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		86.90 1	88.67 1	81.57 21	91.50 1	63.30 114	84.80 32	87.77 9	86.18 1	96.26 1	96.06 1	90.32 1	84.49 67	68.08 83	97.05 1	96.93 1

TDRefinement		86.32 2	86.33 2	86.29 1	88.64 31	81.19 4	88.84 4	90.72 1	78.27 8	87.95 14	92.53 13	79.37 13	84.79 64	74.51 46	96.15 2	92.88 7

RE-MVS-def			85.50 3		86.19 49	79.18 6	87.23 8	86.27 19	77.51 10	87.65 18	90.73 47	81.38 7		78.11 23	94.46 36	84.89 92

SR-MVS		84.51 5	85.27 4	82.25 18	88.52 33	77.71 13	86.81 16	85.25 36	77.42 13	86.15 38	90.24 71	81.69 5	85.94 33	77.77 26	93.58 61	83.09 147

SR-MVS-dyc-post		84.75 3	85.26 5	83.21 3	86.19 49	79.18 6	87.23 8	86.27 19	77.51 10	87.65 18	90.73 47	79.20 14	85.58 47	78.11 23	94.46 36	84.89 92

HPM-MVS_fast		84.59 4	85.10 6	83.06 4	88.60 32	75.83 23	86.27 24	86.89 15	73.69 23	86.17 37	91.70 25	78.23 19	85.20 56	79.45 12	94.91 24	88.15 47

LTVRE_ROB	75.46 1	84.22 6	84.98 7	81.94 20	84.82 73	75.40 25	91.60 3	87.80 7	73.52 24	88.90 11	93.06 6	71.39 68	81.53 112	81.53 3	92.15 82	88.91 38
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
ACMMP		84.22 6	84.84 8	82.35 17	89.23 21	76.66 22	87.65 6	85.89 25	71.03 41	85.85 42	90.58 51	78.77 16	85.78 40	79.37 15	95.17 16	84.62 103
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
HPM-MVS		84.12 8	84.63 9	82.60 13	88.21 35	74.40 31	85.24 28	87.21 13	70.69 44	85.14 54	90.42 58	78.99 15	86.62 12	80.83 5	94.93 23	86.79 63
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		84.12 8	84.55 10	82.80 10	89.42 17	79.74 5	88.19 5	84.43 57	71.96 38	84.70 61	90.56 52	77.12 25	86.18 25	79.24 17	95.36 12	82.49 164

mPP-MVS		84.01 10	84.39 11	82.88 6	90.65 3	81.38 3	87.08 12	82.79 82	72.41 34	85.11 55	90.85 44	76.65 28	84.89 61	79.30 16	94.63 33	82.35 166

APD-MVS_3200maxsize		83.57 13	84.33 12	81.31 28	82.83 107	73.53 40	85.50 27	87.45 12	74.11 19	86.45 35	90.52 55	80.02 10	84.48 68	77.73 27	94.34 47	85.93 74

LPG-MVS_test		83.47 16	84.33 12	80.90 32	87.00 39	70.41 60	82.04 56	86.35 16	69.77 49	87.75 15	91.13 34	81.83 3	86.20 23	77.13 34	95.96 5	86.08 71

APDe-MVS		82.88 23	84.14 14	79.08 52	84.80 75	66.72 90	86.54 20	85.11 38	72.00 37	86.65 31	91.75 24	78.20 20	87.04 8	77.93 25	94.32 48	83.47 137

COLMAP_ROB	72.78 3	83.75 11	84.11 15	82.68 12	82.97 104	74.39 32	87.18 10	88.18 6	78.98 6	86.11 40	91.47 30	79.70 12	85.76 41	66.91 98	95.46 11	87.89 48
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
HFP-MVS		83.39 17	84.03 16	81.48 23	89.25 20	75.69 24	87.01 14	84.27 60	70.23 45	84.47 64	90.43 57	76.79 26	85.94 33	79.58 10	94.23 51	82.82 156

ACMMPR		83.62 12	83.93 17	82.69 11	89.78 10	77.51 18	87.01 14	84.19 64	70.23 45	84.49 63	90.67 50	75.15 41	86.37 17	79.58 10	94.26 49	84.18 121

MTAPA		83.19 18	83.87 18	81.13 30	91.16 2	78.16 11	84.87 30	80.63 122	72.08 36	84.93 56	90.79 45	74.65 46	84.42 70	80.98 4	94.75 28	80.82 192

region2R		83.54 14	83.86 19	82.58 14	89.82 9	77.53 16	87.06 13	84.23 63	70.19 47	83.86 71	90.72 49	75.20 40	86.27 20	79.41 14	94.25 50	83.95 125

XVS		83.51 15	83.73 20	82.85 8	89.43 15	77.61 14	86.80 17	84.66 52	72.71 27	82.87 82	90.39 62	73.86 52	86.31 18	78.84 19	94.03 53	84.64 101

ZNCC-MVS		83.12 20	83.68 21	81.45 24	89.14 24	73.28 42	86.32 23	85.97 24	67.39 58	84.02 68	90.39 62	74.73 45	86.46 14	80.73 6	94.43 40	84.60 106

SteuartSystems-ACMMP		83.07 21	83.64 22	81.35 26	85.14 68	71.00 54	85.53 26	84.78 45	70.91 42	85.64 45	90.41 59	75.55 38	87.69 3	79.75 7	95.08 19	85.36 83
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		83.19 18	83.54 23	82.14 19	90.54 4	79.00 8	86.42 22	83.59 73	71.31 39	81.26 102	90.96 39	74.57 47	84.69 65	78.41 21	94.78 27	82.74 159
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SED-MVS		81.78 31	83.48 24	76.67 81	86.12 53	61.06 131	83.62 42	84.72 48	72.61 30	87.38 24	89.70 81	77.48 23	85.89 38	75.29 40	94.39 41	83.08 148

MP-MVS-pluss		82.54 26	83.46 25	79.76 41	88.88 30	68.44 76	81.57 59	86.33 18	63.17 104	85.38 52	91.26 33	76.33 30	84.67 66	83.30 1	94.96 22	86.17 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMP	69.50 8	82.64 25	83.38 26	80.40 37	86.50 45	69.44 67	82.30 53	86.08 23	66.80 62	86.70 30	89.99 76	81.64 6	85.95 32	74.35 47	96.11 3	85.81 76
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	69.25 9	82.11 29	83.31 27	78.49 63	88.17 36	73.96 34	83.11 49	84.52 56	66.40 66	87.45 22	89.16 93	81.02 8	80.52 135	74.27 48	95.73 7	80.98 188
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMMP_NAP		82.33 27	83.28 28	79.46 48	89.28 18	69.09 74	83.62 42	84.98 41	64.77 86	83.97 69	91.02 38	75.53 39	85.93 35	82.00 2	94.36 45	83.35 142

GST-MVS		82.79 24	83.27 29	81.34 27	88.99 26	73.29 41	85.94 25	85.13 37	68.58 56	84.14 67	90.21 73	73.37 56	86.41 15	79.09 18	93.98 56	84.30 120

PGM-MVS		83.07 21	83.25 30	82.54 15	89.57 13	77.21 20	82.04 56	85.40 33	67.96 57	84.91 59	90.88 42	75.59 36	86.57 13	78.16 22	94.71 30	83.82 126

PMVS	70.70 6	81.70 32	83.15 31	77.36 75	90.35 5	82.82 2	82.15 54	79.22 147	74.08 20	87.16 28	91.97 19	84.80 2	76.97 194	64.98 108	93.61 60	72.28 281
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DVP-MVS		81.15 37	83.12 32	75.24 101	86.16 51	60.78 137	83.77 40	80.58 124	72.48 32	85.83 43	90.41 59	78.57 17	85.69 43	75.86 37	94.39 41	79.24 219
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
DPE-MVS		82.00 30	83.02 33	78.95 57	85.36 65	67.25 85	82.91 50	84.98 41	73.52 24	85.43 51	90.03 75	76.37 29	86.97 10	74.56 45	94.02 55	82.62 161
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PEN-MVS		80.46 46	82.91 34	73.11 127	89.83 8	39.02 306	77.06 111	82.61 86	80.04 4	90.60 6	92.85 9	74.93 44	85.21 55	63.15 128	95.15 17	95.09 2

DTE-MVSNet		80.35 48	82.89 35	72.74 142	89.84 7	37.34 321	77.16 108	81.81 96	80.45 3	90.92 3	92.95 7	74.57 47	86.12 28	63.65 121	94.68 31	94.76 6

PS-CasMVS		80.41 47	82.86 36	73.07 129	89.93 6	39.21 303	77.15 109	81.28 106	79.74 5	90.87 4	92.73 11	75.03 43	84.93 60	63.83 120	95.19 15	95.07 3

DVP-MVS++		81.24 35	82.74 37	76.76 80	83.14 96	60.90 135	91.64 1	85.49 29	74.03 21	84.93 56	90.38 64	66.82 105	85.90 36	77.43 30	90.78 114	83.49 134

SMA-MVS		82.12 28	82.68 38	80.43 36	88.90 29	69.52 65	85.12 29	84.76 46	63.53 98	84.23 66	91.47 30	72.02 62	87.16 6	79.74 9	94.36 45	84.61 104
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
ACMH+	66.64 10	81.20 36	82.48 39	77.35 76	81.16 129	62.39 119	80.51 66	87.80 7	73.02 26	87.57 20	91.08 36	80.28 9	82.44 97	64.82 109	96.10 4	87.21 57

UA-Net		81.56 33	82.28 40	79.40 49	88.91 28	69.16 72	84.67 33	80.01 136	75.34 15	79.80 117	94.91 2	69.79 82	80.25 139	72.63 58	94.46 36	88.78 42

WR-MVS_H		80.22 50	82.17 41	74.39 106	89.46 14	42.69 280	78.24 95	82.24 89	78.21 9	89.57 9	92.10 18	68.05 95	85.59 46	66.04 101	95.62 9	94.88 5

SF-MVS		80.72 43	81.80 42	77.48 73	82.03 117	64.40 107	83.41 46	88.46 5	65.28 78	84.29 65	89.18 91	73.73 55	83.22 86	76.01 36	93.77 58	84.81 98

CPTT-MVS		81.51 34	81.76 43	80.76 34	89.20 22	78.75 9	86.48 21	82.03 93	68.80 52	80.92 106	88.52 107	72.00 63	82.39 98	74.80 42	93.04 68	81.14 182

APD-MVS		81.13 38	81.73 44	79.36 50	84.47 80	70.53 59	83.85 38	83.70 71	69.43 51	83.67 73	88.96 99	75.89 34	86.41 15	72.62 59	92.95 69	81.14 182
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVSNet		79.48 54	81.65 45	72.98 132	89.66 12	39.06 305	76.76 112	80.46 126	78.91 7	90.32 7	91.70 25	68.49 90	84.89 61	63.40 125	95.12 18	95.01 4

OPM-MVS		80.99 41	81.63 46	79.07 53	86.86 43	69.39 68	79.41 82	84.00 69	65.64 70	85.54 49	89.28 87	76.32 31	83.47 82	74.03 49	93.57 62	84.35 117
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SD-MVS		80.28 49	81.55 47	76.47 86	83.57 90	67.83 80	83.39 47	85.35 35	64.42 88	86.14 39	87.07 126	74.02 51	80.97 126	77.70 28	92.32 80	80.62 199
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		80.54 44	81.06 48	78.98 56	87.01 38	72.91 43	80.23 74	85.56 28	66.56 65	85.64 45	89.57 83	69.12 86	80.55 134	72.51 60	93.37 63	83.48 136

