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.

RA-MVS		89.45 1	92.17 1	86.27 1	91.85 3	92.27 4	91.70 5	77.27 1	93.64 1	83.31 2	94.34 1	91.13 2	82.62 1	90.26 1	88.26 5	90.90 14	95.32 5

DPE-MVS		88.63 6	91.29 6	85.53 4	90.87 10	92.20 5	91.98 2	76.00 8	90.55 11	82.09 7	93.85 4	90.75 3	81.25 2	88.62 10	87.59 17	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 2	91.86 2	85.97 2	92.55 2	92.38 1	91.69 6	76.31 5	93.31 2	83.11 4	92.44 7	91.18 1	81.17 3	89.55 3	87.93 10	91.01 10	96.21 1

SED-MVS		88.85 3	91.59 4	85.67 3	90.54 18	92.29 3	91.71 4	76.40 4	92.41 4	83.24 3	92.50 6	90.64 5	81.10 4	89.53 4	88.02 8	91.00 11	95.73 3

MED-MVS		88.73 4	91.48 5	85.53 4	90.94 9	91.91 7	91.93 3	76.42 3	92.32 5	81.78 8	94.25 2	90.22 7	80.98 5	89.21 8	87.96 9	91.13 5	94.45 9

MSP-MVS		88.09 8	90.84 7	84.88 10	90.00 27	91.80 8	91.63 7	75.80 9	91.99 6	81.23 10	92.54 5	89.18 9	80.89 6	87.99 18	87.91 11	89.70 50	94.51 8
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 7	90.84 7	84.92 9	90.52 19	91.48 10	91.33 8	75.06 16	90.82 9	80.74 12	94.25 2	90.29 6	80.86 7	87.82 19	86.80 25	91.03 7	94.45 9

APDe-MVS		88.00 9	90.50 9	85.08 7	90.95 8	91.58 9	92.03 1	75.53 14	91.15 7	80.10 18	92.27 8	88.34 14	80.80 8	88.00 17	86.99 21	91.09 6	95.16 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		88.67 5	91.62 3	85.22 6	90.47 20	92.36 2	90.69 13	76.15 6	93.08 3	82.75 5	92.19 9	90.71 4	80.45 9	89.27 7	87.91 11	90.82 16	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 15	88.91 17	84.41 13	90.66 13	90.10 16	90.78 11	75.64 11	87.38 19	78.72 22	90.68 13	86.82 20	80.15 10	87.13 28	86.45 32	90.51 25	93.83 17
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		86.88 14	89.23 13	84.14 15	89.78 30	88.67 33	90.59 14	73.46 30	88.99 14	80.52 15	91.26 10	88.65 12	79.91 11	86.96 32	86.22 34	90.59 24	93.83 17
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 12	88.92 16	84.95 8	92.61 1	87.91 44	90.23 19	76.06 7	88.85 15	81.20 11	87.33 16	87.93 15	79.47 12	88.59 11	88.23 6	90.15 39	93.60 23

SF-MVS		87.47 11	89.70 11	84.86 11	91.26 7	91.10 11	90.90 10	75.65 10	89.21 12	81.25 9	91.12 11	88.93 10	78.82 13	87.42 23	86.23 33	91.28 3	93.90 16

CNVR-MVS		86.36 17	88.19 20	84.23 14	91.33 6	89.84 18	90.34 15	75.56 12	87.36 20	78.97 21	81.19 32	86.76 21	78.74 14	89.30 6	88.58 2	90.45 31	94.33 13

SD-MVS		86.96 13	89.45 12	84.05 17	90.13 23	89.23 26	89.77 22	74.59 18	89.17 13	80.70 13	89.93 14	89.67 8	78.47 15	87.57 22	86.79 26	90.67 22	93.76 19
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 25	86.62 27	83.39 20	90.55 17	89.82 20	89.29 25	73.89 26	84.38 33	76.03 34	79.01 35	85.90 24	78.47 15	87.81 20	86.11 36	92.11 1	93.29 25

HFP-MVS		86.15 18	87.95 21	84.06 16	90.80 11	89.20 27	89.62 23	74.26 20	87.52 17	80.63 14	86.82 19	84.19 32	78.22 17	87.58 21	87.19 19	90.81 17	93.13 28

SMA-MVS		87.56 10	90.17 10	84.52 12	91.71 4	90.57 12	90.77 12	75.19 15	90.67 10	80.50 16	86.59 20	88.86 11	78.09 18	89.92 2	89.41 1	90.84 15	95.19 6
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 22	86.59 28	83.88 18	91.48 5	88.88 28	89.79 21	75.54 13	86.67 23	77.94 27	76.55 38	84.99 28	78.07 19	88.04 15	87.68 15	90.46 30	93.31 24

TSAR-MVS + GP.		83.69 33	86.58 29	80.32 39	85.14 58	86.96 48	84.91 55	70.25 45	84.71 31	73.91 42	85.16 24	85.63 25	77.92 20	85.44 46	85.71 39	89.77 46	92.45 30

MSLP-MVS++		82.09 40	82.66 43	81.42 33	87.03 48	87.22 47	85.82 47	70.04 46	80.30 49	78.66 23	68.67 90	81.04 48	77.81 21	85.19 50	84.88 47	89.19 61	91.31 41

ACMMPR		85.52 20	87.53 23	83.17 24	90.13 23	89.27 24	89.30 24	73.97 24	86.89 22	77.14 29	86.09 21	83.18 36	77.74 22	87.42 23	87.20 18	90.77 18	92.63 29

DeepC-MVS_fast	78.24 3	84.27 32	85.50 34	82.85 25	90.46 21	89.24 25	87.83 38	74.24 21	84.88 28	76.23 33	75.26 44	81.05 47	77.62 23	88.02 16	87.62 16	90.69 21	92.41 31
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 28	86.03 32	83.37 21	89.29 36	90.38 15	88.61 31	76.50 2	86.25 25	77.22 28	75.12 45	80.28 49	77.59 24	88.39 12	88.17 7	91.02 9	93.66 21
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 23	88.93 15	81.06 35	88.77 40	90.48 14	85.46 51	73.08 32	90.97 8	73.77 43	84.81 25	85.95 23	77.43 25	88.22 13	87.73 13	87.85 105	94.34 12

MP-MVS		85.50 21	87.40 24	83.28 22	90.65 14	89.51 23	89.16 28	74.11 22	83.70 37	78.06 26	85.54 23	84.89 31	77.31 26	87.40 25	87.14 20	90.41 33	93.65 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		85.99 19	88.31 19	83.27 23	90.73 12	89.84 18	90.27 18	74.31 19	84.56 32	75.88 35	87.32 17	85.04 27	77.31 26	89.01 9	88.46 3	91.14 4	93.96 15
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		84.74 29	86.43 30	82.77 26	89.48 34	88.13 42	88.64 30	73.93 25	84.92 27	76.77 31	81.94 30	83.50 34	77.29 28	86.92 33	86.49 31	90.49 26	93.14 27

3Dnovator+	75.73 4	82.40 38	82.76 42	81.97 31	88.02 43	89.67 21	86.60 43	71.48 40	81.28 48	78.18 25	64.78 117	77.96 56	77.13 29	87.32 26	86.83 24	90.41 33	91.48 40

PGM-MVS		84.42 31	86.29 31	82.23 28	90.04 26	88.82 29	89.23 26	71.74 39	82.82 42	74.61 38	84.41 26	82.09 39	77.03 30	87.13 28	86.73 28	90.73 20	92.06 35

ACMMP_NAP		86.52 16	89.01 14	83.62 19	90.28 22	90.09 17	90.32 17	74.05 23	88.32 16	79.74 19	87.04 18	85.59 26	76.97 31	89.35 5	88.44 4	90.35 35	94.27 14

AdaColmap		79.74 50	78.62 69	81.05 36	89.23 37	86.06 57	84.95 54	71.96 37	79.39 53	75.51 36	63.16 123	68.84 125	76.51 32	83.55 66	82.85 63	88.13 86	86.46 90

