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.

SED-MVS		95.53 1	95.79 1	95.23 1	97.60 10	98.92 1	95.99 5	92.05 7	97.14 1	94.19 1	94.71 6	93.25 2	95.08 1	94.32 11	92.59 15	96.49 18	99.58 3

DPE-MVS		95.10 2	95.53 2	94.60 5	97.77 8	98.64 5	96.60 4	92.45 5	96.34 6	91.41 6	96.70 2	92.26 6	93.56 6	93.68 18	91.73 30	95.79 39	99.37 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.06 3	95.37 4	94.70 3	97.59 11	98.89 2	95.37 12	92.04 8	96.85 3	94.00 2	92.81 14	93.02 3	92.93 7	94.22 14	92.15 21	96.30 25	99.61 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
DVP-MVS++		95.03 4	95.03 5	95.03 2	97.91 6	98.84 3	95.80 6	91.88 10	96.65 5	93.15 3	93.79 8	90.11 12	95.03 2	94.20 16	92.39 16	96.44 22	99.22 10

MSP-MVS		95.00 5	95.47 3	94.45 6	96.78 19	98.11 10	95.72 8	90.91 14	96.68 4	91.57 5	96.98 1	89.47 14	94.76 3	95.24 3	92.15 21	96.98 7	99.64 1
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
CNVR-MVS		94.53 6	94.85 7	94.15 8	98.03 4	98.59 6	95.56 9	92.91 2	94.86 13	88.46 14	91.32 21	90.83 10	94.03 5	95.20 4	94.16 5	95.89 34	99.01 16

SF-MVS		94.40 7	94.15 12	94.70 3	98.25 3	98.24 8	96.86 3	93.46 1	94.87 12	90.26 9	95.96 3	88.42 17	92.76 10	92.29 31	90.84 41	96.62 13	98.44 26

APDe-MVS		94.31 8	94.30 10	94.33 7	97.57 12	98.06 12	95.79 7	91.98 9	95.50 9	92.19 4	95.25 4	87.97 20	92.93 7	93.01 24	91.02 39	95.52 41	99.29 8

MCST-MVS		94.10 9	94.77 8	93.31 10	98.31 2	98.34 7	95.43 10	92.54 4	94.41 16	83.05 31	91.38 19	90.97 9	92.24 14	95.05 6	94.02 6	98.31 1	99.20 11

HPM-MVS++		94.04 10	94.96 6	92.96 12	97.93 5	97.71 18	94.65 15	91.01 13	95.91 7	87.43 16	93.52 11	92.63 5	92.29 13	94.22 14	92.34 18	94.47 63	98.37 27

NCCC		93.59 11	94.00 14	93.10 11	97.90 7	97.93 14	95.40 11	92.39 6	94.47 15	84.94 21	91.21 22	89.32 15	92.53 11	93.90 17	92.98 12	95.44 43	98.22 30

SMA-MVS		93.47 12	94.29 11	92.52 14	97.72 9	97.77 17	94.46 18	90.19 17	94.96 11	87.15 17	90.15 26	90.99 8	91.49 17	94.31 12	93.33 10	94.10 69	98.53 24
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
APD-MVS		93.47 12	93.44 17	93.50 9	97.06 15	97.09 27	95.27 13	91.47 11	95.71 8	89.57 11	93.66 9	86.28 26	92.81 9	92.06 34	90.70 42	94.83 60	98.60 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		93.36 14	94.33 9	92.22 16	94.68 43	97.89 16	94.56 16	90.89 15	94.80 14	90.04 10	93.53 10	90.14 11	89.78 23	92.74 27	92.17 19	93.35 109	99.07 14
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
TSAR-MVS + MP.		93.07 15	93.53 16	92.53 13	94.23 46	97.54 21	94.75 14	89.87 18	95.26 10	89.20 13	93.16 12	88.19 19	92.15 15	91.79 39	89.65 58	94.99 56	99.16 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		92.86 16	93.19 19	92.47 15	95.78 35	97.40 22	97.39 1	92.56 3	92.88 24	81.84 38	81.31 39	92.95 4	91.21 18	96.54 1	97.33 1	96.01 32	93.94 110

SteuartSystems-ACMMP		92.31 17	93.31 18	91.15 22	96.88 17	97.36 23	93.95 22	89.44 20	92.62 25	83.20 28	94.34 7	85.55 28	88.95 30	93.07 23	91.90 26	94.51 62	98.30 28
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 18	92.91 22	91.28 21	96.95 16	97.36 23	93.66 23	89.23 22	93.33 19	83.71 26	90.53 23	86.84 23	90.39 20	93.30 22	91.56 32	93.74 81	97.43 46

HFP-MVS		92.02 19	92.13 24	91.89 19	97.16 14	96.46 39	93.57 24	87.60 25	93.79 18	88.17 15	93.15 13	83.94 38	91.19 19	90.81 49	89.83 53	93.66 85	96.94 61

train_agg		91.99 20	93.71 15	89.98 27	96.42 27	97.03 29	94.31 20	89.05 23	93.33 19	77.75 46	95.06 5	88.27 18	88.38 37	92.02 36	91.41 34	94.00 73	98.84 19

DeepC-MVS_fast	86.59 2	91.69 21	91.39 27	92.05 18	97.43 13	96.92 32	94.05 21	90.23 16	93.31 22	83.19 29	77.91 45	84.23 34	92.42 12	94.62 9	94.83 3	95.00 55	97.88 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + GP.		91.29 22	93.11 21	89.18 32	87.81 89	96.21 45	92.51 33	83.83 44	94.24 17	83.77 25	91.87 18	89.62 13	90.07 21	90.40 54	90.31 46	97.09 6	99.10 13

ACMMPR		91.15 23	91.44 26	90.81 23	96.61 21	96.25 43	93.09 25	87.08 28	93.32 21	84.78 22	92.08 17	82.10 44	89.71 24	90.24 55	89.82 54	93.61 90	96.30 74

DeepPCF-MVS	86.71 1	91.00 24	94.05 13	87.43 43	95.58 38	98.17 9	86.22 74	88.59 24	97.01 2	76.77 54	85.11 35	88.90 16	87.29 44	95.02 7	94.69 4	90.15 180	99.48 6

TSAR-MVS + ACMM		90.98 25	93.18 20	88.42 37	95.69 36	96.73 34	94.52 17	86.97 31	92.99 23	76.32 55	92.31 16	86.64 24	84.40 70	92.97 25	92.02 23	92.62 132	98.59 22

MP-MVS		90.81 26	91.45 25	90.06 26	96.59 22	96.33 42	92.46 34	87.19 27	90.27 39	82.54 34	91.38 19	84.88 31	88.27 38	90.58 52	89.30 63	93.30 111	97.44 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		90.57 27	90.68 29	90.44 24	96.13 29	95.90 51	92.77 30	86.86 32	92.12 29	84.19 23	89.18 29	82.37 42	89.43 27	89.65 67	88.43 74	93.27 112	97.13 54

MSLP-MVS++		90.33 28	88.82 39	92.10 17	96.52 25	95.93 47	94.35 19	86.26 33	88.37 54	89.24 12	75.94 51	82.60 41	89.71 24	89.45 70	92.17 19	96.51 17	97.24 51

