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 33	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 14	85.07 55	99.27 1	99.54 1

TDRefinement		93.52 2	93.39 3	93.88 1	95.94 14	90.26 3	95.70 4	96.46 2	90.58 8	92.86 47	96.29 16	88.16 33	94.17 92	86.07 45	98.48 17	97.22 19

LTVRE_ROB	86.10 1	93.04 3	93.44 2	91.82 20	93.73 60	85.72 30	96.79 1	95.51 8	88.86 12	95.63 8	96.99 8	84.81 67	93.16 132	91.10 1	97.53 70	96.58 30
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
HPM-MVS_fast		92.50 4	92.54 5	92.37 5	95.93 15	85.81 29	92.99 12	94.23 22	85.21 35	92.51 55	95.13 44	90.65 9	95.34 52	88.06 8	98.15 34	95.95 41

SR-MVS-dyc-post		92.41 5	92.41 6	92.39 4	94.13 51	88.95 5	92.87 13	94.16 27	88.75 14	93.79 28	94.43 68	88.83 24	95.51 44	87.16 29	97.60 64	92.73 158

SR-MVS		92.23 6	92.34 7	91.91 15	94.89 37	87.85 8	92.51 23	93.87 45	88.20 19	93.24 39	94.02 91	90.15 16	95.67 34	86.82 33	97.34 74	92.19 185

HPM-MVS		92.13 7	92.20 9	91.91 15	95.58 25	84.67 42	93.51 8	94.85 14	82.88 59	91.77 68	93.94 99	90.55 12	95.73 31	88.50 6	98.23 27	95.33 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
APD-MVS_3200maxsize		92.05 8	92.24 8	91.48 21	93.02 78	85.17 35	92.47 25	95.05 13	87.65 22	93.21 40	94.39 73	90.09 17	95.08 61	86.67 35	97.60 64	94.18 95

COLMAP_ROB	83.01 3	91.97 9	91.95 10	92.04 10	93.68 62	86.15 20	93.37 10	95.10 12	90.28 9	92.11 61	95.03 46	89.75 20	94.93 65	79.95 111	98.27 25	95.04 64
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMMP		91.91 10	91.87 15	92.03 11	95.53 26	85.91 24	93.35 11	94.16 27	82.52 62	92.39 58	94.14 85	89.15 23	95.62 35	87.35 24	98.24 26	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
mPP-MVS		91.69 11	91.47 22	92.37 5	96.04 12	88.48 7	92.72 17	92.60 93	83.09 56	91.54 70	94.25 79	87.67 41	95.51 44	87.21 28	98.11 35	93.12 146

CP-MVS		91.67 12	91.58 19	91.96 12	95.29 30	87.62 9	93.38 9	93.36 59	83.16 55	91.06 81	94.00 92	88.26 30	95.71 32	87.28 27	98.39 20	92.55 167

XVS		91.54 13	91.36 24	92.08 8	95.64 23	86.25 18	92.64 18	93.33 61	85.07 36	89.99 99	94.03 90	86.57 52	95.80 25	87.35 24	97.62 62	94.20 92

MTAPA		91.52 14	91.60 18	91.29 26	96.59 4	86.29 17	92.02 30	91.81 118	84.07 44	92.00 64	94.40 72	86.63 51	95.28 55	88.59 5	98.31 23	92.30 178

UA-Net		91.49 15	91.53 20	91.39 23	94.98 34	82.95 54	93.52 7	92.79 88	88.22 18	88.53 129	97.64 2	83.45 81	94.55 78	86.02 48	98.60 12	96.67 27

ACMMPR		91.49 15	91.35 26	91.92 14	95.74 19	85.88 26	92.58 21	93.25 67	81.99 65	91.40 72	94.17 84	87.51 42	95.87 19	87.74 13	97.76 55	93.99 103

LPG-MVS_test		91.47 17	91.68 16	90.82 33	94.75 40	81.69 59	90.00 57	94.27 19	82.35 63	93.67 33	94.82 52	91.18 4	95.52 42	85.36 52	98.73 6	95.23 59

region2R		91.44 18	91.30 30	91.87 17	95.75 18	85.90 25	92.63 20	93.30 65	81.91 67	90.88 87	94.21 80	87.75 39	95.87 19	87.60 18	97.71 58	93.83 112

HFP-MVS		91.30 19	91.39 23	91.02 29	95.43 28	84.66 43	92.58 21	93.29 66	81.99 65	91.47 71	93.96 96	88.35 29	95.56 39	87.74 13	97.74 57	92.85 155

ZNCC-MVS		91.26 20	91.34 27	91.01 30	95.73 20	83.05 52	92.18 28	94.22 24	80.14 88	91.29 76	93.97 93	87.93 38	95.87 19	88.65 4	97.96 45	94.12 99

APDe-MVS		91.22 21	91.92 11	89.14 64	92.97 80	78.04 89	92.84 15	94.14 31	83.33 53	93.90 24	95.73 27	88.77 25	96.41 2	87.60 18	97.98 42	92.98 152
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PGM-MVS		91.20 22	90.95 39	91.93 13	95.67 22	85.85 27	90.00 57	93.90 42	80.32 85	91.74 69	94.41 71	88.17 32	95.98 11	86.37 38	97.99 40	93.96 106

SteuartSystems-ACMMP		91.16 23	91.36 24	90.55 37	93.91 56	80.97 66	91.49 37	93.48 57	82.82 60	92.60 54	93.97 93	88.19 31	96.29 5	87.61 17	98.20 31	94.39 87
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		91.14 24	90.91 40	91.83 18	96.18 10	86.88 13	92.20 27	93.03 80	82.59 61	88.52 130	94.37 74	86.74 50	95.41 50	86.32 39	98.21 29	93.19 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
GST-MVS		90.96 25	91.01 36	90.82 33	95.45 27	82.73 55	91.75 35	93.74 48	80.98 79	91.38 73	93.80 103	87.20 46	95.80 25	87.10 31	97.69 59	93.93 107

MP-MVS-pluss		90.81 26	91.08 33	89.99 46	95.97 13	79.88 71	88.13 99	94.51 17	75.79 140	92.94 44	94.96 47	88.36 28	95.01 63	90.70 2	98.40 19	95.09 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMH+	77.89 11	90.73 27	91.50 21	88.44 76	93.00 79	76.26 116	89.65 70	95.55 7	87.72 21	93.89 26	94.94 48	91.62 3	93.44 123	78.35 128	98.76 3	95.61 48

ACMMP_NAP		90.65 28	91.07 35	89.42 59	95.93 15	79.54 76	89.95 61	93.68 52	77.65 119	91.97 65	94.89 49	88.38 27	95.45 48	89.27 3	97.87 50	93.27 138

ACMM	79.39 9	90.65 28	90.99 37	89.63 55	95.03 33	83.53 47	89.62 71	93.35 60	79.20 100	93.83 27	93.60 111	90.81 7	92.96 138	85.02 57	98.45 18	92.41 172
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		90.60 30	90.34 47	91.38 24	89.03 184	84.23 45	93.58 6	94.68 16	90.65 7	90.33 93	93.95 98	84.50 69	95.37 51	80.87 101	95.50 143	94.53 79

ACMP	79.16 10	90.54 31	90.60 45	90.35 41	94.36 43	80.98 65	89.16 81	94.05 36	79.03 103	92.87 46	93.74 107	90.60 11	95.21 58	82.87 79	98.76 3	94.87 67
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DPE-MVS		90.53 32	91.08 33	88.88 67	93.38 69	78.65 83	89.15 82	94.05 36	84.68 40	93.90 24	94.11 88	88.13 34	96.30 4	84.51 63	97.81 52	91.70 201
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SED-MVS		90.46 33	91.64 17	86.93 97	94.18 46	72.65 143	90.47 51	93.69 50	83.77 47	94.11 22	94.27 75	90.28 14	95.84 23	86.03 46	97.92 46	92.29 179

SMA-MVS		90.31 34	90.48 46	89.83 50	95.31 29	79.52 77	90.98 43	93.24 68	75.37 147	92.84 48	95.28 38	85.58 62	96.09 7	87.92 10	97.76 55	93.88 110
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 35	90.80 42	88.68 74	92.86 84	77.09 104	91.19 40	95.74 5	81.38 73	92.28 59	93.80 103	86.89 49	94.64 73	85.52 51	97.51 71	94.30 91

v7n		90.13 36	90.96 38	87.65 89	91.95 110	71.06 171	89.99 59	93.05 77	86.53 26	94.29 18	96.27 17	82.69 88	94.08 95	86.25 42	97.63 61	97.82 8

PMVS	80.48 6	90.08 37	90.66 44	88.34 79	96.71 3	92.97 1	90.31 54	89.57 181	88.51 17	90.11 95	95.12 45	90.98 6	88.92 247	77.55 142	97.07 82	83.13 335
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DVP-MVS++		90.07 38	91.09 32	87.00 95	91.55 127	72.64 145	96.19 2	94.10 34	85.33 33	93.49 36	94.64 60	81.12 117	95.88 17	87.41 22	95.94 126	92.48 169

DVP-MVS		90.06 39	91.32 28	86.29 109	94.16 49	72.56 149	90.54 48	91.01 139	83.61 50	93.75 30	94.65 57	89.76 18	95.78 28	86.42 36	97.97 43	90.55 231
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 39	91.92 11	84.47 148	96.56 6	58.83 303	89.04 83	92.74 90	91.40 5	96.12 4	96.06 22	87.23 45	95.57 38	79.42 120	98.74 5	99.00 2

PEN-MVS		90.03 41	91.88 14	84.48 147	96.57 5	58.88 300	88.95 84	93.19 69	91.62 4	96.01 6	96.16 20	87.02 47	95.60 36	78.69 125	98.72 8	98.97 3

OurMVSNet-221017-0		90.01 42	89.74 52	90.83 32	93.16 76	80.37 68	91.91 33	93.11 73	81.10 77	95.32 10	97.24 5	72.94 207	94.85 67	85.07 55	97.78 53	97.26 16

DTE-MVSNet		89.98 43	91.91 13	84.21 157	96.51 7	57.84 310	88.93 85	92.84 87	91.92 3	96.16 3	96.23 18	86.95 48	95.99 10	79.05 122	98.57 14	98.80 6

XVG-ACMP-BASELINE		89.98 43	89.84 50	90.41 39	94.91 36	84.50 44	89.49 76	93.98 38	79.68 92	92.09 62	93.89 101	83.80 76	93.10 135	82.67 83	98.04 36	93.64 124

3Dnovator+	83.92 2	89.97 45	89.66 53	90.92 31	91.27 136	81.66 62	91.25 38	94.13 32	88.89 11	88.83 124	94.26 78	77.55 149	95.86 22	84.88 59	95.87 130	95.24 58

WR-MVS_H		89.91 46	91.31 29	85.71 125	96.32 9	62.39 257	89.54 74	93.31 64	90.21 10	95.57 9	95.66 29	81.42 114	95.90 15	80.94 100	98.80 2	98.84 5

OPM-MVS		89.80 47	89.97 48	89.27 61	94.76 39	79.86 72	86.76 122	92.78 89	78.78 106	92.51 55	93.64 110	88.13 34	93.84 104	84.83 60	97.55 67	94.10 101
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
mvs_tets		89.78 48	89.27 59	91.30 25	93.51 65	84.79 40	89.89 63	90.63 149	70.00 218	94.55 15	96.67 11	87.94 37	93.59 115	84.27 65	95.97 123	95.52 49

anonymousdsp		89.73 49	88.88 66	92.27 7	89.82 169	86.67 14	90.51 50	90.20 166	69.87 219	95.06 11	96.14 21	84.28 72	93.07 136	87.68 15	96.34 106	97.09 21

test_djsdf		89.62 50	89.01 63	91.45 22	92.36 95	82.98 53	91.98 31	90.08 169	71.54 199	94.28 20	96.54 13	81.57 112	94.27 84	86.26 40	96.49 100	97.09 21

XVG-OURS-SEG-HR		89.59 51	89.37 57	90.28 42	94.47 42	85.95 23	86.84 118	93.91 41	80.07 89	86.75 164	93.26 115	93.64 2	90.93 193	84.60 62	90.75 263	93.97 105

