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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DPE-MVS		88.63 5	91.29 5	85.53 3	90.87 9	92.20 4	91.98 2	76.00 7	90.55 10	82.09 6	93.85 3	90.75 2	81.25 1	88.62 9	87.59 16	90.96 12	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 5	76.31 4	93.31 1	83.11 3	92.44 6	91.18 1	81.17 2	89.55 2	87.93 9	91.01 10	96.21 1

SED-MVS		88.85 2	91.59 3	85.67 2	90.54 17	92.29 3	91.71 4	76.40 3	92.41 3	83.24 2	92.50 5	90.64 4	81.10 3	89.53 3	88.02 7	91.00 11	95.73 3

MED-MVS		88.73 3	91.48 4	85.53 3	90.94 8	91.91 6	91.93 3	76.42 2	92.32 4	81.78 7	94.25 1	90.22 6	80.98 4	89.21 7	87.96 8	91.13 5	94.45 8

MSP-MVS		88.09 7	90.84 6	84.88 9	90.00 26	91.80 7	91.63 6	75.80 8	91.99 5	81.23 9	92.54 4	89.18 8	80.89 5	87.99 17	87.91 10	89.70 49	94.51 7
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
aaEdge-Enhanced		88.11 6	90.84 6	84.92 8	90.52 18	91.48 9	91.33 7	75.06 15	90.82 8	80.74 11	94.25 1	90.29 5	80.86 6	87.82 18	86.80 24	91.03 7	94.45 8

APDe-MVS		88.00 8	90.50 8	85.08 6	90.95 7	91.58 8	92.03 1	75.53 13	91.15 6	80.10 17	92.27 7	88.34 13	80.80 7	88.00 16	86.99 20	91.09 6	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		88.67 4	91.62 2	85.22 5	90.47 19	92.36 2	90.69 12	76.15 5	93.08 2	82.75 4	92.19 8	90.71 3	80.45 8	89.27 6	87.91 10	90.82 15	95.84 2
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
APD-MVS		86.84 14	88.91 16	84.41 12	90.66 12	90.10 15	90.78 10	75.64 10	87.38 18	78.72 21	90.68 12	86.82 19	80.15 9	87.13 27	86.45 31	90.51 24	93.83 16
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		86.88 13	89.23 12	84.14 14	89.78 29	88.67 32	90.59 13	73.46 29	88.99 13	80.52 14	91.26 9	88.65 11	79.91 10	86.96 31	86.22 33	90.59 23	93.83 16
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		87.09 11	88.92 15	84.95 7	92.61 1	87.91 43	90.23 18	76.06 6	88.85 14	81.20 10	87.33 15	87.93 14	79.47 11	88.59 10	88.23 5	90.15 38	93.60 22

SF-MVS		87.47 10	89.70 10	84.86 10	91.26 6	91.10 10	90.90 9	75.65 9	89.21 11	81.25 8	91.12 10	88.93 9	78.82 12	87.42 22	86.23 32	91.28 3	93.90 15

CNVR-MVS		86.36 16	88.19 19	84.23 13	91.33 5	89.84 17	90.34 14	75.56 11	87.36 19	78.97 20	81.19 31	86.76 20	78.74 13	89.30 5	88.58 2	90.45 30	94.33 12

SD-MVS		86.96 12	89.45 11	84.05 16	90.13 22	89.23 25	89.77 21	74.59 17	89.17 12	80.70 12	89.93 13	89.67 7	78.47 14	87.57 21	86.79 25	90.67 21	93.76 18
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
MCST-MVS		85.13 24	86.62 26	83.39 19	90.55 16	89.82 19	89.29 24	73.89 25	84.38 32	76.03 33	79.01 34	85.90 23	78.47 14	87.81 19	86.11 35	92.11 1	93.29 24

HFP-MVS		86.15 17	87.95 20	84.06 15	90.80 10	89.20 26	89.62 22	74.26 19	87.52 16	80.63 13	86.82 18	84.19 31	78.22 16	87.58 20	87.19 18	90.81 16	93.13 27

SMA-MVS		87.56 9	90.17 9	84.52 11	91.71 3	90.57 11	90.77 11	75.19 14	90.67 9	80.50 15	86.59 19	88.86 10	78.09 17	89.92 1	89.41 1	90.84 14	95.19 5
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
NCCC		85.34 21	86.59 27	83.88 17	91.48 4	88.88 27	89.79 20	75.54 12	86.67 22	77.94 26	76.55 37	84.99 27	78.07 18	88.04 14	87.68 14	90.46 29	93.31 23

TSAR-MVS + GP.		83.69 32	86.58 28	80.32 38	85.14 57	86.96 47	84.91 54	70.25 44	84.71 30	73.91 41	85.16 23	85.63 24	77.92 19	85.44 45	85.71 38	89.77 45	92.45 29

MSLP-MVS++		82.09 39	82.66 42	81.42 32	87.03 47	87.22 46	85.82 46	70.04 45	80.30 48	78.66 22	68.67 89	81.04 47	77.81 20	85.19 49	84.88 46	89.19 60	91.31 40

ACMMPR		85.52 19	87.53 22	83.17 23	90.13 22	89.27 23	89.30 23	73.97 23	86.89 21	77.14 28	86.09 20	83.18 35	77.74 21	87.42 22	87.20 17	90.77 17	92.63 28

DeepC-MVS_fast	78.24 3	84.27 31	85.50 33	82.85 24	90.46 20	89.24 24	87.83 37	74.24 20	84.88 27	76.23 32	75.26 43	81.05 46	77.62 22	88.02 15	87.62 15	90.69 20	92.41 30
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS	78.47 2	84.81 27	86.03 31	83.37 20	89.29 35	90.38 14	88.61 30	76.50 1	86.25 24	77.22 27	75.12 44	80.28 48	77.59 23	88.39 11	88.17 6	91.02 9	93.66 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	79.04 1	85.30 22	88.93 14	81.06 34	88.77 39	90.48 13	85.46 50	73.08 31	90.97 7	73.77 42	84.81 24	85.95 22	77.43 24	88.22 12	87.73 12	87.85 104	94.34 11

MP-MVS		85.50 20	87.40 23	83.28 21	90.65 13	89.51 22	89.16 27	74.11 21	83.70 36	78.06 25	85.54 22	84.89 30	77.31 25	87.40 24	87.14 19	90.41 32	93.65 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		85.99 18	88.31 18	83.27 22	90.73 11	89.84 17	90.27 17	74.31 18	84.56 31	75.88 34	87.32 16	85.04 26	77.31 25	89.01 8	88.46 3	91.14 4	93.96 14
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		84.74 28	86.43 29	82.77 25	89.48 33	88.13 41	88.64 29	73.93 24	84.92 26	76.77 30	81.94 29	83.50 33	77.29 27	86.92 32	86.49 30	90.49 25	93.14 26

3Dnovator+	75.73 4	82.40 37	82.76 41	81.97 30	88.02 42	89.67 20	86.60 42	71.48 39	81.28 47	78.18 24	64.78 116	77.96 55	77.13 28	87.32 25	86.83 23	90.41 32	91.48 39

PGM-MVS		84.42 30	86.29 30	82.23 27	90.04 25	88.82 28	89.23 25	71.74 38	82.82 41	74.61 37	84.41 25	82.09 38	77.03 29	87.13 27	86.73 27	90.73 19	92.06 34

ACMMP_NAP		86.52 15	89.01 13	83.62 18	90.28 21	90.09 16	90.32 16	74.05 22	88.32 15	79.74 18	87.04 17	85.59 25	76.97 30	89.35 4	88.44 4	90.35 34	94.27 13

AdaColmap		79.74 49	78.62 68	81.05 35	89.23 36	86.06 56	84.95 53	71.96 36	79.39 52	75.51 35	63.16 122	68.84 124	76.51 31	83.55 65	82.85 62	88.13 85	86.46 89

CS-MVS		79.22 54	81.11 53	77.01 57	81.36 83	84.03 75	80.35 88	63.25 105	73.43 73	70.37 62	74.10 49	76.03 63	76.40 32	86.32 40	83.95 53	90.34 35	89.93 52

CPTT-MVS		81.77 40	83.10 40	80.21 39	85.93 53	86.45 53	87.72 39	70.98 41	82.54 43	71.53 53	74.23 48	81.49 43	76.31 33	82.85 75	81.87 70	88.79 71	92.26 32

EC-MVSNet		79.44 51	81.35 50	77.22 55	82.95 66	84.67 69	81.31 81	63.65 99	72.47 77	68.75 72	73.15 51	78.33 52	75.99 34	86.06 43	83.96 52	90.67 21	90.79 44

train_agg		84.86 26	87.21 25	82.11 28	90.59 15	85.47 61	89.81 19	73.55 28	83.95 33	73.30 43	89.84 14	87.23 17	75.61 35	86.47 36	85.46 41	89.78 44	92.06 34