CS-MVS		79.22 55	81.11 54	77.01 58	81.36 84	84.03 76	80.35 89	63.25 106	73.43 74	70.37 63	74.10 50	76.03 64	76.40 33	86.32 41	83.95 54	90.34 36	89.93 53

CPTT-MVS		81.77 41	83.10 41	80.21 40	85.93 54	86.45 54	87.72 40	70.98 42	82.54 44	71.53 54	74.23 49	81.49 44	76.31 34	82.85 76	81.87 71	88.79 72	92.26 33

EC-MVSNet		79.44 52	81.35 51	77.22 56	82.95 67	84.67 70	81.31 82	63.65 100	72.47 78	68.75 73	73.15 52	78.33 53	75.99 35	86.06 44	83.96 53	90.67 22	90.79 45

train_agg		84.86 27	87.21 26	82.11 29	90.59 16	85.47 62	89.81 20	73.55 29	83.95 34	73.30 44	89.84 15	87.23 18	75.61 36	86.47 37	85.46 42	89.78 45	92.06 35

ACMMP		83.42 34	85.27 35	81.26 34	88.47 42	88.49 36	88.31 36	72.09 36	83.42 38	72.77 46	82.65 27	78.22 54	75.18 37	86.24 42	85.76 38	90.74 19	92.13 34
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 62	80.72 56	76.53 62	81.11 90	83.88 79	79.69 101	63.72 99	73.80 70	69.95 68	75.40 43	76.17 61	74.85 38	84.50 57	82.78 64	89.87 44	88.54 65

MVSMamba_PlusPlus		80.48 44	82.51 45	78.11 52	82.79 69	86.47 53	83.22 62	66.95 71	77.74 55	70.45 62	73.88 51	77.56 57	74.81 39	86.85 34	85.52 40	90.43 32	89.55 59

TSAR-MVS + ACMM		85.10 26	88.81 18	80.77 38	89.55 33	88.53 35	88.59 32	72.55 34	87.39 18	71.90 48	90.95 12	87.55 16	74.57 40	87.08 30	86.54 30	87.47 115	93.67 20

MGCNet		84.63 30	87.25 25	81.59 32	88.58 41	90.50 13	87.82 39	69.16 56	83.82 36	78.46 24	82.32 28	84.97 29	74.56 41	88.16 14	87.72 14	90.94 13	93.24 26

CNLPA		77.20 71	77.54 78	76.80 61	82.63 71	84.31 73	79.77 96	64.64 88	85.17 26	73.18 45	56.37 162	69.81 116	74.53 42	81.12 103	78.69 137	86.04 157	87.29 77

OPM-MVS		79.68 51	79.28 67	80.15 41	87.99 44	86.77 50	88.52 33	72.72 33	64.55 131	67.65 82	67.87 96	74.33 73	74.31 43	86.37 39	85.25 44	89.73 49	89.81 55
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
3Dnovator	73.76 5	79.75 49	80.52 59	78.84 46	84.94 63	87.35 45	84.43 57	65.54 81	78.29 54	73.97 41	63.00 125	75.62 67	74.07 44	85.00 51	85.34 43	90.11 40	89.04 61

CSCG		85.28 24	87.68 22	82.49 27	89.95 28	91.99 6	88.82 29	71.20 41	86.41 24	79.63 20	79.26 33	88.36 13	73.94 45	86.64 35	86.67 29	91.40 2	94.41 11

PLC	68.99 11	75.68 91	75.31 110	76.12 66	82.94 68	81.26 119	79.94 94	66.10 75	77.15 58	66.86 91	59.13 145	68.53 127	73.73 46	80.38 122	79.04 130	87.13 123	81.68 160
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMM	72.26 8	78.86 61	78.13 73	79.71 43	86.89 49	83.40 87	86.02 45	70.50 43	75.28 62	71.49 55	63.01 124	69.26 119	73.57 47	84.11 60	83.98 52	89.76 47	87.84 70
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETV-MVS		77.32 70	78.81 68	75.58 74	82.24 77	83.64 85	79.98 92	64.02 96	69.64 97	63.90 109	70.89 66	69.94 115	73.41 48	85.39 49	83.91 55	89.92 42	88.31 66

OMC-MVS		80.26 45	82.59 44	77.54 54	83.04 66	85.54 61	83.25 61	65.05 86	87.32 21	72.42 47	72.04 59	78.97 51	73.30 49	83.86 61	81.60 76	88.15 85	88.83 63

MVS_111021_HR		80.13 46	81.46 50	78.58 48	85.77 55	85.17 66	83.45 60	69.28 53	74.08 68	70.31 64	74.31 48	75.26 68	73.13 50	86.46 38	85.15 45	89.53 52	89.81 55

PHI-MVS		82.36 39	85.89 33	78.24 50	86.40 52	89.52 22	85.52 49	69.52 52	82.38 45	65.67 94	81.35 31	82.36 38	73.07 51	87.31 27	86.76 27	89.24 57	91.56 39

DPM-MVS		83.30 35	84.33 38	82.11 29	89.56 32	88.49 36	90.33 16	73.24 31	83.85 35	76.46 32	72.43 57	82.65 37	73.02 52	86.37 39	86.91 22	90.03 41	89.62 57

CANet		81.62 42	83.41 39	79.53 44	87.06 47	88.59 34	85.47 50	67.96 62	76.59 59	74.05 40	74.69 46	81.98 40	72.98 53	86.14 43	85.47 41	89.68 51	90.42 50

QAPM		78.47 64	80.22 62	76.43 63	85.03 60	86.75 51	80.62 88	66.00 77	73.77 71	65.35 98	65.54 113	78.02 55	72.69 54	83.71 63	83.36 60	88.87 69	90.41 51

MVS_111021_LR		78.13 66	79.85 65	76.13 65	81.12 89	81.50 114	80.28 91	65.25 84	76.09 60	71.32 56	76.49 39	72.87 85	72.21 55	82.79 77	81.29 79	86.59 142	87.91 69

MAR-MVS		79.21 56	80.32 61	77.92 53	87.46 45	88.15 41	83.95 58	67.48 68	74.28 65	68.25 76	64.70 118	77.04 58	72.17 56	85.42 47	85.00 46	88.22 82	87.62 74
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		72.46 120	74.19 117	70.44 124	62.50 238	81.17 120	79.90 95	62.46 138	64.52 132	57.52 134	71.49 63	59.15 164	72.08 57	78.61 154	81.11 81	88.16 84	83.29 146

ACMP	73.23 7	79.79 48	80.53 58	78.94 45	85.61 56	85.68 60	85.61 48	69.59 50	77.33 57	71.00 58	74.45 47	69.16 120	71.88 58	83.15 72	83.37 59	89.92 42	90.57 49
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	71.42 9	77.69 68	80.05 63	74.94 85	80.68 103	84.52 72	81.36 81	63.14 115	84.77 29	64.82 102	68.72 88	75.91 65	71.86 59	81.62 85	79.55 118	87.80 107	85.24 123
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDPH-MVS		82.64 37	85.03 37	79.86 42	89.41 35	88.31 39	88.32 35	71.84 38	80.11 50	67.47 83	82.09 29	81.44 45	71.85 60	85.89 45	86.15 35	90.24 37	91.25 42

Casviewmamba		78.51 63	79.92 64	76.87 60	82.72 70	85.98 58	82.91 63	65.64 80	75.65 61	69.03 72	70.43 72	74.36 72	71.80 61	83.70 64	81.55 77	89.10 64	87.78 71