CANet		89.98 29	90.42 33	89.47 31	94.13 47	98.05 13	91.76 39	83.27 47	90.87 36	81.90 37	72.32 59	84.82 32	88.42 35	94.52 10	93.78 8	97.34 4	98.58 23

PGM-MVS		89.97 30	90.64 31	89.18 32	96.53 24	95.90 51	93.06 26	82.48 55	90.04 41	80.37 40	92.75 15	80.96 49	88.93 31	89.88 63	89.08 67	93.69 84	95.86 78

PHI-MVS		89.88 31	92.75 23	86.52 53	94.97 40	97.57 20	89.99 50	84.56 40	92.52 27	69.72 88	90.35 25	87.11 22	84.89 62	91.82 38	92.37 17	95.02 54	97.51 42

CSCG		89.81 32	89.69 34	89.96 28	96.55 23	97.90 15	92.89 28	87.06 29	88.74 51	86.17 18	78.24 44	86.53 25	84.75 65	87.82 91	90.59 43	92.32 137	98.01 33

X-MVS		89.73 33	90.65 30	88.66 35	96.44 26	95.93 47	92.26 36	86.98 30	90.73 37	76.32 55	89.56 28	82.05 45	86.51 50	89.98 61	89.60 59	93.43 104	96.72 69

EPNet		89.30 34	90.89 28	87.44 42	95.67 37	96.81 33	91.13 42	83.12 49	91.14 33	76.31 59	87.60 31	80.40 53	84.45 68	92.13 33	91.12 38	93.96 74	97.01 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	84.14 3	88.80 35	88.03 45	89.71 30	94.83 41	96.56 35	92.57 32	89.38 21	89.25 47	79.59 42	70.02 68	77.05 65	88.24 39	92.44 29	92.79 13	93.65 88	98.10 32
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		88.76 36	90.43 32	86.81 49	96.04 31	96.53 38	92.95 27	85.95 35	90.36 38	67.93 94	85.80 34	80.69 50	83.82 73	90.81 49	91.85 29	94.18 67	96.99 59

3Dnovator+	81.14 5	88.59 37	87.49 48	89.88 29	95.83 34	96.45 41	91.94 38	82.41 56	87.09 59	85.94 20	62.80 98	85.37 29	89.46 26	91.51 41	91.89 28	93.72 82	97.30 49

ACMMP		88.48 38	88.71 40	88.22 39	94.61 44	95.53 57	90.64 46	85.60 37	90.97 34	78.62 44	89.88 27	74.20 79	86.29 51	88.16 88	86.37 94	93.57 91	95.86 78
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
AdaColmap		88.46 39	85.75 62	91.62 20	96.25 28	95.35 61	90.71 44	91.08 12	90.22 40	86.17 18	74.33 55	73.67 82	92.00 16	86.31 107	85.82 103	93.52 94	94.53 97

MVS_0304		88.43 40	89.46 36	87.21 44	91.85 59	97.60 19	92.62 31	81.10 62	87.16 58	73.80 66	72.19 61	83.36 40	87.03 45	94.64 8	93.67 9	96.88 9	97.64 41

3Dnovator	80.58 8	88.20 41	86.53 54	90.15 25	96.86 18	96.46 39	91.97 37	83.06 50	85.16 64	83.66 27	62.28 101	82.15 43	88.98 29	90.99 46	92.65 14	96.38 24	96.03 75

CPTT-MVS		88.17 42	87.84 46	88.55 36	93.33 49	93.75 82	92.33 35	84.75 39	89.87 43	81.72 39	83.93 36	81.12 48	88.45 34	85.42 116	84.07 122	90.72 172	96.72 69

MVS_111021_HR		87.82 43	88.84 38	86.62 51	94.42 45	97.36 23	88.21 59	83.26 48	83.42 67	72.52 76	82.63 37	76.93 66	84.95 61	91.93 37	91.15 37	96.39 23	98.49 25

DELS-MVS		87.75 44	86.92 52	88.71 34	94.69 42	97.34 26	92.78 29	84.50 41	77.87 91	81.94 36	67.17 76	75.49 74	82.84 79	95.38 2	95.93 2	95.55 40	99.27 9
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
MVSTER		87.68 45	89.12 37	86.01 55	88.11 87	90.05 119	89.28 53	77.05 87	91.37 30	79.97 41	76.70 49	85.25 30	84.89 62	93.53 19	91.41 34	96.73 11	95.55 85

MVS_111021_LR		87.58 46	88.67 41	86.31 54	92.58 53	95.89 53	86.20 75	82.49 54	89.08 49	77.47 50	86.20 33	74.22 78	85.49 56	90.03 60	88.52 72	93.66 85	96.74 67

QAPM		87.06 47	86.46 55	87.75 40	96.63 20	97.09 27	91.71 40	82.62 53	80.58 80	71.28 81	66.04 83	84.24 33	87.01 46	89.93 62	89.91 52	97.26 5	97.44 44

PVSNet_BlendedMVS		86.98 48	87.05 50	86.90 46	93.03 50	96.98 30	86.57 71	81.82 58	89.78 44	82.78 32	71.54 62	66.07 113	80.73 91	93.46 20	91.97 24	96.45 20	99.53 4

PVSNet_Blended		86.98 48	87.05 50	86.90 46	93.03 50	96.98 30	86.57 71	81.82 58	89.78 44	82.78 32	71.54 62	66.07 113	80.73 91	93.46 20	91.97 24	96.45 20	99.53 4

ETV-MVS		86.94 50	89.49 35	83.95 69	87.28 96	95.61 56	83.58 103	76.37 94	92.59 26	73.20 68	80.35 40	76.42 69	87.38 43	92.20 32	90.45 45	95.90 33	98.83 20

CS-MVS-test		86.72 51	88.35 42	84.83 63	91.78 60	96.03 46	81.71 114	76.71 88	91.19 32	77.12 53	77.64 47	75.63 73	87.59 42	90.82 48	89.11 65	94.06 71	97.99 35

CS-MVS		86.70 52	87.61 47	85.65 56	91.33 64	95.64 55	84.73 91	76.64 90	88.68 52	77.78 45	74.87 52	72.86 86	89.09 28	92.89 26	90.18 49	94.31 66	98.16 31

EC-MVSNet		86.42 53	88.31 43	84.20 67	86.61 103	94.08 76	86.20 75	72.18 125	89.06 50	76.02 60	74.48 54	80.47 52	88.90 32	92.03 35	90.07 50	95.30 44	98.00 34

OMC-MVS		86.38 54	86.21 59	86.57 52	92.30 55	94.35 75	87.60 63	83.51 46	92.32 28	77.37 51	72.27 60	77.83 58	86.59 49	87.62 93	85.95 100	92.08 141	93.11 124

HQP-MVS		86.17 55	87.35 49	84.80 64	91.41 63	92.37 99	91.05 43	84.35 43	88.52 53	64.21 101	87.05 32	68.91 102	84.80 64	89.12 73	88.16 78	92.96 123	97.31 48

canonicalmvs		85.93 56	86.26 58	85.54 57	88.94 77	95.44 58	89.56 51	76.01 96	87.83 55	77.70 47	76.43 50	68.66 104	87.80 41	87.02 96	91.51 33	93.25 113	96.95 60

