184	76.03 165	92.03 239	93.33 134

WB-MVS		76.06 270	80.01 226	64.19 380	89.96 170	20.58 422	72.18 355	68.19 381	83.21 59	86.46 184	93.49 117	70.19 237	78.97 353	65.96 266	90.46 276	93.02 149

MSDG		80.06 228	79.99 227	80.25 244	83.91 297	68.04 203	77.51 297	89.19 195	77.65 126	81.94 268	83.45 328	76.37 176	86.31 289	63.31 294	86.59 328	86.41 304

tttt0517		81.07 205	79.58 228	85.52 129	88.99 187	66.45 218	87.03 119	75.51 335	73.76 169	88.32 141	90.20 221	37.96 396	94.16 97	79.36 122	95.13 157	95.93 41

IterMVS-SCA-FT		80.64 212	79.41 229	84.34 154	83.93 296	69.66 184	76.28 318	81.09 299	72.43 195	86.47 183	90.19 222	60.46 287	93.15 136	77.45 147	86.39 331	90.22 246

patch_mono-2		78.89 235	79.39 230	77.41 288	84.78 279	68.11 201	75.60 326	83.11 281	60.96 315	79.36 306	89.89 229	75.18 183	72.97 371	73.32 199	92.30 231	91.15 220

wuyk23d		75.13 278	79.30 231	62.63 383	75.56 383	75.18 126	80.89 249	73.10 354	75.06 157	94.76 16	95.32 41	87.73 43	52.85 414	34.16 413	97.11 82	59.85 410

DPM-MVS		80.10 227	79.18 232	82.88 199	90.71 153	69.74 182	78.87 278	90.84 150	60.29 322	75.64 341	85.92 295	67.28 250	93.11 137	71.24 216	91.79 244	85.77 312

PM-MVS		80.20 224	79.00 233	83.78 168	88.17 208	86.66 19	81.31 242	66.81 389	69.64 229	88.33 140	90.19 222	64.58 263	83.63 325	71.99 213	90.03 279	81.06 378

mvsmamba		80.30 221	78.87 234	84.58 146	88.12 210	67.55 206	92.35 29	84.88 266	63.15 288	85.33 203	90.91 198	50.71 343	95.20 62	66.36 263	87.98 309	90.99 223

FE-MVS		79.98 229	78.86 235	83.36 182	86.47 245	66.45 218	89.73 70	84.74 270	72.80 191	84.22 232	91.38 181	44.95 376	93.60 117	63.93 287	91.50 251	90.04 253

test1111		78.53 242	78.85 236	77.56 285	92.22 103	47.49 383	82.61 216	69.24 378	72.43 195	85.28 204	94.20 85	51.91 337	90.07 229	65.36 275	96.45 103	95.11 61

AUN-MVS		81.18 204	78.78 237	88.39 79	90.93 147	82.14 62	82.51 222	83.67 277	64.69 282	80.29 296	85.91 296	51.07 341	92.38 157	76.29 162	93.63 207	90.65 237

mvs_anonymous		78.13 245	78.76 238	76.23 305	79.24 355	50.31 374	78.69 280	84.82 268	61.60 306	83.09 252	92.82 138	73.89 200	87.01 274	68.33 252	86.41 330	91.37 215

MAR-MVS		80.24 223	78.74 239	84.73 142	86.87 242	78.18 92	85.75 145	87.81 215	65.67 272	77.84 319	78.50 375	73.79 201	90.53 213	61.59 308	90.87 265	85.49 316
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
ECVR-MVS		78.44 243	78.63 240	77.88 281	91.85 117	48.95 377	83.68 188	69.91 374	72.30 201	84.26 231	94.20 85	51.89 338	89.82 234	63.58 290	96.02 122	94.87 66

FMVSNet3		78.80 238	78.55 241	79.57 254	82.89 317	56.89 326	81.76 236	85.77 247	69.04 235	86.00 190	90.44 215	51.75 339	90.09 228	65.95 267	93.34 210	91.72 206

test_yl		78.71 240	78.51 242	79.32 257	84.32 289	58.84 307	78.38 283	85.33 254	75.99 142	82.49 259	86.57 283	58.01 305	90.02 231	62.74 296	92.73 226	89.10 268

DCV-MVSNet		78.71 240	78.51 242	79.32 257	84.32 289	58.84 307	78.38 283	85.33 254	75.99 142	82.49 259	86.57 283	58.01 305	90.02 231	62.74 296	92.73 226	89.10 268

EPNet		80.37 218	78.41 244	86.23 113	76.75 372	73.28 139	87.18 116	77.45 318	76.24 138	68.14 383	88.93 243	65.41 261	93.85 105	69.47 234	96.12 118	91.55 213
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPMNet		78.88 236	78.28 245	80.68 239	79.58 349	62.64 257	82.58 218	94.16 32	74.80 158	75.72 339	92.59 145	48.69 350	95.56 42	73.48 196	82.91 367	83.85 338

cl22		78.97 234	78.21 246	81.24 229	77.74 362	59.01 304	77.46 300	87.13 224	65.79 267	84.32 225	85.10 308	58.96 301	90.88 202	75.36 173	92.03 239	93.84 110

PAPR		78.84 237	78.10 247	81.07 231	85.17 274	60.22 290	82.21 232	90.57 158	62.51 292	75.32 345	84.61 316	74.99 185	92.30 161	59.48 320	88.04 308	90.68 235

PVSNet_BlendedMVS		78.80 238	77.84 248	81.65 222	84.43 285	63.41 245	79.49 267	90.44 161	61.70 304	75.43 342	87.07 278	69.11 243	91.44 182	60.68 313	92.24 235	90.11 251

Vis-MVSNet (Re-imp)		77.82 248	77.79 249	77.92 280	88.82 191	51.29 368	83.28 197	71.97 362	74.04 165	82.23 264	89.78 230	57.38 311	89.41 246	57.22 331	95.41 146	93.05 148

Patchmtry		76.56 265	77.46 250	73.83 320	79.37 354	46.60 387	82.41 225	76.90 324	73.81 168	85.56 200	92.38 152	48.07 353	83.98 322	63.36 293	95.31 152	90.92 226