APD-MVS		89.54 52	89.63 54	89.26 62	92.57 89	81.34 64	90.19 56	93.08 76	80.87 81	91.13 79	93.19 116	86.22 57	95.97 12	82.23 89	97.18 79	90.45 233
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
jajsoiax		89.41 53	88.81 68	91.19 28	93.38 69	84.72 41	89.70 66	90.29 163	69.27 222	94.39 16	96.38 15	86.02 60	93.52 119	83.96 67	95.92 128	95.34 53

CPTT-MVS		89.39 54	88.98 65	90.63 36	95.09 32	86.95 12	92.09 29	92.30 100	79.74 91	87.50 149	92.38 144	81.42 114	93.28 128	83.07 75	97.24 77	91.67 202

ACMH	76.49 14	89.34 55	91.14 31	83.96 162	92.50 92	70.36 177	89.55 72	93.84 46	81.89 68	94.70 13	95.44 34	90.69 8	88.31 257	83.33 71	98.30 24	93.20 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testf1		89.30 56	89.12 60	89.84 48	88.67 193	85.64 31	90.61 46	93.17 70	86.02 29	93.12 41	95.30 36	84.94 64	89.44 238	74.12 178	96.10 118	94.45 82

APD_test2		89.30 56	89.12 60	89.84 48	88.67 193	85.64 31	90.61 46	93.17 70	86.02 29	93.12 41	95.30 36	84.94 64	89.44 238	74.12 178	96.10 118	94.45 82

CP-MVSNet		89.27 58	90.91 40	84.37 149	96.34 8	58.61 306	88.66 92	92.06 106	90.78 6	95.67 7	95.17 43	81.80 110	95.54 41	79.00 123	98.69 9	98.95 4

XVG-OURS		89.18 59	88.83 67	90.23 43	94.28 44	86.11 22	85.91 132	93.60 55	80.16 87	89.13 121	93.44 113	83.82 75	90.98 191	83.86 69	95.30 151	93.60 126

DeepC-MVS	82.31 4	89.15 60	89.08 62	89.37 60	93.64 63	79.07 79	88.54 94	94.20 25	73.53 166	89.71 106	94.82 52	85.09 63	95.77 30	84.17 66	98.03 38	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
UniMVSNet_ETH3D		89.12 61	90.72 43	84.31 155	97.00 2	64.33 233	89.67 69	88.38 196	88.84 13	94.29 18	97.57 3	90.48 13	91.26 183	72.57 202	97.65 60	97.34 15

MSP-MVS		89.08 62	88.16 73	91.83 18	95.76 17	86.14 21	92.75 16	93.90 42	78.43 111	89.16 119	92.25 151	72.03 220	96.36 3	88.21 7	90.93 257	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
SD-MVS		88.96 63	89.88 49	86.22 112	91.63 121	77.07 105	89.82 64	93.77 47	78.90 104	92.88 45	92.29 149	86.11 58	90.22 214	86.24 43	97.24 77	91.36 209
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 64	88.45 71	90.38 40	94.92 35	85.85 27	89.70 66	91.27 132	78.20 113	86.69 167	92.28 150	80.36 126	95.06 62	86.17 44	96.49 100	90.22 237

test_0402		88.65 65	89.58 56	85.88 121	92.55 90	72.22 157	84.01 168	89.44 183	88.63 16	94.38 17	95.77 26	86.38 56	93.59 115	79.84 112	95.21 152	91.82 197

DP-MVS		88.60 66	89.01 63	87.36 91	91.30 134	77.50 97	87.55 106	92.97 83	87.95 20	89.62 110	92.87 130	84.56 68	93.89 101	77.65 140	96.62 94	90.70 225

APD_test1		88.40 67	87.91 75	89.88 47	89.50 173	86.65 16	89.98 60	91.91 112	84.26 42	90.87 88	93.92 100	82.18 101	89.29 242	73.75 185	94.81 171	93.70 120

Anonymous20231211		88.40 67	89.62 55	84.73 142	90.46 155	65.27 223	88.86 86	93.02 81	87.15 23	93.05 43	97.10 6	82.28 100	92.02 164	76.70 152	97.99 40	96.88 25

PS-MVSNAJss		88.31 69	87.90 76	89.56 57	93.31 71	77.96 92	87.94 102	91.97 109	70.73 208	94.19 21	96.67 11	76.94 159	94.57 76	83.07 75	96.28 108	96.15 33

RRT_MVS		88.30 70	87.83 77	89.70 52	93.62 64	75.70 121	92.36 26	89.06 188	77.34 122	93.63 35	95.83 25	65.40 254	95.90 15	85.01 58	98.23 27	97.49 13

OMC-MVS		88.19 71	87.52 81	90.19 44	91.94 112	81.68 61	87.49 108	93.17 70	76.02 134	88.64 127	91.22 177	84.24 73	93.37 126	77.97 138	97.03 83	95.52 49

CS-MVS		88.14 72	87.67 80	89.54 58	89.56 171	79.18 78	90.47 51	94.77 15	79.37 98	84.32 215	89.33 229	83.87 74	94.53 79	82.45 85	94.89 167	94.90 65

TSAR-MVS + MP.		88.14 72	87.82 78	89.09 65	95.72 21	76.74 108	92.49 24	91.19 135	67.85 242	86.63 168	94.84 51	79.58 132	95.96 13	87.62 16	94.50 179	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
tt0805		88.09 74	89.79 51	82.98 189	93.26 73	63.94 237	91.10 41	89.64 178	85.07 36	90.91 85	91.09 182	89.16 22	91.87 169	82.03 90	95.87 130	93.13 144

EC-MVSNet		88.01 75	88.32 72	87.09 93	89.28 178	72.03 159	90.31 54	96.31 3	80.88 80	85.12 196	89.67 223	84.47 70	95.46 47	82.56 84	96.26 111	93.77 118

RPSCF		88.00 76	86.93 94	91.22 27	90.08 162	89.30 4	89.68 68	91.11 136	79.26 99	89.68 107	94.81 55	82.44 92	87.74 261	76.54 155	88.74 287	96.61 29

AllTest		87.97 77	87.40 85	89.68 53	91.59 122	83.40 48	89.50 75	95.44 9	79.47 94	88.00 141	93.03 122	82.66 89	91.47 176	70.81 211	96.14 115	94.16 96

mvsmamba		87.87 78	87.23 86	89.78 51	92.31 99	76.51 112	91.09 42	91.87 113	72.61 186	92.16 60	95.23 41	66.01 249	95.59 37	86.02 48	97.78 53	97.24 17

TranMVSNet+NR-MVSNet		87.86 79	88.76 69	85.18 133	94.02 54	64.13 234	84.38 161	91.29 131	84.88 39	92.06 63	93.84 102	86.45 54	93.73 106	73.22 193	98.66 10	97.69 9

nrg030		87.85 80	88.49 70	85.91 119	90.07 164	69.73 181	87.86 103	94.20 25	74.04 158	92.70 53	94.66 56	85.88 61	91.50 175	79.72 115	97.32 75	96.50 31

CNVR-MVS		87.81 81	87.68 79	88.21 81	92.87 82	77.30 103	85.25 144	91.23 133	77.31 124	87.07 158	91.47 171	82.94 86	94.71 70	84.67 61	96.27 110	92.62 165

HQP_MVS		87.75 82	87.43 84	88.70 73	93.45 66	76.42 113	89.45 77	93.61 53	79.44 96	86.55 169	92.95 127	74.84 180	95.22 56	80.78 103	95.83 132	94.46 80

MM		87.64 83	87.15 87	89.09 65	89.51 172	76.39 115	88.68 91	86.76 225	84.54 41	83.58 232	93.78 105	73.36 203	96.48 1	87.98 9	96.21 112	94.41 86

NCCC		87.36 84	86.87 95	88.83 68	92.32 98	78.84 82	86.58 126	91.09 137	78.77 107	84.85 204	90.89 190	80.85 120	95.29 53	81.14 98	95.32 148	92.34 176

DeepPCF-MVS	81.24 5	87.28 85	86.21 105	90.49 38	91.48 131	84.90 38	83.41 186	92.38 98	70.25 215	89.35 118	90.68 199	82.85 87	94.57 76	79.55 117	95.95 125	92.00 192

SixPastTwentyTwo		87.20 86	87.45 83	86.45 106	92.52 91	69.19 190	87.84 104	88.05 204	81.66 70	94.64 14	96.53 14	65.94 250	94.75 69	83.02 77	96.83 88	95.41 51

CS-MVS-test		87.00 87	86.43 101	88.71 72	89.46 174	77.46 98	89.42 79	95.73 6	77.87 117	81.64 267	87.25 263	82.43 93	94.53 79	77.65 140	96.46 102	94.14 98

UniMVSNet (Re)		86.87 88	86.98 93	86.55 104	93.11 77	68.48 194	83.80 177	92.87 85	80.37 83	89.61 112	91.81 162	77.72 146	94.18 90	75.00 171	98.53 15	96.99 24

Vis-MVSNet		86.86 89	86.58 98	87.72 86	92.09 106	77.43 100	87.35 109	92.09 105	78.87 105	84.27 220	94.05 89	78.35 140	93.65 108	80.54 107	91.58 245	92.08 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_NR-MVSNet		86.84 90	87.06 90	86.17 115	92.86 84	67.02 206	82.55 212	91.56 121	83.08 57	90.92 83	91.82 161	78.25 141	93.99 97	74.16 176	98.35 21	97.49 13

DU-MVS		86.80 91	86.99 92	86.21 113	93.24 74	67.02 206	83.16 195	92.21 101	81.73 69	90.92 83	91.97 155	77.20 153	93.99 97	74.16 176	98.35 21	97.61 10

casdiffmvs_mvg		86.72 92	87.51 82	84.36 151	87.09 231	65.22 224	84.16 163	94.23 22	77.89 116	91.28 77	93.66 109	84.35 71	92.71 144	80.07 108	94.87 170	95.16 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.01_n		86.68 93	86.52 99	87.18 92	85.94 259	78.30 85	86.93 116	92.20 102	65.94 253	89.16 119	93.16 118	83.10 84	89.89 227	87.81 11	94.43 182	93.35 134

IS-MVSNet		86.66 94	86.82 97	86.17 115	92.05 108	66.87 209	91.21 39	88.64 193	86.30 28	89.60 113	92.59 138	69.22 233	94.91 66	73.89 182	97.89 49	96.72 26

v10		86.54 95	87.10 89	84.84 137	88.16 207	63.28 243	86.64 125	92.20 102	75.42 146	92.81 50	94.50 64	74.05 191	94.06 96	83.88 68	96.28 108	97.17 20

pmmvs6		86.52 96	88.06 74	81.90 209	92.22 102	62.28 260	84.66 154	89.15 186	83.54 52	89.85 103	97.32 4	88.08 36	86.80 276	70.43 219	97.30 76	96.62 28

PHI-MVS		86.38 97	85.81 113	88.08 82	88.44 201	77.34 101	89.35 80	93.05 77	73.15 177	84.76 205	87.70 254	78.87 136	94.18 90	80.67 105	96.29 107	92.73 158

MVS_0304		86.35 98	85.92 109	87.66 88	89.21 181	73.16 140	88.40 96	83.63 268	81.27 74	80.87 277	94.12 87	71.49 224	95.71 32	87.79 12	96.50 99	94.11 100

CSCG		86.26 99	86.47 100	85.60 127	90.87 147	74.26 129	87.98 101	91.85 114	80.35 84	89.54 116	88.01 247	79.09 134	92.13 160	75.51 164	95.06 159	90.41 234

DeepC-MVS_fast	80.27 8	86.23 100	85.65 117	87.96 85	91.30 134	76.92 106	87.19 110	91.99 108	70.56 209	84.96 200	90.69 198	80.01 129	95.14 59	78.37 127	95.78 137	91.82 197
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v8		86.22 101	86.83 96	84.36 151	87.82 211	62.35 259	86.42 128	91.33 130	76.78 128	92.73 52	94.48 66	73.41 200	93.72 107	83.10 74	95.41 144	97.01 23