MAR-MVS		85.65 57	86.30 57	84.88 62	95.51 39	95.89 53	86.50 73	76.71 88	89.23 48	68.59 91	70.93 66	74.49 76	88.55 33	89.40 71	90.30 47	93.42 105	93.88 115
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
PCF-MVS	82.38 4	85.52 58	84.41 67	86.81 49	91.51 62	96.23 44	90.27 47	89.81 19	77.87 91	70.67 84	69.20 70	77.86 56	85.55 55	85.92 112	86.38 93	93.03 120	97.43 46
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		85.43 59	84.24 70	86.83 48	87.69 92	93.16 90	90.01 49	82.72 52	87.17 57	79.28 43	71.43 65	65.81 116	86.02 52	87.33 95	86.96 87	95.25 50	97.83 38
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OpenMVS	77.91 11	85.09 60	83.42 74	87.03 45	96.12 30	96.55 37	89.36 52	81.59 60	79.19 87	75.20 62	55.84 129	79.04 55	84.45 68	88.47 82	89.35 62	95.48 42	95.48 86

TSAR-MVS + COLMAP		84.93 61	85.79 61	83.92 70	90.90 66	93.57 86	89.25 54	82.00 57	91.29 31	61.66 110	88.25 30	59.46 136	86.71 48	89.79 64	87.09 84	93.01 121	91.09 146

TAPA-MVS	80.99 7	84.83 62	84.42 66	85.31 59	91.89 58	93.73 84	88.53 58	82.80 51	89.99 42	69.78 87	71.53 64	75.03 75	85.47 57	86.26 108	84.54 117	93.39 107	89.90 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	81.02 6	84.81 63	81.81 93	88.31 38	93.77 48	90.35 114	88.80 56	84.47 42	86.76 60	82.17 35	66.56 79	71.01 94	88.41 36	85.48 114	84.28 120	92.26 139	88.21 169
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		84.75 64	86.43 56	82.79 75	86.88 99	95.36 60	82.84 110	76.39 93	87.61 56	71.03 82	74.33 55	71.12 93	85.16 58	89.69 66	88.70 71	94.40 64	98.23 29

CNLPA		84.72 65	82.14 87	87.73 41	92.85 52	93.83 81	84.70 92	85.07 38	90.90 35	83.16 30	56.28 125	71.53 90	88.14 40	84.19 121	84.00 126	92.48 134	94.26 104

MVS_Test		84.60 66	85.13 65	83.99 68	88.17 85	95.27 65	88.21 59	73.15 116	84.31 66	70.55 85	68.67 74	68.78 103	86.99 47	91.71 40	91.90 26	96.84 10	95.27 91

casdiffmvs_mvg		83.97 67	82.62 83	85.54 57	87.71 90	94.38 74	88.93 55	80.11 66	77.34 95	77.57 49	63.01 97	65.95 115	84.96 60	90.69 51	90.23 48	93.95 75	96.74 67
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs		83.84 68	82.65 82	85.22 60	87.25 97	94.62 71	86.01 79	79.62 67	79.48 84	77.59 48	61.92 104	64.34 120	85.57 54	90.55 53	90.51 44	95.26 48	97.14 53
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		83.83 69	84.38 68	83.18 74	86.65 101	94.59 72	85.79 82	73.78 113	85.83 62	72.94 69	69.28 69	70.80 96	83.45 76	86.80 99	87.59 80	96.47 19	95.77 82

diffmvs		83.69 70	83.17 78	84.31 65	85.45 115	93.92 77	86.89 66	78.62 70	82.71 73	75.95 61	66.78 78	63.90 123	83.84 72	87.90 90	89.16 64	95.10 53	97.82 39
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CANet_DTU		83.33 71	86.59 53	79.53 99	88.88 78	94.87 68	86.63 70	68.85 148	85.45 63	50.54 156	77.86 46	69.94 99	85.62 53	92.63 28	90.88 40	96.63 12	94.46 98

DI_MVS_plusplus_trai		83.32 72	82.53 85	84.25 66	86.26 109	93.66 85	90.23 48	77.16 86	77.05 99	74.06 65	53.74 138	74.33 77	83.61 75	91.40 43	89.82 54	94.17 68	97.73 40

baseline1		82.63 73	82.02 88	83.34 73	88.30 84	91.89 103	88.03 62	80.86 63	75.05 106	65.96 96	64.27 90	72.20 88	80.01 95	91.32 44	89.56 60	96.90 8	89.85 157

PVSNet_Blended_VisFu		82.55 74	83.70 73	81.21 86	89.66 70	95.15 67	82.41 111	77.36 85	72.53 125	73.64 67	61.15 107	77.19 64	70.35 153	91.31 45	89.72 57	93.84 77	98.85 18

ET-MVSNet_ETH3D		82.37 75	85.68 63	78.51 109	62.90 212	94.66 69	87.06 65	73.57 114	83.13 69	61.52 112	78.37 43	76.01 71	89.99 22	84.14 122	89.03 68	96.03 31	94.42 99

PMMVS		82.26 76	85.48 64	78.51 109	85.92 112	91.92 102	78.30 142	70.77 133	86.30 61	61.11 114	82.46 38	70.88 95	84.70 66	88.05 89	84.78 113	90.24 179	93.98 108

ACMP	79.58 9	82.23 77	81.82 92	82.71 76	88.15 86	90.95 111	85.23 87	78.52 72	81.70 75	72.52 76	78.41 42	60.63 131	80.48 93	82.88 133	83.44 130	91.37 158	94.70 95
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CHOSEN 280x420		82.15 78	85.87 60	77.80 114	86.54 105	93.42 88	81.74 113	59.96 190	78.99 89	63.99 102	74.50 53	83.95 37	80.99 86	89.53 69	85.01 108	93.56 93	95.71 84

LGP-MVS_train		82.12 79	82.57 84	81.59 82	89.26 74	90.23 117	88.76 57	78.05 73	81.26 77	61.64 111	79.52 41	62.11 126	79.59 97	85.20 117	84.68 115	92.27 138	95.02 93

FMVSNet3		81.93 80	81.98 89	81.88 81	79.49 152	87.02 135	88.15 61	72.57 119	83.02 70	72.63 73	56.55 121	73.48 83	82.34 82	91.49 42	91.20 36	96.07 27	91.13 145

test2506		81.91 81	81.78 95	82.06 80	89.09 75	95.32 62	84.61 94	77.54 81	74.61 110	68.77 90	63.80 94	67.53 107	77.09 106	90.19 57	89.01 69	95.27 45	92.00 137

thisisatest0530		81.67 82	84.27 69	78.63 105	85.53 113	93.88 80	81.77 112	73.84 110	81.35 76	63.85 104	68.79 72	77.64 60	73.02 134	88.73 80	85.73 104	93.76 80	93.80 119

tttt0517		81.51 83	84.12 72	78.47 111	85.33 117	93.74 83	81.42 117	73.84 110	81.21 78	63.59 105	68.73 73	77.46 63	73.02 134	88.47 82	85.73 104	93.63 89	93.49 123

FA-MVS(training)		81.41 84	81.98 89	80.76 92	87.58 93	94.59 72	83.09 105	61.18 187	79.80 83	74.74 63	58.46 113	69.76 100	82.12 83	88.90 76	87.00 85	95.83 37	95.33 88