OpenMVS_ROB	70.19 17	77.77 250	77.46 250	78.71 264	84.39 288	61.15 278	81.18 246	82.52 286	62.45 295	83.34 247	87.37 270	66.20 256	88.66 258	64.69 282	85.02 347	86.32 305

CL-MVSNet_self_test		76.81 260	77.38 252	75.12 312	86.90 240	51.34 366	73.20 350	80.63 303	68.30 243	81.80 274	88.40 250	66.92 253	80.90 339	55.35 344	94.90 168	93.12 146

thisisatest0530		79.07 233	77.33 253	84.26 157	87.13 232	64.58 233	83.66 189	75.95 330	68.86 237	85.22 205	87.36 271	38.10 393	93.57 121	75.47 171	94.28 188	94.62 74

MonoMVSNet		76.66 262	77.26 254	74.86 314	79.86 347	54.34 344	86.26 137	86.08 241	71.08 215	85.59 198	88.68 246	53.95 329	85.93 297	63.86 288	80.02 382	84.32 329

CANet_DTU		77.81 249	77.05 255	80.09 247	81.37 330	59.90 294	83.26 198	88.29 208	69.16 233	67.83 386	83.72 324	60.93 284	89.47 241	69.22 238	89.70 284	90.88 228

pmmvs-eth3d		78.42 244	77.04 256	82.57 206	87.44 226	74.41 130	80.86 250	79.67 307	55.68 351	84.69 216	90.31 219	60.91 285	85.42 306	62.20 300	91.59 249	87.88 289

miper_enhance_ethall		77.83 247	76.93 257	80.51 240	76.15 379	58.01 316	75.47 330	88.82 198	58.05 336	83.59 241	80.69 354	64.41 264	91.20 188	73.16 206	92.03 239	92.33 181

MDA-MVSNet-bldmvs		77.47 252	76.90 258	79.16 259	79.03 357	64.59 232	66.58 387	75.67 333	73.15 186	88.86 124	88.99 242	66.94 252	81.23 338	64.71 281	88.22 307	91.64 210

xiu_mvs_v2_base		77.19 255	76.75 259	78.52 267	87.01 238	61.30 276	75.55 329	87.12 227	61.24 312	74.45 350	78.79 373	77.20 160	90.93 198	64.62 284	84.80 354	83.32 347

USDC		76.63 263	76.73 260	76.34 302	83.46 303	57.20 323	80.02 258	88.04 213	52.14 373	83.65 240	91.25 184	63.24 273	86.65 284	54.66 349	94.11 193	85.17 318

PS-MVSNAJ		77.04 257	76.53 261	78.56 266	87.09 236	61.40 274	75.26 331	87.13 224	61.25 311	74.38 352	77.22 386	76.94 166	90.94 197	64.63 283	84.83 353	83.35 346

TAMVS		78.08 246	76.36 262	83.23 186	90.62 154	72.87 143	79.08 274	80.01 306	61.72 303	81.35 282	86.92 280	63.96 269	88.78 256	50.61 370	93.01 220	88.04 285

IterMVS		76.91 258	76.34 263	78.64 265	80.91 335	64.03 239	76.30 317	79.03 310	64.88 281	83.11 250	89.16 239	59.90 293	84.46 315	68.61 248	85.15 345	87.42 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
XXY-MVS		74.44 289	76.19 264	69.21 354	84.61 283	52.43 359	71.70 358	77.18 322	60.73 318	80.60 290	90.96 196	75.44 179	69.35 383	56.13 337	88.33 302	85.86 311

miper_lstm_enhance		76.45 267	76.10 265	77.51 286	76.72 373	60.97 284	64.69 391	85.04 261	63.98 285	83.20 249	88.22 252	56.67 315	78.79 355	73.22 200	93.12 217	92.78 157

BH-w/o		76.57 264	76.07 266	78.10 276	86.88 241	65.92 223	77.63 294	86.33 236	65.69 271	80.89 287	79.95 363	68.97 245	90.74 207	53.01 360	85.25 342	77.62 389

TR-MVS		76.77 261	75.79 267	79.72 251	86.10 261	65.79 224	77.14 302	83.02 282	65.20 279	81.40 281	82.10 342	66.30 255	90.73 208	55.57 341	85.27 341	82.65 354

jason		77.42 253	75.75 268	82.43 209	87.10 235	69.27 188	77.99 288	81.94 292	51.47 377	77.84 319	85.07 311	60.32 289	89.00 250	70.74 222	89.27 290	89.03 271
jason: jason.
MVSTER		77.09 256	75.70 269	81.25 227	75.27 387	61.08 279	77.49 299	85.07 259	60.78 317	86.55 177	88.68 246	43.14 385	90.25 217	73.69 194	90.67 271	92.42 174

D2MVS		76.84 259	75.67 270	80.34 243	80.48 343	62.16 269	73.50 347	84.80 269	57.61 340	82.24 263	87.54 266	51.31 340	87.65 267	70.40 227	93.19 216	91.23 217

PVSNet_Blended		76.49 266	75.40 271	79.76 250	84.43 285	63.41 245	75.14 332	90.44 161	57.36 342	75.43 342	78.30 376	69.11 243	91.44 182	60.68 313	87.70 314	84.42 328

CDS-MVSNet		77.32 254	75.40 271	83.06 190	89.00 186	72.48 154	77.90 290	82.17 290	60.81 316	78.94 311	83.49 327	59.30 297	88.76 257	54.64 350	92.37 230	87.93 288
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
thres600view7		75.97 271	75.35 273	77.85 283	87.01 238	51.84 364	80.45 253	73.26 352	75.20 155	83.10 251	86.31 289	45.54 367	89.05 249	55.03 347	92.24 235	92.66 163

test_fmvs3		75.72 274	75.20 274	77.27 289	75.01 390	69.47 186	78.93 275	84.88 266	46.67 391	87.08 165	87.84 260	50.44 346	71.62 376	77.42 149	88.53 298	90.72 232

thres100view900		75.45 275	75.05 275	76.66 298	87.27 228	51.88 363	81.07 247	73.26 352	75.68 148	83.25 248	86.37 286	45.54 367	88.80 253	51.98 365	90.99 258	89.31 263

cascas		76.29 269	74.81 276	80.72 238	84.47 284	62.94 251	73.89 344	87.34 218	55.94 349	75.16 347	76.53 391	63.97 268	91.16 190	65.00 278	90.97 261	88.06 284