ACMMP		83.42 33	85.27 34	81.26 33	88.47 41	88.49 35	88.31 35	72.09 35	83.42 37	72.77 45	82.65 26	78.22 53	75.18 36	86.24 41	85.76 37	90.74 18	92.13 33
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
SPE-MVS-test		78.79 61	80.72 55	76.53 61	81.11 89	83.88 78	79.69 100	63.72 98	73.80 69	69.95 67	75.40 42	76.17 60	74.85 37	84.50 56	82.78 63	89.87 43	88.54 64

MVSMamba_PlusPlus		80.48 43	82.51 44	78.11 51	82.79 68	86.47 52	83.22 61	66.95 70	77.74 54	70.45 61	73.88 50	77.56 56	74.81 38	86.85 33	85.52 39	90.43 31	89.55 58

TSAR-MVS + ACMM		85.10 25	88.81 17	80.77 37	89.55 32	88.53 34	88.59 31	72.55 33	87.39 17	71.90 47	90.95 11	87.55 15	74.57 39	87.08 29	86.54 29	87.47 114	93.67 19

MGCNet		84.63 29	87.25 24	81.59 31	88.58 40	90.50 12	87.82 38	69.16 55	83.82 35	78.46 23	82.32 27	84.97 28	74.56 40	88.16 13	87.72 13	90.94 13	93.24 25

CNLPA		77.20 70	77.54 77	76.80 60	82.63 70	84.31 72	79.77 95	64.64 87	85.17 25	73.18 44	56.37 161	69.81 115	74.53 41	81.12 102	78.69 136	86.04 156	87.29 76

OPM-MVS		79.68 50	79.28 66	80.15 40	87.99 43	86.77 49	88.52 32	72.72 32	64.55 130	67.65 81	67.87 95	74.33 72	74.31 42	86.37 38	85.25 43	89.73 48	89.81 54
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
3Dnovator	73.76 5	79.75 48	80.52 58	78.84 45	84.94 62	87.35 44	84.43 56	65.54 80	78.29 53	73.97 40	63.00 124	75.62 66	74.07 43	85.00 50	85.34 42	90.11 39	89.04 60

CSCG		85.28 23	87.68 21	82.49 26	89.95 27	91.99 5	88.82 28	71.20 40	86.41 23	79.63 19	79.26 32	88.36 12	73.94 44	86.64 34	86.67 28	91.40 2	94.41 10

PLC	68.99 11	75.68 90	75.31 109	76.12 65	82.94 67	81.26 118	79.94 93	66.10 74	77.15 57	66.86 90	59.13 144	68.53 126	73.73 45	80.38 121	79.04 129	87.13 122	81.68 159
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMM	72.26 8	78.86 60	78.13 72	79.71 42	86.89 48	83.40 86	86.02 44	70.50 42	75.28 61	71.49 54	63.01 123	69.26 118	73.57 46	84.11 59	83.98 51	89.76 46	87.84 69
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETV-MVS		77.32 69	78.81 67	75.58 73	82.24 76	83.64 84	79.98 91	64.02 95	69.64 96	63.90 108	70.89 65	69.94 114	73.41 47	85.39 48	83.91 54	89.92 41	88.31 65

OMC-MVS		80.26 44	82.59 43	77.54 53	83.04 65	85.54 60	83.25 60	65.05 85	87.32 20	72.42 46	72.04 58	78.97 50	73.30 48	83.86 60	81.60 75	88.15 84	88.83 62

MVS_111021_HR		80.13 45	81.46 49	78.58 47	85.77 54	85.17 65	83.45 59	69.28 52	74.08 67	70.31 63	74.31 47	75.26 67	73.13 49	86.46 37	85.15 44	89.53 51	89.81 54

PHI-MVS		82.36 38	85.89 32	78.24 49	86.40 51	89.52 21	85.52 48	69.52 51	82.38 44	65.67 93	81.35 30	82.36 37	73.07 50	87.31 26	86.76 26	89.24 56	91.56 38

DPM-MVS		83.30 34	84.33 37	82.11 28	89.56 31	88.49 35	90.33 15	73.24 30	83.85 34	76.46 31	72.43 56	82.65 36	73.02 51	86.37 38	86.91 21	90.03 40	89.62 56

CANet		81.62 41	83.41 38	79.53 43	87.06 46	88.59 33	85.47 49	67.96 61	76.59 58	74.05 39	74.69 45	81.98 39	72.98 52	86.14 42	85.47 40	89.68 50	90.42 49

QAPM		78.47 63	80.22 61	76.43 62	85.03 59	86.75 50	80.62 87	66.00 76	73.77 70	65.35 97	65.54 112	78.02 54	72.69 53	83.71 62	83.36 59	88.87 68	90.41 50

MVS_111021_LR		78.13 65	79.85 64	76.13 64	81.12 88	81.50 113	80.28 90	65.25 83	76.09 59	71.32 55	76.49 38	72.87 84	72.21 54	82.79 76	81.29 78	86.59 141	87.91 68

MAR-MVS		79.21 55	80.32 60	77.92 52	87.46 44	88.15 40	83.95 57	67.48 67	74.28 64	68.25 75	64.70 117	77.04 57	72.17 55	85.42 46	85.00 45	88.22 81	87.62 73
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
ET-MVSNet_ETH3D		72.46 119	74.19 116	70.44 123	62.50 237	81.17 119	79.90 94	62.46 137	64.52 131	57.52 133	71.49 62	59.15 163	72.08 56	78.61 153	81.11 80	88.16 83	83.29 145

ACMP	73.23 7	79.79 47	80.53 57	78.94 44	85.61 55	85.68 59	85.61 47	69.59 49	77.33 56	71.00 57	74.45 46	69.16 119	71.88 57	83.15 71	83.37 58	89.92 41	90.57 48
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	71.42 9	77.69 67	80.05 62	74.94 84	80.68 102	84.52 71	81.36 80	63.14 114	84.77 28	64.82 101	68.72 87	75.91 64	71.86 58	81.62 84	79.55 117	87.80 106	85.24 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDPH-MVS		82.64 36	85.03 36	79.86 41	89.41 34	88.31 38	88.32 34	71.84 37	80.11 49	67.47 82	82.09 28	81.44 44	71.85 59	85.89 44	86.15 34	90.24 36	91.25 41

Casviewmamba		78.51 62	79.92 63	76.87 59	82.72 69	85.98 57	82.91 62	65.64 79	75.65 60	69.03 71	70.43 71	74.36 71	71.80 60	83.70 63	81.55 76	89.10 63	87.78 70

PCF-MVS	73.28 6	79.42 52	80.41 59	78.26 48	84.88 63	88.17 39	86.08 43	69.85 46	75.23 62	68.43 74	68.03 94	78.38 51	71.76 61	81.26 98	80.65 95	88.56 75	91.18 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVS		83.23 35	85.20 35	80.92 36	89.71 30	88.68 29	88.21 36	73.60 26	82.57 42	71.81 50	77.07 35	81.92 40	71.72 62	86.98 30	86.86 22	90.47 26	92.36 31

viewdifsd2359ckpt09		77.36 68	78.39 71	76.16 63	79.98 112	85.78 58	82.78 63	65.29 82	70.87 87	68.68 73	68.99 81	70.81 107	71.70 63	82.68 77	81.86 71	88.56 75	87.71 72

HQP-MVS		81.19 42	83.27 39	78.76 46	87.40 45	85.45 62	86.95 40	70.47 43	81.31 46	66.91 88	79.24 33	76.63 58	71.67 64	84.43 57	83.78 55	89.19 60	92.05 36

EIA-MVS		75.64 92	76.60 101	74.53 90	82.43 73	83.84 79	78.32 120	62.28 139	65.96 118	63.28 112	68.95 82	67.54 131	71.61 65	82.55 78	81.63 74	89.24 56	85.72 105

TSAR-MVS + COLMAP		78.34 64	81.64 48	74.48 92	80.13 111	85.01 66	81.73 76	65.93 78	84.75 29	61.68 114	85.79 21	66.27 137	71.39 66	82.91 74	80.78 86	86.01 157	85.98 93

LGP-MVS_train		79.83 46	81.22 52	78.22 50	86.28 52	85.36 64	86.76 41	69.59 49	77.34 55	65.14 98	75.68 40	70.79 108	71.37 67	84.60 53	84.01 50	90.18 37	90.74 45

TPM-MVS					90.07 24	88.36 37	88.45 33			77.10 29	75.60 41	83.98 32	71.33 68			89.75 47	89.62 56
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
Fast-Effi-MVS+		73.11 113	73.66 121	72.48 102	77.72 133	80.88 125	78.55 115	58.83 187	65.19 124	60.36 119	59.98 138	62.42 149	71.22 69	81.66 83	80.61 97	88.20 82	84.88 130

LS3D		74.08 104	73.39 124	74.88 85	85.05 58	82.62 106	79.71 98	68.66 56	72.82 74	58.80 124	57.61 155	61.31 153	71.07 70	80.32 122	78.87 134	86.00 158	80.18 175

casdiffseed414692147		75.68 90	75.69 108	75.67 71	81.52 80	84.14 74	81.64 78	64.19 94	68.92 99	67.29 85	61.24 128	67.12 133	71.02 71	81.17 99	80.83 85	88.36 77	86.40 90