OPM-MVS		81.34 85	78.18 111	85.02 61	91.27 65	91.78 104	90.66 45	83.62 45	62.39 154	65.91 97	63.35 95	64.33 121	85.03 59	87.77 92	85.88 102	93.66 85	91.75 141
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		81.21 86	83.36 77	78.70 103	83.22 130	92.71 92	80.32 123	74.25 109	80.39 81	63.94 103	68.89 71	68.44 105	74.67 120	89.61 68	86.68 91	95.83 37	96.81 66

IS_MVSNet		80.92 87	84.14 71	77.16 117	87.43 94	93.90 79	80.44 119	74.64 103	75.05 106	61.10 115	65.59 85	76.89 67	67.39 161	90.88 47	90.05 51	91.95 145	96.62 72

ACMM	78.09 10	80.91 88	78.39 108	83.86 71	89.61 73	87.71 132	85.16 88	80.67 65	79.04 88	74.18 64	63.82 93	60.84 130	82.59 80	84.33 119	83.59 129	90.96 166	89.39 162
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		80.82 89	82.79 80	78.52 107	86.31 108	92.37 99	79.83 126	74.51 104	73.79 117	64.46 100	67.01 77	80.63 51	74.33 123	85.63 113	84.35 119	91.68 151	95.79 81

CostFormer		80.72 90	81.81 93	79.44 101	86.50 106	91.65 105	84.31 96	59.84 191	80.86 79	72.69 71	62.46 100	73.74 80	79.93 96	82.58 137	84.50 118	93.37 108	96.90 64

GBi-Net		80.72 90	80.49 97	81.00 89	78.18 156	86.19 149	86.73 67	72.57 119	83.02 70	72.63 73	56.55 121	73.48 83	80.99 86	86.57 101	86.83 88	94.89 57	90.77 149

test1		80.72 90	80.49 97	81.00 89	78.18 156	86.19 149	86.73 67	72.57 119	83.02 70	72.63 73	56.55 121	73.48 83	80.99 86	86.57 101	86.83 88	94.89 57	90.77 149

UGNet		80.71 93	83.09 79	77.93 113	87.02 98	92.71 92	80.28 124	76.53 91	73.83 116	71.35 80	70.07 67	73.71 81	58.93 181	87.39 94	86.97 86	93.48 101	96.94 61
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
CHOSEN 1792x2688		80.23 94	79.16 105	81.48 84	91.97 56	96.56 35	86.18 77	75.40 100	76.17 102	61.32 113	37.43 199	61.08 129	76.52 112	92.35 30	91.64 31	97.46 3	98.86 17

thres100view900		79.83 95	77.79 115	82.21 77	88.42 81	93.54 87	87.07 64	81.11 61	70.15 132	61.01 116	56.65 119	51.22 153	81.78 84	89.77 65	85.95 100	93.84 77	97.26 50

Effi-MVS+		79.80 96	80.04 99	79.52 100	85.53 113	93.31 89	85.28 85	70.68 135	74.15 112	58.79 125	62.03 103	60.51 132	83.37 77	88.41 84	86.09 99	93.49 100	95.80 80

ECVR-MVS		79.76 97	78.27 109	81.50 83	89.09 75	95.32 62	84.61 94	77.54 81	74.61 110	65.38 98	50.22 150	56.31 147	77.09 106	90.19 57	89.01 69	95.27 45	92.25 132

DCV-MVSNet		79.76 97	79.17 104	80.44 95	84.65 121	84.51 173	84.20 97	72.36 124	75.17 105	70.81 83	66.21 82	66.56 110	80.99 86	82.89 132	84.56 116	89.65 185	94.30 103

FC-MVSNet-train		79.54 99	78.20 110	81.09 88	86.55 104	88.63 128	79.96 125	78.53 71	70.90 130	68.24 92	65.87 84	56.45 146	80.29 94	86.20 110	84.08 121	92.97 122	95.31 90

test-LLR		79.52 100	83.42 74	74.97 126	81.79 135	91.26 106	76.17 163	70.57 136	77.71 93	52.14 143	66.26 80	77.47 61	73.10 130	87.02 96	87.16 82	96.05 29	97.02 56

FMVSNet2		79.24 101	78.14 112	80.53 94	78.18 156	86.19 149	86.73 67	71.91 126	72.97 120	70.48 86	50.63 148	66.56 110	80.99 86	90.10 59	89.77 56	94.89 57	90.77 149

TESTMET0.1,1		79.15 102	83.42 74	74.18 132	79.81 150	91.26 106	76.17 163	67.83 161	77.71 93	52.14 143	66.26 80	77.47 61	73.10 130	87.02 96	87.16 82	96.05 29	97.02 56

tfpn200view9		79.05 103	77.21 119	81.18 87	88.42 81	92.55 97	85.12 89	77.94 75	70.15 132	61.01 116	56.65 119	51.22 153	81.11 85	88.23 85	84.80 112	93.50 99	96.90 64

test1111		78.99 104	77.77 116	80.42 96	88.64 79	95.31 64	83.39 104	77.67 79	72.76 123	61.91 108	49.58 153	55.59 149	75.67 117	90.23 56	89.09 66	95.23 51	91.83 140

PatchMatch-RL		78.75 105	76.47 126	81.41 85	88.53 80	91.10 108	78.09 143	77.51 84	77.33 96	71.98 78	64.38 89	48.10 166	82.55 81	84.06 123	82.35 139	89.78 182	87.97 171

LS3D		78.72 106	75.79 131	82.15 78	91.91 57	89.39 124	83.66 101	85.88 36	76.81 100	59.22 124	57.67 116	58.53 140	83.72 74	82.07 142	81.63 150	88.50 193	84.39 182

thres200		78.69 107	76.71 122	80.99 91	88.35 83	92.56 95	86.03 78	77.94 75	66.27 139	60.66 118	56.08 126	51.11 155	79.45 98	88.23 85	85.54 107	93.52 94	97.20 52

Anonymous20231211		78.61 108	75.57 134	82.15 78	84.43 125	90.26 115	84.08 99	77.68 78	71.09 128	72.90 70	39.24 193	66.21 112	84.23 71	82.15 140	84.04 123	89.61 186	96.03 75

IB-MVS	74.10 12	78.52 109	78.51 107	78.52 107	90.15 68	95.39 59	71.95 183	77.53 83	74.95 108	77.25 52	58.93 111	55.92 148	58.37 183	79.01 167	87.89 79	95.88 35	97.47 43
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
EPNet_dtu		78.49 110	81.96 91	74.45 131	92.57 54	88.74 127	82.98 106	78.83 69	83.28 68	44.64 187	77.40 48	67.73 106	53.98 192	85.44 115	84.91 109	93.71 83	86.22 177
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres400		78.39 111	76.39 127	80.73 93	88.02 88	92.94 91	84.77 90	78.88 68	65.20 147	59.70 122	55.20 132	50.85 156	79.45 98	88.81 77	84.81 111	93.57 91	96.91 63

UA-Net		78.30 112	80.92 96	75.25 125	87.42 95	92.48 98	79.54 129	75.49 99	60.47 158	60.52 119	68.44 75	84.08 36	57.54 185	88.54 81	88.45 73	90.96 166	83.97 184

Vis-MVSNet (Re-imp)		78.28 113	82.68 81	73.16 143	86.64 102	92.68 94	78.07 144	74.48 105	74.05 113	53.47 136	64.22 91	76.52 68	54.28 188	88.96 75	88.29 76	92.03 143	94.00 107