PCF-MVS	73.28 6	79.42 53	80.41 60	78.26 49	84.88 64	88.17 40	86.08 44	69.85 47	75.23 63	68.43 75	68.03 95	78.38 52	71.76 62	81.26 99	80.65 96	88.56 76	91.18 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVS		83.23 36	85.20 36	80.92 37	89.71 31	88.68 30	88.21 37	73.60 27	82.57 43	71.81 51	77.07 36	81.92 41	71.72 63	86.98 31	86.86 23	90.47 27	92.36 32

viewdifsd2359ckpt09		77.36 69	78.39 72	76.16 64	79.98 113	85.78 59	82.78 64	65.29 83	70.87 88	68.68 74	68.99 82	70.81 108	71.70 64	82.68 78	81.86 72	88.56 76	87.71 73

HQP-MVS		81.19 43	83.27 40	78.76 47	87.40 46	85.45 63	86.95 41	70.47 44	81.31 47	66.91 89	79.24 34	76.63 59	71.67 65	84.43 58	83.78 56	89.19 61	92.05 37

EIA-MVS		75.64 93	76.60 102	74.53 91	82.43 74	83.84 80	78.32 121	62.28 140	65.96 119	63.28 113	68.95 83	67.54 132	71.61 66	82.55 79	81.63 75	89.24 57	85.72 106

TSAR-MVS + COLMAP		78.34 65	81.64 49	74.48 93	80.13 112	85.01 67	81.73 77	65.93 79	84.75 30	61.68 115	85.79 22	66.27 138	71.39 67	82.91 75	80.78 87	86.01 158	85.98 94

LGP-MVS_train		79.83 47	81.22 53	78.22 51	86.28 53	85.36 65	86.76 42	69.59 50	77.34 56	65.14 99	75.68 41	70.79 109	71.37 68	84.60 54	84.01 51	90.18 38	90.74 46

TPM-MVS					90.07 25	88.36 38	88.45 34			77.10 30	75.60 42	83.98 33	71.33 69			89.75 48	89.62 57
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
Fast-Effi-MVS+		73.11 114	73.66 122	72.48 103	77.72 134	80.88 126	78.55 116	58.83 188	65.19 125	60.36 120	59.98 139	62.42 150	71.22 70	81.66 84	80.61 98	88.20 83	84.88 131

LS3D		74.08 105	73.39 125	74.88 86	85.05 59	82.62 107	79.71 99	68.66 57	72.82 75	58.80 125	57.61 156	61.31 154	71.07 71	80.32 123	78.87 135	86.00 159	80.18 176

casdiffseed414692147		75.68 91	75.69 109	75.67 72	81.52 81	84.14 75	81.64 79	64.19 95	68.92 100	67.29 86	61.24 129	67.12 134	71.02 72	81.17 100	80.83 86	88.36 78	86.40 91

Effi-MVS+		75.28 96	76.20 105	74.20 94	81.15 88	83.24 90	81.11 83	63.13 116	66.37 115	60.27 121	64.30 121	68.88 124	70.93 73	81.56 87	81.69 74	88.61 74	87.35 75

ACM-MVS					90.61 15	87.94 43	89.23 26		81.83 46	74.47 39	75.82 40	83.33 35	70.56 74			89.02 65	91.80 38

viewdifsd2359ckpt13		76.26 81	77.31 89	75.03 83	80.14 110	83.77 83	81.58 80	62.80 124	70.34 89	67.83 81	68.06 94	70.93 105	70.20 75	81.46 90	79.88 107	87.63 112	86.71 87

OpenMVS	70.44 10	76.15 87	76.82 97	75.37 81	85.01 61	84.79 68	78.99 111	62.07 142	71.27 84	67.88 80	57.91 155	72.36 87	70.15 76	82.23 83	81.41 78	88.12 87	87.78 71

hybridcas		76.97 72	78.42 71	75.27 82	81.21 86	84.20 74	81.90 73	62.85 122	74.06 69	66.89 90	68.88 84	73.96 75	70.06 77	82.31 82	79.54 119	88.71 73	85.99 93

DELS-MVS		79.15 59	81.07 55	76.91 59	83.54 65	87.31 46	84.45 56	64.92 87	69.98 90	69.34 71	71.62 61	76.26 60	69.84 78	86.57 36	85.90 37	89.39 54	89.88 54
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 88	76.54 103	75.51 77	80.71 98	83.10 93	81.74 75	63.03 117	68.89 101	69.71 69	66.73 108	70.84 106	69.76 79	80.88 107	79.61 114	88.11 89	85.72 106

E6		76.06 88	76.54 103	75.51 77	80.71 98	83.10 93	81.74 75	63.03 117	68.89 101	69.71 69	66.73 108	70.84 106	69.76 79	80.88 107	79.61 114	88.11 89	85.72 106

sasdasda		79.16 57	82.37 46	75.41 79	82.33 75	86.38 55	80.80 85	63.18 112	82.90 40	67.34 84	72.79 54	76.07 62	69.62 81	83.46 69	84.41 49	89.20 59	90.60 47

canonicalmvs		79.16 57	82.37 46	75.41 79	82.33 75	86.38 55	80.80 85	63.18 112	82.90 40	67.34 84	72.79 54	76.07 62	69.62 81	83.46 69	84.41 49	89.20 59	90.60 47

E3new		76.51 78	77.22 90	75.69 70	80.74 96	83.07 95	81.99 68	63.23 109	71.18 85	70.52 61	68.77 86	71.75 92	69.61 83	80.73 109	79.18 126	88.03 96	85.85 101

E3		76.51 78	77.21 91	75.69 70	80.74 96	83.06 98	81.98 69	63.22 110	71.17 86	70.55 60	68.77 86	71.76 91	69.61 83	80.73 109	79.18 126	88.03 96	85.84 103

E4		76.24 82	76.77 100	75.61 73	80.69 100	83.05 99	81.98 69	63.25 106	69.47 98	70.06 65	67.40 101	71.46 94	69.59 85	80.73 109	79.37 123	88.10 91	85.95 96

viewcassd2359sk11		76.64 75	77.43 85	75.72 69	80.75 95	83.07 95	81.95 71	63.20 111	72.02 83	70.88 59	69.50 79	72.02 90	69.58 86	80.68 114	78.98 132	87.97 98	85.74 104

E2		76.70 74	77.54 78	75.73 67	80.76 94	83.07 95	81.91 72	63.15 114	72.42 79	71.09 57	70.03 76	72.22 88	69.53 87	80.57 116	78.80 136	87.91 101	85.64 109

viewmanbaseed2359cas		76.36 80	77.87 75	74.60 90	79.81 114	82.88 104	81.69 78	61.02 155	72.14 82	67.97 78	69.61 78	72.45 86	69.53 87	81.53 88	79.83 109	87.57 113	86.65 88

PatchMatch-RL		67.78 169	66.65 190	69.10 141	73.01 185	72.69 214	68.49 212	61.85 145	62.93 145	60.20 122	56.83 161	50.42 234	69.52 89	75.62 185	74.46 196	81.51 214	73.62 231

casdiffmvs		76.76 73	78.46 70	74.77 87	80.32 108	83.73 84	80.65 87	63.24 108	73.58 72	66.11 93	69.39 81	74.09 74	69.49 90	82.52 80	79.35 125	88.84 71	86.52 89
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 90	77.01 95	74.49 92	79.69 116	82.87 105	81.77 74	61.06 153	69.37 99	67.26 87	66.73 108	71.63 93	69.48 91	81.51 89	80.20 102	87.69 109	86.77 86

E5new		76.23 83	76.79 98	75.58 74	80.69 100	83.05 99	82.00 66	63.37 103	69.73 93	70.01 66	67.77 98	71.43 97	69.37 92	80.50 117	79.13 128	88.04 93	85.92 97

E5		76.23 83	76.79 98	75.58 74	80.69 100	83.05 99	82.00 66	63.37 103	69.73 93	70.01 66	67.77 98	71.43 97	69.37 92	80.50 117	79.13 128	88.04 93	85.92 97