LS3D		80.99 41	80.85 49	81.41 25	78.37 161	71.37 50	87.45 7	85.87 26	77.48 12	81.98 91	89.95 78	69.14 85	85.26 52	66.15 99	91.24 96	87.61 52

DeepC-MVS	72.44 4	81.00 40	80.83 50	81.50 22	86.70 44	70.03 64	82.06 55	87.00 14	59.89 126	80.91 107	90.53 53	72.19 60	88.56 1	73.67 52	94.52 35	85.92 75
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator+	73.19 2	81.08 39	80.48 51	82.87 7	81.41 125	72.03 45	84.38 34	86.23 22	77.28 14	80.65 110	90.18 74	59.80 169	87.58 4	73.06 55	91.34 94	89.01 34

v7n		79.37 56	80.41 52	76.28 88	78.67 160	55.81 170	79.22 84	82.51 88	70.72 43	87.54 21	92.44 14	68.00 97	81.34 114	72.84 56	91.72 84	91.69 10

9.14			80.22 53		80.68 131		80.35 71	87.69 10	59.90 125	83.00 79	88.20 114	74.57 47	81.75 110	73.75 51	93.78 57

ACMH	63.62 14	77.50 72	80.11 54	69.68 183	79.61 140	56.28 166	78.81 87	83.62 72	63.41 102	87.14 29	90.23 72	76.11 32	73.32 231	67.58 89	94.44 39	79.44 217
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-OURS-SEG-HR		79.62 52	79.99 55	78.49 63	86.46 46	74.79 29	77.15 109	85.39 34	66.73 63	80.39 113	88.85 101	74.43 50	78.33 175	74.73 44	85.79 195	82.35 166

XVG-OURS		79.51 53	79.82 56	78.58 62	86.11 56	74.96 28	76.33 121	84.95 43	66.89 60	82.75 85	88.99 98	66.82 105	78.37 173	74.80 42	90.76 117	82.40 165

HPM-MVS++		79.89 51	79.80 57	80.18 39	89.02 25	78.44 10	83.49 45	80.18 133	64.71 87	78.11 135	88.39 110	65.46 120	83.14 87	77.64 29	91.20 97	78.94 222

MSP-MVS		80.49 45	79.67 58	82.96 5	89.70 11	77.46 19	87.16 11	85.10 39	64.94 85	81.05 104	88.38 111	57.10 196	87.10 7	79.75 7	83.87 221	84.31 118
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
test_0402		78.17 69	79.48 59	74.24 108	83.50 91	59.15 151	72.52 155	74.60 201	75.34 15	88.69 13	91.81 22	75.06 42	82.37 99	65.10 106	88.68 155	81.20 180

DP-MVS		78.44 66	79.29 60	75.90 92	81.86 120	65.33 97	79.05 85	84.63 54	74.83 18	80.41 112	86.27 152	71.68 64	83.45 83	62.45 132	92.40 77	78.92 223

UniMVSNet_ETH3D		76.74 78	79.02 61	69.92 182	89.27 19	43.81 268	74.47 145	71.70 222	72.33 35	85.50 50	93.65 3	77.98 21	76.88 197	54.60 198	91.64 86	89.08 32

TSAR-MVS + MP.		79.05 57	78.81 62	79.74 42	88.94 27	67.52 83	86.61 19	81.38 104	51.71 218	77.15 146	91.42 32	65.49 119	87.20 5	79.44 13	87.17 181	84.51 113
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OMC-MVS		79.41 55	78.79 63	81.28 29	80.62 132	70.71 58	80.91 62	84.76 46	62.54 108	81.77 94	86.65 141	71.46 66	83.53 81	67.95 87	92.44 76	89.60 24

HQP_MVS		78.77 60	78.78 64	78.72 59	85.18 66	65.18 99	82.74 51	85.49 29	65.45 73	78.23 132	89.11 94	60.83 159	86.15 26	71.09 66	90.94 106	84.82 96

mvs_tets		78.93 58	78.67 65	79.72 43	84.81 74	73.93 35	80.65 64	76.50 185	51.98 215	87.40 23	91.86 21	76.09 33	78.53 165	68.58 78	90.20 123	86.69 66

CNVR-MVS		78.49 64	78.59 66	78.16 67	85.86 60	67.40 84	78.12 98	81.50 100	63.92 92	77.51 143	86.56 145	68.43 92	84.82 63	73.83 50	91.61 88	82.26 169

OurMVSNet-221017-0		78.57 62	78.53 67	78.67 60	80.48 133	64.16 108	80.24 73	82.06 92	61.89 112	88.77 12	93.32 4	57.15 194	82.60 96	70.08 72	92.80 71	89.25 28

tt0805		76.12 82	78.43 68	69.20 189	81.32 126	41.37 288	76.72 113	77.64 173	63.78 95	82.06 90	87.88 120	79.78 11	79.05 156	64.33 113	92.40 77	87.17 60

test_djsdf		78.88 59	78.27 69	80.70 35	81.42 124	71.24 52	83.98 36	75.72 192	52.27 210	87.37 26	92.25 16	68.04 96	80.56 132	72.28 62	91.15 99	90.32 22

jajsoiax		78.51 63	78.16 70	79.59 47	84.65 77	73.83 37	80.42 68	76.12 187	51.33 224	87.19 27	91.51 29	73.79 54	78.44 169	68.27 81	90.13 127	86.49 68

NCCC		78.25 67	78.04 71	78.89 58	85.61 62	69.45 66	79.80 79	80.99 115	65.77 69	75.55 174	86.25 154	67.42 99	85.42 48	70.10 71	90.88 112	81.81 175

anonymousdsp		78.60 61	77.80 72	81.00 31	78.01 167	74.34 33	80.09 75	76.12 187	50.51 234	89.19 10	90.88 42	71.45 67	77.78 187	73.38 53	90.60 119	90.90 18

RRT_MVS		78.18 68	77.69 73	79.66 46	83.14 96	61.34 128	83.29 48	80.34 131	57.43 151	86.65 31	91.79 23	50.52 228	86.01 29	71.36 65	94.65 32	91.62 11

TranMVSNet+NR-MVSNet		76.13 81	77.66 74	71.56 159	84.61 78	42.57 282	70.98 182	78.29 164	68.67 55	83.04 78	89.26 88	72.99 58	80.75 131	55.58 191	95.47 10	91.35 13

AllTest		77.66 70	77.43 75	78.35 65	79.19 149	70.81 55	78.60 90	88.64 3	65.37 76	80.09 115	88.17 115	70.33 75	78.43 170	55.60 188	90.90 110	85.81 76

DROMVSNet		77.08 76	77.39 76	76.14 90	76.86 185	56.87 164	80.32 72	87.52 11	63.45 100	74.66 187	84.52 178	69.87 81	84.94 59	69.76 74	89.59 138	86.60 67

PS-MVSNAJss		77.54 71	77.35 77	78.13 69	84.88 72	66.37 92	78.55 91	79.59 142	53.48 202	86.29 36	92.43 15	62.39 141	80.25 139	67.90 88	90.61 118	87.77 49

Anonymous20231211		75.54 88	77.19 78	70.59 168	77.67 173	45.70 257	74.73 141	80.19 132	68.80 52	82.95 81	92.91 8	66.26 112	76.76 199	58.41 168	92.77 72	89.30 27

DeepPCF-MVS	71.07 5	78.48 65	77.14 79	82.52 16	84.39 83	77.04 21	76.35 119	84.05 67	56.66 159	80.27 114	85.31 171	68.56 89	87.03 9	67.39 93	91.26 95	83.50 133

CDPH-MVS		77.33 73	77.06 80	78.14 68	84.21 84	63.98 109	76.07 125	83.45 74	54.20 189	77.68 142	87.18 122	69.98 79	85.37 49	68.01 85	92.72 74	85.08 89

testf1		75.66 86	76.57 81	72.95 133	67.07 292	67.62 81	76.10 123	80.68 120	64.95 83	86.58 33	90.94 40	71.20 70	71.68 254	60.46 148	91.13 101	79.56 213

APD_test2		75.66 86	76.57 81	72.95 133	67.07 292	67.62 81	76.10 123	80.68 120	64.95 83	86.58 33	90.94 40	71.20 70	71.68 254	60.46 148	91.13 101	79.56 213

train_agg		76.38 80	76.55 83	75.86 93	85.47 63	69.32 70	76.42 117	78.69 156	54.00 194	76.97 148	86.74 135	66.60 109	81.10 120	72.50 61	91.56 90	77.15 242

mvsmamba		77.20 74	76.37 84	79.69 45	80.34 135	61.52 126	80.58 65	82.12 91	53.54 201	83.93 70	91.03 37	49.49 234	85.97 31	73.26 54	93.08 67	91.59 12

SixPastTwentyTwo		75.77 83	76.34 85	74.06 111	81.69 122	54.84 175	76.47 114	75.49 194	64.10 91	87.73 17	92.24 17	50.45 230	81.30 116	67.41 91	91.46 92	86.04 73

DeepC-MVS_fast	69.89 7	77.17 75	76.33 86	79.70 44	83.90 88	67.94 78	80.06 77	83.75 70	56.73 158	74.88 182	85.32 170	65.54 118	87.79 2	65.61 104	91.14 100	83.35 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v10		75.69 85	76.20 87	74.16 109	74.44 218	48.69 221	75.84 129	82.93 81	59.02 135	85.92 41	89.17 92	58.56 179	82.74 94	70.73 68	89.14 149	91.05 15

casdiffmvs_mvg		75.26 91	76.18 88	72.52 147	72.87 243	49.47 216	72.94 154	84.71 50	59.49 129	80.90 108	88.81 102	70.07 78	79.71 147	67.40 92	88.39 157	88.40 46
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		76.51 79	76.00 89	78.06 70	77.02 178	64.77 104	80.78 63	82.66 85	60.39 122	74.15 193	83.30 198	69.65 83	82.07 105	69.27 76	86.75 186	87.36 55

nrg030		74.87 102	75.99 90	71.52 160	74.90 207	49.88 215	74.10 149	82.58 87	54.55 183	83.50 75	89.21 90	71.51 65	75.74 207	61.24 139	92.34 79	88.94 37

MSLP-MVS++		74.48 104	75.78 91	70.59 168	84.66 76	62.40 118	78.65 89	84.24 62	60.55 121	77.71 141	81.98 212	63.12 134	77.64 189	62.95 129	88.14 160	71.73 286

UniMVSNet_NR-MVSNet		74.90 100	75.65 92	72.64 145	83.04 102	45.79 254	69.26 201	78.81 153	66.66 64	81.74 96	86.88 130	63.26 133	81.07 122	56.21 183	94.98 20	91.05 15

v8		75.07 95	75.64 93	73.35 122	73.42 231	47.46 240	75.20 132	81.45 102	60.05 124	85.64 45	89.26 88	58.08 186	81.80 109	69.71 75	87.97 165	90.79 19

DU-MVS		74.91 99	75.57 94	72.93 136	83.50 91	45.79 254	69.47 198	80.14 134	65.22 79	81.74 96	87.08 124	61.82 147	81.07 122	56.21 183	94.98 20	91.93 8

UniMVSNet (Re)		75.00 97	75.48 95	73.56 120	83.14 96	47.92 233	70.41 190	81.04 114	63.67 96	79.54 119	86.37 150	62.83 135	81.82 108	57.10 175	95.25 14	90.94 17