GA-MVS		75.83 272	74.61 277	79.48 256	81.87 322	59.25 300	73.42 348	82.88 283	68.68 239	79.75 301	81.80 347	50.62 344	89.46 242	66.85 258	85.64 338	89.72 256

testgi		72.36 305	74.61 277	65.59 374	80.56 342	42.82 402	68.29 377	73.35 351	66.87 259	81.84 271	89.93 227	72.08 226	66.92 396	46.05 392	92.54 228	87.01 299

test20.03		73.75 294	74.59 279	71.22 341	81.11 333	51.12 370	70.15 371	72.10 361	70.42 220	80.28 298	91.50 178	64.21 266	74.72 370	46.96 389	94.58 180	87.82 291

lupinMVS		76.37 268	74.46 280	82.09 211	85.54 268	69.26 189	76.79 307	80.77 302	50.68 384	76.23 332	82.82 336	58.69 302	88.94 251	69.85 231	88.77 295	88.07 282

EU-MVSNet		75.12 279	74.43 281	77.18 290	83.11 315	59.48 298	85.71 147	82.43 288	39.76 411	85.64 197	88.76 244	44.71 378	87.88 265	73.86 190	85.88 337	84.16 334

tfpn200view9		74.86 283	74.23 282	76.74 297	86.24 255	52.12 360	79.24 271	73.87 345	73.34 179	81.82 272	84.60 317	46.02 361	88.80 253	51.98 365	90.99 258	89.31 263

thres400		75.14 277	74.23 282	77.86 282	86.24 255	52.12 360	79.24 271	73.87 345	73.34 179	81.82 272	84.60 317	46.02 361	88.80 253	51.98 365	90.99 258	92.66 163

ppachtmachnet_test		74.73 286	74.00 284	76.90 294	80.71 340	56.89 326	71.53 361	78.42 312	58.24 333	79.32 308	82.92 335	57.91 308	84.26 319	65.60 273	91.36 253	89.56 258

1112_ss		74.82 284	73.74 285	78.04 278	89.57 172	60.04 291	76.49 315	87.09 228	54.31 359	73.66 356	79.80 364	60.25 290	86.76 283	58.37 324	84.15 358	87.32 296

Patchmatch-RL test		74.48 287	73.68 286	76.89 295	84.83 278	66.54 216	72.29 354	69.16 379	57.70 338	86.76 171	86.33 287	45.79 366	82.59 329	69.63 233	90.65 274	81.54 369

CMPMVS	59.41 20	75.12 279	73.57 287	79.77 249	75.84 382	67.22 207	81.21 245	82.18 289	50.78 382	76.50 328	87.66 264	55.20 325	82.99 328	62.17 302	90.64 275	89.09 270
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
baseline1		73.26 297	73.54 288	72.43 334	84.92 277	47.79 382	79.89 260	74.00 343	65.93 264	78.81 312	86.28 290	56.36 317	81.63 336	56.63 333	79.04 389	87.87 290

MVP-Stereo		75.81 273	73.51 289	82.71 201	89.35 178	73.62 134	80.06 256	85.20 256	60.30 321	73.96 353	87.94 257	57.89 309	89.45 243	52.02 364	74.87 400	85.06 320
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test2506		74.12 290	73.39 290	76.28 303	91.85 117	44.20 397	84.06 175	48.20 418	72.30 201	81.90 269	94.20 85	27.22 418	89.77 237	64.81 280	96.02 122	94.87 66

new-patchmatchnet		70.10 326	73.37 291	60.29 390	81.23 332	16.95 425	59.54 401	74.62 338	62.93 289	80.97 284	87.93 258	62.83 279	71.90 374	55.24 345	95.01 165	92.00 197

reproduce_monomvs		74.09 291	73.23 292	76.65 299	76.52 374	54.54 342	77.50 298	81.40 297	65.85 266	82.86 256	86.67 282	27.38 416	84.53 314	70.24 228	90.66 273	90.89 227

PatchMatch-RL		74.48 287	73.22 293	78.27 274	87.70 218	85.26 38	75.92 324	70.09 372	64.34 283	76.09 335	81.25 352	65.87 259	78.07 357	53.86 352	83.82 360	71.48 398

Test_1112_low_res		73.90 293	73.08 294	76.35 301	90.35 159	55.95 329	73.40 349	86.17 239	50.70 383	73.14 357	85.94 294	58.31 304	85.90 300	56.51 334	83.22 364	87.20 297

CR-MVSNet		74.00 292	73.04 295	76.85 296	79.58 349	62.64 257	82.58 218	76.90 324	50.50 385	75.72 339	92.38 152	48.07 353	84.07 321	68.72 247	82.91 367	83.85 338

pmmvs4		74.92 282	72.98 296	80.73 237	84.95 276	71.71 167	76.23 319	77.59 317	52.83 367	77.73 323	86.38 285	56.35 318	84.97 310	57.72 330	87.05 321	85.51 315

test_fmvs2		73.57 295	72.80 297	75.90 307	72.74 403	68.84 195	77.07 304	84.32 273	45.14 397	82.89 254	84.22 320	48.37 351	70.36 380	73.40 198	87.03 322	88.52 277

ET-MVSNet_ETH3D		75.28 276	72.77 298	82.81 200	83.03 316	68.11 201	77.09 303	76.51 328	60.67 319	77.60 324	80.52 358	38.04 394	91.15 191	70.78 220	90.68 270	89.17 266

PatchT		70.52 322	72.76 299	63.79 382	79.38 353	33.53 416	77.63 294	65.37 393	73.61 172	71.77 364	92.79 141	44.38 379	75.65 366	64.53 285	85.37 340	82.18 362