DI_MVS_pp		75.13 98	76.12 106	73.96 95	78.18 128	81.55 112	80.97 84	62.54 134	68.59 104	65.13 100	61.43 128	74.81 69	69.32 94	81.01 105	79.59 116	87.64 111	85.89 99

casdiffmvs_mvg		77.79 67	79.55 66	75.73 67	81.56 80	84.70 69	82.12 65	64.26 94	74.27 66	67.93 79	70.83 67	74.66 70	69.19 95	83.33 71	81.94 70	89.29 56	87.14 80
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 94	77.13 93	73.31 98	79.07 122	81.32 117	79.98 92	60.12 170	69.72 95	64.11 108	70.53 71	73.22 80	68.90 96	80.14 130	79.48 121	87.67 110	85.50 116

Effi-MVS+-dtu		71.82 124	71.86 139	71.78 109	78.77 123	80.47 130	78.55 116	61.67 150	60.68 162	55.49 143	58.48 149	65.48 140	68.85 97	76.92 176	75.55 189	87.35 117	85.46 117

ACMH	65.37 14	70.71 135	70.00 150	71.54 110	82.51 73	82.47 108	77.78 125	68.13 59	56.19 194	46.06 211	54.30 176	51.20 230	68.68 98	80.66 115	80.72 89	86.07 153	84.45 137
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 131	70.09 149	72.85 100	82.59 72	81.13 121	78.56 115	68.04 60	61.55 156	52.52 171	51.50 211	54.14 203	68.56 99	78.85 151	79.50 120	86.82 131	83.94 140

CLD-MVS		79.35 54	81.23 52	77.16 57	85.01 61	86.92 49	85.87 46	60.89 157	80.07 52	75.35 37	72.96 53	73.21 81	68.43 100	85.41 48	84.63 48	87.41 116	85.44 118
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		74.23 104	74.84 115	73.52 96	80.42 107	81.46 115	79.77 96	61.06 153	67.23 112	63.67 110	59.56 142	68.74 126	67.90 101	80.25 128	79.37 123	88.31 79	87.26 78

HyFIR lowres test		69.47 150	68.94 164	70.09 130	76.77 143	82.93 103	76.63 139	60.17 168	59.00 171	54.03 151	40.54 249	65.23 141	67.89 102	76.54 182	78.30 145	85.03 186	80.07 177

viewdifsd2359ckpt07		74.55 101	76.09 107	72.75 101	79.51 118	81.32 117	80.29 90	58.44 191	68.61 103	65.63 95	68.17 93	71.24 102	67.64 103	80.13 131	77.62 156	84.96 190	85.56 112

FA-MVS(training)		73.66 108	74.95 113	72.15 104	78.63 126	80.46 131	78.92 113	54.79 216	69.71 96	65.37 97	62.04 126	66.89 136	67.10 104	80.72 112	79.87 108	88.10 91	84.97 128

PVSNet_Blended_VisFu		76.57 76	77.90 74	75.02 84	80.56 104	86.58 52	79.24 106	66.18 74	64.81 128	68.18 77	65.61 111	71.45 95	67.05 105	84.16 59	81.80 73	88.90 67	90.92 44

PVSNet_BlendedMVS		76.21 85	77.52 80	74.69 88	79.46 119	83.79 81	77.50 128	64.34 92	69.88 91	71.88 49	68.54 91	70.42 111	67.05 105	83.48 67	79.63 112	87.89 103	86.87 82

PVSNet_Blended		76.21 85	77.52 80	74.69 88	79.46 119	83.79 81	77.50 128	64.34 92	69.88 91	71.88 49	68.54 91	70.42 111	67.05 105	83.48 67	79.63 112	87.89 103	86.87 82

v10		70.22 141	69.76 154	70.74 115	74.79 167	80.30 135	79.22 107	59.81 174	57.71 180	56.58 140	54.22 182	55.31 191	66.95 108	78.28 157	77.47 161	87.12 125	85.07 126

v1192		69.50 149	68.83 165	70.29 126	74.49 171	80.92 125	78.55 116	60.54 161	55.04 204	54.21 148	52.79 200	52.33 223	66.92 109	77.88 164	77.35 166	87.04 126	85.51 115

CHOSEN 1792x2688		69.20 153	69.26 160	69.13 140	76.86 142	78.93 148	77.27 131	60.12 170	61.86 153	54.42 147	42.54 242	61.61 153	66.91 110	78.55 155	78.14 147	79.23 225	83.23 147

v1921920		69.03 154	68.32 173	69.86 132	74.03 176	80.37 132	77.55 126	60.25 167	54.62 208	53.59 162	52.36 207	51.50 229	66.75 111	77.17 173	76.69 175	86.96 127	85.56 112

v144192		69.34 151	68.68 169	70.12 129	74.06 175	80.54 128	78.08 124	60.54 161	54.99 206	54.13 150	52.92 198	52.80 221	66.73 112	77.13 174	76.72 173	87.15 119	85.63 111

v1240		68.64 159	67.89 180	69.51 137	73.89 178	80.26 136	76.73 138	59.97 173	53.43 216	53.08 166	51.82 210	50.84 232	66.62 113	76.79 178	76.77 172	86.78 134	85.34 121

diffmvs_AUTHOR		74.91 99	77.47 83	71.92 106	75.60 159	80.50 129	79.48 104	60.02 172	72.41 80	64.39 105	70.63 68	73.27 79	66.55 114	79.97 132	78.34 144	85.46 171	87.17 79

viewmambaseed2359dif		73.61 110	75.14 111	71.84 108	75.87 152	79.69 138	78.99 111	60.42 165	68.19 106	64.15 107	67.85 97	71.20 103	66.55 114	77.41 170	75.78 184	85.04 185	85.85 101

v1144		69.93 145	69.36 159	70.61 119	74.89 166	80.93 123	79.11 109	60.64 159	55.97 196	55.31 145	53.85 185	54.14 203	66.54 116	78.10 159	77.44 162	87.14 122	85.09 125

diffmvs		74.86 100	77.37 87	71.93 105	75.62 157	80.35 133	79.42 105	60.15 169	72.81 76	64.63 104	71.51 62	73.11 84	66.53 117	79.02 149	77.98 148	85.25 181	86.83 84
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt11		72.49 118	74.10 118	70.61 119	75.87 152	78.53 156	76.92 133	58.16 193	65.69 122	61.34 118	67.21 103	68.35 129	66.51 118	77.91 162	75.60 186	84.86 193	85.43 119

viewmsd2359difaftdt		72.49 118	74.10 118	70.61 119	75.87 152	78.53 156	76.92 133	58.16 193	65.69 122	61.33 119	67.21 103	68.34 130	66.51 118	77.91 162	75.60 186	84.86 193	85.42 120

viewmamba		75.22 97	77.49 82	72.57 102	76.60 144	81.01 122	79.77 96	61.77 146	73.47 73	65.40 96	70.61 69	73.19 82	66.50 120	79.78 135	78.52 140	85.35 174	85.88 100

dtuplus		73.53 111	74.92 114	71.90 107	76.10 146	79.51 141	79.17 108	60.44 164	67.27 111	64.19 106	66.90 107	71.30 101	66.48 121	77.95 161	75.99 182	85.02 187	85.54 114

v2v482		70.05 144	69.46 158	70.74 115	74.62 170	80.32 134	79.00 110	60.62 160	57.41 182	56.89 137	55.43 169	55.14 193	66.39 122	77.25 172	77.14 168	86.90 128	83.57 145

v8		70.23 140	69.86 152	70.67 118	74.69 169	79.82 137	78.79 114	59.18 181	58.80 172	58.20 131	55.00 171	57.33 178	66.31 123	77.51 168	76.71 174	86.82 131	83.88 141

onestephybrid01		75.35 95	77.46 84	72.88 99	77.26 139	81.58 111	79.70 100	62.48 137	71.05 87	66.34 92	70.12 75	73.78 76	66.25 124	80.29 124	78.58 138	85.23 182	86.83 84