IS-MVSNet		75.10 94	75.42 96	74.15 110	79.23 147	48.05 231	79.43 80	78.04 168	70.09 48	79.17 123	88.02 119	53.04 214	83.60 79	58.05 170	93.76 59	90.79 19

APD_test1		75.04 96	75.38 97	74.02 112	69.89 266	70.15 62	76.46 115	79.71 138	65.50 72	82.99 80	88.60 106	66.94 102	72.35 244	59.77 158	88.54 156	79.56 213

HQP-MVS		75.24 92	75.01 98	75.94 91	82.37 111	58.80 154	77.32 105	84.12 65	59.08 131	71.58 226	85.96 164	58.09 184	85.30 51	67.38 94	89.16 146	83.73 131

X-MVStestdata		76.81 77	74.79 99	82.85 8	89.43 15	77.61 14	86.80 17	84.66 52	72.71 27	82.87 82	9.95 374	73.86 52	86.31 18	78.84 19	94.03 53	84.64 101

FC-MVSNet-test		73.32 116	74.78 100	68.93 197	79.21 148	36.57 323	71.82 170	79.54 144	57.63 150	82.57 87	90.38 64	59.38 172	78.99 158	57.91 171	94.56 34	91.23 14

Vis-MVSNet		74.85 103	74.56 101	75.72 94	81.63 123	64.64 105	76.35 119	79.06 149	62.85 106	73.33 205	88.41 109	62.54 139	79.59 150	63.94 119	82.92 230	82.94 152
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
AdaColmap		74.22 105	74.56 101	73.20 125	81.95 118	60.97 133	79.43 80	80.90 116	65.57 71	72.54 216	81.76 216	70.98 73	85.26 52	47.88 252	90.00 128	73.37 269

CSCG		74.12 106	74.39 103	73.33 123	79.35 144	61.66 125	77.45 104	81.98 94	62.47 110	79.06 124	80.19 234	61.83 146	78.79 162	59.83 157	87.35 174	79.54 216

RPSCF		75.76 84	74.37 104	79.93 40	74.81 209	77.53 16	77.53 103	79.30 146	59.44 130	78.88 125	89.80 80	71.26 69	73.09 233	57.45 172	80.89 253	89.17 31

PHI-MVS		74.92 98	74.36 105	76.61 82	76.40 188	62.32 120	80.38 69	83.15 77	54.16 191	73.23 207	80.75 225	62.19 144	83.86 74	68.02 84	90.92 109	83.65 132

TAPA-MVS	65.27 12	75.16 93	74.29 106	77.77 71	74.86 208	68.08 77	77.89 99	84.04 68	55.15 172	76.19 170	83.39 192	66.91 103	80.11 143	60.04 155	90.14 126	85.13 87
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CS-MVS-test		74.89 101	74.23 107	76.86 79	77.01 179	62.94 117	78.98 86	84.61 55	58.62 138	70.17 245	80.80 224	66.74 108	81.96 106	61.74 135	89.40 144	85.69 81

PAPM_NR		73.91 107	74.16 108	73.16 126	81.90 119	53.50 185	81.28 60	81.40 103	66.17 67	73.30 206	83.31 197	59.96 165	83.10 89	58.45 167	81.66 248	82.87 154

NR-MVSNet		73.62 110	74.05 109	72.33 153	83.50 91	43.71 269	65.65 254	77.32 177	64.32 89	75.59 173	87.08 124	62.45 140	81.34 114	54.90 194	95.63 8	91.93 8

F-COLMAP		75.29 90	73.99 110	79.18 51	81.73 121	71.90 46	81.86 58	82.98 79	59.86 127	72.27 218	84.00 185	64.56 128	83.07 90	51.48 219	87.19 180	82.56 163

baseline		73.10 119	73.96 111	70.51 170	71.46 252	46.39 252	72.08 160	84.40 58	55.95 165	76.62 160	86.46 148	67.20 100	78.03 182	64.22 114	87.27 178	87.11 61

casdiffmvs		73.06 122	73.84 112	70.72 166	71.32 253	46.71 248	70.93 183	84.26 61	55.62 168	77.46 144	87.10 123	67.09 101	77.81 185	63.95 117	86.83 184	87.64 51
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FIs		72.56 135	73.80 113	68.84 200	78.74 159	37.74 317	71.02 181	79.83 137	56.12 163	80.88 109	89.45 85	58.18 181	78.28 176	56.63 177	93.36 64	90.51 21

Anonymous20240529		72.56 135	73.79 114	68.86 199	76.89 184	45.21 259	68.80 210	77.25 179	67.16 59	76.89 152	90.44 56	65.95 115	74.19 227	50.75 225	90.00 128	87.18 59

GeoE		73.14 118	73.77 115	71.26 163	78.09 165	52.64 190	74.32 146	79.56 143	56.32 162	76.35 168	83.36 196	70.76 74	77.96 183	63.32 126	81.84 242	83.18 146

pmmvs6		71.82 142	73.66 116	66.31 228	75.94 196	42.01 284	66.99 236	72.53 217	63.45 100	76.43 166	92.78 10	72.95 59	69.69 269	51.41 220	90.46 120	87.22 56

K. test v3		73.67 109	73.61 117	73.87 114	79.78 138	55.62 173	74.69 143	62.04 296	66.16 68	84.76 60	93.23 5	49.47 235	80.97 126	65.66 103	86.67 187	85.02 91

v1192		73.40 114	73.42 118	73.32 124	74.65 215	48.67 222	72.21 158	81.73 97	52.76 207	81.85 92	84.56 177	57.12 195	82.24 103	68.58 78	87.33 175	89.06 33

v1144		73.29 117	73.39 119	73.01 130	74.12 223	48.11 229	72.01 162	81.08 113	53.83 198	81.77 94	84.68 175	58.07 187	81.91 107	68.10 82	86.86 183	88.99 36

canonicalmvs		72.29 139	73.38 120	69.04 192	74.23 219	47.37 241	73.93 150	83.18 76	54.36 184	76.61 161	81.64 218	72.03 61	75.34 211	57.12 174	87.28 177	84.40 115

EPP-MVSNet		73.86 108	73.38 120	75.31 99	78.19 163	53.35 187	80.45 67	77.32 177	65.11 81	76.47 165	86.80 131	49.47 235	83.77 75	53.89 206	92.72 74	88.81 41

MCST-MVS		73.42 113	73.34 122	73.63 119	81.28 127	59.17 150	74.80 139	83.13 78	45.50 270	72.84 211	83.78 188	65.15 123	80.99 124	64.54 110	89.09 151	80.73 196

114514_t		73.40 114	73.33 123	73.64 118	84.15 86	57.11 162	78.20 96	80.02 135	43.76 284	72.55 215	86.07 162	64.00 131	83.35 85	60.14 153	91.03 105	80.45 202

Baseline_NR-MVSNet		70.62 154	73.19 124	62.92 260	76.97 180	34.44 339	68.84 206	70.88 240	60.25 123	79.50 120	90.53 53	61.82 147	69.11 273	54.67 197	95.27 13	85.22 84

v1240		73.06 122	73.14 125	72.84 139	74.74 211	47.27 243	71.88 169	81.11 110	51.80 217	82.28 89	84.21 182	56.22 203	82.34 100	68.82 77	87.17 181	88.91 38

VDDNet		71.60 144	73.13 126	67.02 221	86.29 47	41.11 290	69.97 192	66.50 262	68.72 54	74.74 183	91.70 25	59.90 166	75.81 205	48.58 244	91.72 84	84.15 122

IterMVS-LS		73.01 124	73.12 127	72.66 144	73.79 227	49.90 211	71.63 171	78.44 161	58.22 140	80.51 111	86.63 142	58.15 183	79.62 148	62.51 130	88.20 159	88.48 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		72.99 126	73.06 128	72.77 140	74.58 216	47.48 239	71.90 168	80.44 127	51.57 220	81.46 100	84.11 184	58.04 188	82.12 104	67.98 86	87.47 171	88.70 43

CNLPA		73.44 112	73.03 129	74.66 102	78.27 162	75.29 26	75.99 126	78.49 160	65.39 75	75.67 172	83.22 202	61.23 155	66.77 291	53.70 208	85.33 201	81.92 174

v1921920		72.96 128	72.98 130	72.89 138	74.67 212	47.58 238	71.92 167	80.69 119	51.70 219	81.69 98	83.89 186	56.58 201	82.25 102	68.34 80	87.36 173	88.82 40

MVS_111021_HR		72.98 127	72.97 131	72.99 131	80.82 130	65.47 96	68.81 208	72.77 214	57.67 147	75.76 171	82.38 209	71.01 72	77.17 192	61.38 138	86.15 191	76.32 246

Gipuma		69.55 167	72.83 132	59.70 284	63.63 318	53.97 182	80.08 76	75.93 190	64.24 90	73.49 202	88.93 100	57.89 190	62.46 308	59.75 159	91.55 91	62.67 341
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
bld_raw_dy_0_64		72.85 130	72.76 133	73.09 128	85.08 70	64.80 103	78.72 88	64.22 282	51.92 216	83.13 77	90.26 70	39.21 294	69.91 267	70.73 68	91.60 89	84.56 108

DP-MVS Recon		73.57 111	72.69 134	76.23 89	82.85 106	63.39 112	74.32 146	82.96 80	57.75 145	70.35 242	81.98 212	64.34 130	84.41 71	49.69 233	89.95 130	80.89 190

dcpmvs_2		71.02 150	72.65 135	66.16 229	76.06 195	50.49 202	71.97 163	79.36 145	50.34 235	82.81 84	83.63 189	64.38 129	67.27 285	61.54 137	83.71 225	80.71 198

v2v482		72.55 137	72.58 136	72.43 150	72.92 242	46.72 247	71.41 174	79.13 148	55.27 170	81.17 103	85.25 172	55.41 205	81.13 119	67.25 97	85.46 197	89.43 26

WR-MVS		71.20 147	72.48 137	67.36 216	84.98 71	35.70 331	64.43 269	68.66 252	65.05 82	81.49 99	86.43 149	57.57 192	76.48 201	50.36 229	93.32 65	89.90 23

FMVSNet1		71.06 148	72.48 137	66.81 222	77.65 174	40.68 294	71.96 164	73.03 209	61.14 116	79.45 121	90.36 67	60.44 161	75.20 213	50.20 230	88.05 162	84.54 109

CLD-MVS		72.88 129	72.36 139	74.43 105	77.03 177	54.30 179	68.77 211	83.43 75	52.12 212	76.79 157	74.44 291	69.54 84	83.91 73	55.88 186	93.25 66	85.09 88
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Effi-MVS+-dtu		75.43 89	72.28 140	84.91 2	77.05 176	83.58 1	78.47 92	77.70 172	57.68 146	74.89 181	78.13 263	64.80 126	84.26 72	56.46 181	85.32 202	86.88 62

Effi-MVS+		72.10 140	72.28 140	71.58 158	74.21 221	50.33 204	74.72 142	82.73 83	62.62 107	70.77 238	76.83 273	69.96 80	80.97 126	60.20 150	78.43 278	83.45 139

ETV-MVS		72.72 132	72.16 142	74.38 107	76.90 183	55.95 167	73.34 152	84.67 51	62.04 111	72.19 221	70.81 317	65.90 116	85.24 54	58.64 165	84.96 209	81.95 173

EI-MVSNet-Vis-set		72.78 131	71.87 143	75.54 97	74.77 210	59.02 152	72.24 157	71.56 225	63.92 92	78.59 127	71.59 313	66.22 113	78.60 164	67.58 89	80.32 259	89.00 35