Anonymous20240529		86.20 102	87.13 88	83.42 178	90.19 160	64.55 231	84.55 156	90.71 146	85.85 31	89.94 102	95.24 40	82.13 102	90.40 210	69.19 231	96.40 105	95.31 55

test_fmvsmconf0.1_n		86.18 103	85.88 111	87.08 94	85.26 267	78.25 86	85.82 135	91.82 116	65.33 266	88.55 128	92.35 148	82.62 91	89.80 229	86.87 32	94.32 185	93.18 143

CDPH-MVS		86.17 104	85.54 118	88.05 84	92.25 100	75.45 122	83.85 174	92.01 107	65.91 255	86.19 178	91.75 165	83.77 77	94.98 64	77.43 145	96.71 92	93.73 119

NR-MVSNet		86.00 105	86.22 104	85.34 131	93.24 74	64.56 230	82.21 224	90.46 153	80.99 78	88.42 132	91.97 155	77.56 148	93.85 102	72.46 203	98.65 11	97.61 10

train_agg		85.98 106	85.28 123	88.07 83	92.34 96	79.70 74	83.94 170	90.32 158	65.79 256	84.49 209	90.97 186	81.93 106	93.63 110	81.21 97	96.54 97	90.88 219

FC-MVSNet-test		85.93 107	87.05 91	82.58 200	92.25 100	56.44 321	85.75 136	93.09 75	77.33 123	91.94 66	94.65 57	74.78 182	93.41 125	75.11 170	98.58 13	97.88 7

test_fmvsmconf_n		85.88 108	85.51 119	86.99 96	84.77 274	78.21 87	85.40 143	91.39 128	65.32 267	87.72 145	91.81 162	82.33 96	89.78 230	86.68 34	94.20 189	92.99 151

Effi-MVS+-dtu		85.82 109	83.38 155	93.14 3	87.13 227	91.15 2	87.70 105	88.42 195	74.57 154	83.56 233	85.65 286	78.49 139	94.21 88	72.04 205	92.88 218	94.05 102

TAPA-MVS	77.73 12	85.71 110	84.83 129	88.37 78	88.78 192	79.72 73	87.15 112	93.50 56	69.17 223	85.80 187	89.56 224	80.76 121	92.13 160	73.21 198	95.51 142	93.25 140
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
canonicalmvs		85.50 111	86.14 106	83.58 174	87.97 208	67.13 204	87.55 106	94.32 18	73.44 168	88.47 131	87.54 257	86.45 54	91.06 190	75.76 163	93.76 197	92.54 168

EPP-MVSNet		85.47 112	85.04 126	86.77 101	91.52 130	69.37 185	91.63 36	87.98 206	81.51 72	87.05 159	91.83 160	66.18 248	95.29 53	70.75 214	96.89 85	95.64 46

GeoE		85.45 113	85.81 113	84.37 149	90.08 162	67.07 205	85.86 134	91.39 128	72.33 192	87.59 147	90.25 211	84.85 66	92.37 154	78.00 136	91.94 238	93.66 121

FIs		85.35 114	86.27 103	82.60 199	91.86 114	57.31 314	85.10 148	93.05 77	75.83 139	91.02 82	93.97 93	73.57 196	92.91 142	73.97 181	98.02 39	97.58 12

test_fmvsmvis_n_1920		85.22 115	85.36 122	84.81 138	85.80 261	76.13 119	85.15 147	92.32 99	61.40 295	91.33 74	90.85 193	83.76 78	86.16 289	84.31 64	93.28 208	92.15 187

casdiffmvs		85.21 116	85.85 112	83.31 181	86.17 254	62.77 250	83.03 197	93.93 40	74.69 153	88.21 137	92.68 137	82.29 99	91.89 168	77.87 139	93.75 199	95.27 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		85.20 117	85.93 108	83.02 188	86.30 248	62.37 258	84.55 156	93.96 39	74.48 155	87.12 153	92.03 154	82.30 98	91.94 165	78.39 126	94.21 188	94.74 73

K. test v3		85.14 118	84.73 130	86.37 107	91.13 141	69.63 183	85.45 141	76.68 318	84.06 45	92.44 57	96.99 8	62.03 271	94.65 72	80.58 106	93.24 209	94.83 72

EI-MVSNet-Vis-set		85.12 119	84.53 137	86.88 98	84.01 286	72.76 142	83.91 173	85.18 248	80.44 82	88.75 125	85.49 288	80.08 128	91.92 166	82.02 91	90.85 261	95.97 39

EI-MVSNet-UG-set		85.04 120	84.44 139	86.85 99	83.87 290	72.52 151	83.82 175	85.15 249	80.27 86	88.75 125	85.45 290	79.95 130	91.90 167	81.92 94	90.80 262	96.13 34

X-MVStestdata		85.04 120	82.70 168	92.08 8	95.64 23	86.25 18	92.64 18	93.33 61	85.07 36	89.99 99	16.05 400	86.57 52	95.80 25	87.35 24	97.62 62	94.20 92

MSLP-MVS++		85.00 122	86.03 107	81.90 209	91.84 117	71.56 168	86.75 123	93.02 81	75.95 137	87.12 153	89.39 227	77.98 142	89.40 241	77.46 143	94.78 172	84.75 309

F-COLMAP		84.97 123	83.42 154	89.63 55	92.39 94	83.40 48	88.83 87	91.92 111	73.19 176	80.18 290	89.15 233	77.04 157	93.28 128	65.82 262	92.28 229	92.21 184

bld_raw_dy_0_64		84.85 124	84.44 139	86.07 117	93.73 60	74.93 125	88.57 93	81.90 284	70.44 210	91.28 77	95.18 42	56.62 307	89.28 243	85.15 54	97.09 81	93.99 103

3Dnovator	80.37 7	84.80 125	84.71 133	85.06 135	86.36 246	74.71 126	88.77 89	90.00 171	75.65 142	84.96 200	93.17 117	74.06 190	91.19 185	78.28 130	91.09 251	89.29 255

IterMVS-LS		84.73 126	84.98 127	83.96 162	87.35 222	63.66 238	83.25 191	89.88 173	76.06 132	89.62 110	92.37 147	73.40 202	92.52 149	78.16 133	94.77 174	95.69 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_111021_HR		84.63 127	84.34 144	85.49 130	90.18 161	75.86 120	79.23 265	87.13 216	73.35 169	85.56 191	89.34 228	83.60 80	90.50 208	76.64 153	94.05 193	90.09 242

HQP-MVS		84.61 128	84.06 147	86.27 110	91.19 137	70.66 173	84.77 149	92.68 91	73.30 172	80.55 282	90.17 215	72.10 216	94.61 74	77.30 147	94.47 180	93.56 129

v1192		84.57 129	84.69 134	84.21 157	87.75 213	62.88 247	83.02 198	91.43 125	69.08 225	89.98 101	90.89 190	72.70 211	93.62 113	82.41 86	94.97 164	96.13 34

FMVSNet1		84.55 130	85.45 120	81.85 211	90.27 159	61.05 273	86.83 119	88.27 201	78.57 110	89.66 109	95.64 30	75.43 173	90.68 203	69.09 232	95.33 147	93.82 113

v1144		84.54 131	84.72 132	84.00 160	87.67 216	62.55 254	82.97 200	90.93 142	70.32 214	89.80 104	90.99 185	73.50 197	93.48 121	81.69 96	94.65 177	95.97 39

Gipuma		84.44 132	86.33 102	78.78 255	84.20 285	73.57 133	89.55 72	90.44 154	84.24 43	84.38 212	94.89 49	76.35 170	80.40 332	76.14 159	96.80 90	82.36 344
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MCST-MVS		84.36 133	83.93 150	85.63 126	91.59 122	71.58 166	83.52 183	92.13 104	61.82 288	83.96 226	89.75 222	79.93 131	93.46 122	78.33 129	94.34 184	91.87 196

VDDNet		84.35 134	85.39 121	81.25 220	95.13 31	59.32 293	85.42 142	81.11 289	86.41 27	87.41 150	96.21 19	73.61 195	90.61 206	66.33 255	96.85 86	93.81 116

ETV-MVS		84.31 135	83.91 151	85.52 128	88.58 197	70.40 176	84.50 160	93.37 58	78.76 108	84.07 224	78.72 361	80.39 125	95.13 60	73.82 184	92.98 216	91.04 215

v1240		84.30 136	84.51 138	83.65 171	87.65 217	61.26 270	82.85 204	91.54 122	67.94 240	90.68 90	90.65 202	71.71 222	93.64 109	82.84 80	94.78 172	96.07 36

MVS_111021_LR		84.28 137	83.76 152	85.83 123	89.23 180	83.07 51	80.99 240	83.56 269	72.71 184	86.07 181	89.07 234	81.75 111	86.19 288	77.11 149	93.36 204	88.24 268

h-mvs33		84.25 138	82.76 167	88.72 71	91.82 119	82.60 56	84.00 169	84.98 255	71.27 201	86.70 165	90.55 204	63.04 268	93.92 100	78.26 131	94.20 189	89.63 247

v144192		84.24 139	84.41 141	83.71 170	87.59 219	61.57 266	82.95 201	91.03 138	67.82 243	89.80 104	90.49 205	73.28 204	93.51 120	81.88 95	94.89 167	96.04 38

dcpmvs_2		84.23 140	85.14 124	81.50 217	88.61 196	61.98 264	82.90 203	93.11 73	68.66 231	92.77 51	92.39 143	78.50 138	87.63 263	76.99 151	92.30 226	94.90 65

v1921920		84.23 140	84.37 143	83.79 166	87.64 218	61.71 265	82.91 202	91.20 134	67.94 240	90.06 96	90.34 208	72.04 219	93.59 115	82.32 87	94.91 165	96.07 36

VDD-MVS		84.23 140	84.58 136	83.20 185	91.17 140	65.16 226	83.25 191	84.97 256	79.79 90	87.18 152	94.27 75	74.77 183	90.89 196	69.24 228	96.54 97	93.55 131

v2v482		84.09 143	84.24 145	83.62 172	87.13 227	61.40 267	82.71 207	89.71 176	72.19 195	89.55 114	91.41 172	70.70 228	93.20 130	81.02 99	93.76 197	96.25 32

EG-PatchMatch MVS		84.08 144	84.11 146	83.98 161	92.22 102	72.61 148	82.20 226	87.02 221	72.63 185	88.86 122	91.02 184	78.52 137	91.11 188	73.41 190	91.09 251	88.21 269

DP-MVS Recon		84.05 145	83.22 157	86.52 105	91.73 120	75.27 123	83.23 193	92.40 96	72.04 196	82.04 257	88.33 243	77.91 144	93.95 99	66.17 256	95.12 157	90.34 236

TransMVSNet (Re)		84.02 146	85.74 115	78.85 254	91.00 144	55.20 331	82.29 220	87.26 212	79.65 93	88.38 134	95.52 33	83.00 85	86.88 274	67.97 246	96.60 95	94.45 82

Baseline_NR-MVSNet		84.00 147	85.90 110	78.29 266	91.47 132	53.44 340	82.29 220	87.00 224	79.06 102	89.55 114	95.72 28	77.20 153	86.14 290	72.30 204	98.51 16	95.28 56

TSAR-MVS + GP.		83.95 148	82.69 169	87.72 86	89.27 179	81.45 63	83.72 179	81.58 288	74.73 152	85.66 188	86.06 281	72.56 213	92.69 146	75.44 166	95.21 152	89.01 263

alignmvs		83.94 149	83.98 149	83.80 165	87.80 212	67.88 201	84.54 158	91.42 127	73.27 175	88.41 133	87.96 248	72.33 214	90.83 198	76.02 161	94.11 191	92.69 162

Effi-MVS+		83.90 150	84.01 148	83.57 175	87.22 225	65.61 222	86.55 127	92.40 96	78.64 109	81.34 272	84.18 309	83.65 79	92.93 140	74.22 175	87.87 299	92.17 186

CANet		83.79 151	82.85 166	86.63 102	86.17 254	72.21 158	83.76 178	91.43 125	77.24 125	74.39 338	87.45 259	75.36 174	95.42 49	77.03 150	92.83 219	92.25 183

pm-mvs1		83.69 152	84.95 128	79.91 241	90.04 166	59.66 290	82.43 216	87.44 209	75.52 144	87.85 143	95.26 39	81.25 116	85.65 299	68.74 238	96.04 120	94.42 85