MSDG		78.11 114	73.17 147	83.86 71	91.78 60	86.83 137	85.25 86	86.02 34	72.84 122	69.69 89	51.43 145	54.00 151	77.61 102	81.95 145	82.27 141	92.83 128	82.91 189

HyFIR lowres test		78.08 115	76.81 120	79.56 98	90.77 67	94.64 70	82.97 107	69.85 141	69.81 134	59.53 123	33.52 204	64.66 117	78.97 100	88.77 79	88.38 75	95.27 45	97.86 37

GeoE		78.04 116	77.52 118	78.65 104	84.51 123	90.84 112	80.94 118	69.24 146	72.86 121	66.06 95	53.45 139	60.46 133	77.37 103	84.20 120	84.85 110	93.78 79	96.00 77

test-mter		77.90 117	82.44 86	72.60 148	78.52 154	90.24 116	73.85 176	65.31 175	76.37 101	51.29 147	65.58 86	75.94 72	71.36 144	85.98 111	86.26 95	95.26 48	96.71 71

thres600view7		77.66 118	75.67 132	79.98 97	87.71 90	92.56 95	83.79 100	77.94 75	64.41 149	58.69 126	54.32 137	50.54 157	78.23 101	88.23 85	83.06 133	93.52 94	96.55 73

MS-PatchMatch		77.47 119	76.48 125	78.63 105	89.89 69	90.42 113	85.42 84	69.53 143	70.79 131	60.43 120	50.05 151	70.62 98	70.66 150	86.71 100	82.54 136	95.86 36	84.23 183

Fast-Effi-MVS+		77.37 120	76.68 123	78.17 112	82.84 132	89.94 120	81.47 116	68.01 157	72.99 119	60.26 121	55.07 133	53.20 152	82.99 78	86.47 106	86.12 98	93.46 102	92.98 127

dmvs_re		77.25 121	75.86 130	78.86 102	81.08 141	89.36 125	84.15 98	80.73 64	73.02 118	55.58 132	58.33 114	48.97 162	75.32 118	83.92 126	86.25 96	96.29 26	91.20 144

Vis-MVSNet		77.24 122	79.99 102	74.02 133	84.62 122	93.92 77	80.33 122	72.55 122	62.58 153	55.25 134	64.45 88	69.49 101	57.00 186	88.78 78	88.21 77	94.36 65	92.54 129
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MDTV_nov1_ep13		77.20 123	80.04 99	73.90 135	82.22 133	90.14 118	79.25 133	61.52 185	78.63 90	56.98 127	65.52 87	72.80 87	73.05 132	80.93 153	83.20 131	90.36 176	89.05 165

EPMVS		77.16 124	79.08 106	74.92 127	86.73 100	91.98 101	78.62 138	55.44 199	79.43 85	56.59 129	61.24 106	70.73 97	76.97 109	80.59 156	81.43 156	95.15 52	88.17 170

tpm cat1		76.93 125	76.19 129	77.79 115	85.08 120	88.58 129	82.96 108	59.33 192	75.72 104	72.64 72	51.25 146	64.41 119	75.74 116	77.90 175	80.10 172	90.97 165	95.35 87

PatchmatchNet		76.85 126	80.03 101	73.15 144	84.08 127	91.04 110	77.76 148	55.85 198	79.43 85	52.74 141	62.08 102	76.02 70	74.56 121	79.92 161	81.41 157	93.92 76	90.29 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		76.80 127	76.33 128	77.35 116	84.07 128	84.11 174	81.54 115	68.52 150	66.17 140	61.74 109	57.84 115	64.31 122	74.88 119	83.48 129	86.21 97	93.34 110	92.16 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		76.57 128	76.78 121	76.32 120	80.94 143	89.75 121	82.94 109	72.64 118	59.01 164	62.95 107	58.60 112	62.67 125	66.91 163	86.26 108	87.20 81	91.57 153	93.97 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		76.41 129	79.90 103	72.35 152	84.26 126	85.24 164	75.57 170	54.56 201	79.95 82	52.72 142	64.22 91	77.84 57	73.73 127	80.48 157	81.37 158	93.25 113	90.20 155

tpmrst		76.27 130	77.65 117	74.66 129	86.13 111	89.53 123	79.31 132	54.91 200	77.19 98	56.27 130	55.87 128	64.58 118	77.25 104	80.85 154	80.21 169	94.07 70	95.32 89

dps		75.76 131	75.02 136	76.63 119	84.51 123	88.12 130	77.51 149	58.33 194	75.91 103	71.98 78	57.37 117	57.85 141	76.81 111	77.89 176	78.40 181	90.63 173	89.63 159

CR-MVSNet		74.84 132	77.91 113	71.26 165	81.77 137	85.52 160	78.32 140	54.14 203	74.05 113	51.09 150	50.00 152	71.38 92	70.77 148	86.48 104	84.03 124	91.46 157	93.92 112

Effi-MVS+-dtu		74.57 133	74.60 140	74.53 130	81.38 139	86.74 139	80.39 121	67.70 162	67.36 138	53.06 137	59.86 109	57.50 142	75.84 115	80.19 159	78.62 179	88.79 192	91.95 139

RPSCF		74.27 134	73.24 146	75.48 124	81.01 142	80.18 196	76.24 162	72.37 123	74.84 109	68.24 92	72.47 58	67.39 108	73.89 124	71.05 200	69.38 207	81.14 212	77.37 201

FMVSNet1		74.26 135	71.95 152	76.95 118	74.28 188	83.94 176	83.61 102	69.99 139	57.08 170	65.08 99	42.39 182	57.41 143	76.98 108	86.57 101	86.83 88	91.77 150	89.42 160

GA-MVS		73.62 136	74.52 141	72.58 149	79.93 148	89.29 126	78.02 145	71.67 129	60.79 157	42.68 191	54.41 136	49.07 161	70.07 154	89.39 72	86.55 92	93.13 118	92.12 135

Fast-Effi-MVS+-dtu		73.56 137	75.32 135	71.50 161	80.35 145	86.83 137	79.72 127	58.07 195	67.64 137	44.83 184	60.28 108	54.07 150	73.59 129	81.90 147	82.30 140	92.46 135	94.18 105

tpm		73.50 138	74.85 137	71.93 155	83.19 131	86.84 136	78.61 139	55.91 197	65.64 142	48.90 163	56.30 124	61.09 128	72.31 136	79.10 166	80.61 168	92.68 130	94.35 102

RPMNet		73.46 139	77.85 114	68.34 175	81.71 138	85.52 160	73.83 177	50.54 210	74.05 113	46.10 178	53.03 142	71.91 89	66.31 165	83.55 127	82.18 143	91.55 155	94.71 94

USDC		73.43 140	72.31 150	74.73 128	80.86 144	86.21 147	80.42 120	71.83 128	71.69 127	46.94 171	59.60 110	42.58 187	76.47 113	82.66 136	81.22 161	91.88 147	82.24 195

pmmvs4		73.38 141	71.53 155	75.55 123	75.95 174	85.24 164	77.25 153	71.59 130	71.03 129	63.10 106	49.09 158	44.22 177	73.73 127	82.04 143	80.18 170	91.68 151	88.89 167