CANet		73.00 125	71.84 144	76.48 85	75.82 197	61.28 129	74.81 137	80.37 129	63.17 104	62.43 304	80.50 229	61.10 157	85.16 58	64.00 116	84.34 217	83.01 151

MVS_111021_LR		72.10 140	71.82 145	72.95 133	79.53 142	73.90 36	70.45 189	66.64 261	56.87 155	76.81 156	81.76 216	68.78 87	71.76 252	61.81 133	83.74 223	73.18 271

PCF-MVS	63.80 13	72.70 133	71.69 146	75.72 94	78.10 164	60.01 144	73.04 153	81.50 100	45.34 274	79.66 118	84.35 181	65.15 123	82.65 95	48.70 242	89.38 145	84.50 114
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EI-MVSNet-UG-set		72.63 134	71.68 147	75.47 98	74.67 212	58.64 157	72.02 161	71.50 226	63.53 98	78.58 129	71.39 316	65.98 114	78.53 165	67.30 96	80.18 261	89.23 29

TransMVSNet (Re)		69.62 165	71.63 148	63.57 249	76.51 187	35.93 329	65.75 253	71.29 232	61.05 117	75.02 179	89.90 79	65.88 117	70.41 266	49.79 232	89.48 140	84.38 116

h-mvs33		73.08 120	71.61 149	77.48 73	83.89 89	72.89 44	70.47 188	71.12 237	54.28 185	77.89 136	83.41 191	49.04 238	80.98 125	63.62 122	90.77 116	78.58 226

TSAR-MVS + GP.		73.08 120	71.60 150	77.54 72	78.99 156	70.73 57	74.96 134	69.38 248	60.73 120	74.39 191	78.44 257	57.72 191	82.78 93	60.16 152	89.60 137	79.11 221

LCM-MVSNet-Re		69.10 174	71.57 151	61.70 268	70.37 262	34.30 341	61.45 290	79.62 139	56.81 156	89.59 8	88.16 117	68.44 91	72.94 234	42.30 284	87.33 175	77.85 239

API-MVS		70.97 151	71.51 152	69.37 185	75.20 202	55.94 168	80.99 61	76.84 182	62.48 109	71.24 234	77.51 269	61.51 151	80.96 129	52.04 215	85.76 196	71.22 291

VDD-MVS		70.81 152	71.44 153	68.91 198	79.07 154	46.51 249	67.82 223	70.83 241	61.23 115	74.07 196	88.69 103	59.86 167	75.62 208	51.11 222	90.28 122	84.61 104

MG-MVS		70.47 156	71.34 154	67.85 211	79.26 146	40.42 298	74.67 144	75.15 198	58.41 139	68.74 263	88.14 118	56.08 204	83.69 78	59.90 156	81.71 247	79.43 218

3Dnovator	65.95 11	71.50 145	71.22 155	72.34 152	73.16 235	63.09 115	78.37 93	78.32 162	57.67 147	72.22 220	84.61 176	54.77 206	78.47 167	60.82 146	81.07 252	75.45 252

FA-MVS(test-final)		71.27 146	71.06 156	71.92 156	73.96 224	52.32 193	76.45 116	76.12 187	59.07 134	74.04 197	86.18 155	52.18 218	79.43 152	59.75 159	81.76 243	84.03 123

alignmvs		70.54 155	71.00 157	69.15 191	73.50 229	48.04 232	69.85 195	79.62 139	53.94 197	76.54 163	82.00 211	59.00 175	74.68 220	57.32 173	87.21 179	84.72 99

EG-PatchMatch MVS		70.70 153	70.88 158	70.16 176	82.64 110	58.80 154	71.48 172	73.64 205	54.98 173	76.55 162	81.77 215	61.10 157	78.94 159	54.87 195	80.84 254	72.74 276

V42		71.06 148	70.83 159	71.72 157	67.25 289	47.14 244	65.94 248	80.35 130	51.35 223	83.40 76	83.23 200	59.25 173	78.80 161	65.91 102	80.81 255	89.23 29

MVS_Test		69.84 163	70.71 160	67.24 217	67.49 288	43.25 276	69.87 194	81.22 109	52.69 208	71.57 229	86.68 138	62.09 145	74.51 222	66.05 100	78.74 274	83.96 124

hse-mvs2		72.32 138	70.66 161	77.31 77	83.10 101	71.77 47	69.19 203	71.45 228	54.28 185	77.89 136	78.26 259	49.04 238	79.23 153	63.62 122	89.13 150	80.92 189

VPA-MVSNet		68.71 179	70.37 162	63.72 247	76.13 192	38.06 315	64.10 271	71.48 227	56.60 161	74.10 195	88.31 112	64.78 127	69.72 268	47.69 254	90.15 125	83.37 141

PLC	62.01 16	71.79 143	70.28 163	76.33 87	80.31 136	68.63 75	78.18 97	81.24 107	54.57 182	67.09 275	80.63 227	59.44 170	81.74 111	46.91 259	84.17 218	78.63 224
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ANet_high		67.08 202	69.94 164	58.51 293	57.55 347	27.09 366	58.43 310	76.80 183	63.56 97	82.40 88	91.93 20	59.82 168	64.98 299	50.10 231	88.86 154	83.46 138

c3_l		69.82 164	69.89 165	69.61 184	66.24 298	43.48 272	68.12 220	79.61 141	51.43 222	77.72 140	80.18 235	54.61 209	78.15 181	63.62 122	87.50 170	87.20 58

pm-mvs1		68.40 183	69.85 166	64.04 245	73.10 239	39.94 300	64.61 267	70.50 242	55.52 169	73.97 198	89.33 86	63.91 132	68.38 277	49.68 234	88.02 163	83.81 127

BH-untuned		69.39 170	69.46 167	69.18 190	77.96 168	56.88 163	68.47 217	77.53 174	56.77 157	77.79 139	79.63 241	60.30 163	80.20 142	46.04 265	80.65 256	70.47 297

v148		69.38 171	69.39 168	69.36 186	69.14 275	44.56 263	68.83 207	72.70 215	54.79 177	78.59 127	84.12 183	54.69 207	76.74 200	59.40 162	82.20 236	86.79 63

TinyColmap		67.98 190	69.28 169	64.08 243	67.98 283	46.82 246	70.04 191	75.26 196	53.05 204	77.36 145	86.79 132	59.39 171	72.59 241	45.64 268	88.01 164	72.83 274

QAPM		69.18 173	69.26 170	68.94 196	71.61 251	52.58 191	80.37 70	78.79 155	49.63 243	73.51 201	85.14 173	53.66 212	79.12 155	55.11 193	75.54 294	75.11 257

MIMVSNet1		66.57 205	69.23 171	58.59 292	81.26 128	37.73 318	64.06 272	57.62 308	57.02 154	78.40 131	90.75 46	62.65 136	58.10 321	41.77 289	89.58 139	79.95 208

DPM-MVS		69.98 161	69.22 172	72.26 154	82.69 109	58.82 153	70.53 187	81.23 108	47.79 259	64.16 291	80.21 232	51.32 225	83.12 88	60.14 153	84.95 210	74.83 259

UGNet		70.20 158	69.05 173	73.65 117	76.24 190	63.64 110	75.87 128	72.53 217	61.48 114	60.93 314	86.14 158	52.37 217	77.12 193	50.67 226	85.21 203	80.17 207
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
MVSFormer		69.93 162	69.03 174	72.63 146	74.93 205	59.19 148	83.98 36	75.72 192	52.27 210	63.53 300	76.74 274	43.19 269	80.56 132	72.28 62	78.67 276	78.14 233

EI-MVSNet		69.61 166	69.01 175	71.41 162	73.94 225	49.90 211	71.31 177	71.32 230	58.22 140	75.40 177	70.44 319	58.16 182	75.85 203	62.51 130	79.81 265	88.48 44

PVSNet_Blended_VisFu		70.04 159	68.88 176	73.53 121	82.71 108	63.62 111	74.81 137	81.95 95	48.53 252	67.16 274	79.18 249	51.42 224	78.38 172	54.39 201	79.72 268	78.60 225

GBi-Net		68.30 185	68.79 177	66.81 222	73.14 236	40.68 294	71.96 164	73.03 209	54.81 174	74.72 184	90.36 67	48.63 244	75.20 213	47.12 256	85.37 198	84.54 109

test1		68.30 185	68.79 177	66.81 222	73.14 236	40.68 294	71.96 164	73.03 209	54.81 174	74.72 184	90.36 67	48.63 244	75.20 213	47.12 256	85.37 198	84.54 109

OpenMVS	62.51 15	68.76 178	68.75 179	68.78 201	70.56 260	53.91 183	78.29 94	77.35 176	48.85 250	70.22 244	83.52 190	52.65 216	76.93 195	55.31 192	81.99 238	75.49 251

Fast-Effi-MVS+-dtu		70.00 160	68.74 180	73.77 115	73.47 230	64.53 106	71.36 175	78.14 167	55.81 167	68.84 262	74.71 288	65.36 121	75.75 206	52.00 216	79.00 272	81.03 185

eth_miper_zixun_eth		69.42 169	68.73 181	71.50 161	67.99 282	46.42 250	67.58 225	78.81 153	50.72 231	78.13 134	80.34 231	50.15 232	80.34 137	60.18 151	84.65 211	87.74 50

PAPR		69.20 172	68.66 182	70.82 165	75.15 204	47.77 235	75.31 131	81.11 110	49.62 244	66.33 277	79.27 246	61.53 150	82.96 91	48.12 250	81.50 250	81.74 176

DELS-MVS		68.83 176	68.31 183	70.38 171	70.55 261	48.31 225	63.78 276	82.13 90	54.00 194	68.96 258	75.17 284	58.95 176	80.06 144	58.55 166	82.74 232	82.76 157
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
Fast-Effi-MVS+		68.81 177	68.30 184	70.35 172	74.66 214	48.61 223	66.06 247	78.32 162	50.62 232	71.48 232	75.54 280	68.75 88	79.59 150	50.55 228	78.73 275	82.86 155

cl____		68.26 189	68.26 185	68.29 206	64.98 310	43.67 270	65.89 249	74.67 199	50.04 240	76.86 154	82.42 208	48.74 242	75.38 209	60.92 145	89.81 133	85.80 80

DIV-MVS_self_test		68.27 188	68.26 185	68.29 206	64.98 310	43.67 270	65.89 249	74.67 199	50.04 240	76.86 154	82.43 207	48.74 242	75.38 209	60.94 144	89.81 133	85.81 76

FMVSNet2		67.48 197	68.21 187	65.29 234	73.14 236	38.94 307	68.81 208	71.21 236	54.81 174	76.73 158	86.48 147	48.63 244	74.60 221	47.98 251	86.11 193	82.35 166

BH-RMVSNet		68.69 180	68.20 188	70.14 177	76.40 188	53.90 184	64.62 266	73.48 207	58.01 142	73.91 199	81.78 214	59.09 174	78.22 177	48.59 243	77.96 283	78.31 229

miper_ehance_all_eth		68.36 184	68.16 189	68.98 194	65.14 309	43.34 274	67.07 235	78.92 152	49.11 248	76.21 169	77.72 266	53.48 213	77.92 184	61.16 141	84.59 213	85.68 82

tfpnnormal		66.48 206	67.93 190	62.16 266	73.40 232	36.65 322	63.45 278	64.99 273	55.97 164	72.82 212	87.80 121	57.06 197	69.10 274	48.31 248	87.54 168	80.72 197