HyFIR lowres test		75.12 279	72.66 300	82.50 207	91.44 135	65.19 229	72.47 353	87.31 219	46.79 390	80.29 296	84.30 319	52.70 334	92.10 167	51.88 369	86.73 326	90.22 246

MVS		73.21 299	72.59 301	75.06 313	80.97 334	60.81 286	81.64 239	85.92 246	46.03 395	71.68 365	77.54 381	68.47 246	89.77 237	55.70 340	85.39 339	74.60 395

SCA		73.32 296	72.57 302	75.58 310	81.62 326	55.86 332	78.89 277	71.37 367	61.73 302	74.93 348	83.42 329	60.46 287	87.01 274	58.11 328	82.63 372	83.88 335

1314		73.22 298	72.56 303	75.20 311	80.41 344	57.84 317	81.64 239	85.36 253	51.68 376	73.10 358	76.65 390	61.45 282	85.19 308	63.54 291	79.21 387	82.59 355

HY-MVS	64.64 18	73.03 300	72.47 304	74.71 316	83.36 307	54.19 345	82.14 235	81.96 291	56.76 348	69.57 378	86.21 291	60.03 291	84.83 312	49.58 376	82.65 370	85.11 319

UnsupCasMVSNet_eth		71.63 313	72.30 305	69.62 351	76.47 376	52.70 357	70.03 372	80.97 300	59.18 327	79.36 306	88.21 253	60.50 286	69.12 384	58.33 326	77.62 394	87.04 298

FPMVS		72.29 307	72.00 306	73.14 325	88.63 197	85.00 40	74.65 337	67.39 383	71.94 206	77.80 321	87.66 264	50.48 345	75.83 365	49.95 372	79.51 383	58.58 412

Anonymous20231206		71.38 316	71.88 307	69.88 348	86.31 252	54.37 343	70.39 369	74.62 338	52.57 369	76.73 327	88.76 244	59.94 292	72.06 373	44.35 396	93.23 215	83.23 349

FMVSNet5		72.10 308	71.69 308	73.32 323	81.57 327	53.02 354	76.77 308	78.37 313	63.31 286	76.37 329	91.85 166	36.68 398	78.98 352	47.87 385	92.45 229	87.95 287

our_test_3		71.85 309	71.59 309	72.62 331	80.71 340	53.78 348	69.72 373	71.71 366	58.80 330	78.03 316	80.51 359	56.61 316	78.84 354	62.20 300	86.04 336	85.23 317

MIMVSNet		71.09 318	71.59 309	69.57 352	87.23 229	50.07 375	78.91 276	71.83 363	60.20 324	71.26 366	91.76 172	55.08 327	76.09 363	41.06 401	87.02 323	82.54 358

test_vis1_n_1920		71.30 317	71.58 311	70.47 344	77.58 365	59.99 293	74.25 338	84.22 274	51.06 379	74.85 349	79.10 370	55.10 326	68.83 386	68.86 244	79.20 388	82.58 356

thres200		72.34 306	71.55 312	74.70 317	83.48 302	51.60 365	75.02 333	73.71 348	70.14 226	78.56 315	80.57 357	46.20 359	88.20 263	46.99 388	89.29 288	84.32 329

CVMVSNet		72.62 303	71.41 313	76.28 303	83.25 310	60.34 289	83.50 192	79.02 311	37.77 415	76.33 330	85.10 308	49.60 349	87.41 270	70.54 225	77.54 395	81.08 376

EPNet_dtu		72.87 302	71.33 314	77.49 287	77.72 363	60.55 288	82.35 226	75.79 331	66.49 262	58.39 413	81.06 353	53.68 330	85.98 296	53.55 355	92.97 222	85.95 309
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing3		71.53 314	70.79 315	73.77 321	88.89 190	41.86 404	76.60 314	59.12 408	72.83 190	80.97 284	82.08 344	19.80 424	87.33 272	65.12 277	91.68 247	92.13 192

ttmdpeth		71.72 311	70.67 316	74.86 314	73.08 400	55.88 331	77.41 301	69.27 377	55.86 350	78.66 313	93.77 110	38.01 395	75.39 367	60.12 316	89.87 282	93.31 136

test_vis3_rt		71.42 315	70.67 316	73.64 322	69.66 410	70.46 177	66.97 386	89.73 184	42.68 407	88.20 143	83.04 331	43.77 380	60.07 408	65.35 276	86.66 327	90.39 244

CHOSEN 1792x2688		72.45 304	70.56 318	78.13 275	90.02 169	63.08 250	68.72 376	83.16 280	42.99 405	75.92 337	85.46 301	57.22 313	85.18 309	49.87 374	81.67 374	86.14 307

thisisatest0515		73.00 301	70.52 319	80.46 241	81.45 328	59.90 294	73.16 351	74.31 342	57.86 337	76.08 336	77.78 379	37.60 397	92.12 166	65.00 278	91.45 252	89.35 262

YYNet1		70.06 327	70.44 320	68.90 356	73.76 394	53.42 352	58.99 404	67.20 385	58.42 332	87.10 163	85.39 304	59.82 294	67.32 393	59.79 318	83.50 363	85.96 308

MDA-MVSNet_test_wron		70.05 328	70.44 320	68.88 357	73.84 393	53.47 350	58.93 405	67.28 384	58.43 331	87.09 164	85.40 303	59.80 295	67.25 394	59.66 319	83.54 362	85.92 310

test_fmvs1_n		70.94 319	70.41 322	72.53 333	73.92 392	66.93 213	75.99 323	84.21 275	43.31 404	79.40 305	79.39 368	43.47 381	68.55 388	69.05 241	84.91 350	82.10 363

MS-PatchMatch		70.93 320	70.22 323	73.06 326	81.85 323	62.50 260	73.82 345	77.90 314	52.44 370	75.92 337	81.27 351	55.67 322	81.75 334	55.37 343	77.70 393	74.94 394

pmmvs5		70.73 321	70.07 324	72.72 329	77.03 370	52.73 356	74.14 339	75.65 334	50.36 386	72.17 363	85.37 305	55.42 324	80.67 341	52.86 361	87.59 315	84.77 322