Effi-MVS+		75.28 95	76.20 104	74.20 93	81.15 87	83.24 89	81.11 82	63.13 115	66.37 114	60.27 120	64.30 120	68.88 123	70.93 72	81.56 86	81.69 73	88.61 73	87.35 74

ACM-MVS					90.61 14	87.94 42	89.23 25		81.83 45	74.47 38	75.82 39	83.33 34	70.56 73			89.02 64	91.80 37

viewdifsd2359ckpt13		76.26 80	77.31 88	75.03 82	80.14 109	83.77 82	81.58 79	62.80 123	70.34 88	67.83 80	68.06 93	70.93 104	70.20 74	81.46 89	79.88 106	87.63 111	86.71 86

OpenMVS	70.44 10	76.15 86	76.82 96	75.37 80	85.01 60	84.79 67	78.99 110	62.07 141	71.27 83	67.88 79	57.91 154	72.36 86	70.15 75	82.23 82	81.41 77	88.12 86	87.78 70

hybridcas		76.97 71	78.42 70	75.27 81	81.21 85	84.20 73	81.90 72	62.85 121	74.06 68	66.89 89	68.88 83	73.96 74	70.06 76	82.31 81	79.54 118	88.71 72	85.99 92

DELS-MVS		79.15 58	81.07 54	76.91 58	83.54 64	87.31 45	84.45 55	64.92 86	69.98 89	69.34 70	71.62 60	76.26 59	69.84 77	86.57 35	85.90 36	89.39 53	89.88 53
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
E6new		76.06 87	76.54 102	75.51 76	80.71 97	83.10 92	81.74 74	63.03 116	68.89 100	69.71 68	66.73 107	70.84 105	69.76 78	80.88 106	79.61 113	88.11 88	85.72 105

E6		76.06 87	76.54 102	75.51 76	80.71 97	83.10 92	81.74 74	63.03 116	68.89 100	69.71 68	66.73 107	70.84 105	69.76 78	80.88 106	79.61 113	88.11 88	85.72 105

sasdasda		79.16 56	82.37 45	75.41 78	82.33 74	86.38 54	80.80 84	63.18 111	82.90 39	67.34 83	72.79 53	76.07 61	69.62 80	83.46 68	84.41 48	89.20 58	90.60 46

canonicalmvs		79.16 56	82.37 45	75.41 78	82.33 74	86.38 54	80.80 84	63.18 111	82.90 39	67.34 83	72.79 53	76.07 61	69.62 80	83.46 68	84.41 48	89.20 58	90.60 46

E3new		76.51 77	77.22 89	75.69 69	80.74 95	83.07 94	81.99 67	63.23 108	71.18 84	70.52 60	68.77 85	71.75 91	69.61 82	80.73 108	79.18 125	88.03 95	85.85 100

E3		76.51 77	77.21 90	75.69 69	80.74 95	83.06 97	81.98 68	63.22 109	71.17 85	70.55 59	68.77 85	71.76 90	69.61 82	80.73 108	79.18 125	88.03 95	85.84 102

E4		76.24 81	76.77 99	75.61 72	80.69 99	83.05 98	81.98 68	63.25 105	69.47 97	70.06 64	67.40 100	71.46 93	69.59 84	80.73 108	79.37 122	88.10 90	85.95 95

viewcassd2359sk11		76.64 74	77.43 84	75.72 68	80.75 94	83.07 94	81.95 70	63.20 110	72.02 82	70.88 58	69.50 78	72.02 89	69.58 85	80.68 113	78.98 131	87.97 97	85.74 103

E2		76.70 73	77.54 77	75.73 66	80.76 93	83.07 94	81.91 71	63.15 113	72.42 78	71.09 56	70.03 75	72.22 87	69.53 86	80.57 115	78.80 135	87.91 100	85.64 108

viewmanbaseed2359cas		76.36 79	77.87 74	74.60 89	79.81 113	82.88 103	81.69 77	61.02 154	72.14 81	67.97 77	69.61 77	72.45 85	69.53 86	81.53 87	79.83 108	87.57 112	86.65 87

PatchMatch-RL		67.78 168	66.65 189	69.10 140	73.01 184	72.69 213	68.49 211	61.85 144	62.93 144	60.20 121	56.83 160	50.42 233	69.52 88	75.62 184	74.46 195	81.51 213	73.62 230

casdiffmvs		76.76 72	78.46 69	74.77 86	80.32 107	83.73 83	80.65 86	63.24 107	73.58 71	66.11 92	69.39 80	74.09 73	69.49 89	82.52 79	79.35 124	88.84 70	86.52 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmacassd2359aftdt		75.85 89	77.01 94	74.49 91	79.69 115	82.87 104	81.77 73	61.06 152	69.37 98	67.26 86	66.73 107	71.63 92	69.48 90	81.51 88	80.20 101	87.69 108	86.77 85

E5new		76.23 82	76.79 97	75.58 73	80.69 99	83.05 98	82.00 65	63.37 102	69.73 92	70.01 65	67.77 97	71.43 96	69.37 91	80.50 116	79.13 127	88.04 92	85.92 96

E5		76.23 82	76.79 97	75.58 73	80.69 99	83.05 98	82.00 65	63.37 102	69.73 92	70.01 65	67.77 97	71.43 96	69.37 91	80.50 116	79.13 127	88.04 92	85.92 96

DI_MVS_pp		75.13 97	76.12 105	73.96 94	78.18 127	81.55 111	80.97 83	62.54 133	68.59 103	65.13 99	61.43 127	74.81 68	69.32 93	81.01 104	79.59 115	87.64 110	85.89 98

casdiffmvs_mvg		77.79 66	79.55 65	75.73 66	81.56 79	84.70 68	82.12 64	64.26 93	74.27 65	67.93 78	70.83 66	74.66 69	69.19 94	83.33 70	81.94 69	89.29 55	87.14 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		75.37 93	77.13 92	73.31 97	79.07 121	81.32 116	79.98 91	60.12 169	69.72 94	64.11 107	70.53 70	73.22 79	68.90 95	80.14 129	79.48 120	87.67 109	85.50 115

Effi-MVS+-dtu		71.82 123	71.86 138	71.78 108	78.77 122	80.47 129	78.55 115	61.67 149	60.68 161	55.49 142	58.48 148	65.48 139	68.85 96	76.92 175	75.55 188	87.35 116	85.46 116

ACMH	65.37 14	70.71 134	70.00 149	71.54 109	82.51 72	82.47 107	77.78 124	68.13 58	56.19 193	46.06 210	54.30 175	51.20 229	68.68 97	80.66 114	80.72 88	86.07 152	84.45 136
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 130	70.09 148	72.85 99	82.59 71	81.13 120	78.56 114	68.04 59	61.55 155	52.52 170	51.50 210	54.14 202	68.56 98	78.85 150	79.50 119	86.82 130	83.94 139

CLD-MVS		79.35 53	81.23 51	77.16 56	85.01 60	86.92 48	85.87 45	60.89 156	80.07 51	75.35 36	72.96 52	73.21 80	68.43 99	85.41 47	84.63 47	87.41 115	85.44 117
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		74.23 103	74.84 114	73.52 95	80.42 106	81.46 114	79.77 95	61.06 152	67.23 111	63.67 109	59.56 141	68.74 125	67.90 100	80.25 127	79.37 122	88.31 78	87.26 77

HyFIR lowres test		69.47 149	68.94 163	70.09 129	76.77 142	82.93 102	76.63 138	60.17 167	59.00 170	54.03 150	40.54 248	65.23 140	67.89 101	76.54 181	78.30 144	85.03 185	80.07 176

viewdifsd2359ckpt07		74.55 100	76.09 106	72.75 100	79.51 117	81.32 116	80.29 89	58.44 190	68.61 102	65.63 94	68.17 92	71.24 101	67.64 102	80.13 130	77.62 155	84.96 189	85.56 111

FA-MVS(training)		73.66 107	74.95 112	72.15 103	78.63 125	80.46 130	78.92 112	54.79 215	69.71 95	65.37 96	62.04 125	66.89 135	67.10 103	80.72 111	79.87 107	88.10 90	84.97 127

PVSNet_Blended_VisFu		76.57 75	77.90 73	75.02 83	80.56 103	86.58 51	79.24 105	66.18 73	64.81 127	68.18 76	65.61 110	71.45 94	67.05 104	84.16 58	81.80 72	88.90 66	90.92 43

PVSNet_BlendedMVS		76.21 84	77.52 79	74.69 87	79.46 118	83.79 80	77.50 127	64.34 91	69.88 90	71.88 48	68.54 90	70.42 110	67.05 104	83.48 66	79.63 111	87.89 102	86.87 81

PVSNet_Blended		76.21 84	77.52 79	74.69 87	79.46 118	83.79 80	77.50 127	64.34 91	69.88 90	71.88 48	68.54 90	70.42 110	67.05 104	83.48 66	79.63 111	87.89 102	86.87 81

v10		70.22 140	69.76 153	70.74 114	74.79 166	80.30 134	79.22 106	59.81 173	57.71 179	56.58 139	54.22 181	55.31 190	66.95 107	78.28 156	77.47 160	87.12 124	85.07 125

v1192		69.50 148	68.83 164	70.29 125	74.49 170	80.92 124	78.55 115	60.54 160	55.04 203	54.21 147	52.79 199	52.33 222	66.92 108	77.88 163	77.35 165	87.04 125	85.51 114