IterMVS-LS		71.69 126	72.82 132	70.37 125	77.54 136	76.34 182	75.13 150	60.46 163	61.53 157	57.57 133	64.89 116	67.33 133	66.04 125	77.09 175	77.37 165	85.48 170	85.18 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		71.52 128	69.87 151	73.44 97	82.21 78	79.35 143	79.52 102	64.59 89	66.15 117	61.87 114	53.21 193	56.09 187	65.85 126	78.94 150	78.50 141	86.60 141	76.85 206

V42		68.76 158	69.63 155	67.74 153	64.93 234	78.01 160	78.30 122	56.48 206	58.65 173	56.30 141	54.26 180	57.03 181	64.85 127	77.47 169	77.01 170	85.60 166	84.96 129

hybridnocas07		74.37 103	77.06 94	71.23 111	75.13 163	79.34 144	78.54 119	59.23 180	72.65 77	64.95 101	71.17 64	73.19 82	64.72 128	79.45 142	77.65 155	84.81 196	85.97 95

hybrid		74.08 105	76.76 101	70.95 114	74.70 168	79.04 146	78.40 120	58.80 189	72.23 81	64.74 103	70.55 70	73.40 77	64.45 129	79.06 148	77.38 163	84.61 197	85.64 109

EPNet		79.08 60	80.62 57	77.28 55	88.90 39	83.17 92	83.65 59	72.41 35	74.41 64	67.15 88	76.78 37	74.37 71	64.43 130	83.70 64	83.69 57	87.15 119	88.19 67
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thisisatest0530		71.48 129	73.01 128	69.70 135	73.83 179	78.62 154	74.53 158	59.12 182	64.13 134	58.63 127	64.60 119	58.63 167	64.27 131	80.28 126	80.17 105	87.82 106	84.64 134

tttt0517		71.41 130	72.95 129	69.60 136	73.70 181	78.70 153	74.42 162	59.12 182	63.89 138	58.35 130	64.56 120	58.39 174	64.27 131	80.29 124	80.17 105	87.74 108	84.69 133

RPSCF		67.64 173	71.25 141	63.43 200	61.86 240	70.73 223	67.26 217	50.86 238	74.20 67	58.91 124	67.49 100	69.33 118	64.10 133	71.41 211	68.45 231	77.61 229	77.17 203

LTVRE_ROB	59.44 16	61.82 226	62.64 229	60.87 215	72.83 190	77.19 173	64.37 235	58.97 184	33.56 265	28.00 253	52.59 206	42.21 256	63.93 134	74.52 192	76.28 179	77.15 232	82.13 151
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		72.06 122	74.24 116	69.51 137	70.39 209	75.97 185	76.91 136	57.36 200	64.64 130	61.39 117	68.86 85	63.76 145	63.46 135	81.44 92	79.70 111	87.56 114	85.31 122

PMMVS		65.06 192	69.17 162	60.26 218	55.25 264	63.43 250	66.71 224	43.01 259	62.41 148	50.64 179	69.44 80	67.04 135	63.29 136	74.36 194	73.54 200	82.68 211	73.99 230

IterMVS-SCA-FT		66.89 182	69.22 161	64.17 191	71.30 204	75.64 187	71.33 193	53.17 224	57.63 181	49.08 189	60.72 133	60.05 160	63.09 137	74.99 190	73.92 197	77.07 233	81.57 161

EPP-MVSNet		74.00 107	77.41 86	70.02 131	80.53 105	83.91 78	74.99 153	62.68 132	65.06 126	49.77 185	68.68 89	72.09 89	63.06 138	82.49 81	80.73 88	89.12 63	88.91 62

CHOSEN 280x420		58.70 237	61.88 235	54.98 241	55.45 263	50.55 268	64.92 232	40.36 261	55.21 201	38.13 237	48.31 224	63.76 145	63.03 139	73.73 198	68.58 228	68.00 263	73.04 233

TinyColmap		62.84 209	61.03 238	64.96 185	69.61 214	71.69 219	68.48 213	59.76 175	55.41 199	47.69 201	47.33 232	34.20 267	62.76 140	74.52 192	72.59 206	81.44 215	71.47 235

Fast-Effi-MVS+-dtu		68.34 160	69.47 157	67.01 169	75.15 161	77.97 166	77.12 132	55.40 213	57.87 175	46.68 206	56.17 163	60.39 156	62.36 141	76.32 183	76.25 181	85.35 174	81.34 162

Anonymous20231211		71.90 123	72.48 134	71.21 112	80.14 110	81.53 113	76.92 133	62.89 121	64.46 133	58.94 123	43.80 238	70.98 104	62.22 142	80.70 113	80.19 104	86.18 149	85.73 105

DCV-MVSNet		73.65 109	75.78 108	71.16 113	80.19 109	79.27 145	77.45 130	61.68 149	66.73 114	58.72 126	65.31 114	69.96 114	62.19 143	81.29 98	80.97 83	86.74 135	86.91 81

USDC		67.36 177	67.90 179	66.74 174	71.72 196	75.23 194	71.58 192	60.28 166	67.45 110	50.54 181	60.93 131	45.20 251	62.08 144	76.56 181	74.50 195	84.25 199	75.38 220

Anonymous202405211			72.16 137		80.85 93	81.85 110	76.88 137	65.40 82	62.89 146		46.35 234	67.99 131	62.05 145	81.15 102	80.38 100	85.97 160	84.50 135

MS-PatchMatch		70.17 142	70.49 146	69.79 133	80.98 92	77.97 166	77.51 127	58.95 185	62.33 149	55.22 146	53.14 194	65.90 139	62.03 146	79.08 147	77.11 169	84.08 201	77.91 196

baseline2		69.69 146	70.27 148	69.01 142	75.72 156	77.13 174	73.82 173	58.94 186	61.35 158	57.09 136	61.68 127	57.17 180	61.99 147	78.10 159	76.58 176	86.48 145	79.85 178

v148		67.85 167	67.53 181	68.23 148	73.25 184	77.57 172	74.26 166	57.36 200	55.70 198	57.45 135	53.53 187	55.42 190	61.96 148	75.23 188	73.92 197	85.08 184	81.32 163

pmmvs4		67.89 166	67.39 185	68.48 147	71.60 200	73.57 211	74.45 159	60.98 156	64.65 129	57.97 132	54.95 172	51.73 228	61.88 149	73.78 197	75.11 191	83.99 203	77.91 196

CostFormer		68.92 155	69.58 156	68.15 149	75.98 150	76.17 184	78.22 123	51.86 233	65.80 120	61.56 116	63.57 122	62.83 148	61.85 150	70.40 227	68.67 224	79.42 223	79.62 182

tpm cat1		65.41 188	63.81 218	67.28 164	75.61 158	72.88 213	75.32 144	52.85 227	62.97 144	63.66 111	53.24 192	53.29 218	61.83 151	65.54 247	64.14 249	74.43 247	74.60 223

CANet_DTU		73.29 113	76.96 96	69.00 143	77.04 141	82.06 109	79.49 103	56.30 211	67.85 109	53.29 165	71.12 65	70.37 113	61.81 152	81.59 86	80.96 84	86.09 152	84.73 132

MGCFI-Net		76.55 77	81.71 48	70.52 123	81.71 79	84.62 71	75.02 152	62.17 141	82.91 39	53.58 163	72.78 56	75.87 66	61.75 153	82.96 74	82.61 66	88.86 70	90.26 52

baseline		70.45 138	74.09 120	66.20 177	70.95 206	75.67 186	74.26 166	53.57 220	68.33 105	58.42 128	69.87 77	71.45 95	61.55 154	74.84 191	74.76 194	78.42 227	83.72 143

SCA		65.40 189	66.58 191	64.02 194	70.65 207	73.37 212	67.35 216	53.46 222	63.66 139	54.14 149	60.84 132	60.20 159	61.50 155	69.96 232	68.14 233	77.01 234	69.91 238