UniMVSNet_NR-MVSNet		73.11 142	72.59 148	73.71 138	76.90 165	86.58 143	77.01 154	75.82 97	65.59 143	48.82 164	50.97 147	48.42 164	71.61 140	79.19 165	83.03 134	92.11 140	94.37 100

FMVSNet5		72.83 143	73.89 144	71.59 159	67.42 206	76.28 204	75.88 167	63.74 179	77.27 97	54.59 135	53.32 140	71.48 91	73.85 125	81.95 145	81.69 148	94.06 71	75.20 205

PatchT		72.66 144	76.58 124	68.09 177	79.02 153	86.09 153	59.81 205	51.78 208	72.00 126	51.09 150	46.84 162	66.70 109	70.77 148	86.48 104	84.03 124	96.07 27	93.92 112

ACMH	71.22 14	72.65 145	70.13 160	75.59 122	86.19 110	86.14 152	75.76 168	77.63 80	54.79 178	46.16 177	53.28 141	47.28 168	77.24 105	78.91 168	81.18 162	90.57 174	89.33 163
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		72.43 146	74.05 142	70.55 169	80.34 146	81.17 190	77.44 150	61.00 189	63.57 152	46.82 173	55.88 127	59.09 139	65.03 167	83.15 130	83.83 127	92.67 131	91.65 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH+	72.14 13	72.38 147	69.34 167	75.93 121	85.21 118	84.89 168	76.96 157	76.04 95	59.76 159	51.63 146	50.37 149	48.69 163	76.90 110	76.06 184	78.69 177	88.85 191	86.90 175

DU-MVS		72.19 148	71.35 156	73.17 142	75.95 174	86.02 154	77.01 154	74.42 106	65.39 145	48.82 164	49.10 156	42.81 185	71.61 140	78.67 169	83.10 132	91.22 161	94.37 100

IterMVS-SCA-FT		72.18 149	73.96 143	70.11 171	80.15 147	81.11 191	77.42 151	61.09 188	63.67 151	46.73 174	55.77 130	59.15 138	63.95 170	82.83 134	83.70 128	91.31 159	91.49 143

UniMVSNet (Re)		72.12 150	72.28 151	71.93 155	76.77 166	87.38 134	75.73 169	73.51 115	65.76 141	50.24 158	48.65 159	46.49 169	63.85 171	80.10 160	82.47 137	91.49 156	95.13 92

ADS-MVSNet		72.11 151	73.72 145	70.24 170	81.24 140	86.59 142	74.75 173	50.56 209	72.58 124	49.17 161	55.40 131	61.46 127	73.80 126	76.01 185	78.14 182	91.93 146	85.86 178

gg-mvs-nofinetune		72.10 152	74.79 138	68.97 174	83.31 129	95.22 66	85.66 83	48.77 211	35.68 214	22.17 221	30.49 207	77.73 59	76.37 114	94.30 13	93.03 11	97.55 2	97.05 55

TAMVS		72.06 153	71.76 154	72.41 151	76.68 167	88.12 130	74.82 172	68.09 155	53.52 183	56.91 128	52.94 143	56.93 145	66.91 163	81.37 150	82.44 138	91.07 163	86.99 174

v2v482		71.73 154	69.80 162	73.99 134	75.88 178	86.66 141	79.58 128	71.90 127	57.58 168	50.41 157	45.35 166	43.24 183	73.05 132	79.69 162	82.18 143	93.08 119	93.87 116

test0.0.03 1		71.70 155	74.68 139	68.23 176	81.79 135	83.81 177	68.64 187	70.57 136	68.81 136	43.47 188	62.77 99	60.09 135	51.77 199	82.48 138	81.67 149	93.16 116	83.13 187

V42		71.58 156	70.11 161	73.30 141	75.66 181	86.68 140	79.17 135	69.92 140	59.29 163	52.80 140	44.36 170	45.66 171	68.83 155	79.48 164	81.49 153	93.44 103	93.82 118

NR-MVSNet		71.47 157	71.11 157	71.90 157	77.73 161	86.02 154	76.88 158	74.42 106	65.39 145	46.09 179	49.10 156	39.87 200	64.27 169	81.40 149	82.24 142	91.99 144	93.75 120

v8		71.42 158	69.69 163	73.43 140	76.45 170	85.12 167	79.53 130	67.47 165	59.34 162	52.90 139	44.60 168	45.82 170	71.05 146	79.56 163	81.45 155	93.17 115	91.96 138

TranMVSNet+NR-MVSNet		71.12 159	70.24 159	72.15 153	76.01 173	84.80 170	76.55 160	75.65 98	61.99 155	45.29 182	48.42 160	43.07 184	67.55 159	78.28 172	82.83 135	91.85 148	92.29 130

v10		70.97 160	69.44 164	72.75 145	75.90 177	84.58 172	79.43 131	66.45 170	58.07 166	49.93 159	43.87 176	43.68 178	71.91 138	82.04 143	81.70 147	92.89 126	92.11 136

v1144		70.93 161	69.42 166	72.70 146	75.48 182	86.26 145	79.22 134	69.39 145	55.61 175	48.05 169	43.47 177	42.55 188	71.51 142	82.11 141	81.74 146	92.56 133	94.17 106

thisisatest0515		70.62 162	71.94 153	69.07 173	76.48 169	85.59 159	68.03 188	68.02 156	59.70 160	52.94 138	52.19 144	50.36 158	58.10 184	83.15 130	81.63 150	90.87 169	90.99 147

Baseline_NR-MVSNet		70.61 163	68.87 170	72.65 147	75.95 174	80.49 194	75.92 166	74.75 102	65.10 148	48.78 166	41.28 188	44.28 176	68.45 156	78.67 169	79.64 173	92.04 142	92.62 128

v148		70.34 164	68.46 173	72.54 150	76.04 172	86.38 144	74.83 171	72.73 117	55.88 174	55.26 133	43.32 179	43.49 179	64.52 168	76.93 182	80.11 171	91.85 148	93.11 124

v1192		70.32 165	68.77 171	72.12 154	74.76 184	85.62 158	78.73 136	68.53 149	55.08 177	46.34 176	42.39 182	40.67 195	71.90 139	82.27 139	81.53 152	92.43 136	93.86 117

v144192		70.10 166	68.55 172	71.90 157	74.55 185	85.67 157	77.81 146	68.22 154	54.65 179	46.91 172	42.76 180	41.27 192	70.95 147	80.48 157	81.11 166	92.96 123	93.90 114

pmmvs5		70.01 167	69.31 168	70.82 168	75.80 180	86.26 145	72.94 178	67.91 158	53.84 182	47.22 170	47.31 161	41.47 191	67.61 158	83.93 125	81.93 145	93.42 105	90.42 153

COLMAP_ROB	66.31 15	69.91 168	66.61 178	73.76 136	86.44 107	82.76 181	76.59 159	76.46 92	63.82 150	50.92 154	45.60 165	49.13 160	65.87 166	74.96 190	74.45 197	86.30 202	75.57 204
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1921920		69.85 169	68.38 174	71.58 160	74.35 186	85.39 162	77.78 147	67.88 160	54.64 180	45.39 181	42.11 185	39.97 199	71.10 145	81.68 148	81.17 164	92.96 123	93.69 122

pm-mvs1		69.62 170	68.07 176	71.44 162	77.21 163	85.32 163	76.11 165	71.05 131	46.55 203	51.17 149	41.83 186	48.20 165	61.81 177	84.00 124	81.14 165	91.28 160	89.42 160