CHOSEN 1792x2688		69.20 152	69.26 159	69.13 139	76.86 141	78.93 147	77.27 130	60.12 169	61.86 152	54.42 146	42.54 241	61.61 152	66.91 109	78.55 154	78.14 146	79.23 224	83.23 146

v1921920		69.03 153	68.32 172	69.86 131	74.03 175	80.37 131	77.55 125	60.25 166	54.62 207	53.59 161	52.36 206	51.50 228	66.75 110	77.17 172	76.69 174	86.96 126	85.56 111

v144192		69.34 150	68.68 168	70.12 128	74.06 174	80.54 127	78.08 123	60.54 160	54.99 205	54.13 149	52.92 197	52.80 220	66.73 111	77.13 173	76.72 172	87.15 118	85.63 110

v1240		68.64 158	67.89 179	69.51 136	73.89 177	80.26 135	76.73 137	59.97 172	53.43 215	53.08 165	51.82 209	50.84 231	66.62 112	76.79 177	76.77 171	86.78 133	85.34 120

diffmvs_AUTHOR		74.91 98	77.47 82	71.92 105	75.60 158	80.50 128	79.48 103	60.02 171	72.41 79	64.39 104	70.63 67	73.27 78	66.55 113	79.97 131	78.34 143	85.46 170	87.17 78

viewmambaseed2359dif		73.61 109	75.14 110	71.84 107	75.87 151	79.69 137	78.99 110	60.42 164	68.19 105	64.15 106	67.85 96	71.20 102	66.55 113	77.41 169	75.78 183	85.04 184	85.85 100

v1144		69.93 144	69.36 158	70.61 118	74.89 165	80.93 122	79.11 108	60.64 158	55.97 195	55.31 144	53.85 184	54.14 202	66.54 115	78.10 158	77.44 161	87.14 121	85.09 124

diffmvs		74.86 99	77.37 86	71.93 104	75.62 156	80.35 132	79.42 104	60.15 168	72.81 75	64.63 103	71.51 61	73.11 83	66.53 116	79.02 148	77.98 147	85.25 180	86.83 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt11		72.49 117	74.10 117	70.61 118	75.87 151	78.53 155	76.92 132	58.16 192	65.69 121	61.34 117	67.21 102	68.35 128	66.51 117	77.91 161	75.60 185	84.86 192	85.43 118

viewmsd2359difaftdt		72.49 117	74.10 117	70.61 118	75.87 151	78.53 155	76.92 132	58.16 192	65.69 121	61.33 118	67.21 102	68.34 129	66.51 117	77.91 161	75.60 185	84.86 192	85.42 119

viewmamba		75.22 96	77.49 81	72.57 101	76.60 143	81.01 121	79.77 95	61.77 145	73.47 72	65.40 95	70.61 68	73.19 81	66.50 119	79.78 134	78.52 139	85.35 173	85.88 99

dtuplus		73.53 110	74.92 113	71.90 106	76.10 145	79.51 140	79.17 107	60.44 163	67.27 110	64.19 105	66.90 106	71.30 100	66.48 120	77.95 160	75.99 181	85.02 186	85.54 113

v2v482		70.05 143	69.46 157	70.74 114	74.62 169	80.32 133	79.00 109	60.62 159	57.41 181	56.89 136	55.43 168	55.14 192	66.39 121	77.25 171	77.14 167	86.90 127	83.57 144

v8		70.23 139	69.86 151	70.67 117	74.69 168	79.82 136	78.79 113	59.18 180	58.80 171	58.20 130	55.00 170	57.33 177	66.31 122	77.51 167	76.71 173	86.82 130	83.88 140

onestephybrid01		75.35 94	77.46 83	72.88 98	77.26 138	81.58 110	79.70 99	62.48 136	71.05 86	66.34 91	70.12 74	73.78 75	66.25 123	80.29 123	78.58 137	85.23 181	86.83 83

IterMVS-LS		71.69 125	72.82 131	70.37 124	77.54 135	76.34 181	75.13 149	60.46 162	61.53 156	57.57 132	64.89 115	67.33 132	66.04 124	77.09 174	77.37 164	85.48 169	85.18 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		71.52 127	69.87 150	73.44 96	82.21 77	79.35 142	79.52 101	64.59 88	66.15 116	61.87 113	53.21 192	56.09 186	65.85 125	78.94 149	78.50 140	86.60 140	76.85 205

V42		68.76 157	69.63 154	67.74 152	64.93 233	78.01 159	78.30 121	56.48 205	58.65 172	56.30 140	54.26 179	57.03 180	64.85 126	77.47 168	77.01 169	85.60 165	84.96 128

hybridnocas07		74.37 102	77.06 93	71.23 110	75.13 162	79.34 143	78.54 118	59.23 179	72.65 76	64.95 100	71.17 63	73.19 81	64.72 127	79.45 141	77.65 154	84.81 195	85.97 94

hybrid		74.08 104	76.76 100	70.95 113	74.70 167	79.04 145	78.40 119	58.80 188	72.23 80	64.74 102	70.55 69	73.40 76	64.45 128	79.06 147	77.38 162	84.61 196	85.64 108

EPNet		79.08 59	80.62 56	77.28 54	88.90 38	83.17 91	83.65 58	72.41 34	74.41 63	67.15 87	76.78 36	74.37 70	64.43 129	83.70 63	83.69 56	87.15 118	88.19 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thisisatest0530		71.48 128	73.01 127	69.70 134	73.83 178	78.62 153	74.53 157	59.12 181	64.13 133	58.63 126	64.60 118	58.63 166	64.27 130	80.28 125	80.17 104	87.82 105	84.64 133

tttt0517		71.41 129	72.95 128	69.60 135	73.70 180	78.70 152	74.42 161	59.12 181	63.89 137	58.35 129	64.56 119	58.39 173	64.27 130	80.29 123	80.17 104	87.74 107	84.69 132

RPSCF		67.64 172	71.25 140	63.43 199	61.86 239	70.73 222	67.26 216	50.86 237	74.20 66	58.91 123	67.49 99	69.33 117	64.10 132	71.41 210	68.45 230	77.61 228	77.17 202

LTVRE_ROB	59.44 16	61.82 225	62.64 228	60.87 214	72.83 189	77.19 172	64.37 234	58.97 183	33.56 264	28.00 252	52.59 205	42.21 255	63.93 133	74.52 191	76.28 178	77.15 231	82.13 150
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
MVSTER		72.06 121	74.24 115	69.51 136	70.39 208	75.97 184	76.91 135	57.36 199	64.64 129	61.39 116	68.86 84	63.76 144	63.46 134	81.44 91	79.70 110	87.56 113	85.31 121

PMMVS		65.06 191	69.17 161	60.26 217	55.25 263	63.43 249	66.71 223	43.01 258	62.41 147	50.64 178	69.44 79	67.04 134	63.29 135	74.36 193	73.54 199	82.68 210	73.99 229

IterMVS-SCA-FT		66.89 181	69.22 160	64.17 190	71.30 203	75.64 186	71.33 192	53.17 223	57.63 180	49.08 188	60.72 132	60.05 159	63.09 136	74.99 189	73.92 196	77.07 232	81.57 160

EPP-MVSNet		74.00 106	77.41 85	70.02 130	80.53 104	83.91 77	74.99 152	62.68 131	65.06 125	49.77 184	68.68 88	72.09 88	63.06 137	82.49 80	80.73 87	89.12 62	88.91 61

CHOSEN 280x420		58.70 236	61.88 234	54.98 240	55.45 262	50.55 267	64.92 231	40.36 260	55.21 200	38.13 236	48.31 223	63.76 144	63.03 138	73.73 197	68.58 227	68.00 262	73.04 232

TinyColmap		62.84 208	61.03 237	64.96 184	69.61 213	71.69 218	68.48 212	59.76 174	55.41 198	47.69 200	47.33 231	34.20 266	62.76 139	74.52 191	72.59 205	81.44 214	71.47 234

Fast-Effi-MVS+-dtu		68.34 159	69.47 156	67.01 168	75.15 160	77.97 165	77.12 131	55.40 212	57.87 174	46.68 205	56.17 162	60.39 155	62.36 140	76.32 182	76.25 180	85.35 173	81.34 161

Anonymous20231211		71.90 122	72.48 133	71.21 111	80.14 109	81.53 112	76.92 132	62.89 120	64.46 132	58.94 122	43.80 237	70.98 103	62.22 141	80.70 112	80.19 103	86.18 148	85.73 104

DCV-MVSNet		73.65 108	75.78 107	71.16 112	80.19 108	79.27 144	77.45 129	61.68 148	66.73 113	58.72 125	65.31 113	69.96 113	62.19 142	81.29 97	80.97 82	86.74 134	86.91 80