LFMVS		67.06 203	67.89 191	64.56 239	78.02 166	38.25 312	70.81 186	59.60 303	65.18 80	71.06 236	86.56 145	43.85 265	75.22 212	46.35 263	89.63 136	80.21 206

AUN-MVS		70.22 157	67.88 192	77.22 78	82.96 105	71.61 48	69.08 204	71.39 229	49.17 247	71.70 224	78.07 264	37.62 304	79.21 154	61.81 133	89.15 148	80.82 192

tttt0517		69.46 168	67.79 193	74.46 103	75.34 200	52.72 189	75.05 133	63.27 288	54.69 179	78.87 126	84.37 180	26.63 356	81.15 118	63.95 117	87.93 166	89.51 25

VPNet		65.58 211	67.56 194	59.65 285	79.72 139	30.17 358	60.27 300	62.14 292	54.19 190	71.24 234	86.63 142	58.80 177	67.62 282	44.17 276	90.87 113	81.18 181

KD-MVS_self_test		66.38 207	67.51 195	62.97 258	61.76 325	34.39 340	58.11 312	75.30 195	50.84 230	77.12 147	85.42 169	56.84 199	69.44 270	51.07 223	91.16 98	85.08 89

diffmvs		67.42 199	67.50 196	67.20 218	62.26 323	45.21 259	64.87 263	77.04 180	48.21 253	71.74 223	79.70 240	58.40 180	71.17 258	64.99 107	80.27 260	85.22 84
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MSDG		67.47 198	67.48 197	67.46 215	70.70 257	54.69 177	66.90 239	78.17 165	60.88 119	70.41 241	74.76 286	61.22 156	73.18 232	47.38 255	76.87 286	74.49 261

EPNet		69.10 174	67.32 198	74.46 103	68.33 279	61.27 130	77.56 101	63.57 286	60.95 118	56.62 332	82.75 205	51.53 223	81.24 117	54.36 202	90.20 123	80.88 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LF4IMVS		67.50 196	67.31 199	68.08 209	58.86 342	61.93 121	71.43 173	75.90 191	44.67 280	72.42 217	80.20 233	57.16 193	70.44 264	58.99 164	86.12 192	71.88 284

EIA-MVS		68.59 182	67.16 200	72.90 137	75.18 203	55.64 172	69.39 199	81.29 105	52.44 209	64.53 287	70.69 318	60.33 162	82.30 101	54.27 203	76.31 289	80.75 195

xiu_mvs_v1_base_debu		67.87 191	67.07 201	70.26 173	79.13 151	61.90 122	67.34 229	71.25 233	47.98 255	67.70 267	74.19 296	61.31 152	72.62 238	56.51 178	78.26 280	76.27 247

xiu_mvs_v1_base		67.87 191	67.07 201	70.26 173	79.13 151	61.90 122	67.34 229	71.25 233	47.98 255	67.70 267	74.19 296	61.31 152	72.62 238	56.51 178	78.26 280	76.27 247

xiu_mvs_v1_base_debi		67.87 191	67.07 201	70.26 173	79.13 151	61.90 122	67.34 229	71.25 233	47.98 255	67.70 267	74.19 296	61.31 152	72.62 238	56.51 178	78.26 280	76.27 247

iter_conf_final		68.69 180	67.00 204	73.76 116	73.68 228	52.33 192	75.96 127	73.54 206	50.56 233	69.90 248	82.85 203	24.76 365	83.73 76	65.40 105	86.33 190	85.22 84

FE-MVS		68.29 187	66.96 205	72.26 154	74.16 222	54.24 180	77.55 102	73.42 208	57.65 149	72.66 213	84.91 174	32.02 329	81.49 113	48.43 246	81.85 241	81.04 184

Anonymous202405211		66.02 208	66.89 206	63.43 252	74.22 220	38.14 313	59.00 306	66.13 264	63.33 103	69.76 251	85.95 165	51.88 219	70.50 263	44.23 275	87.52 169	81.64 177

cl22		67.14 201	66.51 207	69.03 193	63.20 319	43.46 273	66.88 240	76.25 186	49.22 246	74.48 189	77.88 265	45.49 255	77.40 191	60.64 147	84.59 213	86.24 69

wuyk23d		61.97 249	66.25 208	49.12 328	58.19 346	60.77 139	66.32 245	52.97 334	55.93 166	90.62 5	86.91 129	73.07 57	35.98 369	20.63 372	91.63 87	50.62 359

MAR-MVS		67.72 194	66.16 209	72.40 151	74.45 217	64.99 102	74.87 135	77.50 175	48.67 251	65.78 281	68.58 338	57.01 198	77.79 186	46.68 262	81.92 239	74.42 262
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
Anonymous20240521		63.55 233	66.07 210	55.99 301	66.18 300	44.04 267	68.77 211	68.80 250	46.99 264	72.57 214	85.84 166	39.87 290	50.22 331	53.40 213	92.23 81	73.71 268

IterMVS-SCA-FT		67.68 195	66.07 210	72.49 149	73.34 233	58.20 159	63.80 275	65.55 270	48.10 254	76.91 151	82.64 206	45.20 256	78.84 160	61.20 140	77.89 284	80.44 203

iter_conf05		67.34 200	65.62 212	72.50 148	69.82 267	47.06 245	72.19 159	76.86 181	45.32 275	72.86 210	82.85 203	20.53 372	83.73 76	61.13 142	89.02 152	86.70 65

mvs_anonymous		65.08 216	65.49 213	63.83 246	63.79 316	37.60 319	66.52 244	69.82 246	43.44 288	73.46 203	86.08 161	58.79 178	71.75 253	51.90 217	75.63 293	82.15 170

ECVR-MVS		64.82 218	65.22 214	63.60 248	78.80 157	31.14 355	66.97 237	56.47 318	54.23 187	69.94 247	88.68 104	37.23 305	74.81 219	45.28 272	89.41 142	84.86 94

test1111		64.62 221	65.19 215	62.93 259	79.01 155	29.91 359	65.45 257	54.41 326	54.09 192	71.47 233	88.48 108	37.02 306	74.29 226	46.83 261	89.94 131	84.58 107

thisisatest0530		67.05 204	65.16 216	72.73 143	73.10 239	50.55 201	71.26 179	63.91 284	50.22 237	74.46 190	80.75 225	26.81 355	80.25 139	59.43 161	86.50 188	87.37 54

FMVSNet3		65.00 217	65.16 216	64.52 240	69.47 271	37.56 320	66.63 242	70.38 243	51.55 221	74.72 184	83.27 199	37.89 303	74.44 223	47.12 256	85.37 198	81.57 178

VNet		64.01 232	65.15 218	60.57 279	73.28 234	35.61 332	57.60 314	67.08 259	54.61 181	66.76 276	83.37 194	56.28 202	66.87 287	42.19 285	85.20 204	79.23 220

ab-mvs		64.11 230	65.13 219	61.05 275	71.99 249	38.03 316	67.59 224	68.79 251	49.08 249	65.32 283	86.26 153	58.02 189	66.85 289	39.33 301	79.79 267	78.27 230

test_yl		65.11 214	65.09 220	65.18 235	70.59 258	40.86 292	63.22 283	72.79 212	57.91 143	68.88 260	79.07 252	42.85 272	74.89 217	45.50 269	84.97 206	79.81 209

DCV-MVSNet		65.11 214	65.09 220	65.18 235	70.59 258	40.86 292	63.22 283	72.79 212	57.91 143	68.88 260	79.07 252	42.85 272	74.89 217	45.50 269	84.97 206	79.81 209

RPMNet		65.77 210	65.08 222	67.84 212	66.37 295	48.24 227	70.93 183	86.27 19	54.66 180	61.35 308	86.77 134	33.29 317	85.67 45	55.93 185	70.17 327	69.62 305

miper_enhance_ethall		65.86 209	65.05 223	68.28 208	61.62 327	42.62 281	64.74 264	77.97 169	42.52 293	73.42 204	72.79 306	49.66 233	77.68 188	58.12 169	84.59 213	84.54 109

PVSNet_BlendedMVS		65.38 212	64.30 224	68.61 202	69.81 268	49.36 217	65.60 256	78.96 150	45.50 270	59.98 317	78.61 255	51.82 220	78.20 178	44.30 273	84.11 219	78.27 230

BH-w/o		64.81 219	64.29 225	66.36 227	76.08 194	54.71 176	65.61 255	75.23 197	50.10 239	71.05 237	71.86 312	54.33 210	79.02 157	38.20 312	76.14 290	65.36 328

patch_mono-2		62.73 244	64.08 226	58.68 291	70.36 263	55.87 169	60.84 296	64.11 283	41.23 300	64.04 292	78.22 260	60.00 164	48.80 334	54.17 204	83.71 225	71.37 288

xiu_mvs_v2_base		64.43 226	63.96 227	65.85 233	77.72 172	51.32 197	63.63 277	72.31 220	45.06 279	61.70 305	69.66 327	62.56 137	73.93 230	49.06 239	73.91 306	72.31 280

CANet_DTU		64.04 231	63.83 228	64.66 238	68.39 276	42.97 278	73.45 151	74.50 202	52.05 214	54.78 339	75.44 283	43.99 264	70.42 265	53.49 210	78.41 279	80.59 200

TAMVS		65.31 213	63.75 229	69.97 181	82.23 115	59.76 146	66.78 241	63.37 287	45.20 276	69.79 250	79.37 245	47.42 250	72.17 245	34.48 335	85.15 205	77.99 237

PS-MVSNAJ		64.27 229	63.73 230	65.90 232	77.82 170	51.42 196	63.33 280	72.33 219	45.09 278	61.60 306	68.04 339	62.39 141	73.95 229	49.07 238	73.87 307	72.34 279

PM-MVS		64.49 224	63.61 231	67.14 220	76.68 186	75.15 27	68.49 216	42.85 358	51.17 227	77.85 138	80.51 228	45.76 251	66.31 294	52.83 214	76.35 288	59.96 350

TR-MVS		64.59 222	63.54 232	67.73 214	75.75 199	50.83 200	63.39 279	70.29 244	49.33 245	71.55 230	74.55 289	50.94 226	78.46 168	40.43 297	75.69 292	73.89 266

CL-MVSNet_self_test		62.44 247	63.40 233	59.55 286	72.34 246	32.38 348	56.39 318	64.84 275	51.21 226	67.46 271	81.01 223	50.75 227	63.51 306	38.47 310	88.12 161	82.75 158

OpenMVS_ROB	54.93 17	63.23 237	63.28 234	63.07 256	69.81 268	45.34 258	68.52 215	67.14 258	43.74 285	70.61 240	79.22 247	47.90 248	72.66 237	48.75 241	73.84 308	71.21 292

pmmvs-eth3d		64.41 227	63.27 235	67.82 213	75.81 198	60.18 143	69.49 197	62.05 295	38.81 314	74.13 194	82.23 210	43.76 266	68.65 275	42.53 283	80.63 258	74.63 260

Vis-MVSNet (Re-imp)		62.74 243	63.21 236	61.34 273	72.19 247	31.56 352	67.31 233	53.87 327	53.60 200	69.88 249	83.37 194	40.52 286	70.98 259	41.40 291	86.78 185	81.48 179

USDC		62.80 242	63.10 237	61.89 267	65.19 306	43.30 275	67.42 228	74.20 203	35.80 327	72.25 219	84.48 179	45.67 253	71.95 250	37.95 314	84.97 206	70.42 299