PAPM		71.77 310	70.06 325	76.92 293	86.39 247	53.97 346	76.62 312	86.62 234	53.44 363	63.97 403	84.73 315	57.79 310	92.34 159	39.65 404	81.33 378	84.45 327

Syy-MVS		69.40 336	70.03 326	67.49 366	81.72 324	38.94 409	71.00 363	61.99 399	61.38 308	70.81 370	72.36 402	61.37 283	79.30 350	64.50 286	85.18 343	84.22 331

test_vis1_n		70.29 323	69.99 327	71.20 342	75.97 381	66.50 217	76.69 310	80.81 301	44.22 400	75.43 342	77.23 385	50.00 347	68.59 387	66.71 261	82.85 369	78.52 388

EGC-MVSNET		74.79 285	69.99 327	89.19 65	94.89 38	87.00 15	91.89 37	86.28 237	1.09 420	2.23 422	95.98 27	81.87 114	89.48 240	79.76 115	95.96 125	91.10 221

UnsupCasMVSNet_bld		69.21 338	69.68 329	67.82 364	79.42 352	51.15 369	67.82 381	75.79 331	54.15 360	77.47 325	85.36 306	59.26 298	70.64 379	48.46 382	79.35 385	81.66 367

tpmvs		70.16 325	69.56 330	71.96 337	74.71 391	48.13 379	79.63 262	75.45 336	65.02 280	70.26 374	81.88 346	45.34 372	85.68 304	58.34 325	75.39 399	82.08 364

MVStest1		70.05 328	69.26 331	72.41 335	58.62 422	55.59 335	76.61 313	65.58 391	53.44 363	89.28 120	93.32 120	22.91 422	71.44 378	74.08 186	89.52 286	90.21 250

test_cas_vis1_n_1920		69.20 339	69.12 332	69.43 353	73.68 395	62.82 254	70.38 370	77.21 321	46.18 394	80.46 295	78.95 372	52.03 336	65.53 401	65.77 272	77.45 396	79.95 384

gg-mvs-nofinetune		68.96 340	69.11 333	68.52 362	76.12 380	45.32 393	83.59 190	55.88 413	86.68 29	64.62 402	97.01 9	30.36 409	83.97 323	44.78 395	82.94 366	76.26 391

test_fmvs1		69.57 334	69.05 334	71.14 343	69.15 411	65.77 225	73.98 342	83.32 279	42.83 406	77.77 322	78.27 377	43.39 384	68.50 389	68.39 251	84.38 357	79.15 386

WB-MVSnew		68.72 342	69.01 335	67.85 363	83.22 312	43.98 398	74.93 334	65.98 390	55.09 353	73.83 354	79.11 369	65.63 260	71.89 375	38.21 409	85.04 346	87.69 292

testing91		69.94 331	68.99 336	72.80 328	83.81 299	45.89 390	71.57 360	73.64 350	68.24 244	70.77 372	77.82 378	34.37 401	84.44 316	53.64 354	87.00 324	88.07 282

IB-MVS	62.13 19	71.64 312	68.97 337	79.66 253	80.80 339	62.26 266	73.94 343	76.90 324	63.27 287	68.63 382	76.79 388	33.83 402	91.84 174	59.28 321	87.26 316	84.88 321
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
PatchmatchNet		69.71 333	68.83 338	72.33 336	77.66 364	53.60 349	79.29 269	69.99 373	57.66 339	72.53 361	82.93 334	46.45 358	80.08 347	60.91 312	72.09 403	83.31 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
N_pmnet		70.20 324	68.80 339	74.38 318	80.91 335	84.81 43	59.12 403	76.45 329	55.06 354	75.31 346	82.36 341	55.74 321	54.82 413	47.02 387	87.24 317	83.52 342

CostFormer		69.98 330	68.68 340	73.87 319	77.14 368	50.72 372	79.26 270	74.51 340	51.94 375	70.97 369	84.75 314	45.16 375	87.49 269	55.16 346	79.23 386	83.40 345

WBMVS		68.76 341	68.43 341	69.75 350	83.29 308	40.30 407	67.36 383	72.21 360	57.09 345	77.05 326	85.53 299	33.68 403	80.51 343	48.79 380	90.90 263	88.45 278

WTY-MVS		67.91 345	68.35 342	66.58 371	80.82 338	48.12 380	65.96 388	72.60 355	53.67 362	71.20 367	81.68 349	58.97 300	69.06 385	48.57 381	81.67 374	82.55 357

MDTV_nov1_ep13			68.29 343		78.03 361	43.87 399	74.12 340	72.22 359	52.17 371	67.02 389	85.54 298	45.36 371	80.85 340	55.73 338	84.42 356

testing99		69.27 337	68.15 344	72.63 330	83.29 308	45.45 392	71.15 362	71.08 368	67.34 255	70.43 373	77.77 380	32.24 406	84.35 318	53.72 353	86.33 332	88.10 281

tpm		67.95 344	68.08 345	67.55 365	78.74 360	43.53 400	75.60 326	67.10 388	54.92 355	72.23 362	88.10 254	42.87 386	75.97 364	52.21 363	80.95 381	83.15 350