USDC		67.36 176	67.90 178	66.74 173	71.72 195	75.23 193	71.58 191	60.28 165	67.45 109	50.54 180	60.93 130	45.20 250	62.08 143	76.56 180	74.50 194	84.25 198	75.38 219

Anonymous202405211			72.16 136		80.85 92	81.85 109	76.88 136	65.40 81	62.89 145		46.35 233	67.99 130	62.05 144	81.15 101	80.38 99	85.97 159	84.50 134

MS-PatchMatch		70.17 141	70.49 145	69.79 132	80.98 91	77.97 165	77.51 126	58.95 184	62.33 148	55.22 145	53.14 193	65.90 138	62.03 145	79.08 146	77.11 168	84.08 200	77.91 195

baseline2		69.69 145	70.27 147	69.01 141	75.72 155	77.13 173	73.82 172	58.94 185	61.35 157	57.09 135	61.68 126	57.17 179	61.99 146	78.10 158	76.58 175	86.48 144	79.85 177

v148		67.85 166	67.53 180	68.23 147	73.25 183	77.57 171	74.26 165	57.36 199	55.70 197	57.45 134	53.53 186	55.42 189	61.96 147	75.23 187	73.92 196	85.08 183	81.32 162

pmmvs4		67.89 165	67.39 184	68.48 146	71.60 199	73.57 210	74.45 158	60.98 155	64.65 128	57.97 131	54.95 171	51.73 227	61.88 148	73.78 196	75.11 190	83.99 202	77.91 195

CostFormer		68.92 154	69.58 155	68.15 148	75.98 149	76.17 183	78.22 122	51.86 232	65.80 119	61.56 115	63.57 121	62.83 147	61.85 149	70.40 226	68.67 223	79.42 222	79.62 181

tpm cat1		65.41 187	63.81 217	67.28 163	75.61 157	72.88 212	75.32 143	52.85 226	62.97 143	63.66 110	53.24 191	53.29 217	61.83 150	65.54 246	64.14 248	74.43 246	74.60 222

CANet_DTU		73.29 112	76.96 95	69.00 142	77.04 140	82.06 108	79.49 102	56.30 210	67.85 108	53.29 164	71.12 64	70.37 112	61.81 151	81.59 85	80.96 83	86.09 151	84.73 131

MGCFI-Net		76.55 76	81.71 47	70.52 122	81.71 78	84.62 70	75.02 151	62.17 140	82.91 38	53.58 162	72.78 55	75.87 65	61.75 152	82.96 73	82.61 65	88.86 69	90.26 51

baseline		70.45 137	74.09 119	66.20 176	70.95 205	75.67 185	74.26 165	53.57 219	68.33 104	58.42 127	69.87 76	71.45 94	61.55 153	74.84 190	74.76 193	78.42 226	83.72 142

SCA		65.40 188	66.58 190	64.02 193	70.65 206	73.37 211	67.35 215	53.46 221	63.66 138	54.14 148	60.84 131	60.20 158	61.50 154	69.96 231	68.14 232	77.01 233	69.91 237

GA-MVS		68.14 160	69.17 161	66.93 170	73.77 179	78.50 157	74.45 158	58.28 191	55.11 202	48.44 190	60.08 136	53.99 205	61.50 154	78.43 155	77.57 157	85.13 182	80.54 170

anonymousdsp		65.28 189	67.98 176	62.13 205	58.73 254	73.98 209	67.10 218	50.69 239	48.41 240	47.66 201	54.27 177	52.75 221	61.45 156	76.71 179	80.20 101	87.13 122	89.53 59

v7n		67.05 180	66.94 186	67.17 164	72.35 190	78.97 146	73.26 181	58.88 186	51.16 230	50.90 177	48.21 224	50.11 235	60.96 157	77.70 164	77.38 162	86.68 138	85.05 126

CR-MVSNet		64.83 193	65.54 196	64.01 194	70.64 207	69.41 226	65.97 227	52.74 227	57.81 176	52.65 167	54.27 177	56.31 185	60.92 158	72.20 205	73.09 201	81.12 217	75.69 214

PatchT		61.97 221	64.04 214	59.55 222	60.49 241	67.40 234	56.54 254	48.65 247	56.69 186	52.65 167	51.10 213	52.14 225	60.92 158	72.20 205	73.09 201	78.03 227	75.69 214

dps		64.00 202	62.99 224	65.18 180	73.29 182	72.07 216	68.98 207	53.07 225	57.74 178	58.41 128	55.55 166	47.74 243	60.89 160	69.53 234	67.14 241	76.44 236	71.19 235

IterMVS		66.36 182	68.30 173	64.10 191	69.48 215	74.61 200	73.41 179	50.79 238	57.30 182	48.28 192	60.64 133	59.92 160	60.85 161	74.14 194	72.66 204	81.80 212	78.82 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TDRefinement		66.09 184	65.03 204	67.31 161	69.73 212	76.75 176	75.33 142	64.55 89	60.28 165	49.72 185	45.63 235	42.83 254	60.46 162	75.75 183	75.95 182	84.08 200	78.04 194

PatchmatchNet		64.21 200	64.65 209	63.69 196	71.29 204	68.66 230	69.63 200	51.70 234	63.04 142	53.77 159	59.83 140	58.34 174	60.23 163	68.54 240	66.06 244	75.56 241	68.08 244
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
gm-plane-assit		57.00 240	57.62 247	56.28 235	76.10 145	62.43 255	47.62 266	46.57 253	33.84 263	23.24 258	37.52 249	40.19 259	59.61 164	79.81 133	77.55 158	84.55 197	72.03 233

0.3-1-1-0.015		65.09 190	65.15 201	65.01 183	66.63 226	75.00 196	71.90 188	54.57 216	56.32 192	53.88 153	53.63 185	58.58 168	59.47 165	68.39 242	68.46 229	83.62 204	75.64 216

0.4-1-1-0.1		65.57 186	65.82 193	65.29 179	67.19 220	75.61 187	72.13 187	55.16 214	57.12 183	53.84 157	54.57 173	58.80 165	59.40 166	69.22 237	69.01 220	83.99 202	76.43 208

0.4-1-1-0.2		64.94 192	65.02 205	64.85 185	66.45 227	74.76 197	71.66 189	54.40 217	55.85 196	53.84 157	53.97 182	58.62 167	59.33 167	68.27 243	68.20 231	83.40 206	75.47 218

IB-MVS	66.94 12	71.21 131	71.66 139	70.68 116	79.18 120	82.83 105	72.61 182	61.77 145	59.66 167	63.44 111	53.26 190	59.65 161	59.16 168	76.78 178	82.11 68	87.90 101	87.33 75
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
test2506		71.72 124	72.95 128	70.29 125	81.49 81	83.27 87	75.74 140	67.59 65	68.19 105	49.81 183	61.15 129	49.73 237	58.82 169	84.76 51	82.94 60	88.27 79	80.63 169

ECVR-MVS		72.20 120	73.91 120	70.20 127	81.49 81	83.27 87	75.74 140	67.59 65	68.19 105	49.31 187	55.77 163	62.00 151	58.82 169	84.76 51	82.94 60	88.27 79	80.41 173

dtuonly		61.60 227	64.61 211	58.09 227	59.71 244	62.36 256	72.50 184	42.52 259	58.12 173	43.84 222	54.51 174	62.39 150	58.60 171	71.88 208	69.50 215	71.34 255	73.52 231

UniMVSNet_NR-MVSNet		70.59 135	72.19 134	68.72 143	77.72 133	80.72 126	73.81 173	69.65 48	61.99 150	43.23 223	60.54 134	57.50 176	58.57 172	79.56 138	81.07 81	89.34 54	83.97 137

DU-MVS		69.63 146	70.91 142	68.13 149	75.99 147	79.54 138	73.81 173	69.20 53	61.20 159	43.23 223	58.52 146	53.50 209	58.57 172	79.22 144	80.45 98	87.97 97	83.97 137

COLMAP_ROB	62.73 15	67.66 170	66.76 188	68.70 144	80.49 105	77.98 163	75.29 144	62.95 119	63.62 139	49.96 181	47.32 232	50.72 232	58.57 172	76.87 176	75.50 189	84.94 190	75.33 220
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PM-MVS		60.48 230	60.94 238	59.94 218	58.85 252	66.83 237	64.27 235	51.39 235	55.03 204	48.03 193	50.00 218	40.79 258	58.26 175	69.20 238	67.13 242	78.84 225	77.60 199

SixPastTwentyTwo		61.84 223	62.45 230	61.12 213	69.20 216	72.20 215	62.03 243	57.40 197	46.54 247	38.03 237	57.14 159	41.72 256	58.12 176	69.67 233	71.58 208	81.94 211	78.30 188

thisisatest0515		67.40 175	68.78 165	65.80 178	70.02 210	75.24 192	69.36 202	57.37 198	54.94 206	53.67 160	55.53 167	54.85 197	58.00 177	78.19 157	78.91 133	86.39 145	83.78 141

test1111		71.56 126	73.44 123	69.38 138	81.16 86	82.95 101	74.99 152	67.68 63	66.89 112	46.33 207	55.19 169	60.91 154	57.99 178	84.59 54	82.70 64	88.12 86	80.85 166