UniMVSNet_ETH3D		69.49 171	65.86 180	73.72 137	76.51 168	85.88 156	78.65 137	70.52 138	48.08 200	55.71 131	37.64 196	40.56 196	71.38 143	75.05 189	81.49 153	89.57 188	92.29 130

tfpnnormal		69.29 172	65.58 181	73.62 139	79.87 149	84.82 169	76.97 156	75.12 101	45.29 204	49.03 162	35.57 202	37.20 208	68.02 157	82.70 135	81.24 160	92.69 129	92.20 133

v1240		69.28 173	67.82 177	71.00 167	74.09 190	85.13 166	76.54 161	67.28 167	53.17 184	44.70 185	41.55 187	39.38 201	70.51 152	81.29 151	81.18 162	92.88 127	93.02 126

CVMVSNet		68.95 174	70.79 158	66.79 183	79.69 151	83.75 178	72.05 182	70.90 132	56.20 172	36.30 203	54.94 135	59.22 137	54.03 191	78.33 171	78.65 178	87.77 198	84.44 181

MIMVSNet		68.66 175	69.43 165	67.76 178	64.92 209	84.68 171	74.16 174	54.10 205	60.85 156	51.27 148	39.47 192	49.48 159	67.48 160	84.86 118	85.57 106	94.63 61	81.10 196

TDRefinement		67.82 176	64.91 187	71.22 166	82.08 134	81.45 186	77.42 151	73.79 112	59.62 161	48.35 168	42.35 184	42.40 189	60.87 179	74.69 191	74.64 196	84.83 206	79.20 199

anonymousdsp		67.61 177	68.94 169	66.04 184	71.44 202	83.97 175	66.45 192	63.53 181	50.54 193	42.42 192	49.39 154	45.63 172	62.84 174	77.99 174	81.34 159	89.59 187	93.75 120

TinyColmap		67.16 178	63.51 194	71.42 163	77.94 159	79.54 200	72.80 179	69.78 142	56.58 171	45.52 180	44.53 169	33.53 213	74.45 122	76.91 183	77.06 188	88.03 197	76.41 202

FC-MVSNet-test		67.04 179	72.47 149	60.70 201	76.92 164	81.41 187	61.52 202	69.45 144	65.58 144	26.74 217	61.79 105	60.40 134	41.17 208	77.60 178	77.78 184	88.41 194	82.70 191

TransMVSNet (Re)		66.87 180	64.30 189	69.88 172	78.32 155	81.35 189	73.88 175	74.34 108	43.19 208	45.20 183	40.12 190	42.37 190	55.97 187	80.85 154	79.15 174	91.56 154	83.06 188

CMPMVS	50.59 17	66.74 181	62.72 198	71.42 163	85.40 116	89.72 122	72.69 180	70.72 134	51.24 189	51.75 145	38.91 194	44.40 174	63.74 172	70.84 201	71.52 201	84.19 207	72.45 209
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 182	65.51 182	67.51 179	71.63 201	83.10 179	70.89 186	65.02 176	50.13 196	44.68 186	39.59 191	38.77 202	62.57 175	77.59 179	78.91 175	90.29 178	90.44 152

EG-PatchMatch MVS		66.23 183	65.20 184	67.43 180	77.74 160	86.20 148	72.51 181	63.68 180	43.95 206	43.44 189	36.22 201	45.43 173	54.04 190	81.00 152	80.95 167	93.15 117	82.67 192

WR-MVS		64.98 184	66.59 179	63.09 194	74.34 187	82.68 182	64.98 198	69.17 147	54.42 181	36.18 204	44.32 171	44.35 175	44.65 202	73.60 192	77.83 183	89.21 190	88.96 166

gm-plane-assit		64.86 185	68.15 175	61.02 200	76.44 171	68.29 213	41.60 218	53.37 206	34.68 216	26.19 219	33.22 205	57.09 144	71.97 137	95.12 5	93.97 7	96.54 16	94.66 96

CP-MVSNet		64.84 186	64.97 185	64.69 189	72.09 197	81.04 192	66.66 191	67.53 164	52.45 186	37.40 199	44.00 175	38.37 204	53.54 194	72.26 196	76.93 189	90.94 168	89.75 158

MDTV_nov1_ep13_2view		64.72 187	64.94 186	64.46 190	71.14 203	81.94 185	67.53 189	54.54 202	55.92 173	43.29 190	44.02 174	43.27 182	59.87 180	71.85 198	74.77 195	90.36 176	82.82 190

MVS-HIRNet		64.63 188	64.03 193	65.33 186	75.01 183	82.84 180	58.54 209	52.10 207	55.42 176	49.29 160	29.83 210	43.48 180	66.97 162	78.28 172	78.81 176	90.07 181	79.52 198

pmnet_mix02		64.58 189	64.11 192	65.12 187	74.16 189	80.17 197	63.24 200	67.91 158	57.87 167	41.69 193	45.86 164	40.99 194	53.97 193	69.92 204	71.67 200	89.77 183	82.29 194

LTVRE_ROB	63.07 16	64.49 190	63.16 197	66.04 184	77.47 162	82.64 183	70.98 185	65.02 176	34.01 217	29.61 213	49.12 155	35.58 212	70.57 151	75.10 188	78.45 180	82.60 210	87.24 173
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
PEN-MVS		64.35 191	64.29 190	64.42 191	72.67 193	79.83 198	66.97 190	68.24 153	51.21 190	35.29 206	44.09 172	38.51 203	52.36 197	71.06 199	77.65 185	90.99 164	87.68 172

pmmvs6		64.24 192	61.77 202	67.12 181	72.39 196	81.39 188	71.33 184	65.95 174	36.05 213	48.48 167	30.55 206	43.45 181	58.75 182	77.88 177	76.36 192	85.83 203	86.70 176

pmmvs-eth3d		64.24 192	61.96 200	66.90 182	66.35 207	76.04 206	66.09 194	66.31 171	52.59 185	50.94 153	37.61 197	32.79 215	62.43 176	75.78 186	75.48 194	89.27 189	83.39 186

PS-CasMVS		64.22 194	64.19 191	64.25 192	71.86 199	80.67 193	66.42 193	67.43 166	50.64 192	36.48 201	42.60 181	37.46 207	52.56 196	71.98 197	76.69 191	90.76 170	89.29 164

WR-MVS_H		64.14 195	65.36 183	62.71 196	72.47 195	82.33 184	65.13 195	66.99 168	51.81 188	36.47 202	43.33 178	42.77 186	43.99 204	72.41 195	75.99 193	91.20 162	88.86 168

SixPastTwentyTwo		63.75 196	63.42 195	64.13 193	72.91 192	80.34 195	61.29 203	63.90 178	49.58 197	40.42 195	54.99 134	37.13 209	60.90 178	68.46 205	70.80 202	85.37 205	82.65 193

PM-MVS		63.52 197	62.51 199	64.70 188	64.79 211	76.08 205	65.07 196	62.08 183	58.13 165	46.56 175	44.98 167	31.31 216	62.89 173	72.58 194	69.93 206	86.81 200	84.55 180