AdaColmap		83.66 153	83.69 153	83.57 175	90.05 165	72.26 156	86.29 130	90.00 171	78.19 114	81.65 266	87.16 265	83.40 82	94.24 87	61.69 296	94.76 175	84.21 317

MIMVSNet1		83.63 154	84.59 135	80.74 229	94.06 53	62.77 250	82.72 206	84.53 261	77.57 121	90.34 92	95.92 24	76.88 165	85.83 297	61.88 294	97.42 72	93.62 125

test_fmvsm_n_1920		83.60 155	82.89 165	85.74 124	85.22 268	77.74 95	84.12 165	90.48 152	59.87 314	86.45 177	91.12 181	75.65 171	85.89 295	82.28 88	90.87 259	93.58 127

WR-MVS		83.56 156	84.40 142	81.06 225	93.43 68	54.88 332	78.67 273	85.02 253	81.24 75	90.74 89	91.56 169	72.85 208	91.08 189	68.00 245	98.04 36	97.23 18

CNLPA		83.55 157	83.10 162	84.90 136	89.34 177	83.87 46	84.54 158	88.77 190	79.09 101	83.54 234	88.66 240	74.87 179	81.73 324	66.84 251	92.29 228	89.11 257

LCM-MVSNet-Re		83.48 158	85.06 125	78.75 256	85.94 259	55.75 326	80.05 249	94.27 19	76.47 129	96.09 5	94.54 63	83.31 83	89.75 233	59.95 306	94.89 167	90.75 222

hse-mvs2		83.47 159	81.81 182	88.47 75	91.03 143	82.27 57	82.61 208	83.69 266	71.27 201	86.70 165	86.05 282	63.04 268	92.41 152	78.26 131	93.62 203	90.71 224

V42		83.47 159	83.37 156	83.75 168	83.16 300	63.33 242	81.31 234	90.23 165	69.51 221	90.91 85	90.81 195	74.16 189	92.29 158	80.06 109	90.22 270	95.62 47

VPA-MVSNet		83.47 159	84.73 130	79.69 245	90.29 158	57.52 313	81.30 236	88.69 192	76.29 130	87.58 148	94.44 67	80.60 124	87.20 268	66.60 254	96.82 89	94.34 89

PAPM_NR		83.23 162	83.19 159	83.33 180	90.90 146	65.98 218	88.19 98	90.78 145	78.13 115	80.87 277	87.92 251	73.49 199	92.42 151	70.07 221	88.40 289	91.60 204

CLD-MVS		83.18 163	82.64 170	84.79 139	89.05 183	67.82 202	77.93 281	92.52 94	68.33 233	85.07 197	81.54 338	82.06 103	92.96 138	69.35 227	97.91 48	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
ANet_high		83.17 164	85.68 116	75.65 300	81.24 318	45.26 380	79.94 251	92.91 84	83.83 46	91.33 74	96.88 10	80.25 127	85.92 292	68.89 235	95.89 129	95.76 43

FA-MVS(test-final)		83.13 165	83.02 163	83.43 177	86.16 256	66.08 217	88.00 100	88.36 197	75.55 143	85.02 198	92.75 135	65.12 255	92.50 150	74.94 172	91.30 249	91.72 199

114514_t		83.10 166	82.54 173	84.77 141	92.90 81	69.10 192	86.65 124	90.62 150	54.66 341	81.46 269	90.81 195	76.98 158	94.38 83	72.62 201	96.18 113	90.82 221

UGNet		82.78 167	81.64 184	86.21 113	86.20 253	76.24 117	86.86 117	85.68 240	77.07 126	73.76 342	92.82 131	69.64 230	91.82 171	69.04 234	93.69 200	90.56 230
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		82.75 168	81.93 180	85.19 132	82.08 307	80.15 70	85.53 139	88.76 191	68.01 237	85.58 190	87.75 253	71.80 221	86.85 275	74.02 180	93.87 196	88.58 266

EI-MVSNet		82.61 169	82.42 175	83.20 185	83.25 297	63.66 238	83.50 184	85.07 250	76.06 132	86.55 169	85.10 296	73.41 200	90.25 211	78.15 135	90.67 265	95.68 45

QAPM		82.59 170	82.59 172	82.58 200	86.44 241	66.69 210	89.94 62	90.36 157	67.97 239	84.94 202	92.58 140	72.71 210	92.18 159	70.63 217	87.73 301	88.85 264

fmvsm_s_conf0.1_n_a		82.58 171	81.93 180	84.50 146	87.68 215	73.35 134	86.14 131	77.70 307	61.64 293	85.02 198	91.62 167	77.75 145	86.24 285	82.79 81	87.07 308	93.91 109

Fast-Effi-MVS+-dtu		82.54 172	81.41 192	85.90 120	85.60 262	76.53 111	83.07 196	89.62 180	73.02 179	79.11 300	83.51 314	80.74 122	90.24 213	68.76 237	89.29 278	90.94 217

MVS_Test		82.47 173	83.22 157	80.22 238	82.62 306	57.75 312	82.54 213	91.96 110	71.16 205	82.89 244	92.52 142	77.41 150	90.50 208	80.04 110	87.84 300	92.40 173

v148		82.31 174	82.48 174	81.81 214	85.59 263	59.66 290	81.47 233	86.02 236	72.85 180	88.05 140	90.65 202	70.73 227	90.91 195	75.15 169	91.79 239	94.87 67

API-MVS		82.28 175	82.61 171	81.30 219	86.29 249	69.79 179	88.71 90	87.67 208	78.42 112	82.15 255	84.15 310	77.98 142	91.59 174	65.39 265	92.75 220	82.51 343

MVSFormer		82.23 176	81.57 189	84.19 159	85.54 264	69.26 187	91.98 31	90.08 169	71.54 199	76.23 320	85.07 299	58.69 293	94.27 84	86.26 40	88.77 285	89.03 261

fmvsm_s_conf0.5_n_a		82.21 177	81.51 191	84.32 154	86.56 239	73.35 134	85.46 140	77.30 311	61.81 289	84.51 208	90.88 192	77.36 151	86.21 287	82.72 82	86.97 312	93.38 133

EIA-MVS		82.19 178	81.23 197	85.10 134	87.95 209	69.17 191	83.22 194	93.33 61	70.42 211	78.58 303	79.77 354	77.29 152	94.20 89	71.51 207	88.96 283	91.93 195

fmvsm_s_conf0.1_n		82.17 179	81.59 187	83.94 164	86.87 237	71.57 167	85.19 146	77.42 310	62.27 287	84.47 211	91.33 174	76.43 167	85.91 293	83.14 72	87.14 306	94.33 90

PCF-MVS	74.62 15	82.15 180	80.92 201	85.84 122	89.43 175	72.30 155	80.53 244	91.82 116	57.36 330	87.81 144	89.92 219	77.67 147	93.63 110	58.69 311	95.08 158	91.58 205
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PLC	73.85 16	82.09 181	80.31 208	87.45 90	90.86 148	80.29 69	85.88 133	90.65 148	68.17 235	76.32 319	86.33 276	73.12 206	92.61 148	61.40 299	90.02 273	89.44 250
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
fmvsm_l_conf0.5_n		82.06 182	81.54 190	83.60 173	83.94 287	73.90 131	83.35 188	86.10 233	58.97 316	83.80 228	90.36 207	74.23 188	86.94 273	82.90 78	90.22 270	89.94 244

GBi-Net		82.02 183	82.07 177	81.85 211	86.38 243	61.05 273	86.83 119	88.27 201	72.43 187	86.00 182	95.64 30	63.78 262	90.68 203	65.95 258	93.34 205	93.82 113

test1		82.02 183	82.07 177	81.85 211	86.38 243	61.05 273	86.83 119	88.27 201	72.43 187	86.00 182	95.64 30	63.78 262	90.68 203	65.95 258	93.34 205	93.82 113

OpenMVS	76.72 13	81.98 185	82.00 179	81.93 208	84.42 280	68.22 196	88.50 95	89.48 182	66.92 248	81.80 264	91.86 157	72.59 212	90.16 216	71.19 210	91.25 250	87.40 282

KD-MVS_self_test		81.93 186	83.14 161	78.30 265	84.75 275	52.75 344	80.37 246	89.42 184	70.24 216	90.26 94	93.39 114	74.55 187	86.77 277	68.61 240	96.64 93	95.38 52

fmvsm_s_conf0.5_n		81.91 187	81.30 194	83.75 168	86.02 258	71.56 168	84.73 152	77.11 314	62.44 284	84.00 225	90.68 199	76.42 168	85.89 295	83.14 72	87.11 307	93.81 116

SDMVSNet		81.90 188	83.17 160	78.10 269	88.81 190	62.45 256	76.08 311	86.05 235	73.67 163	83.41 235	93.04 120	82.35 95	80.65 331	70.06 222	95.03 160	91.21 211

tfpnnormal		81.79 189	82.95 164	78.31 264	88.93 187	55.40 327	80.83 243	82.85 275	76.81 127	85.90 186	94.14 85	74.58 186	86.51 281	66.82 252	95.68 141	93.01 150

c3_l		81.64 190	81.59 187	81.79 215	80.86 324	59.15 297	78.61 274	90.18 167	68.36 232	87.20 151	87.11 267	69.39 231	91.62 173	78.16 133	94.43 182	94.60 75

PVSNet_Blended_VisFu		81.55 191	80.49 206	84.70 144	91.58 125	73.24 138	84.21 162	91.67 120	62.86 279	80.94 275	87.16 265	67.27 242	92.87 143	69.82 224	88.94 284	87.99 273

fmvsm_l_conf0.5_n_a		81.46 192	80.87 202	83.25 182	83.73 291	73.21 139	83.00 199	85.59 242	58.22 322	82.96 243	90.09 217	72.30 215	86.65 279	81.97 93	89.95 274	89.88 245

DELS-MVS		81.44 193	81.25 195	82.03 207	84.27 284	62.87 248	76.47 305	92.49 95	70.97 206	81.64 267	83.83 311	75.03 177	92.70 145	74.29 174	92.22 232	90.51 232
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		81.31 194	81.61 186	80.41 235	86.38 243	58.75 304	83.93 172	86.58 227	72.43 187	87.65 146	92.98 124	63.78 262	90.22 214	66.86 249	93.92 195	92.27 181

TinyColmap		81.25 195	82.34 176	77.99 272	85.33 266	60.68 281	82.32 219	88.33 199	71.26 203	86.97 160	92.22 153	77.10 156	86.98 272	62.37 288	95.17 154	86.31 293

AUN-MVS		81.18 196	78.78 229	88.39 77	90.93 145	82.14 58	82.51 214	83.67 267	64.69 271	80.29 286	85.91 285	51.07 332	92.38 153	76.29 158	93.63 202	90.65 228

tttt0517		81.07 197	79.58 220	85.52 128	88.99 186	66.45 213	87.03 114	75.51 326	73.76 162	88.32 136	90.20 212	37.96 385	94.16 94	79.36 121	95.13 155	95.93 42

Fast-Effi-MVS+		81.04 198	80.57 203	82.46 204	87.50 220	63.22 244	78.37 277	89.63 179	68.01 237	81.87 260	82.08 332	82.31 97	92.65 147	67.10 248	88.30 295	91.51 207

BH-untuned		80.96 199	80.99 199	80.84 228	88.55 198	68.23 195	80.33 247	88.46 194	72.79 183	86.55 169	86.76 271	74.72 184	91.77 172	61.79 295	88.99 282	82.52 342

eth_miper_zixun_eth		80.84 200	80.22 212	82.71 197	81.41 316	60.98 276	77.81 283	90.14 168	67.31 246	86.95 161	87.24 264	64.26 258	92.31 156	75.23 168	91.61 243	94.85 71

xiu_mvs_v1_base_debu		80.84 200	80.14 214	82.93 192	88.31 202	71.73 162	79.53 256	87.17 213	65.43 262	79.59 292	82.73 326	76.94 159	90.14 219	73.22 193	88.33 291	86.90 287

xiu_mvs_v1_base		80.84 200	80.14 214	82.93 192	88.31 202	71.73 162	79.53 256	87.17 213	65.43 262	79.59 292	82.73 326	76.94 159	90.14 219	73.22 193	88.33 291	86.90 287

xiu_mvs_v1_base_debi		80.84 200	80.14 214	82.93 192	88.31 202	71.73 162	79.53 256	87.17 213	65.43 262	79.59 292	82.73 326	76.94 159	90.14 219	73.22 193	88.33 291	86.90 287