Patchmatch-test		65.91 357	67.38 346	61.48 388	75.51 384	43.21 401	68.84 375	63.79 397	62.48 293	72.80 360	83.42 329	44.89 377	59.52 410	48.27 384	86.45 329	81.70 366

sss		66.92 349	67.26 347	65.90 373	77.23 367	51.10 371	64.79 390	71.72 365	52.12 374	70.13 375	80.18 361	57.96 307	65.36 402	50.21 371	81.01 380	81.25 373

dmvs_re		66.81 352	66.98 348	66.28 372	76.87 371	58.68 311	71.66 359	72.24 358	60.29 322	69.52 379	73.53 399	52.38 335	64.40 404	44.90 394	81.44 377	75.76 392

baseline2		69.77 332	66.89 349	78.41 270	79.51 351	58.09 313	76.23 319	69.57 375	57.50 341	64.82 401	77.45 383	46.02 361	88.44 259	53.08 357	77.83 391	88.70 275

tpm2		68.45 343	66.83 350	73.30 324	78.93 359	48.50 378	79.76 261	71.76 364	47.50 389	69.92 376	83.60 325	42.07 387	88.40 260	48.44 383	79.51 383	83.01 352

test-LLR		67.21 347	66.74 351	68.63 360	76.45 377	55.21 338	67.89 378	67.14 386	62.43 297	65.08 398	72.39 400	43.41 382	69.37 381	61.00 310	84.89 351	81.31 371

tpmrst		66.28 356	66.69 352	65.05 378	72.82 402	39.33 408	78.20 286	70.69 371	53.16 366	67.88 385	80.36 360	48.18 352	74.75 369	58.13 327	70.79 405	81.08 376

JIA-IIPM		69.41 335	66.64 353	77.70 284	73.19 397	71.24 172	75.67 325	65.56 392	70.42 220	65.18 397	92.97 133	33.64 404	83.06 326	53.52 356	69.61 409	78.79 387

testing11		67.38 346	65.93 354	71.73 339	83.37 306	46.60 387	70.95 365	69.40 376	62.47 294	66.14 390	76.66 389	31.22 407	84.10 320	49.10 378	84.10 359	84.49 325

test_f		64.31 366	65.85 355	59.67 391	66.54 415	62.24 268	57.76 407	70.96 369	40.13 409	84.36 223	82.09 343	46.93 355	51.67 415	61.99 303	81.89 373	65.12 406

KD-MVS_2432*1600		66.87 350	65.81 356	70.04 346	67.50 412	47.49 383	62.56 395	79.16 308	61.21 313	77.98 317	80.61 355	25.29 420	82.48 330	53.02 358	84.92 348	80.16 382

miper_refine_blended		66.87 350	65.81 356	70.04 346	67.50 412	47.49 383	62.56 395	79.16 308	61.21 313	77.98 317	80.61 355	25.29 420	82.48 330	53.02 358	84.92 348	80.16 382

PVSNet	58.17 21	66.41 355	65.63 358	68.75 358	81.96 321	49.88 376	62.19 397	72.51 357	51.03 380	68.04 384	75.34 396	50.84 342	74.77 368	45.82 393	82.96 365	81.60 368

UWE-MVS		66.43 354	65.56 359	69.05 355	84.15 293	40.98 405	73.06 352	64.71 395	54.84 356	76.18 334	79.62 367	29.21 411	80.50 344	38.54 408	89.75 283	85.66 313

testing222		66.93 348	65.30 360	71.81 338	83.38 305	45.83 391	72.06 356	67.50 382	64.12 284	69.68 377	76.37 392	27.34 417	83.00 327	38.88 405	88.38 301	86.62 303

tpm cat1		66.76 353	65.21 361	71.42 340	77.09 369	50.62 373	78.01 287	73.68 349	44.89 398	68.64 381	79.00 371	45.51 369	82.42 332	49.91 373	70.15 406	81.23 375

test0.0.03 1		64.66 363	64.36 362	65.57 375	75.03 389	46.89 386	64.69 391	61.58 405	62.43 297	71.18 368	77.54 381	43.41 382	68.47 390	40.75 403	82.65 370	81.35 370

test_vis1_rt		65.64 359	64.09 363	70.31 345	66.09 416	70.20 180	61.16 398	81.60 295	38.65 412	72.87 359	69.66 405	52.84 332	60.04 409	56.16 336	77.77 392	80.68 380

myMVS_eth3d		64.66 363	63.89 364	66.97 369	81.72 324	37.39 412	71.00 363	61.99 399	61.38 308	70.81 370	72.36 402	20.96 423	79.30 350	49.59 375	85.18 343	84.22 331

test-mter		65.00 361	63.79 365	68.63 360	76.45 377	55.21 338	67.89 378	67.14 386	50.98 381	65.08 398	72.39 400	28.27 414	69.37 381	61.00 310	84.89 351	81.31 371

ADS-MVSNet2		65.87 358	63.64 366	72.55 332	73.16 398	56.92 325	67.10 384	74.81 337	49.74 387	66.04 392	82.97 332	46.71 356	77.26 360	42.29 398	69.96 407	83.46 343

UBG		64.34 365	63.35 367	67.30 367	83.50 301	40.53 406	67.46 382	65.02 394	54.77 357	67.54 388	74.47 398	32.99 405	78.50 356	40.82 402	83.58 361	82.88 353

ETVMVS		64.67 362	63.34 368	68.64 359	83.44 304	41.89 403	69.56 374	61.70 404	61.33 310	68.74 380	75.76 394	28.76 412	79.35 349	34.65 412	86.16 335	84.67 324

mvsany_test3		65.48 360	62.97 369	73.03 327	69.99 409	76.17 121	64.83 389	43.71 420	43.68 402	80.25 299	87.05 279	52.83 333	63.09 407	51.92 368	72.44 402	79.84 385

MVS-HIRNet		61.16 373	62.92 370	55.87 394	79.09 356	35.34 415	71.83 357	57.98 412	46.56 392	59.05 410	91.14 188	49.95 348	76.43 362	38.74 406	71.92 404	55.84 413

EPMVS		62.47 367	62.63 371	62.01 384	70.63 408	38.74 410	74.76 335	52.86 415	53.91 361	67.71 387	80.01 362	39.40 391	66.60 397	55.54 342	68.81 411	80.68 380

dmvs_testset		60.59 377	62.54 372	54.72 396	77.26 366	27.74 419	74.05 341	61.00 406	60.48 320	65.62 395	67.03 409	55.93 320	68.23 391	32.07 416	69.46 410	68.17 403

ADS-MVSNet		61.90 369	62.19 373	61.03 389	73.16 398	36.42 414	67.10 384	61.75 402	49.74 387	66.04 392	82.97 332	46.71 356	63.21 405	42.29 398	69.96 407	83.46 343