GA-MVS		68.14 161	69.17 162	66.93 171	73.77 180	78.50 158	74.45 159	58.28 192	55.11 203	48.44 191	60.08 137	53.99 206	61.50 155	78.43 156	77.57 158	85.13 183	80.54 171

anonymousdsp		65.28 190	67.98 177	62.13 206	58.73 255	73.98 210	67.10 219	50.69 240	48.41 241	47.66 202	54.27 178	52.75 222	61.45 157	76.71 180	80.20 102	87.13 123	89.53 60

v7n		67.05 181	66.94 187	67.17 165	72.35 191	78.97 147	73.26 182	58.88 187	51.16 231	50.90 178	48.21 225	50.11 236	60.96 158	77.70 165	77.38 163	86.68 139	85.05 127

CR-MVSNet		64.83 194	65.54 197	64.01 195	70.64 208	69.41 227	65.97 228	52.74 228	57.81 177	52.65 168	54.27 178	56.31 186	60.92 159	72.20 206	73.09 202	81.12 218	75.69 215

PatchT		61.97 222	64.04 215	59.55 223	60.49 242	67.40 235	56.54 255	48.65 248	56.69 187	52.65 168	51.10 214	52.14 226	60.92 159	72.20 206	73.09 202	78.03 228	75.69 215

dps		64.00 203	62.99 225	65.18 181	73.29 183	72.07 217	68.98 208	53.07 226	57.74 179	58.41 129	55.55 167	47.74 244	60.89 161	69.53 235	67.14 242	76.44 237	71.19 236

IterMVS		66.36 183	68.30 174	64.10 192	69.48 216	74.61 201	73.41 180	50.79 239	57.30 183	48.28 193	60.64 134	59.92 161	60.85 162	74.14 195	72.66 205	81.80 213	78.82 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TDRefinement		66.09 185	65.03 205	67.31 162	69.73 213	76.75 177	75.33 143	64.55 90	60.28 166	49.72 186	45.63 236	42.83 255	60.46 163	75.75 184	75.95 183	84.08 201	78.04 195

PatchmatchNet		64.21 201	64.65 210	63.69 197	71.29 205	68.66 231	69.63 201	51.70 235	63.04 143	53.77 160	59.83 141	58.34 175	60.23 164	68.54 241	66.06 245	75.56 242	68.08 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
gm-plane-assit		57.00 241	57.62 248	56.28 236	76.10 146	62.43 256	47.62 267	46.57 254	33.84 264	23.24 259	37.52 250	40.19 260	59.61 165	79.81 134	77.55 159	84.55 198	72.03 234

0.3-1-1-0.015		65.09 191	65.15 202	65.01 184	66.63 227	75.00 197	71.90 189	54.57 217	56.32 193	53.88 154	53.63 186	58.58 169	59.47 166	68.39 243	68.46 230	83.62 205	75.64 217

0.4-1-1-0.1		65.57 187	65.82 194	65.29 180	67.19 221	75.61 188	72.13 188	55.16 215	57.12 184	53.84 158	54.57 174	58.80 166	59.40 167	69.22 238	69.01 221	83.99 203	76.43 209

0.4-1-1-0.2		64.94 193	65.02 206	64.85 186	66.45 228	74.76 198	71.66 190	54.40 218	55.85 197	53.84 158	53.97 183	58.62 168	59.33 168	68.27 244	68.20 232	83.40 207	75.47 219

IB-MVS	66.94 12	71.21 132	71.66 140	70.68 117	79.18 121	82.83 106	72.61 183	61.77 146	59.66 168	63.44 112	53.26 191	59.65 162	59.16 169	76.78 179	82.11 69	87.90 102	87.33 76
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		71.72 125	72.95 129	70.29 126	81.49 82	83.27 88	75.74 141	67.59 66	68.19 106	49.81 184	61.15 130	49.73 238	58.82 170	84.76 52	82.94 61	88.27 80	80.63 170

ECVR-MVS		72.20 121	73.91 121	70.20 128	81.49 82	83.27 88	75.74 141	67.59 66	68.19 106	49.31 188	55.77 164	62.00 152	58.82 170	84.76 52	82.94 61	88.27 80	80.41 174

dtuonly		61.60 228	64.61 212	58.09 228	59.71 245	62.36 257	72.50 185	42.52 260	58.12 174	43.84 223	54.51 175	62.39 151	58.60 172	71.88 209	69.50 216	71.34 256	73.52 232

UniMVSNet_NR-MVSNet		70.59 136	72.19 135	68.72 144	77.72 134	80.72 127	73.81 174	69.65 49	61.99 151	43.23 224	60.54 135	57.50 177	58.57 173	79.56 139	81.07 82	89.34 55	83.97 138

DU-MVS		69.63 147	70.91 143	68.13 150	75.99 148	79.54 139	73.81 174	69.20 54	61.20 160	43.23 224	58.52 147	53.50 210	58.57 173	79.22 145	80.45 99	87.97 98	83.97 138

COLMAP_ROB	62.73 15	67.66 171	66.76 189	68.70 145	80.49 106	77.98 164	75.29 145	62.95 120	63.62 140	49.96 182	47.32 233	50.72 233	58.57 173	76.87 177	75.50 190	84.94 191	75.33 221
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PM-MVS		60.48 231	60.94 239	59.94 219	58.85 253	66.83 238	64.27 236	51.39 236	55.03 205	48.03 194	50.00 219	40.79 259	58.26 176	69.20 239	67.13 243	78.84 226	77.60 200

SixPastTwentyTwo		61.84 224	62.45 231	61.12 214	69.20 217	72.20 216	62.03 244	57.40 198	46.54 248	38.03 238	57.14 160	41.72 257	58.12 177	69.67 234	71.58 209	81.94 212	78.30 189

thisisatest0515		67.40 176	68.78 166	65.80 179	70.02 211	75.24 193	69.36 203	57.37 199	54.94 207	53.67 161	55.53 168	54.85 198	58.00 178	78.19 158	78.91 134	86.39 146	83.78 142

test1111		71.56 127	73.44 124	69.38 139	81.16 87	82.95 102	74.99 153	67.68 64	66.89 113	46.33 208	55.19 170	60.91 155	57.99 179	84.59 55	82.70 65	88.12 87	80.85 167

CMPMVS	47.78 17	62.49 216	62.52 230	62.46 203	70.01 212	70.66 224	62.97 240	51.84 234	51.98 223	56.71 139	42.87 240	53.62 207	57.80 180	72.23 204	70.37 213	75.45 244	75.91 212
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GBi-Net		70.78 133	73.37 126	67.76 151	72.95 186	78.00 161	75.15 147	62.72 127	64.13 134	51.44 173	58.37 150	69.02 121	57.59 181	81.33 95	80.72 89	86.70 136	82.02 152

test1		70.78 133	73.37 126	67.76 151	72.95 186	78.00 161	75.15 147	62.72 127	64.13 134	51.44 173	58.37 150	69.02 121	57.59 181	81.33 95	80.72 89	86.70 136	82.02 152

FMVSNet2		70.39 139	72.67 133	67.72 154	72.95 186	78.00 161	75.15 147	62.69 131	63.29 142	51.25 177	55.64 165	68.49 128	57.59 181	80.91 106	80.35 101	86.70 136	82.02 152

FMVSNet3		70.49 137	72.90 131	67.67 156	72.88 189	77.98 164	74.96 156	62.72 127	64.13 134	51.44 173	58.37 150	69.02 121	57.43 184	79.43 143	79.57 117	86.59 142	81.81 159

MDTV_nov1_ep13		64.37 198	65.24 199	63.37 201	68.94 218	70.81 222	72.40 187	50.29 242	60.10 167	53.91 153	60.07 138	59.15 164	57.21 185	69.43 237	67.30 240	77.47 230	69.78 240