IterMVS-SCA-FT		80.64 204	79.41 221	84.34 153	83.93 288	69.66 182	76.28 307	81.09 290	72.43 187	86.47 175	90.19 213	60.46 278	93.15 133	77.45 144	86.39 318	90.22 237

BH-RMVSNet		80.53 205	80.22 212	81.49 218	87.19 226	66.21 216	77.79 284	86.23 231	74.21 157	83.69 229	88.50 241	73.25 205	90.75 200	63.18 285	87.90 298	87.52 280

Anonymous202405211		80.51 206	81.19 198	78.49 261	88.48 199	57.26 315	76.63 301	82.49 278	81.21 76	84.30 218	92.24 152	67.99 239	86.24 285	62.22 289	95.13 155	91.98 194

DIV-MVS_self_test		80.43 207	80.23 210	81.02 226	79.99 332	59.25 294	77.07 294	87.02 221	67.38 244	86.19 178	89.22 230	63.09 266	90.16 216	76.32 156	95.80 135	93.66 121

cl____		80.42 208	80.23 210	81.02 226	79.99 332	59.25 294	77.07 294	87.02 221	67.37 245	86.18 180	89.21 231	63.08 267	90.16 216	76.31 157	95.80 135	93.65 123

diffmvs		80.40 209	80.48 207	80.17 239	79.02 344	60.04 285	77.54 288	90.28 164	66.65 251	82.40 250	87.33 262	73.50 197	87.35 266	77.98 137	89.62 276	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
EPNet		80.37 210	78.41 236	86.23 111	76.75 358	73.28 136	87.18 111	77.45 309	76.24 131	68.14 368	88.93 236	65.41 253	93.85 102	69.47 226	96.12 117	91.55 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
iter_conf_final		80.36 211	78.88 226	84.79 139	86.29 249	66.36 215	86.95 115	86.25 230	68.16 236	82.09 256	89.48 225	36.59 388	94.51 81	79.83 113	94.30 186	93.50 132

miper_ehance_all_eth		80.34 212	80.04 217	81.24 222	79.82 334	58.95 299	77.66 285	89.66 177	65.75 259	85.99 185	85.11 295	68.29 238	91.42 180	76.03 160	92.03 234	93.33 135

MG-MVS		80.32 213	80.94 200	78.47 262	88.18 205	52.62 347	82.29 220	85.01 254	72.01 197	79.24 299	92.54 141	69.36 232	93.36 127	70.65 216	89.19 281	89.45 249

VPNet		80.25 214	81.68 183	75.94 298	92.46 93	47.98 370	76.70 299	81.67 286	73.45 167	84.87 203	92.82 131	74.66 185	86.51 281	61.66 297	96.85 86	93.33 135

MAR-MVS		80.24 215	78.74 231	84.73 142	86.87 237	78.18 88	85.75 136	87.81 207	65.67 261	77.84 308	78.50 362	73.79 194	90.53 207	61.59 298	90.87 259	85.49 302
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		80.20 216	79.00 225	83.78 167	88.17 206	86.66 15	81.31 234	66.81 375	69.64 220	88.33 135	90.19 213	64.58 256	83.63 315	71.99 206	90.03 272	81.06 361

Anonymous20240521		80.18 217	81.25 195	76.95 285	83.15 301	60.84 278	82.46 215	85.99 237	68.76 229	86.78 162	93.73 108	59.13 290	77.44 344	73.71 186	97.55 67	92.56 166

LFMVS		80.15 218	80.56 204	78.89 253	89.19 182	55.93 323	85.22 145	73.78 338	82.96 58	84.28 219	92.72 136	57.38 302	90.07 223	63.80 279	95.75 138	90.68 226

DPM-MVS		80.10 219	79.18 224	82.88 195	90.71 151	69.74 180	78.87 270	90.84 143	60.29 310	75.64 328	85.92 284	67.28 241	93.11 134	71.24 209	91.79 239	85.77 299

MSDG		80.06 220	79.99 219	80.25 237	83.91 289	68.04 200	77.51 289	89.19 185	77.65 119	81.94 258	83.45 316	76.37 169	86.31 284	63.31 284	86.59 315	86.41 291

FE-MVS		79.98 221	78.86 227	83.36 179	86.47 240	66.45 213	89.73 65	84.74 260	72.80 182	84.22 223	91.38 173	44.95 366	93.60 114	63.93 278	91.50 246	90.04 243

sd_testset		79.95 222	81.39 193	75.64 301	88.81 190	58.07 308	76.16 310	82.81 276	73.67 163	83.41 235	93.04 120	80.96 119	77.65 343	58.62 312	95.03 160	91.21 211

ab-mvs		79.67 223	80.56 204	76.99 284	88.48 199	56.93 317	84.70 153	86.06 234	68.95 227	80.78 279	93.08 119	75.30 175	84.62 307	56.78 321	90.90 258	89.43 251

VNet		79.31 224	80.27 209	76.44 292	87.92 210	53.95 336	75.58 317	84.35 262	74.39 156	82.23 253	90.72 197	72.84 209	84.39 309	60.38 305	93.98 194	90.97 216

thisisatest0530		79.07 225	77.33 246	84.26 156	87.13 227	64.58 229	83.66 181	75.95 321	68.86 228	85.22 195	87.36 261	38.10 383	93.57 118	75.47 165	94.28 187	94.62 74

cl22		78.97 226	78.21 238	81.24 222	77.74 348	59.01 298	77.46 291	87.13 216	65.79 256	84.32 215	85.10 296	58.96 292	90.88 197	75.36 167	92.03 234	93.84 111

patch_mono-2		78.89 227	79.39 222	77.41 281	84.78 273	68.11 198	75.60 315	83.11 272	60.96 303	79.36 296	89.89 220	75.18 176	72.97 355	73.32 192	92.30 226	91.15 213

RPMNet		78.88 228	78.28 237	80.68 232	79.58 335	62.64 252	82.58 210	94.16 27	74.80 151	75.72 326	92.59 138	48.69 340	95.56 39	73.48 189	82.91 351	83.85 322

PAPR		78.84 229	78.10 239	81.07 224	85.17 269	60.22 284	82.21 224	90.57 151	62.51 281	75.32 332	84.61 304	74.99 178	92.30 157	59.48 309	88.04 297	90.68 226

iter_conf05		78.81 230	77.35 245	83.21 184	82.98 304	60.75 280	84.09 166	88.34 198	63.12 277	84.25 222	89.48 225	31.41 393	94.51 81	76.64 153	95.83 132	94.38 88

PVSNet_BlendedMVS		78.80 231	77.84 240	81.65 216	84.43 278	63.41 240	79.49 259	90.44 154	61.70 292	75.43 329	87.07 268	69.11 234	91.44 178	60.68 303	92.24 230	90.11 241

FMVSNet3		78.80 231	78.55 233	79.57 247	82.89 305	56.89 319	81.76 228	85.77 239	69.04 226	86.00 182	90.44 206	51.75 330	90.09 222	65.95 258	93.34 205	91.72 199

test_yl		78.71 233	78.51 234	79.32 250	84.32 282	58.84 301	78.38 275	85.33 245	75.99 135	82.49 248	86.57 272	58.01 296	90.02 225	62.74 286	92.73 221	89.10 258

DCV-MVSNet		78.71 233	78.51 234	79.32 250	84.32 282	58.84 301	78.38 275	85.33 245	75.99 135	82.49 248	86.57 272	58.01 296	90.02 225	62.74 286	92.73 221	89.10 258

test1111		78.53 235	78.85 228	77.56 278	92.22 102	47.49 372	82.61 208	69.24 364	72.43 187	85.28 194	94.20 81	51.91 328	90.07 223	65.36 266	96.45 103	95.11 62

ECVR-MVS		78.44 236	78.63 232	77.88 274	91.85 115	48.95 366	83.68 180	69.91 362	72.30 193	84.26 221	94.20 81	51.89 329	89.82 228	63.58 280	96.02 121	94.87 67

pmmvs-eth3d		78.42 237	77.04 248	82.57 202	87.44 221	74.41 128	80.86 242	79.67 298	55.68 336	84.69 206	90.31 210	60.91 276	85.42 300	62.20 290	91.59 244	87.88 276

mvs_anonymous		78.13 238	78.76 230	76.23 297	79.24 341	50.31 363	78.69 272	84.82 258	61.60 294	83.09 242	92.82 131	73.89 193	87.01 269	68.33 244	86.41 317	91.37 208

TAMVS		78.08 239	76.36 254	83.23 183	90.62 152	72.87 141	79.08 266	80.01 297	61.72 291	81.35 271	86.92 270	63.96 261	88.78 251	50.61 357	93.01 215	88.04 272

miper_enhance_ethall		77.83 240	76.93 249	80.51 233	76.15 364	58.01 309	75.47 319	88.82 189	58.05 324	83.59 231	80.69 342	64.41 257	91.20 184	73.16 199	92.03 234	92.33 177

Vis-MVSNet (Re-imp)		77.82 241	77.79 241	77.92 273	88.82 189	51.29 357	83.28 189	71.97 351	74.04 158	82.23 253	89.78 221	57.38 302	89.41 240	57.22 320	95.41 144	93.05 148

CANet_DTU		77.81 242	77.05 247	80.09 240	81.37 317	59.90 288	83.26 190	88.29 200	69.16 224	67.83 371	83.72 312	60.93 275	89.47 235	69.22 230	89.70 275	90.88 219

OpenMVS_ROB	70.19 17	77.77 243	77.46 242	78.71 257	84.39 281	61.15 271	81.18 238	82.52 277	62.45 283	83.34 237	87.37 260	66.20 247	88.66 253	64.69 273	85.02 333	86.32 292

SSC-MVS		77.55 244	81.64 184	65.29 360	90.46 155	20.33 405	73.56 335	68.28 366	85.44 32	88.18 139	94.64 60	70.93 226	81.33 326	71.25 208	92.03 234	94.20 92

MDA-MVSNet-bldmvs		77.47 245	76.90 250	79.16 252	79.03 343	64.59 228	66.58 370	75.67 324	73.15 177	88.86 122	88.99 235	66.94 243	81.23 327	64.71 272	88.22 296	91.64 203

jason		77.42 246	75.75 260	82.43 205	87.10 230	69.27 186	77.99 280	81.94 283	51.47 359	77.84 308	85.07 299	60.32 280	89.00 245	70.74 215	89.27 280	89.03 261
jason: jason.
CDS-MVSNet		77.32 247	75.40 263	83.06 187	89.00 185	72.48 152	77.90 282	82.17 281	60.81 304	78.94 301	83.49 315	59.30 288	88.76 252	54.64 339	92.37 225	87.93 275
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		77.19 248	76.75 251	78.52 260	87.01 233	61.30 269	75.55 318	87.12 219	61.24 300	74.45 337	78.79 360	77.20 153	90.93 193	64.62 275	84.80 340	83.32 331

MVSTER		77.09 249	75.70 261	81.25 220	75.27 372	61.08 272	77.49 290	85.07 250	60.78 305	86.55 169	88.68 239	43.14 375	90.25 211	73.69 187	90.67 265	92.42 171

PS-MVSNAJ		77.04 250	76.53 253	78.56 259	87.09 231	61.40 267	75.26 320	87.13 216	61.25 299	74.38 339	77.22 371	76.94 159	90.94 192	64.63 274	84.83 339	83.35 330

IterMVS		76.91 251	76.34 255	78.64 258	80.91 322	64.03 235	76.30 306	79.03 301	64.88 270	83.11 240	89.16 232	59.90 284	84.46 308	68.61 240	85.15 331	87.42 281
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
D2MVS		76.84 252	75.67 262	80.34 236	80.48 330	62.16 263	73.50 336	84.80 259	57.61 328	82.24 252	87.54 257	51.31 331	87.65 262	70.40 220	93.19 211	91.23 210

CL-MVSNet_self_test		76.81 253	77.38 244	75.12 304	86.90 235	51.34 355	73.20 339	80.63 294	68.30 234	81.80 264	88.40 242	66.92 244	80.90 328	55.35 333	94.90 166	93.12 146