CMPMVS	47.78 17	62.49 215	62.52 229	62.46 202	70.01 211	70.66 223	62.97 239	51.84 233	51.98 222	56.71 138	42.87 239	53.62 206	57.80 179	72.23 203	70.37 212	75.45 243	75.91 211
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GBi-Net		70.78 132	73.37 125	67.76 150	72.95 185	78.00 160	75.15 146	62.72 126	64.13 133	51.44 172	58.37 149	69.02 120	57.59 180	81.33 94	80.72 88	86.70 135	82.02 151

test1		70.78 132	73.37 125	67.76 150	72.95 185	78.00 160	75.15 146	62.72 126	64.13 133	51.44 172	58.37 149	69.02 120	57.59 180	81.33 94	80.72 88	86.70 135	82.02 151

FMVSNet2		70.39 138	72.67 132	67.72 153	72.95 185	78.00 160	75.15 146	62.69 130	63.29 141	51.25 176	55.64 164	68.49 127	57.59 180	80.91 105	80.35 100	86.70 135	82.02 151

FMVSNet3		70.49 136	72.90 130	67.67 155	72.88 188	77.98 163	74.96 155	62.72 126	64.13 133	51.44 172	58.37 149	69.02 120	57.43 183	79.43 142	79.57 116	86.59 141	81.81 158

MDTV_nov1_ep13		64.37 197	65.24 198	63.37 200	68.94 217	70.81 221	72.40 186	50.29 241	60.10 166	53.91 152	60.07 137	59.15 163	57.21 184	69.43 236	67.30 239	77.47 229	69.78 239

FMVSNet1		68.84 155	70.47 146	66.94 169	71.35 202	77.68 168	74.71 156	62.35 138	56.93 185	49.94 182	50.01 216	64.59 141	57.07 185	81.33 94	80.72 88	86.25 146	82.00 154

dtuonlycased		57.34 238	58.57 243	55.91 236	58.42 255	71.89 217	66.93 219	44.93 256	50.31 233	32.39 245	37.40 250	54.78 198	57.03 186	60.42 256	60.80 254	75.75 238	74.39 224

UniMVSNet_ETH3D		67.18 179	67.03 185	67.36 160	74.44 171	78.12 158	74.07 168	66.38 71	52.22 220	46.87 202	48.64 222	51.84 226	56.96 187	77.29 170	78.53 138	85.42 171	82.59 148

pmmvs-eth3d		63.52 203	62.44 231	64.77 186	66.82 225	70.12 225	69.41 201	59.48 176	54.34 211	52.71 166	46.24 234	44.35 252	56.93 188	72.37 200	73.77 198	83.30 207	75.91 211

FC-MVSNet-train		72.60 116	75.07 111	69.71 133	81.10 90	78.79 151	73.74 175	65.23 84	66.10 117	53.34 163	70.36 72	63.40 146	56.92 189	81.44 91	80.96 83	87.93 99	84.46 135

tfpn200view9		68.11 161	68.72 167	67.40 159	77.83 131	78.93 147	74.28 163	62.81 122	56.64 187	46.82 203	52.65 203	53.47 212	56.59 190	80.41 118	78.43 141	86.11 149	80.52 171

thres400		67.95 164	68.62 169	67.17 164	77.90 128	78.59 154	74.27 164	62.72 126	56.34 191	45.77 213	53.00 195	53.35 215	56.46 191	80.21 128	78.43 141	85.91 161	80.43 172

thres200		67.98 163	68.55 170	67.30 162	77.89 130	78.86 149	74.18 167	62.75 124	56.35 190	46.48 206	52.98 196	53.54 208	56.46 191	80.41 118	77.97 148	86.05 154	79.78 179

usedtu_blend_shiyan5		64.27 198	64.70 208	63.77 195	59.06 247	74.03 205	71.65 190	56.37 206	51.17 226	53.88 153	52.71 200	58.58 168	56.43 193	70.13 227	68.14 232	85.26 176	78.14 192

blend_shiyan4		64.82 194	65.21 199	64.37 189	65.04 230	74.06 204	70.30 197	55.30 213	55.39 199	53.88 153	52.71 200	58.58 168	56.43 193	69.45 235	68.13 237	85.30 175	78.14 192

FE-MVSNET3		64.07 201	64.71 207	63.32 201	59.06 247	74.03 205	68.92 208	56.37 206	51.17 226	53.88 153	52.71 200	58.58 168	56.43 193	70.13 227	68.14 232	85.26 176	78.20 189

MVS-HIRNet		54.41 246	52.10 254	57.11 232	58.99 251	56.10 262	49.68 264	49.10 244	46.18 248	52.15 171	33.18 258	46.11 247	56.10 196	63.19 253	59.70 257	76.64 235	60.25 258

Baseline_NR-MVSNet		67.53 174	68.77 166	66.09 177	75.99 147	74.75 198	72.43 185	68.41 57	61.33 158	38.33 235	51.31 211	54.13 204	56.03 197	79.22 144	78.19 145	85.37 172	82.45 149

thres100view900		67.60 173	68.02 175	67.12 166	77.83 131	77.75 167	73.90 170	62.52 134	56.64 187	46.82 203	52.65 203	53.47 212	55.92 198	78.77 151	77.62 155	85.72 162	79.23 183

test-mter		60.84 229	64.62 210	56.42 234	55.99 261	64.18 243	65.39 229	34.23 264	54.39 210	46.21 209	57.40 158	59.49 162	55.86 199	71.02 217	69.65 214	80.87 219	76.20 210

tpmrst		62.00 220	62.35 232	61.58 209	71.62 198	64.14 244	69.07 204	48.22 251	62.21 149	53.93 151	58.26 153	55.30 191	55.81 200	63.22 252	62.62 251	70.85 256	70.70 236

TranMVSNet+NR-MVSNet		69.25 151	70.81 143	67.43 158	77.23 139	79.46 141	73.48 178	69.66 47	60.43 164	39.56 231	58.82 145	53.48 211	55.74 201	79.59 136	81.21 79	88.89 67	82.70 147

thres600view7		67.68 169	68.43 171	66.80 171	77.90 128	78.86 149	73.84 171	62.75 124	56.07 194	44.70 220	52.85 198	52.81 219	55.58 202	80.41 118	77.77 151	86.05 154	80.28 174

Vis-MVSNet		72.77 115	77.20 91	67.59 157	74.19 173	84.01 76	76.61 139	61.69 147	60.62 163	50.61 179	70.25 73	71.31 99	55.57 203	83.85 61	82.28 66	86.90 127	88.08 67
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		67.24 177	66.94 186	67.60 156	78.73 123	81.35 115	73.28 180	59.49 175	46.89 246	51.42 175	43.65 238	53.49 210	55.50 204	81.38 93	80.66 94	87.15 118	81.17 163

test-LLR		64.42 196	64.36 212	64.49 188	75.02 163	63.93 246	66.61 224	61.96 142	54.41 208	47.77 198	57.46 156	60.25 156	55.20 205	70.80 218	69.33 216	80.40 220	74.38 225

TESTMET0.1,1		61.10 228	64.36 212	57.29 230	57.53 256	63.93 246	66.61 224	36.22 263	54.41 208	47.77 198	57.46 156	60.25 156	55.20 205	70.80 218	69.33 216	80.40 220	74.38 225

wanda-best-256-512		62.84 208	63.46 221	62.12 206	59.06 247	74.03 205	68.92 208	56.37 206	51.17 226	48.02 194	48.12 225	54.93 195	55.08 207	70.13 227	68.14 232	85.26 176	77.73 197

FE-blended-shiyan7		62.84 208	63.46 221	62.12 206	59.06 247	74.03 205	68.92 208	56.37 206	51.17 226	48.02 194	48.12 225	54.93 195	55.08 207	70.13 227	68.14 232	85.26 176	77.73 197

blended_shiyan8		62.98 205	63.65 219	62.21 203	59.20 245	74.17 202	69.03 206	56.52 203	51.08 232	47.96 196	48.07 228	55.02 193	55.00 209	70.43 224	68.60 225	85.52 166	78.15 191

blended_shiyan6		62.98 205	63.66 218	62.19 204	59.20 245	74.17 202	69.04 205	56.52 203	51.09 231	47.91 197	48.11 227	55.02 193	54.98 210	70.43 224	68.59 226	85.51 167	78.20 189

dmvs_re		67.22 178	67.92 177	66.40 175	75.94 150	70.55 224	74.97 154	63.87 96	57.07 184	44.75 218	54.29 176	56.72 182	54.65 211	79.53 139	77.51 159	84.20 199	79.78 179

UA-Net		74.47 101	77.80 75	70.59 121	85.33 56	85.40 63	73.54 176	65.98 77	60.65 162	56.00 141	72.11 57	79.15 49	54.63 212	83.13 72	82.25 67	88.04 92	81.92 157