Patchmtry		60.91 257	63.01 238	54.62 306	66.10 301	26.27 369	67.47 227	56.40 319	54.05 193	72.04 222	86.66 139	33.19 318	60.17 315	43.69 277	87.45 172	77.42 240

jason		64.47 225	62.84 239	69.34 188	76.91 182	59.20 147	67.15 234	65.67 267	35.29 328	65.16 284	76.74 274	44.67 260	70.68 260	54.74 196	79.28 271	78.14 233
jason: jason.
cascas		64.59 222	62.77 240	70.05 179	75.27 201	50.02 208	61.79 289	71.61 223	42.46 294	63.68 297	68.89 334	49.33 237	80.35 136	47.82 253	84.05 220	79.78 211

CDS-MVSNet		64.33 228	62.66 241	69.35 187	80.44 134	58.28 158	65.26 259	65.66 268	44.36 281	67.30 273	75.54 280	43.27 268	71.77 251	37.68 315	84.44 216	78.01 236
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS		63.12 238	62.48 242	65.02 237	66.34 297	52.86 188	63.81 274	62.25 291	46.57 267	71.51 231	80.40 230	44.60 261	66.82 290	51.38 221	75.47 295	75.38 254
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_0304		62.51 246	62.27 243	63.25 253	69.39 272	48.47 224	64.05 273	62.48 290	59.69 128	54.10 344	81.04 222	45.71 252	66.31 294	41.38 292	82.58 234	74.96 258

MDA-MVSNet-bldmvs		62.34 248	61.73 244	64.16 241	61.64 326	49.90 211	48.11 343	57.24 314	53.31 203	80.95 105	79.39 244	49.00 240	61.55 312	45.92 266	80.05 262	81.03 185

GA-MVS		62.91 240	61.66 245	66.66 226	67.09 291	44.49 264	61.18 294	69.36 249	51.33 224	69.33 254	74.47 290	36.83 307	74.94 216	50.60 227	74.72 301	80.57 201

PVSNet_Blended		62.90 241	61.64 246	66.69 225	69.81 268	49.36 217	61.23 293	78.96 150	42.04 295	59.98 317	68.86 335	51.82 220	78.20 178	44.30 273	77.77 285	72.52 277

miper_lstm_enhance		61.97 249	61.63 247	62.98 257	60.04 334	45.74 256	47.53 345	70.95 238	44.04 282	73.06 208	78.84 254	39.72 291	60.33 314	55.82 187	84.64 212	82.88 153

MVSTER		63.29 236	61.60 248	68.36 204	59.77 338	46.21 253	60.62 297	71.32 230	41.83 296	75.40 177	79.12 250	30.25 344	75.85 203	56.30 182	79.81 265	83.03 150

lupinMVS		63.36 234	61.49 249	68.97 195	74.93 205	59.19 148	65.80 252	64.52 279	34.68 333	63.53 300	74.25 294	43.19 269	70.62 261	53.88 207	78.67 276	77.10 243

thres600view7		61.82 251	61.38 250	63.12 255	71.81 250	34.93 336	64.64 265	56.99 315	54.78 178	70.33 243	79.74 239	32.07 327	72.42 243	38.61 308	83.46 227	82.02 171

EGC-MVSNET		64.77 220	61.17 251	75.60 96	86.90 42	74.47 30	84.04 35	68.62 253	0.60 376	1.13 378	91.61 28	65.32 122	74.15 228	64.01 115	88.28 158	78.17 232

thres100view900		61.17 256	61.09 252	61.39 272	72.14 248	35.01 335	65.42 258	56.99 315	55.23 171	70.71 239	79.90 237	32.07 327	72.09 246	35.61 330	81.73 244	77.08 244

D2MVS		62.58 245	61.05 253	67.20 218	63.85 315	47.92 233	56.29 319	69.58 247	39.32 309	70.07 246	78.19 261	34.93 312	72.68 236	53.44 211	83.74 223	81.00 187

CMPMVS	48.73 20	61.54 254	60.89 254	63.52 250	61.08 329	51.55 195	68.07 221	68.00 256	33.88 335	65.87 279	81.25 220	37.91 302	67.71 280	49.32 237	82.60 233	71.31 290
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		61.23 255	60.85 255	62.38 264	78.80 157	27.88 365	67.33 232	37.42 371	54.23 187	67.55 270	88.68 104	17.87 377	74.39 224	46.33 264	89.41 142	84.86 94

EU-MVSNet		60.82 258	60.80 256	60.86 278	68.37 277	41.16 289	72.27 156	68.27 255	26.96 358	69.08 255	75.71 278	32.09 326	67.44 283	55.59 190	78.90 273	73.97 264

ET-MVSNet_ETH3D		63.32 235	60.69 257	71.20 164	70.15 265	55.66 171	65.02 262	64.32 280	43.28 292	68.99 257	72.05 311	25.46 362	78.19 180	54.16 205	82.80 231	79.74 212

HyFIR lowres test		63.01 239	60.47 258	70.61 167	83.04 102	54.10 181	59.93 302	72.24 221	33.67 338	69.00 256	75.63 279	38.69 297	76.93 195	36.60 323	75.45 296	80.81 194

PAPM		61.79 252	60.37 259	66.05 230	76.09 193	41.87 285	69.30 200	76.79 184	40.64 306	53.80 345	79.62 242	44.38 262	82.92 92	29.64 353	73.11 311	73.36 270

FPMVS		59.43 269	60.07 260	57.51 296	77.62 175	71.52 49	62.33 287	50.92 339	57.40 152	69.40 253	80.00 236	39.14 295	61.92 311	37.47 318	66.36 342	39.09 370

tfpn200view9		60.35 263	59.97 261	61.51 270	70.78 255	35.35 333	63.27 281	57.47 309	53.00 205	68.31 264	77.09 271	32.45 324	72.09 246	35.61 330	81.73 244	77.08 244

MVS		60.62 261	59.97 261	62.58 262	68.13 281	47.28 242	68.59 213	73.96 204	32.19 342	59.94 319	68.86 335	50.48 229	77.64 189	41.85 288	75.74 291	62.83 339

thres400		60.77 260	59.97 261	63.15 254	70.78 255	35.35 333	63.27 281	57.47 309	53.00 205	68.31 264	77.09 271	32.45 324	72.09 246	35.61 330	81.73 244	82.02 171

ppachtmachnet_test		60.26 264	59.61 264	62.20 265	67.70 286	44.33 265	58.18 311	60.96 299	40.75 305	65.80 280	72.57 307	41.23 279	63.92 303	46.87 260	82.42 235	78.33 228

MVP-Stereo		61.56 253	59.22 265	68.58 203	79.28 145	60.44 141	69.20 202	71.57 224	43.58 287	56.42 333	78.37 258	39.57 293	76.46 202	34.86 334	60.16 356	68.86 312
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Patchmatch-RL test		59.95 265	59.12 266	62.44 263	72.46 245	54.61 178	59.63 303	47.51 351	41.05 303	74.58 188	74.30 293	31.06 338	65.31 296	51.61 218	79.85 264	67.39 315

pmmvs4		60.78 259	59.04 267	66.00 231	73.06 241	57.67 161	64.53 268	60.22 301	36.91 322	65.96 278	77.27 270	39.66 292	68.54 276	38.87 305	74.89 300	71.80 285

1112_ss		59.48 268	58.99 268	60.96 277	77.84 169	42.39 283	61.42 291	68.45 254	37.96 317	59.93 320	67.46 341	45.11 258	65.07 298	40.89 295	71.81 317	75.41 253

1314		59.83 266	58.86 269	62.74 261	65.71 303	44.78 262	68.59 213	72.63 216	33.54 340	61.05 312	67.29 344	43.62 267	71.26 257	49.49 236	67.84 339	72.19 282

Test_1112_low_res		58.78 273	58.69 270	59.04 290	79.41 143	38.13 314	57.62 313	66.98 260	34.74 331	59.62 323	77.56 268	42.92 271	63.65 305	38.66 307	70.73 323	75.35 255

EPNet_dtu		58.93 272	58.52 271	60.16 283	67.91 284	47.70 237	69.97 192	58.02 307	49.73 242	47.28 360	73.02 305	38.14 299	62.34 309	36.57 324	85.99 194	70.43 298
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		58.96 271	58.49 272	60.36 281	66.37 295	48.24 227	70.93 183	56.40 319	32.87 341	61.35 308	86.66 139	33.19 318	63.22 307	48.50 245	70.17 327	69.62 305

CVMVSNet		59.21 270	58.44 273	61.51 270	73.94 225	47.76 236	71.31 177	64.56 278	26.91 359	60.34 316	70.44 319	36.24 309	67.65 281	53.57 209	68.66 335	69.12 310

baseline1		57.82 278	58.36 274	56.19 300	69.17 274	30.76 357	62.94 285	55.21 322	46.04 269	63.83 295	78.47 256	41.20 280	63.68 304	39.44 300	68.99 333	74.13 263

SCA		58.57 275	58.04 275	60.17 282	70.17 264	41.07 291	65.19 260	53.38 332	43.34 291	61.00 313	73.48 300	45.20 256	69.38 271	40.34 298	70.31 326	70.05 300

thisisatest0515		60.48 262	57.86 276	68.34 205	67.25 289	46.42 250	60.58 298	62.14 292	40.82 304	63.58 299	69.12 330	26.28 358	78.34 174	48.83 240	82.13 237	80.26 205

PatchMatch-RL		58.68 274	57.72 277	61.57 269	76.21 191	73.59 39	61.83 288	49.00 346	47.30 263	61.08 310	68.97 332	50.16 231	59.01 318	36.06 329	68.84 334	52.10 358

HY-MVS	49.31 19	57.96 277	57.59 278	59.10 289	66.85 294	36.17 326	65.13 261	65.39 271	39.24 311	54.69 341	78.14 262	44.28 263	67.18 286	33.75 339	70.79 322	73.95 265

test20.03		55.74 286	57.51 279	50.42 321	59.89 337	32.09 350	50.63 337	49.01 345	50.11 238	65.07 285	83.23 200	45.61 254	48.11 339	30.22 349	83.82 222	71.07 294

XXY-MVS		55.19 289	57.40 280	48.56 330	64.45 313	34.84 338	51.54 336	53.59 329	38.99 313	63.79 296	79.43 243	56.59 200	45.57 345	36.92 322	71.29 319	65.25 329

thres200		57.55 279	57.02 281	59.17 287	67.89 285	34.93 336	58.91 308	57.25 313	50.24 236	64.01 293	71.46 315	32.49 323	71.39 256	31.31 345	79.57 269	71.19 293

IB-MVS	49.67 18	59.69 267	56.96 282	67.90 210	68.19 280	50.30 205	61.42 291	65.18 272	47.57 261	55.83 336	67.15 345	23.77 368	79.60 149	43.56 279	79.97 263	73.79 267
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
testgi		54.00 297	56.86 283	45.45 338	58.20 345	25.81 370	49.05 339	49.50 344	45.43 273	67.84 266	81.17 221	51.81 222	43.20 357	29.30 354	79.41 270	67.34 317

gg-mvs-nofinetune		55.75 285	56.75 284	52.72 314	62.87 320	28.04 364	68.92 205	41.36 366	71.09 40	50.80 352	92.63 12	20.74 371	66.86 288	29.97 351	72.41 313	63.25 338

our_test_3		56.46 282	56.51 285	56.30 299	67.70 286	39.66 302	55.36 326	52.34 337	40.57 307	63.85 294	69.91 326	40.04 289	58.22 320	43.49 280	75.29 299	71.03 295