TR-MVS		76.77 254	75.79 259	79.72 244	86.10 257	65.79 220	77.14 292	83.02 273	65.20 268	81.40 270	82.10 330	66.30 246	90.73 202	55.57 330	85.27 327	82.65 337

USDC		76.63 255	76.73 252	76.34 294	83.46 293	57.20 316	80.02 250	88.04 205	52.14 355	83.65 230	91.25 176	63.24 265	86.65 279	54.66 338	94.11 191	85.17 304

BH-w/o		76.57 256	76.07 258	78.10 269	86.88 236	65.92 219	77.63 286	86.33 228	65.69 260	80.89 276	79.95 351	68.97 236	90.74 201	53.01 347	85.25 328	77.62 372

Patchmtry		76.56 257	77.46 242	73.83 310	79.37 340	46.60 376	82.41 217	76.90 315	73.81 161	85.56 191	92.38 144	48.07 343	83.98 312	63.36 283	95.31 150	90.92 218

PVSNet_Blended		76.49 258	75.40 263	79.76 243	84.43 278	63.41 240	75.14 321	90.44 154	57.36 330	75.43 329	78.30 363	69.11 234	91.44 178	60.68 303	87.70 302	84.42 313

miper_lstm_enhance		76.45 259	76.10 257	77.51 279	76.72 359	60.97 277	64.69 374	85.04 252	63.98 274	83.20 239	88.22 244	56.67 306	78.79 341	73.22 193	93.12 212	92.78 157

lupinMVS		76.37 260	74.46 272	82.09 206	85.54 264	69.26 187	76.79 297	80.77 293	50.68 366	76.23 320	82.82 324	58.69 293	88.94 246	69.85 223	88.77 285	88.07 270

cascas		76.29 261	74.81 268	80.72 231	84.47 277	62.94 246	73.89 333	87.34 210	55.94 335	75.16 334	76.53 375	63.97 260	91.16 186	65.00 269	90.97 256	88.06 271

WB-MVS		76.06 262	80.01 218	64.19 363	89.96 168	20.58 404	72.18 343	68.19 367	83.21 54	86.46 176	93.49 112	70.19 229	78.97 339	65.96 257	90.46 269	93.02 149

thres600view7		75.97 263	75.35 265	77.85 276	87.01 233	51.84 353	80.45 245	73.26 342	75.20 148	83.10 241	86.31 278	45.54 357	89.05 244	55.03 336	92.24 230	92.66 163

GA-MVS		75.83 264	74.61 269	79.48 249	81.87 309	59.25 294	73.42 337	82.88 274	68.68 230	79.75 291	81.80 335	50.62 334	89.46 236	66.85 250	85.64 324	89.72 246

MVP-Stereo		75.81 265	73.51 281	82.71 197	89.35 176	73.62 132	80.06 248	85.20 247	60.30 309	73.96 340	87.94 249	57.89 300	89.45 237	52.02 351	74.87 383	85.06 306
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_fmvs3		75.72 266	75.20 266	77.27 282	75.01 375	69.47 184	78.93 267	84.88 257	46.67 373	87.08 157	87.84 252	50.44 336	71.62 360	77.42 146	88.53 288	90.72 223

thres100view900		75.45 267	75.05 267	76.66 291	87.27 223	51.88 352	81.07 239	73.26 342	75.68 141	83.25 238	86.37 275	45.54 357	88.80 248	51.98 352	90.99 253	89.31 253

ET-MVSNet_ETH3D		75.28 268	72.77 289	82.81 196	83.03 303	68.11 198	77.09 293	76.51 319	60.67 307	77.60 313	80.52 346	38.04 384	91.15 187	70.78 213	90.68 264	89.17 256

thres400		75.14 269	74.23 274	77.86 275	86.24 251	52.12 349	79.24 263	73.87 336	73.34 170	81.82 262	84.60 305	46.02 351	88.80 248	51.98 352	90.99 253	92.66 163

wuyk23d		75.13 270	79.30 223	62.63 366	75.56 368	75.18 124	80.89 241	73.10 344	75.06 150	94.76 12	95.32 35	87.73 40	52.85 396	34.16 396	97.11 80	59.85 393

EU-MVSNet		75.12 271	74.43 273	77.18 283	83.11 302	59.48 292	85.71 138	82.43 279	39.76 393	85.64 189	88.76 237	44.71 368	87.88 260	73.86 183	85.88 323	84.16 318

HyFIR lowres test		75.12 271	72.66 291	82.50 203	91.44 133	65.19 225	72.47 341	87.31 211	46.79 372	80.29 286	84.30 307	52.70 325	92.10 163	51.88 356	86.73 313	90.22 237

CMPMVS	59.41 20	75.12 271	73.57 279	79.77 242	75.84 367	67.22 203	81.21 237	82.18 280	50.78 364	76.50 316	87.66 255	55.20 317	82.99 318	62.17 292	90.64 268	89.09 260
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		74.92 274	72.98 287	80.73 230	84.95 270	71.71 165	76.23 308	77.59 308	52.83 349	77.73 312	86.38 274	56.35 310	84.97 304	57.72 319	87.05 309	85.51 301

tfpn200view9		74.86 275	74.23 274	76.74 290	86.24 251	52.12 349	79.24 263	73.87 336	73.34 170	81.82 262	84.60 305	46.02 351	88.80 248	51.98 352	90.99 253	89.31 253

1112_ss		74.82 276	73.74 277	78.04 271	89.57 170	60.04 285	76.49 304	87.09 220	54.31 342	73.66 343	79.80 352	60.25 281	86.76 278	58.37 313	84.15 344	87.32 283

EGC-MVSNET		74.79 277	69.99 317	89.19 63	94.89 37	87.00 11	91.89 34	86.28 229	1.09 401	2.23 403	95.98 23	81.87 109	89.48 234	79.76 114	95.96 124	91.10 214

ppachtmachnet_test		74.73 278	74.00 276	76.90 287	80.71 327	56.89 319	71.53 348	78.42 303	58.24 321	79.32 298	82.92 323	57.91 299	84.26 310	65.60 264	91.36 248	89.56 248

Patchmatch-RL test		74.48 279	73.68 278	76.89 288	84.83 272	66.54 211	72.29 342	69.16 365	57.70 326	86.76 163	86.33 276	45.79 356	82.59 319	69.63 225	90.65 267	81.54 352

PatchMatch-RL		74.48 279	73.22 284	78.27 267	87.70 214	85.26 34	75.92 313	70.09 360	64.34 272	76.09 322	81.25 340	65.87 251	78.07 342	53.86 341	83.82 345	71.48 381

XXY-MVS		74.44 281	76.19 256	69.21 339	84.61 276	52.43 348	71.70 346	77.18 313	60.73 306	80.60 280	90.96 188	75.44 172	69.35 366	56.13 326	88.33 291	85.86 298

test2506		74.12 282	73.39 282	76.28 295	91.85 115	44.20 383	84.06 167	48.20 401	72.30 193	81.90 259	94.20 81	27.22 402	89.77 231	64.81 271	96.02 121	94.87 67

CR-MVSNet		74.00 283	73.04 286	76.85 289	79.58 335	62.64 252	82.58 210	76.90 315	50.50 367	75.72 326	92.38 144	48.07 343	84.07 311	68.72 239	82.91 351	83.85 322

Test_1112_low_res		73.90 284	73.08 285	76.35 293	90.35 157	55.95 322	73.40 338	86.17 232	50.70 365	73.14 344	85.94 283	58.31 295	85.90 294	56.51 323	83.22 348	87.20 284

test20.03		73.75 285	74.59 271	71.22 327	81.11 320	51.12 359	70.15 356	72.10 350	70.42 211	80.28 288	91.50 170	64.21 259	74.72 354	46.96 374	94.58 178	87.82 278

test_fmvs2		73.57 286	72.80 288	75.90 299	72.74 387	68.84 193	77.07 294	84.32 263	45.14 379	82.89 244	84.22 308	48.37 341	70.36 363	73.40 191	87.03 310	88.52 267

SCA		73.32 287	72.57 293	75.58 302	81.62 313	55.86 324	78.89 269	71.37 356	61.73 290	74.93 335	83.42 317	60.46 278	87.01 269	58.11 317	82.63 356	83.88 319

baseline1		73.26 288	73.54 280	72.43 322	84.92 271	47.79 371	79.89 252	74.00 334	65.93 254	78.81 302	86.28 279	56.36 309	81.63 325	56.63 322	79.04 372	87.87 277

1314		73.22 289	72.56 294	75.20 303	80.41 331	57.84 310	81.64 231	85.36 244	51.68 358	73.10 345	76.65 374	61.45 273	85.19 302	63.54 281	79.21 370	82.59 338

MVS		73.21 290	72.59 292	75.06 305	80.97 321	60.81 279	81.64 231	85.92 238	46.03 377	71.68 352	77.54 366	68.47 237	89.77 231	55.70 329	85.39 325	74.60 378

HY-MVS	64.64 18	73.03 291	72.47 295	74.71 306	83.36 296	54.19 334	82.14 227	81.96 282	56.76 334	69.57 363	86.21 280	60.03 282	84.83 306	49.58 363	82.65 354	85.11 305

thisisatest0515		73.00 292	70.52 309	80.46 234	81.45 315	59.90 288	73.16 340	74.31 333	57.86 325	76.08 323	77.78 365	37.60 386	92.12 162	65.00 269	91.45 247	89.35 252

EPNet_dtu		72.87 293	71.33 305	77.49 280	77.72 349	60.55 282	82.35 218	75.79 322	66.49 252	58.39 396	81.06 341	53.68 321	85.98 291	53.55 342	92.97 217	85.95 296
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		72.62 294	71.41 304	76.28 295	83.25 297	60.34 283	83.50 184	79.02 302	37.77 396	76.33 318	85.10 296	49.60 339	87.41 265	70.54 218	77.54 378	81.08 359

CHOSEN 1792x2688		72.45 295	70.56 308	78.13 268	90.02 167	63.08 245	68.72 361	83.16 271	42.99 387	75.92 324	85.46 289	57.22 304	85.18 303	49.87 361	81.67 358	86.14 294

testgi		72.36 296	74.61 269	65.59 357	80.56 329	42.82 388	68.29 362	73.35 341	66.87 249	81.84 261	89.93 218	72.08 218	66.92 379	46.05 377	92.54 223	87.01 286

thres200		72.34 297	71.55 303	74.70 307	83.48 292	51.60 354	75.02 322	73.71 339	70.14 217	78.56 304	80.57 345	46.20 349	88.20 258	46.99 373	89.29 278	84.32 314

FPMVS		72.29 298	72.00 297	73.14 315	88.63 195	85.00 36	74.65 326	67.39 369	71.94 198	77.80 310	87.66 255	50.48 335	75.83 350	49.95 359	79.51 366	58.58 395

FMVSNet5		72.10 299	71.69 299	73.32 313	81.57 314	53.02 343	76.77 298	78.37 304	63.31 275	76.37 317	91.85 158	36.68 387	78.98 338	47.87 370	92.45 224	87.95 274

our_test_3		71.85 300	71.59 300	72.62 319	80.71 327	53.78 337	69.72 358	71.71 355	58.80 318	78.03 305	80.51 347	56.61 308	78.84 340	62.20 290	86.04 322	85.23 303

PAPM		71.77 301	70.06 315	76.92 286	86.39 242	53.97 335	76.62 302	86.62 226	53.44 346	63.97 386	84.73 303	57.79 301	92.34 155	39.65 388	81.33 362	84.45 312

IB-MVS	62.13 19	71.64 302	68.97 325	79.66 246	80.80 326	62.26 261	73.94 332	76.90 315	63.27 276	68.63 367	76.79 373	33.83 391	91.84 170	59.28 310	87.26 304	84.88 307
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		71.63 303	72.30 296	69.62 336	76.47 361	52.70 346	70.03 357	80.97 291	59.18 315	79.36 296	88.21 245	60.50 277	69.12 367	58.33 315	77.62 377	87.04 285

testing3		71.53 304	70.79 306	73.77 311	88.89 188	41.86 390	76.60 303	59.12 391	72.83 181	80.97 273	82.08 332	19.80 407	87.33 267	65.12 268	91.68 242	92.13 188

test_vis3_rt		71.42 305	70.67 307	73.64 312	69.66 393	70.46 175	66.97 369	89.73 174	42.68 389	88.20 138	83.04 319	43.77 370	60.07 391	65.35 267	86.66 314	90.39 235