IS_MVSNet		73.33 111	77.34 87	68.65 145	81.29 84	83.47 85	74.45 158	63.58 101	65.75 120	48.49 189	67.11 105	70.61 109	54.63 212	84.51 55	83.58 57	89.48 52	86.34 91

baseline1		70.10 142	72.17 135	67.69 154	79.74 114	76.80 175	73.91 169	64.38 90	62.74 146	48.30 191	64.94 114	64.08 143	54.17 214	81.46 89	78.92 132	85.66 164	76.22 209

usedtu_dtu_shiyan1		66.26 183	68.15 174	64.06 192	67.01 221	76.52 179	70.61 196	61.10 150	61.86 152	44.86 216	49.77 219	56.69 183	53.97 215	77.58 166	77.88 149	86.80 132	76.78 206

gbinet_0.2-2-1-0.02		62.72 211	63.87 216	61.39 211	57.04 258	74.70 199	69.09 203	57.36 199	47.91 241	45.94 212	47.47 230	55.96 188	53.90 216	71.07 215	68.83 222	84.99 188	81.15 164

tpm		62.41 216	63.15 223	61.55 210	72.24 191	63.79 248	71.31 193	46.12 255	57.82 175	55.33 143	59.90 139	54.74 199	53.63 217	67.24 245	64.29 247	70.65 257	74.25 228

MDTV_nov1_ep13_2view		60.16 231	60.51 240	59.75 219	65.39 229	69.05 229	68.00 213	48.29 249	51.99 221	45.95 211	48.01 229	49.64 238	53.39 218	68.83 239	66.52 243	77.47 229	69.55 240

UniMVSNet (Re)		69.53 147	71.90 137	66.76 172	76.42 144	80.93 122	72.59 183	68.03 60	61.75 154	41.68 228	58.34 152	57.23 178	53.27 219	79.53 139	80.62 96	88.57 74	84.90 129

RPMNet		61.71 226	62.88 225	60.34 216	69.51 214	69.41 226	63.48 237	49.23 243	57.81 176	45.64 214	50.51 214	50.12 234	53.13 220	68.17 244	68.49 228	81.07 218	75.62 217

tfpnnormal		64.27 198	63.64 220	65.02 182	75.84 154	75.61 187	71.24 194	62.52 134	47.79 242	42.97 225	42.65 240	44.49 251	52.66 221	78.77 151	76.86 170	84.88 191	79.29 182

MDA-MVSNet-bldmvs		53.37 249	53.01 253	53.79 244	43.67 268	67.95 233	59.69 249	57.92 195	43.69 250	32.41 244	41.47 242	27.89 272	52.38 222	56.97 263	65.99 245	76.68 234	67.13 245

NR-MVSNet		68.79 156	70.56 144	66.71 174	77.48 136	79.54 138	73.52 177	69.20 53	61.20 159	39.76 230	58.52 146	50.11 235	51.37 223	80.26 126	80.71 92	88.97 65	83.59 143

EPMVS		60.00 232	61.97 233	57.71 229	68.46 218	63.17 252	64.54 233	48.23 250	63.30 140	44.72 219	60.19 135	56.05 187	50.85 224	65.27 249	62.02 252	69.44 259	63.81 252

CVMVSNet		62.55 213	65.89 191	58.64 225	66.95 223	69.15 228	66.49 226	56.29 211	52.46 219	32.70 243	59.27 143	58.21 175	50.09 225	71.77 209	71.39 209	79.31 223	78.99 185

pmmvs5		62.37 219	64.04 214	60.42 215	65.03 231	71.67 219	67.17 217	52.70 229	50.30 234	44.80 217	54.23 180	51.19 230	49.37 226	72.88 199	73.48 200	83.45 205	74.55 223

UGNet		72.78 114	77.67 76	67.07 167	71.65 197	83.24 89	75.20 145	63.62 100	64.93 126	56.72 137	71.82 59	73.30 77	49.02 227	81.02 103	80.70 93	86.22 147	88.67 63
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
pm-mvs1		65.62 185	67.42 182	63.53 198	73.66 181	76.39 180	69.66 199	60.87 157	49.73 237	43.97 221	51.24 212	57.00 181	48.16 228	79.89 132	77.84 150	84.85 194	79.82 178

gg-mvs-nofinetune		62.55 213	65.05 203	59.62 221	78.72 124	77.61 169	70.83 195	53.63 218	39.71 259	22.04 262	36.36 253	64.32 142	47.53 229	81.16 100	79.03 130	85.00 187	77.17 202

pmmvs6		62.41 216	62.88 225	61.87 208	71.38 201	75.18 195	67.76 214	59.45 177	41.64 254	42.52 227	37.33 251	52.91 218	46.87 230	77.67 165	76.26 179	83.23 208	79.18 184

ADS-MVSNet		55.94 243	58.01 244	53.54 245	62.48 238	58.48 259	59.12 251	46.20 254	59.65 168	42.88 226	52.34 207	53.31 216	46.31 231	62.00 254	60.02 256	64.23 264	60.24 259

pmmvs3		47.65 254	49.08 259	45.99 254	44.61 266	54.79 263	50.04 262	31.95 267	33.91 262	29.90 247	30.37 260	33.53 267	46.31 231	63.50 250	63.67 249	73.14 251	63.77 253

TransMVSNet (Re)		64.74 195	65.66 195	63.66 197	77.40 137	75.33 191	69.86 198	62.67 132	47.63 243	41.21 229	50.01 216	52.33 222	45.31 233	79.57 137	77.69 153	85.49 168	77.07 204

FE-MVSNET2		58.78 235	60.53 239	56.73 233	57.08 257	72.23 214	62.74 242	59.35 178	47.17 244	30.52 246	34.62 256	43.62 253	44.57 234	75.24 186	76.57 176	86.11 149	74.30 227

CDS-MVSNet		67.65 171	69.83 152	65.09 181	75.39 159	76.55 178	74.42 161	63.75 97	53.55 213	49.37 186	59.41 142	62.45 148	44.44 235	79.71 135	79.82 109	83.17 209	77.36 201
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		59.58 233	62.81 227	55.81 237	66.03 228	65.64 242	63.86 236	48.74 246	49.95 236	37.07 239	54.77 172	58.54 172	44.44 235	72.29 202	71.79 206	74.70 245	66.66 246

EPNet_dtu		68.08 162	71.00 141	64.67 187	79.64 116	68.62 231	75.05 150	63.30 104	66.36 115	45.27 215	67.40 100	66.84 136	43.64 237	75.37 185	74.98 192	81.15 216	77.44 200
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		57.24 239	60.02 241	53.99 243	56.45 260	62.74 253	65.27 230	47.03 252	55.14 201	39.55 232	40.88 244	53.42 214	41.83 238	72.35 201	71.10 211	73.79 248	64.50 251

ambc			53.42 251		64.99 232	63.36 250	49.96 263		47.07 245	37.12 238	28.97 262	16.36 275	41.82 239	75.10 188	67.34 238	71.55 254	75.72 213

FPMVS		51.87 251	50.00 257	54.07 242	66.83 224	57.25 260	60.25 248	50.91 236	50.25 235	34.36 241	36.04 254	32.02 268	41.49 240	58.98 260	56.07 259	70.56 258	59.36 260

CP-MVSNet		62.68 212	65.49 197	59.40 223	71.84 193	75.34 190	62.87 240	67.04 68	52.64 217	27.19 253	53.38 188	48.15 241	41.40 241	71.26 211	75.68 184	86.07 152	82.00 154

PS-CasMVS		62.38 218	65.06 202	59.25 224	71.73 194	75.21 194	62.77 241	66.99 69	51.94 224	26.96 254	52.00 208	47.52 244	41.06 242	71.16 214	75.60 185	85.97 159	81.97 156

PEN-MVS		62.96 207	65.77 194	59.70 220	73.98 176	75.45 189	63.39 238	67.61 64	52.49 218	25.49 255	53.39 187	49.12 239	40.85 243	71.94 207	77.26 166	86.86 129	80.72 168

MIMVSNet		58.52 237	61.34 236	55.22 239	60.76 240	67.01 236	66.81 221	49.02 245	56.43 189	38.90 233	40.59 247	54.54 201	40.57 244	73.16 198	71.65 207	75.30 244	66.00 247

pmnet_mix02		55.30 244	57.01 248	53.30 246	64.14 234	59.09 258	58.39 253	50.24 242	53.47 214	38.68 234	49.75 220	45.86 248	40.14 245	65.38 248	60.22 255	68.19 261	65.33 249

Vis-MVSNet (Re-imp)		67.83 167	73.52 122	61.19 212	78.37 126	76.72 177	66.80 222	62.96 118	65.50 123	34.17 242	67.19 104	69.68 116	39.20 246	79.39 143	79.44 121	85.68 163	76.73 207

FE-MVSNET		52.98 250	55.99 250	49.47 250	49.71 264	65.83 239	54.09 257	56.91 202	40.70 256	16.86 270	32.90 259	40.15 260	37.83 247	69.80 232	73.04 203	81.41 215	69.49 241