PatchT		53.35 298	56.47 286	43.99 345	64.19 314	17.46 377	59.15 304	43.10 357	52.11 213	54.74 340	86.95 128	29.97 347	49.98 332	43.62 278	74.40 304	64.53 336

CHOSEN 1792x2688		58.09 276	56.30 287	63.45 251	79.95 137	50.93 199	54.07 330	65.59 269	28.56 354	61.53 307	74.33 292	41.09 282	66.52 293	33.91 338	67.69 340	72.92 273

CostFormer		57.35 280	56.14 288	60.97 276	63.76 317	38.43 309	67.50 226	60.22 301	37.14 321	59.12 324	76.34 276	32.78 321	71.99 249	39.12 304	69.27 332	72.47 278

MIMVSNet		54.39 293	56.12 289	49.20 326	72.57 244	30.91 356	59.98 301	48.43 348	41.66 297	55.94 335	83.86 187	41.19 281	50.42 330	26.05 362	75.38 297	66.27 323

test_fmvs3		56.78 281	55.99 290	59.12 288	53.96 364	48.09 230	58.76 309	66.22 263	27.54 356	76.66 159	68.69 337	25.32 364	51.31 328	53.42 212	73.38 309	77.97 238

Anonymous20231206		54.13 294	55.82 291	49.04 329	70.89 254	35.96 328	51.73 335	50.87 340	34.86 329	62.49 303	79.22 247	42.52 275	44.29 353	27.95 359	81.88 240	66.88 319

new-patchmatchnet		52.89 300	55.76 292	44.26 344	59.94 336	6.31 380	37.36 365	50.76 341	41.10 301	64.28 290	79.82 238	44.77 259	48.43 338	36.24 327	87.61 167	78.03 235

FMVSNet5		55.08 290	55.54 293	53.71 308	65.80 302	33.50 345	56.22 320	52.50 336	43.72 286	61.06 311	83.38 193	25.46 362	54.87 324	30.11 350	81.64 249	72.75 275

tpmvs		55.84 284	55.45 294	57.01 297	60.33 333	33.20 346	65.89 249	59.29 305	47.52 262	56.04 334	73.60 299	31.05 339	68.06 279	40.64 296	64.64 345	69.77 303

MS-PatchMatch		55.59 287	54.89 295	57.68 295	69.18 273	49.05 220	61.00 295	62.93 289	35.98 325	58.36 326	68.93 333	36.71 308	66.59 292	37.62 317	63.30 349	57.39 354

tpm2		56.12 283	54.64 296	60.55 280	66.24 298	36.01 327	68.14 219	56.77 317	33.60 339	58.25 327	75.52 282	30.25 344	74.33 225	33.27 340	69.76 331	71.32 289

PatchmatchNet		54.60 292	54.27 297	55.59 302	65.17 308	39.08 304	66.92 238	51.80 338	39.89 308	58.39 325	73.12 304	31.69 332	58.33 319	43.01 282	58.38 362	69.38 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_fmvs2		54.80 291	54.11 298	56.88 298	51.76 368	49.95 210	56.70 317	65.80 266	26.22 360	69.42 252	65.25 348	31.82 330	49.98 332	49.63 235	70.36 325	70.71 296

MDTV_nov1_ep13			54.05 299		65.54 304	29.30 361	59.00 306	55.22 321	35.96 326	52.44 347	75.98 277	30.77 341	59.62 316	38.21 311	73.33 310

test_vis1_n_1920		52.96 299	53.50 300	51.32 319	59.15 340	44.90 261	56.13 321	64.29 281	30.56 352	59.87 321	60.68 357	40.16 288	47.47 340	48.25 249	62.46 350	61.58 347

YYNet1		52.58 302	53.50 300	49.85 322	54.15 362	36.45 325	40.53 358	46.55 353	38.09 316	75.52 175	73.31 303	41.08 283	43.88 354	41.10 293	71.14 321	69.21 309

MDA-MVSNet_test_wron		52.57 303	53.49 302	49.81 323	54.24 361	36.47 324	40.48 359	46.58 352	38.13 315	75.47 176	73.32 302	41.05 284	43.85 355	40.98 294	71.20 320	69.10 311

UnsupCasMVSNet_eth		52.26 305	53.29 303	49.16 327	55.08 358	33.67 344	50.03 338	58.79 306	37.67 318	63.43 302	74.75 287	41.82 277	45.83 344	38.59 309	59.42 358	67.98 314

baseline2		55.57 288	52.74 304	64.05 244	65.26 305	44.11 266	62.38 286	54.43 325	39.03 312	51.21 350	67.35 343	33.66 316	72.45 242	37.14 320	64.22 347	75.60 250

tpm cat1		54.02 296	52.63 305	58.19 294	64.85 312	39.86 301	66.26 246	57.28 312	32.16 343	56.90 330	70.39 321	32.75 322	65.30 297	34.29 336	58.79 359	69.41 307

pmmvs5		52.49 304	52.58 306	52.21 316	54.99 359	32.38 348	55.45 325	53.84 328	32.15 344	55.49 338	74.81 285	38.08 300	57.37 322	34.02 337	74.40 304	66.88 319

tpm		50.60 313	52.42 307	45.14 340	65.18 307	26.29 368	60.30 299	43.50 356	37.41 319	57.01 329	79.09 251	30.20 346	42.32 358	32.77 342	66.36 342	66.81 321

test_fmvs1_n		52.70 301	52.01 308	54.76 304	53.83 365	50.36 203	55.80 323	65.90 265	24.96 363	65.39 282	60.64 358	27.69 353	48.46 336	45.88 267	67.99 337	65.46 327

JIA-IIPM		54.03 295	51.62 309	61.25 274	59.14 341	55.21 174	59.10 305	47.72 349	50.85 229	50.31 356	85.81 167	20.10 374	63.97 302	36.16 328	55.41 367	64.55 335

KD-MVS_2432*1600		52.05 307	51.58 310	53.44 310	52.11 366	31.20 353	44.88 352	64.83 276	41.53 298	64.37 288	70.03 324	15.61 381	64.20 300	36.25 325	74.61 302	64.93 332

miper_refine_blended		52.05 307	51.58 310	53.44 310	52.11 366	31.20 353	44.88 352	64.83 276	41.53 298	64.37 288	70.03 324	15.61 381	64.20 300	36.25 325	74.61 302	64.93 332

tpmrst		50.15 315	51.38 312	46.45 335	56.05 353	24.77 371	64.40 270	49.98 342	36.14 324	53.32 346	69.59 328	35.16 311	48.69 335	39.24 302	58.51 361	65.89 324

PVSNet	43.83 21	51.56 310	51.17 313	52.73 313	68.34 278	38.27 311	48.22 342	53.56 330	36.41 323	54.29 342	64.94 349	34.60 313	54.20 327	30.34 348	69.87 329	65.71 326

N_pmnet		52.06 306	51.11 314	54.92 303	59.64 339	71.03 53	37.42 364	61.62 298	33.68 337	57.12 328	72.10 308	37.94 301	31.03 371	29.13 358	71.35 318	62.70 340

test_vis3_rt		51.94 309	51.04 315	54.65 305	46.32 375	50.13 207	44.34 354	78.17 165	23.62 367	68.95 259	62.81 352	21.41 370	38.52 367	41.49 290	72.22 314	75.30 256

UnsupCasMVSNet_bld		50.01 316	51.03 316	46.95 331	58.61 343	32.64 347	48.31 341	53.27 333	34.27 334	60.47 315	71.53 314	41.40 278	47.07 342	30.68 347	60.78 355	61.13 348

test_fmvs1		51.51 311	50.86 317	53.48 309	49.72 371	49.35 219	54.11 329	64.96 274	24.64 365	63.66 298	59.61 361	28.33 352	48.45 337	45.38 271	67.30 341	62.66 342

test-LLR		50.43 314	50.69 318	49.64 324	60.76 330	41.87 285	53.18 332	45.48 354	43.41 289	49.41 357	60.47 359	29.22 350	44.73 351	42.09 286	72.14 315	62.33 345

test_vis1_n		51.27 312	50.41 319	53.83 307	56.99 349	50.01 209	56.75 316	60.53 300	25.68 361	59.74 322	57.86 362	29.40 349	47.41 341	43.10 281	63.66 348	64.08 337

WTY-MVS		49.39 317	50.31 320	46.62 334	61.22 328	32.00 351	46.61 348	49.77 343	33.87 336	54.12 343	69.55 329	41.96 276	45.40 347	31.28 346	64.42 346	62.47 343

Patchmatch-test		47.93 320	49.96 321	41.84 348	57.42 348	24.26 372	48.75 340	41.49 365	39.30 310	56.79 331	73.48 300	30.48 343	33.87 370	29.29 355	72.61 312	67.39 315

sss		47.59 322	48.32 322	45.40 339	56.73 352	33.96 342	45.17 351	48.51 347	32.11 346	52.37 348	65.79 346	40.39 287	41.91 361	31.85 343	61.97 352	60.35 349

test0.0.03 1		47.72 321	48.31 323	45.93 336	55.53 357	29.39 360	46.40 349	41.21 367	43.41 289	55.81 337	67.65 340	29.22 350	43.77 356	25.73 365	69.87 329	64.62 334

test-mter		48.56 319	48.20 324	49.64 324	60.76 330	41.87 285	53.18 332	45.48 354	31.91 347	49.41 357	60.47 359	18.34 375	44.73 351	42.09 286	72.14 315	62.33 345

MVS-HIRNet		45.53 326	47.29 325	40.24 351	62.29 322	26.82 367	56.02 322	37.41 372	29.74 353	43.69 370	81.27 219	33.96 314	55.48 323	24.46 368	56.79 363	38.43 371

ADS-MVSNet2		48.76 318	47.25 326	53.29 312	55.90 355	40.54 297	47.34 346	54.99 324	31.41 349	50.48 353	72.06 309	31.23 335	54.26 326	25.93 363	55.93 364	65.07 330

EPMVS		45.74 325	46.53 327	43.39 346	54.14 363	22.33 374	55.02 327	35.00 374	34.69 332	51.09 351	70.20 323	25.92 360	42.04 360	37.19 319	55.50 366	65.78 325

test_f		43.79 333	45.63 328	38.24 354	42.29 379	38.58 308	34.76 367	47.68 350	22.22 370	67.34 272	63.15 351	31.82 330	30.60 372	39.19 303	62.28 351	45.53 366

ADS-MVSNet		44.62 330	45.58 329	41.73 349	55.90 355	20.83 375	47.34 346	39.94 369	31.41 349	50.48 353	72.06 309	31.23 335	39.31 365	25.93 363	55.93 364	65.07 330

E-PMN		45.17 327	45.36 330	44.60 342	50.07 369	42.75 279	38.66 362	42.29 362	46.39 268	39.55 371	51.15 368	26.00 359	45.37 348	37.68 315	76.41 287	45.69 365

test_vis1_rt		46.70 324	45.24 331	51.06 320	44.58 376	51.04 198	39.91 360	67.56 257	21.84 371	51.94 349	50.79 369	33.83 315	39.77 364	35.25 333	61.50 353	62.38 344

pmmvs3		46.71 323	45.09 332	51.55 318	56.76 351	48.25 226	55.78 324	39.53 370	24.13 366	50.35 355	63.40 350	15.90 380	51.08 329	29.29 355	70.69 324	55.33 357