Anonymous20231206		71.38 306	71.88 298	69.88 334	86.31 247	54.37 333	70.39 354	74.62 329	52.57 351	76.73 315	88.76 237	59.94 283	72.06 357	44.35 381	93.23 210	83.23 333

test_vis1_n_1920		71.30 307	71.58 302	70.47 330	77.58 351	59.99 287	74.25 327	84.22 264	51.06 361	74.85 336	79.10 357	55.10 318	68.83 369	68.86 236	79.20 371	82.58 339

MIMVSNet		71.09 308	71.59 300	69.57 337	87.23 224	50.07 364	78.91 268	71.83 352	60.20 312	71.26 353	91.76 164	55.08 319	76.09 348	41.06 386	87.02 311	82.54 341

test_fmvs1_n		70.94 309	70.41 312	72.53 321	73.92 377	66.93 208	75.99 312	84.21 265	43.31 386	79.40 295	79.39 355	43.47 371	68.55 371	69.05 233	84.91 336	82.10 346

MS-PatchMatch		70.93 310	70.22 313	73.06 316	81.85 310	62.50 255	73.82 334	77.90 305	52.44 352	75.92 324	81.27 339	55.67 314	81.75 323	55.37 332	77.70 376	74.94 377

pmmvs5		70.73 311	70.07 314	72.72 318	77.03 356	52.73 345	74.14 328	75.65 325	50.36 368	72.17 350	85.37 293	55.42 316	80.67 330	52.86 348	87.59 303	84.77 308

PatchT		70.52 312	72.76 290	63.79 365	79.38 339	33.53 399	77.63 286	65.37 378	73.61 165	71.77 351	92.79 134	44.38 369	75.65 351	64.53 276	85.37 326	82.18 345

test_vis1_n		70.29 313	69.99 317	71.20 328	75.97 366	66.50 212	76.69 300	80.81 292	44.22 382	75.43 329	77.23 370	50.00 337	68.59 370	66.71 253	82.85 353	78.52 371

N_pmnet		70.20 314	68.80 327	74.38 308	80.91 322	84.81 39	59.12 385	76.45 320	55.06 339	75.31 333	82.36 329	55.74 313	54.82 395	47.02 372	87.24 305	83.52 326

tpmvs		70.16 315	69.56 320	71.96 324	74.71 376	48.13 368	79.63 254	75.45 327	65.02 269	70.26 359	81.88 334	45.34 362	85.68 298	58.34 314	75.39 382	82.08 347

new-patchmatchnet		70.10 316	73.37 283	60.29 373	81.23 319	16.95 406	59.54 383	74.62 329	62.93 278	80.97 273	87.93 250	62.83 270	71.90 358	55.24 334	95.01 163	92.00 192

YYNet1		70.06 317	70.44 310	68.90 340	73.76 379	53.42 341	58.99 386	67.20 371	58.42 320	87.10 155	85.39 292	59.82 285	67.32 376	59.79 307	83.50 347	85.96 295

MDA-MVSNet_test_wron		70.05 318	70.44 310	68.88 341	73.84 378	53.47 339	58.93 387	67.28 370	58.43 319	87.09 156	85.40 291	59.80 286	67.25 377	59.66 308	83.54 346	85.92 297

CostFormer		69.98 319	68.68 328	73.87 309	77.14 354	50.72 361	79.26 262	74.51 331	51.94 357	70.97 356	84.75 302	45.16 365	87.49 264	55.16 335	79.23 369	83.40 329

baseline2		69.77 320	66.89 335	78.41 263	79.51 337	58.09 307	76.23 308	69.57 363	57.50 329	64.82 384	77.45 368	46.02 351	88.44 254	53.08 344	77.83 374	88.70 265

PatchmatchNet		69.71 321	68.83 326	72.33 323	77.66 350	53.60 338	79.29 261	69.99 361	57.66 327	72.53 348	82.93 322	46.45 348	80.08 334	60.91 302	72.09 386	83.31 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_fmvs1		69.57 322	69.05 323	71.14 329	69.15 394	65.77 221	73.98 331	83.32 270	42.83 388	77.77 311	78.27 364	43.39 374	68.50 372	68.39 243	84.38 343	79.15 369

JIA-IIPM		69.41 323	66.64 339	77.70 277	73.19 382	71.24 170	75.67 314	65.56 377	70.42 211	65.18 380	92.97 126	33.64 392	83.06 316	53.52 343	69.61 392	78.79 370

Syy-MVS		69.40 324	70.03 316	67.49 350	81.72 311	38.94 392	71.00 349	61.99 382	61.38 296	70.81 357	72.36 385	61.37 274	79.30 336	64.50 277	85.18 329	84.22 315

UnsupCasMVSNet_bld		69.21 325	69.68 319	67.82 348	79.42 338	51.15 358	67.82 366	75.79 322	54.15 343	77.47 314	85.36 294	59.26 289	70.64 362	48.46 367	79.35 368	81.66 350

test_cas_vis1_n_1920		69.20 326	69.12 321	69.43 338	73.68 380	62.82 249	70.38 355	77.21 312	46.18 376	80.46 285	78.95 359	52.03 327	65.53 384	65.77 263	77.45 379	79.95 367

gg-mvs-nofinetune		68.96 327	69.11 322	68.52 346	76.12 365	45.32 379	83.59 182	55.88 396	86.68 24	64.62 385	97.01 7	30.36 395	83.97 313	44.78 380	82.94 350	76.26 374

WB-MVSnew		68.72 328	69.01 324	67.85 347	83.22 299	43.98 384	74.93 323	65.98 376	55.09 338	73.83 341	79.11 356	65.63 252	71.89 359	38.21 392	85.04 332	87.69 279

tpm2		68.45 329	66.83 336	73.30 314	78.93 345	48.50 367	79.76 253	71.76 353	47.50 371	69.92 361	83.60 313	42.07 377	88.40 255	48.44 368	79.51 366	83.01 336

tpm		67.95 330	68.08 331	67.55 349	78.74 346	43.53 386	75.60 315	67.10 374	54.92 340	72.23 349	88.10 246	42.87 376	75.97 349	52.21 350	80.95 365	83.15 334

WTY-MVS		67.91 331	68.35 329	66.58 354	80.82 325	48.12 369	65.96 371	72.60 345	53.67 345	71.20 354	81.68 337	58.97 291	69.06 368	48.57 366	81.67 358	82.55 340

test-LLR		67.21 332	66.74 337	68.63 344	76.45 362	55.21 329	67.89 363	67.14 372	62.43 285	65.08 381	72.39 383	43.41 372	69.37 364	61.00 300	84.89 337	81.31 354

testing222		66.93 333	65.30 344	71.81 325	83.38 295	45.83 378	72.06 344	67.50 368	64.12 273	69.68 362	76.37 376	27.34 401	83.00 317	38.88 389	88.38 290	86.62 290

sss		66.92 334	67.26 333	65.90 356	77.23 353	51.10 360	64.79 373	71.72 354	52.12 356	70.13 360	80.18 349	57.96 298	65.36 385	50.21 358	81.01 364	81.25 356

KD-MVS_2432*1600		66.87 335	65.81 341	70.04 332	67.50 395	47.49 372	62.56 378	79.16 299	61.21 301	77.98 306	80.61 343	25.29 404	82.48 320	53.02 345	84.92 334	80.16 365

miper_refine_blended		66.87 335	65.81 341	70.04 332	67.50 395	47.49 372	62.56 378	79.16 299	61.21 301	77.98 306	80.61 343	25.29 404	82.48 320	53.02 345	84.92 334	80.16 365

dmvs_re		66.81 337	66.98 334	66.28 355	76.87 357	58.68 305	71.66 347	72.24 348	60.29 310	69.52 364	73.53 382	52.38 326	64.40 387	44.90 379	81.44 361	75.76 375

tpm cat1		66.76 338	65.21 345	71.42 326	77.09 355	50.62 362	78.01 279	73.68 340	44.89 380	68.64 366	79.00 358	45.51 359	82.42 322	49.91 360	70.15 389	81.23 358

PVSNet	58.17 21	66.41 339	65.63 343	68.75 342	81.96 308	49.88 365	62.19 380	72.51 347	51.03 362	68.04 369	75.34 380	50.84 333	74.77 352	45.82 378	82.96 349	81.60 351

tpmrst		66.28 340	66.69 338	65.05 361	72.82 386	39.33 391	78.20 278	70.69 359	53.16 348	67.88 370	80.36 348	48.18 342	74.75 353	58.13 316	70.79 388	81.08 359

Patchmatch-test		65.91 341	67.38 332	61.48 371	75.51 369	43.21 387	68.84 360	63.79 380	62.48 282	72.80 347	83.42 317	44.89 367	59.52 393	48.27 369	86.45 316	81.70 349

ADS-MVSNet2		65.87 342	63.64 350	72.55 320	73.16 383	56.92 318	67.10 367	74.81 328	49.74 369	66.04 375	82.97 320	46.71 346	77.26 345	42.29 383	69.96 390	83.46 327

test_vis1_rt		65.64 343	64.09 347	70.31 331	66.09 399	70.20 178	61.16 381	81.60 287	38.65 394	72.87 346	69.66 388	52.84 323	60.04 392	56.16 325	77.77 375	80.68 363

mvsany_test3		65.48 344	62.97 352	73.03 317	69.99 392	76.17 118	64.83 372	43.71 403	43.68 384	80.25 289	87.05 269	52.83 324	63.09 390	51.92 355	72.44 385	79.84 368

test-mter		65.00 345	63.79 349	68.63 344	76.45 362	55.21 329	67.89 363	67.14 372	50.98 363	65.08 381	72.39 383	28.27 399	69.37 364	61.00 300	84.89 337	81.31 354

ETVMVS		64.67 346	63.34 351	68.64 343	83.44 294	41.89 389	69.56 359	61.70 387	61.33 298	68.74 365	75.76 378	28.76 397	79.35 335	34.65 395	86.16 321	84.67 310

myMVS_eth3d		64.66 347	63.89 348	66.97 352	81.72 311	37.39 395	71.00 349	61.99 382	61.38 296	70.81 357	72.36 385	20.96 406	79.30 336	49.59 362	85.18 329	84.22 315

test0.0.03 1		64.66 347	64.36 346	65.57 358	75.03 374	46.89 375	64.69 374	61.58 388	62.43 285	71.18 355	77.54 366	43.41 372	68.47 373	40.75 387	82.65 354	81.35 353

test_f		64.31 349	65.85 340	59.67 374	66.54 398	62.24 262	57.76 388	70.96 357	40.13 391	84.36 213	82.09 331	46.93 345	51.67 397	61.99 293	81.89 357	65.12 389

pmmvs3		62.47 350	60.02 363	69.80 335	71.58 390	64.00 236	70.52 353	58.44 394	39.77 392	66.05 374	75.84 377	27.10 403	72.28 356	46.15 376	84.77 341	73.11 379

EPMVS		62.47 350	62.63 354	62.01 367	70.63 391	38.74 393	74.76 324	52.86 398	53.91 344	67.71 372	80.01 350	39.40 381	66.60 380	55.54 331	68.81 394	80.68 363

ADS-MVSNet		61.90 352	62.19 356	61.03 372	73.16 383	36.42 397	67.10 367	61.75 385	49.74 369	66.04 375	82.97 320	46.71 346	63.21 388	42.29 383	69.96 390	83.46 327

PMMVS		61.65 353	60.38 360	65.47 359	65.40 402	69.26 187	63.97 376	61.73 386	36.80 397	60.11 391	68.43 390	59.42 287	66.35 381	48.97 365	78.57 373	60.81 392

E-PMN		61.59 354	61.62 357	61.49 370	66.81 397	55.40 327	53.77 391	60.34 390	66.80 250	58.90 394	65.50 393	40.48 380	66.12 382	55.72 328	86.25 319	62.95 391

TESTMET0.1,1		61.29 355	60.32 361	64.19 363	72.06 388	51.30 356	67.89 363	62.09 381	45.27 378	60.65 390	69.01 389	27.93 400	64.74 386	56.31 324	81.65 360	76.53 373