E-PMN		61.59 371	61.62 374	61.49 387	66.81 414	55.40 336	53.77 410	60.34 407	66.80 260	58.90 411	65.50 410	40.48 390	66.12 399	55.72 339	86.25 333	62.95 408

DSMNet-mixed		60.98 375	61.61 375	59.09 393	72.88 401	45.05 395	74.70 336	46.61 419	26.20 417	65.34 396	90.32 218	55.46 323	63.12 406	41.72 400	81.30 379	69.09 402

EMVS		61.10 374	60.81 376	61.99 385	65.96 417	55.86 332	53.10 411	58.97 410	67.06 257	56.89 415	63.33 411	40.98 388	67.03 395	54.79 348	86.18 334	63.08 407

PMMVS		61.65 370	60.38 377	65.47 376	65.40 419	69.26 189	63.97 393	61.73 403	36.80 416	60.11 408	68.43 407	59.42 296	66.35 398	48.97 379	78.57 390	60.81 409

TESTMET0.1,1		61.29 372	60.32 378	64.19 380	72.06 404	51.30 367	67.89 378	62.09 398	45.27 396	60.65 407	69.01 406	27.93 415	64.74 403	56.31 335	81.65 376	76.53 390

dp		60.70 376	60.29 379	61.92 386	72.04 405	38.67 411	70.83 366	64.08 396	51.28 378	60.75 406	77.28 384	36.59 399	71.58 377	47.41 386	62.34 413	75.52 393

pmmvs3		62.47 367	60.02 380	69.80 349	71.58 406	64.00 240	70.52 368	58.44 411	39.77 410	66.05 391	75.84 393	27.10 419	72.28 372	46.15 391	84.77 355	73.11 396

PMMVS2		55.64 382	59.27 381	44.74 398	64.30 420	12.32 426	40.60 413	49.79 417	53.19 365	65.06 400	84.81 313	53.60 331	49.76 416	32.68 415	89.41 287	72.15 397

new_pmnet		55.69 381	57.66 382	49.76 397	75.47 385	30.59 417	59.56 400	51.45 416	43.62 403	62.49 404	75.48 395	40.96 389	49.15 417	37.39 410	72.52 401	69.55 401

CHOSEN 280x420		59.08 378	56.52 383	66.76 370	76.51 375	64.39 236	49.62 412	59.00 409	43.86 401	55.66 416	68.41 408	35.55 400	68.21 392	43.25 397	76.78 398	67.69 404

mvsany_test1		58.48 379	56.47 384	64.50 379	65.90 418	68.21 200	56.95 408	42.11 421	38.30 413	65.69 394	77.19 387	56.96 314	59.35 411	46.16 390	58.96 414	65.93 405

PVSNet_0	51.08 22	56.10 380	54.97 385	59.48 392	75.12 388	53.28 353	55.16 409	61.89 401	44.30 399	59.16 409	62.48 412	54.22 328	65.91 400	35.40 411	47.01 415	59.25 411

MVE	40.22 23	51.82 383	50.47 386	55.87 394	62.66 421	51.91 362	31.61 415	39.28 422	40.65 408	50.76 417	74.98 397	56.24 319	44.67 418	33.94 414	64.11 412	71.04 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		41.90 384	42.65 387	39.67 399	70.86 407	21.11 421	61.01 399	21.42 426	57.36 342	57.97 414	50.06 415	16.40 425	58.73 412	21.03 419	27.69 419	39.17 415

kuosan		30.83 385	32.17 388	26.83 401	53.36 423	19.02 424	57.90 406	20.44 427	38.29 414	38.01 418	37.82 417	15.18 426	33.45 420	7.74 421	20.76 420	28.03 416

test_method		30.46 386	29.60 389	33.06 400	17.99 425	3.84 428	13.62 416	73.92 344	2.79 419	18.29 421	53.41 414	28.53 413	43.25 419	22.56 417	35.27 417	52.11 414

cdsmvs_eth3d_5k		20.81 387	27.75 390	0.00 406	0.00 429	0.00 431	0.00 417	85.44 252	0.00 424	0.00 425	82.82 336	81.46 118	0.00 425	0.00 424	0.00 423	0.00 421

tmp_tt		20.25 388	24.50 391	7.49 403	4.47 426	8.70 427	34.17 414	25.16 424	1.00 421	32.43 420	18.49 418	39.37 392	9.21 422	21.64 418	43.75 416	4.57 418

ab-mvs-re		6.65 389	8.87 392	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	79.80 364	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		6.41 390	8.55 393	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	76.94 166	0.00 425	0.00 424	0.00 423	0.00 421

test123		6.27 391	8.08 394	0.84 404	1.11 428	0.57 429	62.90 394	0.82 428	0.54 422	1.07 424	2.75 423	1.26 427	0.30 423	1.04 422	1.26 422	1.66 419

testmvs		5.91 392	7.65 395	0.72 405	1.20 427	0.37 430	59.14 402	0.67 429	0.49 423	1.11 423	2.76 422	0.94 428	0.24 424	1.02 423	1.47 421	1.55 420

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						37.39 412								52.61 362

FOURS1					96.08 12	87.41 14	96.19 2	95.83 5	92.95 3	96.57 3

MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 146					96.05 9	87.45 23	98.17 35	92.40 177

PC_three_1452									58.96 329	90.06 97	91.33 182	80.66 128	93.03 141	75.78 167	95.94 128	92.48 171