FMVSNet1		68.84 156	70.47 147	66.94 170	71.35 203	77.68 169	74.71 157	62.35 139	56.93 186	49.94 183	50.01 217	64.59 142	57.07 186	81.33 95	80.72 89	86.25 147	82.00 155

dtuonlycased		57.34 239	58.57 244	55.91 237	58.42 256	71.89 218	66.93 220	44.93 257	50.31 234	32.39 246	37.40 251	54.78 199	57.03 187	60.42 257	60.80 255	75.75 239	74.39 225

UniMVSNet_ETH3D		67.18 180	67.03 186	67.36 161	74.44 172	78.12 159	74.07 169	66.38 72	52.22 221	46.87 203	48.64 223	51.84 227	56.96 188	77.29 171	78.53 139	85.42 172	82.59 149

pmmvs-eth3d		63.52 204	62.44 232	64.77 187	66.82 226	70.12 226	69.41 202	59.48 177	54.34 212	52.71 167	46.24 235	44.35 253	56.93 189	72.37 201	73.77 199	83.30 208	75.91 212

FC-MVSNet-train		72.60 117	75.07 112	69.71 134	81.10 91	78.79 152	73.74 176	65.23 85	66.10 118	53.34 164	70.36 73	63.40 147	56.92 190	81.44 92	80.96 84	87.93 100	84.46 136

tfpn200view9		68.11 162	68.72 168	67.40 160	77.83 132	78.93 148	74.28 164	62.81 123	56.64 188	46.82 204	52.65 204	53.47 213	56.59 191	80.41 119	78.43 142	86.11 150	80.52 172

thres400		67.95 165	68.62 170	67.17 165	77.90 129	78.59 155	74.27 165	62.72 127	56.34 192	45.77 214	53.00 196	53.35 216	56.46 192	80.21 129	78.43 142	85.91 162	80.43 173

thres200		67.98 164	68.55 171	67.30 163	77.89 131	78.86 150	74.18 168	62.75 125	56.35 191	46.48 207	52.98 197	53.54 209	56.46 192	80.41 119	77.97 149	86.05 155	79.78 180

usedtu_blend_shiyan5		64.27 199	64.70 209	63.77 196	59.06 248	74.03 206	71.65 191	56.37 207	51.17 227	53.88 154	52.71 201	58.58 169	56.43 194	70.13 228	68.14 233	85.26 177	78.14 193

blend_shiyan4		64.82 195	65.21 200	64.37 190	65.04 231	74.06 205	70.30 198	55.30 214	55.39 200	53.88 154	52.71 201	58.58 169	56.43 194	69.45 236	68.13 238	85.30 176	78.14 193

FE-MVSNET3		64.07 202	64.71 208	63.32 202	59.06 248	74.03 206	68.92 209	56.37 207	51.17 227	53.88 154	52.71 201	58.58 169	56.43 194	70.13 228	68.14 233	85.26 177	78.20 190

MVS-HIRNet		54.41 247	52.10 255	57.11 233	58.99 252	56.10 263	49.68 265	49.10 245	46.18 249	52.15 172	33.18 259	46.11 248	56.10 197	63.19 254	59.70 258	76.64 236	60.25 259

Baseline_NR-MVSNet		67.53 175	68.77 167	66.09 178	75.99 148	74.75 199	72.43 186	68.41 58	61.33 159	38.33 236	51.31 212	54.13 205	56.03 198	79.22 145	78.19 146	85.37 173	82.45 150

thres100view900		67.60 174	68.02 176	67.12 167	77.83 132	77.75 168	73.90 171	62.52 135	56.64 188	46.82 204	52.65 204	53.47 213	55.92 199	78.77 152	77.62 156	85.72 163	79.23 184

test-mter		60.84 230	64.62 211	56.42 235	55.99 262	64.18 244	65.39 230	34.23 265	54.39 211	46.21 210	57.40 159	59.49 163	55.86 200	71.02 218	69.65 215	80.87 220	76.20 211

tpmrst		62.00 221	62.35 233	61.58 210	71.62 199	64.14 245	69.07 205	48.22 252	62.21 150	53.93 152	58.26 154	55.30 192	55.81 201	63.22 253	62.62 252	70.85 257	70.70 237

TranMVSNet+NR-MVSNet		69.25 152	70.81 144	67.43 159	77.23 140	79.46 142	73.48 179	69.66 48	60.43 165	39.56 232	58.82 146	53.48 212	55.74 202	79.59 137	81.21 80	88.89 68	82.70 148

thres600view7		67.68 170	68.43 172	66.80 172	77.90 129	78.86 150	73.84 172	62.75 125	56.07 195	44.70 221	52.85 199	52.81 220	55.58 203	80.41 119	77.77 152	86.05 155	80.28 175

Vis-MVSNet		72.77 116	77.20 92	67.59 158	74.19 174	84.01 77	76.61 140	61.69 148	60.62 164	50.61 180	70.25 74	71.31 100	55.57 204	83.85 62	82.28 67	86.90 128	88.08 68
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		67.24 178	66.94 187	67.60 157	78.73 124	81.35 116	73.28 181	59.49 176	46.89 247	51.42 176	43.65 239	53.49 211	55.50 205	81.38 94	80.66 95	87.15 119	81.17 164

test-LLR		64.42 197	64.36 213	64.49 189	75.02 164	63.93 247	66.61 225	61.96 143	54.41 209	47.77 199	57.46 157	60.25 157	55.20 206	70.80 219	69.33 217	80.40 221	74.38 226

TESTMET0.1,1		61.10 229	64.36 213	57.29 231	57.53 257	63.93 247	66.61 225	36.22 264	54.41 209	47.77 199	57.46 157	60.25 157	55.20 206	70.80 219	69.33 217	80.40 221	74.38 226

wanda-best-256-512		62.84 209	63.46 222	62.12 207	59.06 248	74.03 206	68.92 209	56.37 207	51.17 227	48.02 195	48.12 226	54.93 196	55.08 208	70.13 228	68.14 233	85.26 177	77.73 198

FE-blended-shiyan7		62.84 209	63.46 222	62.12 207	59.06 248	74.03 206	68.92 209	56.37 207	51.17 227	48.02 195	48.12 226	54.93 196	55.08 208	70.13 228	68.14 233	85.26 177	77.73 198

blended_shiyan8		62.98 206	63.65 220	62.21 204	59.20 246	74.17 203	69.03 207	56.52 204	51.08 233	47.96 197	48.07 229	55.02 194	55.00 210	70.43 225	68.60 226	85.52 167	78.15 192

blended_shiyan6		62.98 206	63.66 219	62.19 205	59.20 246	74.17 203	69.04 206	56.52 204	51.09 232	47.91 198	48.11 228	55.02 194	54.98 211	70.43 225	68.59 227	85.51 168	78.20 190

dmvs_re		67.22 179	67.92 178	66.40 176	75.94 151	70.55 225	74.97 155	63.87 97	57.07 185	44.75 219	54.29 177	56.72 183	54.65 212	79.53 140	77.51 160	84.20 200	79.78 180

UA-Net		74.47 102	77.80 76	70.59 122	85.33 57	85.40 64	73.54 177	65.98 78	60.65 163	56.00 142	72.11 58	79.15 50	54.63 213	83.13 73	82.25 68	88.04 93	81.92 158

IS_MVSNet		73.33 112	77.34 88	68.65 146	81.29 85	83.47 86	74.45 159	63.58 102	65.75 121	48.49 190	67.11 106	70.61 110	54.63 213	84.51 56	83.58 58	89.48 53	86.34 92

baseline1		70.10 143	72.17 136	67.69 155	79.74 115	76.80 176	73.91 170	64.38 91	62.74 147	48.30 192	64.94 115	64.08 144	54.17 215	81.46 90	78.92 133	85.66 165	76.22 210

usedtu_dtu_shiyan1		66.26 184	68.15 175	64.06 193	67.01 222	76.52 180	70.61 197	61.10 151	61.86 153	44.86 217	49.77 220	56.69 184	53.97 216	77.58 167	77.88 150	86.80 133	76.78 207

gbinet_0.2-2-1-0.02		62.72 212	63.87 217	61.39 212	57.04 259	74.70 200	69.09 204	57.36 200	47.91 242	45.94 213	47.47 231	55.96 189	53.90 217	71.07 216	68.83 223	84.99 189	81.15 165

tpm		62.41 217	63.15 224	61.55 211	72.24 192	63.79 249	71.31 194	46.12 256	57.82 176	55.33 144	59.90 140	54.74 200	53.63 218	67.24 246	64.29 248	70.65 258	74.25 229