MVS-HIRNet		61.16 356	62.92 353	55.87 377	79.09 342	35.34 398	71.83 345	57.98 395	46.56 374	59.05 393	91.14 180	49.95 338	76.43 347	38.74 390	71.92 387	55.84 396

EMVS		61.10 357	60.81 359	61.99 368	65.96 400	55.86 324	53.10 392	58.97 393	67.06 247	56.89 397	63.33 394	40.98 378	67.03 378	54.79 337	86.18 320	63.08 390

DSMNet-mixed		60.98 358	61.61 358	59.09 376	72.88 385	45.05 381	74.70 325	46.61 402	26.20 398	65.34 379	90.32 209	55.46 315	63.12 389	41.72 385	81.30 363	69.09 385

dp		60.70 359	60.29 362	61.92 369	72.04 389	38.67 394	70.83 351	64.08 379	51.28 360	60.75 389	77.28 369	36.59 388	71.58 361	47.41 371	62.34 396	75.52 376

dmvs_testset		60.59 360	62.54 355	54.72 379	77.26 352	27.74 402	74.05 330	61.00 389	60.48 308	65.62 378	67.03 392	55.93 312	68.23 374	32.07 399	69.46 393	68.17 386

CHOSEN 280x420		59.08 361	56.52 366	66.76 353	76.51 360	64.39 232	49.62 393	59.00 392	43.86 383	55.66 398	68.41 391	35.55 390	68.21 375	43.25 382	76.78 381	67.69 387

mvsany_test1		58.48 362	56.47 367	64.50 362	65.90 401	68.21 197	56.95 389	42.11 404	38.30 395	65.69 377	77.19 372	56.96 305	59.35 394	46.16 375	58.96 397	65.93 388

PVSNet_0	51.08 22	56.10 363	54.97 368	59.48 375	75.12 373	53.28 342	55.16 390	61.89 384	44.30 381	59.16 392	62.48 395	54.22 320	65.91 383	35.40 394	47.01 398	59.25 394

new_pmnet		55.69 364	57.66 365	49.76 380	75.47 370	30.59 400	59.56 382	51.45 399	43.62 385	62.49 387	75.48 379	40.96 379	49.15 399	37.39 393	72.52 384	69.55 384

PMMVS2		55.64 365	59.27 364	44.74 381	64.30 403	12.32 407	40.60 394	49.79 400	53.19 347	65.06 383	84.81 301	53.60 322	49.76 398	32.68 398	89.41 277	72.15 380

MVE	40.22 23	51.82 366	50.47 369	55.87 377	62.66 404	51.91 351	31.61 396	39.28 405	40.65 390	50.76 399	74.98 381	56.24 311	44.67 400	33.94 397	64.11 395	71.04 383
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		30.46 367	29.60 370	33.06 382	17.99 406	3.84 409	13.62 397	73.92 335	2.79 400	18.29 402	53.41 397	28.53 398	43.25 401	22.56 400	35.27 400	52.11 397

cdsmvs_eth3d_5k		20.81 368	27.75 371	0.00 387	0.00 410	0.00 412	0.00 398	85.44 243	0.00 405	0.00 406	82.82 324	81.46 113	0.00 406	0.00 405	0.00 404	0.00 402

tmp_tt		20.25 369	24.50 372	7.49 384	4.47 407	8.70 408	34.17 395	25.16 407	1.00 402	32.43 401	18.49 399	39.37 382	9.21 403	21.64 401	43.75 399	4.57 399

ab-mvs-re		6.65 370	8.87 373	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	79.80 352	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

pcd_1.5k_mvsjas		6.41 371	8.55 374	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	76.94 159	0.00 406	0.00 405	0.00 404	0.00 402

test123		6.27 372	8.08 375	0.84 385	1.11 409	0.57 410	62.90 377	0.82 409	0.54 403	1.07 405	2.75 404	1.26 408	0.30 404	1.04 403	1.26 403	1.66 400

testmvs		5.91 373	7.65 376	0.72 386	1.20 408	0.37 411	59.14 384	0.67 410	0.49 404	1.11 404	2.76 403	0.94 409	0.24 405	1.02 404	1.47 402	1.55 401

test_blank		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet_test		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

DCPMVS		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

sosnet-low-res		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

sosnet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uncertanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

Regformer		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

WAC-MVS						37.39 395								52.61 349

FOURS1					96.08 11	87.41 10	96.19 2	95.83 4	92.95 2	96.57 2

MSC_two_6792asdad				88.81 69	91.55 127	77.99 90		91.01 139					96.05 8	87.45 20	98.17 32	92.40 173

PC_three_1452									58.96 317	90.06 96	91.33 174	80.66 123	93.03 137	75.78 162	95.94 126	92.48 169

No_MVS				88.81 69	91.55 127	77.99 90		91.01 139					96.05 8	87.45 20	98.17 32	92.40 173

test_one_0601					93.85 58	73.27 137		94.11 33	86.57 25	93.47 38	94.64 60	88.42 26

eth-test2					0.00 410

eth-test					0.00 410

ZD-MVS					92.22 102	80.48 67		91.85 114	71.22 204	90.38 91	92.98 124	86.06 59	96.11 6	81.99 92	96.75 91

RE-MVS-def			92.61 4		94.13 51	88.95 5	92.87 13	94.16 27	88.75 14	93.79 28	94.43 68	90.64 10		87.16 29	97.60 64	92.73 158

IU-MVS					94.18 46	72.64 145		90.82 144	56.98 332	89.67 108				85.78 50	97.92 46	93.28 137

OPU-MVS				88.27 80	91.89 113	77.83 93	90.47 51				91.22 177	81.12 117	94.68 71	74.48 173	95.35 146	92.29 179

test_241102_TWO								93.71 49	83.77 47	93.49 36	94.27 75	89.27 21	95.84 23	86.03 46	97.82 51	92.04 190

test_241102_ONE					94.18 46	72.65 143		93.69 50	83.62 49	94.11 22	93.78 105	90.28 14	95.50 46

9.14			89.29 58		91.84 117		88.80 88	95.32 11	75.14 149	91.07 80	92.89 129	87.27 44	93.78 105	83.69 70	97.55 67

save fliter					93.75 59	77.44 99	86.31 129	89.72 175	70.80 207

test_0728_THIRD									85.33 33	93.75 30	94.65 57	87.44 43	95.78 28	87.41 22	98.21 29	92.98 152

test_0728_SECOND				86.79 100	94.25 45	72.45 153	90.54 48	94.10 34					95.88 17	86.42 36	97.97 43	92.02 191

test0726					94.16 49	72.56 149	90.63 45	93.90 42	83.61 50	93.75 30	94.49 65	89.76 18

GSMVS																83.88 319

test_part2					93.86 57	77.77 94				92.84 48

sam_mvs1												46.11 350				83.88 319

sam_mvs												45.92 355

ambc				82.98 189	90.55 154	64.86 227	88.20 97	89.15 186		89.40 117	93.96 96	71.67 223	91.38 182	78.83 124	96.55 96	92.71 161

MTGPA								91.81 118

test_post1							78.85 271				3.13 401	45.19 364	80.13 333	58.11 317

test_post											3.10 402	45.43 360	77.22 346

patchmatchnet-post											81.71 336	45.93 354	87.01 269

GG-mvs-BLEND				67.16 351	73.36 381	46.54 377	84.15 164	55.04 397		58.64 395	61.95 396	29.93 396	83.87 314	38.71 391	76.92 380	71.07 382

MTMP							90.66 44	33.14 406

gm-plane-assit					75.42 371	44.97 382			52.17 353		72.36 385		87.90 259	54.10 340

test9_res														80.83 102	96.45 103	90.57 229

TEST9					92.34 96	79.70 74	83.94 170	90.32 158	65.41 265	84.49 209	90.97 186	82.03 104	93.63 110

test_8					92.09 106	78.87 81	83.82 175	90.31 160	65.79 256	84.36 213	90.96 188	81.93 106	93.44 123

agg_prior2														79.68 116	96.16 114	90.22 237

agg_prior					91.58 125	77.69 96		90.30 161		84.32 215			93.18 131

TestCases				89.68 53	91.59 122	83.40 48		95.44 9	79.47 94	88.00 141	93.03 122	82.66 89	91.47 176	70.81 211	96.14 115	94.16 96

test_prior4						78.97 80	84.59 155

test_prior2							83.37 187		75.43 145	84.58 207	91.57 168	81.92 108		79.54 118	96.97 84

test_prior				86.32 108	90.59 153	71.99 160		92.85 86					94.17 92			92.80 156

旧先验2							81.73 229		56.88 333	86.54 174			84.90 305	72.81 200

新几何2							81.72 230

新几何1				82.95 191	93.96 55	78.56 84		80.24 295	55.45 337	83.93 227	91.08 183	71.19 225	88.33 256	65.84 261	93.07 213	81.95 348

旧先验1					91.97 109	71.77 161		81.78 285			91.84 159	73.92 192			93.65 201	83.61 325

无先验							82.81 205	85.62 241	58.09 323				91.41 181	67.95 247		84.48 311

原ACMM2							82.26 223

原ACMM1				84.60 145	92.81 87	74.01 130		91.50 123	62.59 280	82.73 247	90.67 201	76.53 166	94.25 86	69.24 228	95.69 140	85.55 300

test222					93.31 71	76.54 109	79.38 260	77.79 306	52.59 350	82.36 251	90.84 194	66.83 245			91.69 241	81.25 356

testdata2													86.43 283	63.52 282

segment_acmp												81.94 105

testdata				79.54 248	92.87 82	72.34 154		80.14 296	59.91 313	85.47 193	91.75 165	67.96 240	85.24 301	68.57 242	92.18 233	81.06 361

testdata1							79.62 255		73.95 160

test12				86.57 103	90.74 149	72.63 147		90.69 147		82.76 246		79.20 133	94.80 68		95.32 148	92.27 181

plane_prior7					93.45 66	77.31 102

plane_prior6					92.61 88	76.54 109						74.84 180

plane_prior5								93.61 53					95.22 56	80.78 103	95.83 132	94.46 80

plane_prior4											92.95 127

plane_prior3						76.85 107			77.79 118	86.55 169

plane_prior2							89.45 77		79.44 96

plane_prior1					92.83 86

plane_prior						76.42 113	87.15 112		75.94 138						95.03 160

n2								0.00 411

nn								0.00 411

door-mid								74.45 332

lessismore_v0				85.95 118	91.10 142	70.99 172		70.91 358		91.79 67	94.42 70	61.76 272	92.93 140	79.52 119	93.03 214	93.93 107

LGP-MVS_train				90.82 33	94.75 40	81.69 59		94.27 19	82.35 63	93.67 33	94.82 52	91.18 4	95.52 42	85.36 52	98.73 6	95.23 59

test11								91.46 124

door								72.57 346

HQP5-MVS						70.66 173

HQP-NCC					91.19 137		84.77 149		73.30 172	80.55 282

ACMP_Plane					91.19 137		84.77 149		73.30 172	80.55 282

BP-MVS														77.30 147

HQP4-MVS										80.56 281			94.61 74			93.56 129

HQP3-MVS								92.68 91							94.47 180

HQP2-MVS												72.10 216

NP-MVS					91.95 110	74.55 127					90.17 215

MDTV_nov1_ep13_2view						27.60 403	70.76 352		46.47 375	61.27 388		45.20 363		49.18 364		83.75 324

MDTV_nov1_ep13			68.29 330		78.03 347	43.87 385	74.12 329	72.22 349	52.17 353	67.02 373	85.54 287	45.36 361	80.85 329	55.73 327	84.42 342

ACMMP++_ref															95.74 139

ACMMP++															97.35 73

Test By Simon												79.09 134

ITE_SJBPF				90.11 45	90.72 150	84.97 37		90.30 161	81.56 71	90.02 98	91.20 179	82.40 94	90.81 199	73.58 188	94.66 176	94.56 76

DeepMVS_CX				24.13 383	32.95 405	29.49 401		21.63 408	12.07 399	37.95 400	45.07 398	30.84 394	19.21 402	17.94 402	33.06 401	23.69 398

High-resolution multi-view benchmark