TESTMET0.1,1		45.17 327	44.93 333	45.89 337	56.02 354	38.31 310	53.18 332	41.94 364	27.85 355	44.86 366	56.47 363	17.93 376	41.50 362	38.08 313	68.06 336	57.85 352

dp		44.09 332	44.88 334	41.72 350	58.53 344	23.18 373	54.70 328	42.38 361	34.80 330	44.25 368	65.61 347	24.48 367	44.80 350	29.77 352	49.42 369	57.18 355

DSMNet-mixed		43.18 335	44.66 335	38.75 353	54.75 360	28.88 363	57.06 315	27.42 377	13.47 373	47.27 361	77.67 267	38.83 296	39.29 366	25.32 367	60.12 357	48.08 361

EMVS		44.61 331	44.45 336	45.10 341	48.91 372	43.00 277	37.92 363	41.10 368	46.75 266	38.00 373	48.43 371	26.42 357	46.27 343	37.11 321	75.38 297	46.03 364

PMMVS		44.69 329	43.95 337	46.92 332	50.05 370	53.47 186	48.08 344	42.40 360	22.36 369	44.01 369	53.05 366	42.60 274	45.49 346	31.69 344	61.36 354	41.79 368

mvsany_test3		43.76 334	41.01 338	52.01 317	48.09 373	57.74 160	42.47 356	23.85 380	23.30 368	64.80 286	62.17 355	27.12 354	40.59 363	29.17 357	48.11 370	57.69 353

PMMVS2		37.74 339	40.87 339	28.36 356	42.41 378	5.35 381	24.61 369	27.75 376	32.15 344	47.85 359	70.27 322	35.85 310	29.51 373	19.08 373	67.85 338	50.22 360

PVSNet_0	36.71 22	41.12 337	40.78 340	42.14 347	59.97 335	40.13 299	40.97 357	42.24 363	30.81 351	44.86 366	49.41 370	40.70 285	45.12 349	23.15 369	34.96 373	41.16 369

CHOSEN 280x420		41.62 336	39.89 341	46.80 333	61.81 324	51.59 194	33.56 368	35.74 373	27.48 357	37.64 374	53.53 364	23.24 369	42.09 359	27.39 360	58.64 360	46.72 363

new_pmnet		37.55 340	39.80 342	30.79 355	56.83 350	16.46 378	39.35 361	30.65 375	25.59 362	45.26 364	61.60 356	24.54 366	28.02 374	21.60 370	52.80 368	47.90 362

mvsany_test1		37.88 338	35.74 343	44.28 343	47.28 374	49.90 211	36.54 366	24.37 379	19.56 372	45.76 362	53.46 365	32.99 320	37.97 368	26.17 361	35.52 372	44.99 367

MVE	27.91 23	36.69 341	35.64 344	39.84 352	43.37 377	35.85 330	19.49 370	24.61 378	24.68 364	39.05 372	62.63 354	38.67 298	27.10 375	21.04 371	47.25 371	56.56 356
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
cdsmvs_eth3d_5k		17.71 343	23.62 345	0.00 362	0.00 385	0.00 386	0.00 373	70.17 245	0.00 380	0.00 381	74.25 294	68.16 94	0.00 381	0.00 379	0.00 379	0.00 377

test_method		19.26 342	19.12 346	19.71 357	9.09 381	1.91 383	7.79 372	53.44 331	1.42 375	10.27 377	35.80 372	17.42 378	25.11 376	12.44 374	24.38 375	32.10 372

tmp_tt		11.98 344	14.73 347	3.72 359	2.28 382	4.62 382	19.44 371	14.50 382	0.47 377	21.55 375	9.58 375	25.78 361	4.57 378	11.61 375	27.37 374	1.96 374

ab-mvs-re		5.62 345	7.50 348	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	67.46 341	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		5.20 346	6.93 349	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	62.39 141	0.00 381	0.00 379	0.00 379	0.00 377

test123		4.43 347	5.78 350	0.39 361	0.97 383	0.28 384	46.33 350	0.45 384	0.31 378	0.62 379	1.50 378	0.61 384	0.11 380	0.56 377	0.63 377	0.77 376

testmvs		4.06 348	5.28 351	0.41 360	0.64 384	0.16 385	42.54 355	0.31 385	0.26 379	0.50 380	1.40 379	0.77 383	0.17 379	0.56 377	0.55 378	0.90 375

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

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

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

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

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

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

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

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

FOURS1					89.19 23	77.84 12	91.64 1	89.11 2	84.05 2	91.57 2

MSC_two_6792asdad				79.02 54	83.14 96	67.03 87		80.75 117					86.24 21	77.27 32	94.85 25	83.78 128

PC_three_1452									46.98 265	81.83 93	86.28 151	66.55 111	84.47 69	63.31 127	90.78 114	83.49 134

No_MVS				79.02 54	83.14 96	67.03 87		80.75 117					86.24 21	77.27 32	94.85 25	83.78 128

test_one_0601					85.84 61	61.45 127		85.63 27	75.27 17	85.62 48	90.38 64	76.72 27

eth-test2					0.00 385

eth-test					0.00 385

ZD-MVS					83.91 87	69.36 69		81.09 112	58.91 137	82.73 86	89.11 94	75.77 35	86.63 11	72.73 57	92.93 70

IU-MVS					86.12 53	60.90 135		80.38 128	45.49 272	81.31 101				75.64 39	94.39 41	84.65 100

OPU-MVS				78.65 61	83.44 94	66.85 89	83.62 42				86.12 159	66.82 105	86.01 29	61.72 136	89.79 135	83.08 148

test_241102_TWO								84.80 44	72.61 30	84.93 56	89.70 81	77.73 22	85.89 38	75.29 40	94.22 52	83.25 144

test_241102_ONE					86.12 53	61.06 131		84.72 48	72.64 29	87.38 24	89.47 84	77.48 23	85.74 42

save fliter					87.00 39	67.23 86	79.24 83	77.94 170	56.65 160

test_0728_THIRD									74.03 21	85.83 43	90.41 59	75.58 37	85.69 43	77.43 30	94.74 29	84.31 118

test_0728_SECOND				76.57 83	86.20 48	60.57 140	83.77 40	85.49 29					85.90 36	75.86 37	94.39 41	83.25 144

test0726					86.16 51	60.78 137	83.81 39	85.10 39	72.48 32	85.27 53	89.96 77	78.57 17

GSMVS																70.05 300

test_part2					85.90 57	66.44 91				84.61 62

sam_mvs1												31.41 333				70.05 300

sam_mvs												31.21 337

ambc				70.10 178	77.74 171	50.21 206	74.28 148	77.93 171		79.26 122	88.29 113	54.11 211	79.77 146	64.43 111	91.10 103	80.30 204

MTGPA								80.63 122

test_post1							66.63 242				2.08 376	30.66 342	59.33 317	40.34 298

test_post											1.99 377	30.91 340	54.76 325

patchmatchnet-post											68.99 331	31.32 334	69.38 271

GG-mvs-BLEND				52.24 315	60.64 332	29.21 362	69.73 196	42.41 359		45.47 363	52.33 367	20.43 373	68.16 278	25.52 366	65.42 344	59.36 351

MTMP							84.83 31	19.26 381

gm-plane-assit					62.51 321	33.91 343			37.25 320		62.71 353		72.74 235	38.70 306

test9_res														72.12 64	91.37 93	77.40 241

TEST9					85.47 63	69.32 70	76.42 117	78.69 156	53.73 199	76.97 148	86.74 135	66.84 104	81.10 120

test_8					85.09 69	67.89 79	76.26 122	78.66 158	54.00 194	76.89 152	86.72 137	66.60 109	80.89 130

agg_prior2														70.70 70	90.93 108	78.55 227

agg_prior					84.44 82	66.02 94		78.62 159		76.95 150			80.34 137

TestCases				78.35 65	79.19 149	70.81 55		88.64 3	65.37 76	80.09 115	88.17 115	70.33 75	78.43 170	55.60 188	90.90 110	85.81 76

test_prior4						70.14 63	77.57 100

test_prior2							75.57 130		58.92 136	76.53 164	86.78 133	67.83 98		69.81 73	92.76 73

test_prior				75.27 100	82.15 116	59.85 145		84.33 59					83.39 84			82.58 162

旧先验2							71.17 180		45.11 277	78.54 130			61.28 313	59.19 163

新几何2							71.33 176

新几何1				69.99 180	88.37 34	71.34 51		62.08 294	43.85 283	74.99 180	86.11 160	52.85 215	70.57 262	50.99 224	83.23 229	68.05 313

旧先验1					84.55 79	60.36 142		63.69 285			87.05 127	54.65 208			83.34 228	69.66 304

无先验							74.82 136	70.94 239	47.75 260				76.85 198	54.47 199		72.09 283

原ACMM2							74.78 140

原ACMM1				73.90 113	85.90 57	65.15 101		81.67 98	50.97 228	74.25 192	86.16 157	61.60 149	83.54 80	56.75 176	91.08 104	73.00 272

test222					87.30 37	69.15 73	67.85 222	59.59 304	41.06 302	73.05 209	85.72 168	48.03 247			80.65 256	66.92 318

testdata2													67.30 284	48.34 247

segment_acmp												68.30 93

testdata				64.13 242	85.87 59	63.34 113		61.80 297	47.83 258	76.42 167	86.60 144	48.83 241	62.31 310	54.46 200	81.26 251	66.74 322

testdata1							68.34 218		57.24 153

test12				76.51 84	82.28 114	60.94 134		81.64 99		73.60 200		64.88 125	85.19 57		90.42 121	83.38 140

plane_prior7					85.18 66	66.21 93

plane_prior6					84.18 85	65.31 98						60.83 159

plane_prior5								85.49 29					86.15 26	71.09 66	90.94 106	84.82 96

plane_prior4											89.11 94

plane_prior3						65.67 95			63.82 94	78.23 132

plane_prior2							82.74 51		65.45 73

plane_prior1					84.46 81

plane_prior						65.18 99	80.06 77		61.88 113						89.91 132

n2								0.00 386

nn								0.00 386

door-mid								55.02 323

lessismore_v0				72.75 141	79.60 141	56.83 165		57.37 311		83.80 72	89.01 97	47.45 249	78.74 163	64.39 112	86.49 189	82.69 160

LGP-MVS_train				80.90 32	87.00 39	70.41 60		86.35 16	69.77 49	87.75 15	91.13 34	81.83 3	86.20 23	77.13 34	95.96 5	86.08 71

test11								82.71 84

door								52.91 335

HQP5-MVS						58.80 154

HQP-NCC					82.37 111		77.32 105		59.08 131	71.58 226

ACMP_Plane					82.37 111		77.32 105		59.08 131	71.58 226

BP-MVS														67.38 94

HQP4-MVS										71.59 225			85.31 50			83.74 130

HQP3-MVS								84.12 65							89.16 146

HQP2-MVS												58.09 184

NP-MVS					83.34 95	63.07 116					85.97 163

MDTV_nov1_ep13_2view						18.41 376	53.74 331		31.57 348	44.89 365		29.90 348		32.93 341		71.48 287

ACMMP++_ref															89.47 141

ACMMP++															91.96 83

Test By Simon												62.56 137

ITE_SJBPF				80.35 38	76.94 181	73.60 38		80.48 125	66.87 61	83.64 74	86.18 155	70.25 77	79.90 145	61.12 143	88.95 153	87.56 53

DeepMVS_CX				11.83 358	15.51 380	13.86 379		11.25 383	5.76 374	20.85 376	26.46 373	17.06 379	9.22 377	9.69 376	13.82 376	12.42 373

High-resolution multi-view benchmark