DTE-MVSNet		61.85 222	64.96 206	58.22 226	74.32 172	74.39 201	61.01 245	67.85 62	51.76 225	21.91 263	53.28 189	48.17 240	37.74 248	72.22 204	76.44 177	86.52 143	78.49 187

EU-MVSNet		54.63 245	58.69 242	49.90 249	56.99 259	62.70 254	56.41 255	50.64 240	45.95 249	23.14 259	50.42 215	46.51 246	36.63 249	65.51 247	64.85 246	75.57 240	74.91 221

Anonymous20231206		56.36 242	57.80 246	54.67 241	70.08 209	66.39 238	60.46 247	57.54 196	49.50 239	29.30 250	33.86 257	46.64 245	35.18 250	70.44 222	68.88 221	75.47 242	68.88 243

WR-MVS		63.03 204	67.40 183	57.92 228	75.14 161	77.60 170	60.56 246	66.10 74	54.11 212	23.88 256	53.94 183	53.58 207	34.50 251	73.93 195	77.71 152	87.35 116	80.94 165

usedtu_dtu_shiyan2		49.27 252	50.47 255	47.86 252	35.37 272	64.10 245	58.53 252	53.10 224	31.42 267	29.57 248	27.09 265	38.06 264	34.31 252	63.35 251	63.36 250	76.27 237	65.93 248

WR-MVS_H		61.83 224	65.87 192	57.12 231	71.72 195	76.87 174	61.45 244	66.19 72	51.97 223	22.92 260	53.13 194	52.30 224	33.80 253	71.03 216	75.00 191	86.65 139	80.78 167

PMVS	39.38 18	46.06 258	43.30 261	49.28 251	62.93 235	38.75 269	41.88 268	53.50 220	33.33 265	35.46 240	28.90 263	31.01 269	33.04 254	58.61 262	54.63 263	68.86 260	57.88 261
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test0.0.03 1		58.80 234	61.58 235	55.56 238	75.02 163	68.45 232	59.58 250	61.96 142	52.74 216	29.57 248	49.75 220	54.56 200	31.46 255	71.19 212	69.77 213	75.75 238	64.57 250

PatchmatchNet1												40.11 261	29.66 256	59.57 258	55.18 260	57.66 265	53.88 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		47.35 255	50.13 256	44.11 256	59.98 242	51.64 265	51.86 261	44.80 257	49.58 238	20.76 265	40.65 245	40.05 262	29.64 257	59.84 257	55.15 261	57.63 266	54.00 262

DeepMVS_CX						18.74 275	18.55 274	8.02 269	26.96 268	7.33 273	23.81 267	13.05 276	25.99 258	25.17 269		22.45 276	36.25 269

MIMVSNet1		49.27 252	53.25 252	44.62 255	44.61 266	61.52 257	53.61 258	52.18 230	41.62 255	18.68 267	28.14 264	41.58 257	25.50 259	68.46 241	69.04 218	73.15 250	62.37 256

Gipuma		36.38 261	35.80 263	37.07 258	45.76 265	33.90 270	29.81 270	48.47 248	39.91 258	18.02 268	8.00 275	8.14 279	25.14 260	59.29 259	61.02 253	55.19 268	40.31 266
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testgi		54.39 247	57.86 245	50.35 248	71.59 200	67.24 235	54.95 256	53.25 222	43.36 251	23.78 257	44.64 236	47.87 242	24.96 261	70.45 221	68.66 224	73.60 249	62.78 255

new_pmnet		38.40 260	42.64 262	33.44 260	37.54 271	45.00 268	36.60 269	32.72 266	40.27 257	12.72 271	29.89 261	28.90 270	24.78 262	53.17 264	52.90 264	56.31 267	48.34 264

FC-MVSNet-test		56.90 241	65.20 200	47.21 253	66.98 222	63.20 251	49.11 265	58.60 189	59.38 169	11.50 272	65.60 111	56.68 184	24.66 263	71.17 213	71.36 210	72.38 252	69.02 242

test20.03		53.93 248	56.28 249	51.19 247	72.19 192	65.83 239	53.20 259	61.08 151	42.74 252	22.08 261	37.07 252	45.76 249	24.29 264	70.44 222	69.04 218	74.31 247	63.05 254

EMVS		20.98 265	17.15 269	25.44 262	39.51 270	19.37 274	12.66 275	39.59 262	19.10 270	6.62 275	9.27 273	4.40 282	22.43 265	17.99 271	24.40 269	31.81 273	25.53 272

E-PMN		21.77 264	18.24 267	25.89 261	40.22 269	19.58 273	12.46 276	39.87 261	18.68 271	6.71 274	9.57 272	4.31 283	22.36 266	19.89 270	27.28 268	33.73 272	28.34 271

new-patchmatchnet		46.97 256	49.47 258	44.05 257	62.82 236	56.55 261	45.35 267	52.01 231	42.47 253	17.04 269	35.73 255	35.21 265	21.84 267	61.27 255	54.83 262	65.26 263	60.26 257

test_method		22.26 263	25.94 265	17.95 265	3.24 277	7.17 277	23.83 272	7.27 270	37.35 261	20.44 266	21.87 269	39.16 263	18.67 268	34.56 266	20.84 270	34.28 271	20.64 274

MVE	19.12 19	20.47 266	23.27 266	17.20 266	12.66 275	25.41 272	10.52 277	34.14 265	14.79 274	6.53 276	8.79 274	4.68 281	16.64 269	29.49 268	41.63 265	22.73 275	38.11 267
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		11.35 267	17.29 268	4.42 268	6.68 276	7.99 276	2.60 280	0.92 272	16.92 272	0.48 280	22.62 268	12.56 277	9.83 270	17.93 272	14.55 271	6.00 277	28.50 270

MVS_clip		8.39 268	13.78 270	2.10 269	1.74 279	3.70 279	1.20 281	0.34 273	14.88 273	0.07 282	20.38 270	11.54 278	7.32 271	13.39 273	11.44 272	1.94 278	21.14 273

WB-MVS		40.01 259	45.06 260	34.13 259	58.84 253	53.28 264	28.60 271	58.10 194	32.93 266	4.65 277	40.92 243	28.33 271	7.26 272	58.86 261	56.09 258	47.36 269	44.98 265

PMMVS2		25.60 262	29.75 264	20.76 264	28.00 273	30.93 271	23.10 273	29.18 268	23.14 269	1.46 278	18.23 271	16.54 274	5.08 273	40.22 265	41.40 266	37.76 270	37.79 268

tmp_tt				14.50 267	14.68 274	7.17 277	10.46 278	2.21 271	37.73 260	28.71 251	25.26 266	16.98 273	4.37 274	31.49 267	29.77 267	26.56 274

VLMVS		3.55 269	5.54 271	1.24 270	1.79 278	2.25 280	0.89 282	0.17 274	6.40 275	0.53 279	5.78 276	7.21 280	2.77 275	3.56 274	2.98 273	1.27 279	10.57 276

MVS_baseline		2.20 270	3.80 272	0.33 271	0.11 280	0.12 281	0.03 284	0.00 278	3.77 276	0.00 284	5.12 277	3.54 284	1.81 276	1.56 275	1.72 274	0.01 280	10.79 275

GG-mvs-BLEND		46.86 257	67.51 181	22.75 263	0.05 281	76.21 182	64.69 232	0.04 275	61.90 151	0.09 281	55.57 165	71.32 98	0.08 277	70.54 220	67.19 240	71.58 253	69.86 238

test123		0.09 271	0.14 274	0.02 272	0.00 283	0.02 282	0.02 285	0.01 276	0.09 278	0.00 284	0.30 278	0.00 286	0.08 277	0.03 277	0.09 276	0.01 280	0.45 277

testmvs		0.09 271	0.15 273	0.02 272	0.01 282	0.02 282	0.05 283	0.01 276	0.11 277	0.01 283	0.26 279	0.01 285	0.06 279	0.10 276	0.10 275	0.01 280	0.43 278

uanet_test		0.00 273	0.00 275	0.00 274	0.00 283	0.00 284	0.00 286	0.00 278	0.00 279	0.00 284	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 283	0.00 284	0.00 286	0.00 278	0.00 279	0.00 284	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 283	0.00 284	0.00 286	0.00 278	0.00 279	0.00 284	0.00 280	0.00 286	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

PatchmatchNet2					59.93 243	50.56 266	52.11 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										20.85 264	40.60 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							91.33 7	75.06 15		80.35 16						91.03 7

RE-MVS-def										46.24 208

9.14												86.88 18

SR-MVS					88.99 37			73.57 27				87.54 16

our_test_3					67.93 219	70.99 220	66.89 220

MTAPA										83.48 1		86.45 21

MTMP										82.66 5		84.91 29

Patchmatch-RL test							2.85 279

XVS					86.63 49	88.68 29	85.00 51			71.81 50		81.92 40				90.47 26

X-MVStestdata					86.63 49	88.68 29	85.00 51			71.81 50		81.92 40				90.47 26

mPP-MVS					89.90 28							81.29 45

NP-MVS									80.10 50

Patchmtry						65.80 241	65.97 227	52.74 227		52.65 167

High-resolution multi-view benchmark