No_MVS				88.81 71	91.55 129	77.99 94		91.01 146					96.05 9	87.45 23	98.17 35	92.40 177

test_one_0601					93.85 62	73.27 140		94.11 38	86.57 30	93.47 41	94.64 64	88.42 28

eth-test2					0.00 429

eth-test					0.00 429

ZD-MVS					92.22 103	80.48 71		91.85 121	71.22 213	90.38 92	92.98 131	86.06 64	96.11 7	81.99 94	96.75 92

IU-MVS					94.18 50	72.64 147		90.82 151	56.98 346	89.67 109				85.78 52	97.92 49	93.28 137

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 185	81.12 122	94.68 76	74.48 179	95.35 148	92.29 183

test_241102_TWO								93.71 55	83.77 52	93.49 39	94.27 79	89.27 23	95.84 24	86.03 49	97.82 54	92.04 195

test_241102_ONE					94.18 50	72.65 145		93.69 56	83.62 54	94.11 26	93.78 108	90.28 14	95.50 49

save fliter					93.75 63	77.44 103	86.31 135	89.72 185	70.80 217

test_0728_THIRD									85.33 38	93.75 34	94.65 61	87.44 46	95.78 32	87.41 25	98.21 32	92.98 152

test_0728_SECOND				86.79 102	94.25 48	72.45 155	90.54 52	94.10 39					95.88 18	86.42 39	97.97 46	92.02 196

test0726					94.16 53	72.56 151	90.63 49	93.90 48	83.61 55	93.75 34	94.49 69	89.76 18

GSMVS																83.88 335

test_part2					93.86 61	77.77 98				92.84 51

sam_mvs1												46.11 360				83.88 335

sam_mvs												45.92 365

ambc				82.98 193	90.55 156	64.86 231	88.20 100	89.15 196		89.40 118	93.96 99	71.67 231	91.38 186	78.83 126	96.55 97	92.71 161

MTGPA								91.81 125

test_post1							78.85 279				3.13 420	45.19 374	80.13 346	58.11 328

test_post											3.10 421	45.43 370	77.22 361

patchmatchnet-post											81.71 348	45.93 364	87.01 274

GG-mvs-BLEND				67.16 368	73.36 396	46.54 389	84.15 173	55.04 414		58.64 412	61.95 413	29.93 410	83.87 324	38.71 407	76.92 397	71.07 399

MTMP							90.66 48	33.14 423

gm-plane-assit					75.42 386	44.97 396			52.17 371		72.36 402		87.90 264	54.10 351

test9_res														80.83 104	96.45 103	90.57 238

TEST9					92.34 98	79.70 78	83.94 178	90.32 167	65.41 276	84.49 219	90.97 194	82.03 109	93.63 113

test_8					92.09 107	78.87 85	83.82 183	90.31 169	65.79 267	84.36 223	90.96 196	81.93 111	93.44 126

agg_prior2														79.68 117	96.16 115	90.22 246

agg_prior					91.58 127	77.69 100		90.30 170		84.32 225			93.18 134

TestCases				89.68 55	91.59 124	83.40 52		95.44 10	79.47 99	88.00 148	93.03 129	82.66 94	91.47 180	70.81 218	96.14 116	94.16 96

test_prior4						78.97 84	84.59 164

test_prior2							83.37 195		75.43 152	84.58 217	91.57 176	81.92 113		79.54 119	96.97 85

test_prior				86.32 110	90.59 155	71.99 162		92.85 92					94.17 95			92.80 156

旧先验2							81.73 237		56.88 347	86.54 182			84.90 311	72.81 207

新几何2							81.72 238

新几何1				82.95 195	93.96 59	78.56 88		80.24 304	55.45 352	83.93 236	91.08 191	71.19 232	88.33 261	65.84 270	93.07 218	81.95 365

旧先验1					91.97 111	71.77 163		81.78 293			91.84 167	73.92 199			93.65 206	83.61 341

无先验							82.81 213	85.62 250	58.09 335				91.41 185	67.95 255		84.48 326

原ACMM2							82.26 231

原ACMM1				84.60 145	92.81 89	74.01 132		91.50 130	62.59 291	82.73 258	90.67 210	76.53 173	94.25 89	69.24 236	95.69 141	85.55 314

test222					93.31 73	76.54 113	79.38 268	77.79 315	52.59 368	82.36 262	90.84 203	66.83 254			91.69 246	81.25 373

testdata2													86.43 288	63.52 292

segment_acmp												81.94 110

testdata				79.54 255	92.87 84	72.34 156		80.14 305	59.91 325	85.47 202	91.75 173	67.96 249	85.24 307	68.57 250	92.18 238	81.06 378

testdata1							79.62 263		73.95 167

test12				86.57 105	90.74 151	72.63 149		90.69 154		82.76 257		79.20 139	94.80 73		95.32 150	92.27 185

plane_prior7					93.45 68	77.31 106

plane_prior6					92.61 90	76.54 113						74.84 187

plane_prior5								93.61 59					95.22 59	80.78 105	95.83 134	94.46 80

plane_prior4											92.95 134

plane_prior3						76.85 111			77.79 125	86.55 177

plane_prior2							89.45 82		79.44 101

plane_prior1					92.83 88

plane_prior						76.42 116	87.15 117		75.94 145						95.03 162

n2								0.00 430

nn								0.00 430

door-mid								74.45 341

lessismore_v0				85.95 119	91.10 144	70.99 174		70.91 370		91.79 69	94.42 74	61.76 281	92.93 144	79.52 120	93.03 219	93.93 105

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 55	98.73 7	95.23 58

test11								91.46 131

door								72.57 356

HQP5-MVS						70.66 175

HQP-NCC					91.19 139		84.77 158		73.30 181	80.55 292

ACMP_Plane					91.19 139		84.77 158		73.30 181	80.55 292

BP-MVS														77.30 150

HQP4-MVS										80.56 291			94.61 79			93.56 129

HQP3-MVS								92.68 97							94.47 182

HQP2-MVS												72.10 224

NP-MVS					91.95 112	74.55 129					90.17 224

MDTV_nov1_ep13_2view						27.60 420	70.76 367		46.47 393	61.27 405		45.20 373		49.18 377		83.75 340

ACMMP++_ref															95.74 140

ACMMP++															97.35 75

Test By Simon												79.09 140

ITE_SJBPF				90.11 49	90.72 152	84.97 41		90.30 170	81.56 76	90.02 99	91.20 187	82.40 99	90.81 205	73.58 195	94.66 178	94.56 76

DeepMVS_CX				24.13 402	32.95 424	29.49 418		21.63 425	12.07 418	37.95 419	45.07 416	30.84 408	19.21 421	17.94 420	33.06 418	23.69 417

High-resolution multi-view benchmark