DTE-MVSNet		63.26 198	63.41 196	63.08 195	72.59 194	78.56 201	65.03 197	68.28 152	50.53 194	32.38 210	44.03 173	37.79 206	49.48 200	70.83 202	76.73 190	90.73 171	85.42 179

testgi		63.11 199	64.88 188	61.05 199	75.83 179	78.51 202	60.42 204	66.20 172	48.77 198	34.56 207	56.96 118	40.35 197	40.95 209	77.46 180	77.22 187	88.37 196	74.86 207

GG-mvs-BLEND		62.08 200	88.31 43	31.46 214	0.16 226	98.10 11	91.57 41	0.09 222	85.07 65	0.21 227	73.90 57	83.74 39	0.19 224	88.98 74	89.39 61	96.58 14	99.02 15

Anonymous20231206		62.05 201	61.83 201	62.30 198	72.09 197	77.84 203	63.10 201	67.62 163	50.20 195	36.68 200	29.59 211	37.05 210	43.90 205	77.33 181	77.31 186	90.41 175	83.49 185

N_pmnet		60.52 202	58.83 205	62.50 197	68.97 205	75.61 207	59.72 207	66.47 169	51.90 187	41.26 194	35.42 203	35.63 211	52.25 198	67.07 208	70.08 205	86.35 201	76.10 203

EU-MVSNet		58.73 203	60.92 203	56.17 204	66.17 208	72.39 210	58.85 208	61.24 186	48.47 199	27.91 215	46.70 163	40.06 198	39.07 210	68.27 206	70.34 204	83.77 208	80.23 197

test20.03		57.93 204	59.22 204	56.44 203	71.84 200	73.78 209	53.55 212	65.96 173	43.02 209	28.46 214	37.50 198	38.17 205	30.41 214	75.25 187	74.42 198	88.41 194	72.37 210

MDA-MVSNet-bldmvs		54.99 205	52.66 209	57.71 202	52.74 217	74.87 208	55.61 210	68.41 151	43.65 207	32.54 208	37.93 195	22.11 222	54.11 189	48.85 215	67.34 208	82.85 209	73.88 208

new-patchmatchnet		53.91 206	52.69 208	55.33 206	64.83 210	70.90 211	52.24 213	61.75 184	41.09 210	30.82 211	29.90 209	28.22 218	36.69 211	61.52 210	65.08 209	85.64 204	72.14 211

MIMVSNet1		52.76 207	53.95 207	51.38 208	41.96 220	70.79 212	53.56 211	63.03 182	39.36 211	27.83 216	22.73 216	33.07 214	34.47 213	70.49 203	72.69 199	87.41 199	68.51 212

pmmvs3		52.59 208	52.43 210	52.78 207	54.53 216	64.49 215	50.07 214	46.89 214	35.31 215	30.19 212	27.27 213	26.96 220	53.02 195	67.28 207	70.54 203	81.96 211	75.20 205

new_pmnet		50.32 209	51.36 211	49.11 209	49.19 218	64.89 214	48.66 216	47.99 213	47.55 201	26.27 218	29.51 212	28.66 217	44.89 201	61.12 211	62.74 211	77.66 213	65.03 213

FPMVS		50.25 210	45.67 213	55.58 205	70.48 204	60.12 216	59.78 206	59.33 192	46.66 202	37.94 197	30.22 208	27.51 219	35.94 212	50.98 214	47.90 214	70.02 215	56.31 214

test_method		47.92 211	55.39 206	39.21 212	19.90 224	49.24 218	39.29 219	34.65 219	57.37 169	32.54 208	25.11 214	41.02 193	44.31 203	66.58 209	57.57 213	64.59 218	90.82 148

PMVS	36.83 18	40.62 212	36.39 214	45.56 210	58.40 213	33.20 221	32.62 221	56.02 196	28.25 218	37.92 198	22.29 217	26.15 221	25.29 216	48.49 216	43.82 217	63.13 219	52.53 217
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		35.20 213	33.96 215	36.65 213	43.30 219	32.51 222	26.96 223	48.31 212	38.87 212	20.08 222	8.08 219	7.41 226	26.44 215	53.60 212	58.43 212	54.81 220	38.79 219
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		32.52 214	33.92 216	30.88 215	34.15 223	44.70 220	27.79 222	39.69 218	22.21 219	4.31 226	15.73 218	14.13 224	12.45 221	40.11 217	47.00 215	66.88 216	53.54 215

E-PMN		21.42 215	17.56 218	25.94 216	36.25 222	19.02 225	11.56 224	43.72 216	15.25 221	6.99 224	8.04 220	4.53 228	21.77 218	16.13 220	26.16 219	35.34 222	33.77 220

MVE	25.07 19	21.25 216	23.51 217	18.62 218	15.07 225	29.77 224	10.67 226	34.60 220	12.51 222	9.46 223	7.84 221	3.82 229	14.38 220	27.45 219	42.42 218	27.56 224	40.74 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 217	16.32 219	25.62 217	36.41 221	18.93 226	11.51 225	43.75 215	15.65 220	6.53 225	7.56 222	4.68 227	22.03 217	14.56 221	23.10 220	33.51 223	29.77 221

testmvs		0.76 218	1.23 220	0.21 219	0.05 227	0.21 227	0.38 228	0.09 222	0.94 223	0.05 228	2.13 224	0.08 230	0.60 223	0.82 222	0.77 221	0.11 225	3.62 223

test123		0.67 219	1.11 221	0.16 220	0.01 228	0.14 228	0.20 229	0.04 224	0.77 224	0.02 229	2.15 223	0.02 231	0.61 222	0.23 223	0.72 222	0.07 226	3.76 222

uanet_test		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

TPM-MVS					98.35 1	98.66 4	96.92 2			83.78 24	90.39 24	94.36 1	94.48 4			96.58 14	93.94 110

RE-MVS-def										39.41 196

9.14												91.16 7

SR-MVS					96.04 31			87.51 26				87.60 21

Anonymous202405211			75.59 133		85.13 119	91.06 109	84.62 93	77.96 74	69.47 135		40.79 189	63.84 124	84.57 67	83.55 127	84.69 114	89.69 184	95.75 83

our_test_3					73.80 191	79.57 199	64.47 199

ambc			50.35 212		55.61 215	59.93 217	48.73 215		44.08 205	35.81 205	24.01 215	10.64 225	41.57 207	72.83 193	63.35 210	74.99 214	77.61 200

MTAPA										91.14 7		85.84 27

MTMP										90.95 8		84.13 35

Patchmatch-RL test							8.17 227

tmp_tt				39.78 211	56.31 214	31.71 223	35.84 220	15.08 221	82.57 74	50.83 155	63.07 96	47.51 167	15.28 219	52.23 213	44.24 216	65.35 217

XVS					89.65 71	95.93 47	85.97 80			76.32 55		82.05 45				93.51 97

X-MVStestdata					89.65 71	95.93 47	85.97 80			76.32 55		82.05 45				93.51 97

mPP-MVS					95.90 33							80.22 54

NP-MVS									89.55 46

Patchmtry						87.41 133	78.32 140	54.14 203		51.09 150

DeepMVS_CX						48.96 219	43.77 217	40.58 217	50.93 191	24.67 220	36.95 200	20.18 223	41.60 206	38.92 218		52.37 221	53.31 216

High-resolution multi-view benchmark