MDTV_nov1_ep13_2view		60.16 232	60.51 241	59.75 220	65.39 230	69.05 230	68.00 214	48.29 250	51.99 222	45.95 212	48.01 230	49.64 239	53.39 219	68.83 240	66.52 244	77.47 230	69.55 241

UniMVSNet (Re)		69.53 148	71.90 138	66.76 173	76.42 145	80.93 123	72.59 184	68.03 61	61.75 155	41.68 229	58.34 153	57.23 179	53.27 220	79.53 140	80.62 97	88.57 75	84.90 130

RPMNet		61.71 227	62.88 226	60.34 217	69.51 215	69.41 227	63.48 238	49.23 244	57.81 177	45.64 215	50.51 215	50.12 235	53.13 221	68.17 245	68.49 229	81.07 219	75.62 218

tfpnnormal		64.27 199	63.64 221	65.02 183	75.84 155	75.61 188	71.24 195	62.52 135	47.79 243	42.97 226	42.65 241	44.49 252	52.66 222	78.77 152	76.86 171	84.88 192	79.29 183

MDA-MVSNet-bldmvs		53.37 250	53.01 254	53.79 245	43.67 269	67.95 234	59.69 250	57.92 196	43.69 251	32.41 245	41.47 243	27.89 273	52.38 223	56.97 264	65.99 246	76.68 235	67.13 246

NR-MVSNet		68.79 157	70.56 145	66.71 175	77.48 137	79.54 139	73.52 178	69.20 54	61.20 160	39.76 231	58.52 147	50.11 236	51.37 224	80.26 127	80.71 93	88.97 66	83.59 144

EPMVS		60.00 233	61.97 234	57.71 230	68.46 219	63.17 253	64.54 234	48.23 251	63.30 141	44.72 220	60.19 136	56.05 188	50.85 225	65.27 250	62.02 253	69.44 260	63.81 253

CVMVSNet		62.55 214	65.89 192	58.64 226	66.95 224	69.15 229	66.49 227	56.29 212	52.46 220	32.70 244	59.27 144	58.21 176	50.09 226	71.77 210	71.39 210	79.31 224	78.99 186

pmmvs5		62.37 220	64.04 215	60.42 216	65.03 232	71.67 220	67.17 218	52.70 230	50.30 235	44.80 218	54.23 181	51.19 231	49.37 227	72.88 200	73.48 201	83.45 206	74.55 224

UGNet		72.78 115	77.67 77	67.07 168	71.65 198	83.24 90	75.20 146	63.62 101	64.93 127	56.72 138	71.82 60	73.30 78	49.02 228	81.02 104	80.70 94	86.22 148	88.67 64
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		65.62 186	67.42 183	63.53 199	73.66 182	76.39 181	69.66 200	60.87 158	49.73 238	43.97 222	51.24 213	57.00 182	48.16 229	79.89 133	77.84 151	84.85 195	79.82 179

gg-mvs-nofinetune		62.55 214	65.05 204	59.62 222	78.72 125	77.61 170	70.83 196	53.63 219	39.71 260	22.04 263	36.36 254	64.32 143	47.53 230	81.16 101	79.03 131	85.00 188	77.17 203

pmmvs6		62.41 217	62.88 226	61.87 209	71.38 202	75.18 196	67.76 215	59.45 178	41.64 255	42.52 228	37.33 252	52.91 219	46.87 231	77.67 166	76.26 180	83.23 209	79.18 185

ADS-MVSNet		55.94 244	58.01 245	53.54 246	62.48 239	58.48 260	59.12 252	46.20 255	59.65 169	42.88 227	52.34 208	53.31 217	46.31 232	62.00 255	60.02 257	64.23 265	60.24 260

pmmvs3		47.65 255	49.08 260	45.99 255	44.61 267	54.79 264	50.04 263	31.95 268	33.91 263	29.90 248	30.37 261	33.53 268	46.31 232	63.50 251	63.67 250	73.14 252	63.77 254

TransMVSNet (Re)		64.74 196	65.66 196	63.66 198	77.40 138	75.33 192	69.86 199	62.67 133	47.63 244	41.21 230	50.01 217	52.33 223	45.31 234	79.57 138	77.69 154	85.49 169	77.07 205

FE-MVSNET2		58.78 236	60.53 240	56.73 234	57.08 258	72.23 215	62.74 243	59.35 179	47.17 245	30.52 247	34.62 257	43.62 254	44.57 235	75.24 187	76.57 177	86.11 150	74.30 228

CDS-MVSNet		67.65 172	69.83 153	65.09 182	75.39 160	76.55 179	74.42 162	63.75 98	53.55 214	49.37 187	59.41 143	62.45 149	44.44 236	79.71 136	79.82 110	83.17 210	77.36 202
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		59.58 234	62.81 228	55.81 238	66.03 229	65.64 243	63.86 237	48.74 247	49.95 237	37.07 240	54.77 173	58.54 173	44.44 236	72.29 203	71.79 207	74.70 246	66.66 247

EPNet_dtu		68.08 163	71.00 142	64.67 188	79.64 117	68.62 232	75.05 151	63.30 105	66.36 116	45.27 216	67.40 101	66.84 137	43.64 238	75.37 186	74.98 193	81.15 217	77.44 201
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		57.24 240	60.02 242	53.99 244	56.45 261	62.74 254	65.27 231	47.03 253	55.14 202	39.55 233	40.88 245	53.42 215	41.83 239	72.35 202	71.10 212	73.79 249	64.50 252

ambc			53.42 252		64.99 233	63.36 251	49.96 264		47.07 246	37.12 239	28.97 263	16.36 276	41.82 240	75.10 189	67.34 239	71.55 255	75.72 214

FPMVS		51.87 252	50.00 258	54.07 243	66.83 225	57.25 261	60.25 249	50.91 237	50.25 236	34.36 242	36.04 255	32.02 269	41.49 241	58.98 261	56.07 260	70.56 259	59.36 261

CP-MVSNet		62.68 213	65.49 198	59.40 224	71.84 194	75.34 191	62.87 241	67.04 69	52.64 218	27.19 254	53.38 189	48.15 242	41.40 242	71.26 212	75.68 185	86.07 153	82.00 155

PS-CasMVS		62.38 219	65.06 203	59.25 225	71.73 195	75.21 195	62.77 242	66.99 70	51.94 225	26.96 255	52.00 209	47.52 245	41.06 243	71.16 215	75.60 186	85.97 160	81.97 157

PEN-MVS		62.96 208	65.77 195	59.70 221	73.98 177	75.45 190	63.39 239	67.61 65	52.49 219	25.49 256	53.39 188	49.12 240	40.85 244	71.94 208	77.26 167	86.86 130	80.72 169

MIMVSNet		58.52 238	61.34 237	55.22 240	60.76 241	67.01 237	66.81 222	49.02 246	56.43 190	38.90 234	40.59 248	54.54 202	40.57 245	73.16 199	71.65 208	75.30 245	66.00 248

pmnet_mix02		55.30 245	57.01 249	53.30 247	64.14 235	59.09 259	58.39 254	50.24 243	53.47 215	38.68 235	49.75 221	45.86 249	40.14 246	65.38 249	60.22 256	68.19 262	65.33 250

Vis-MVSNet (Re-imp)		67.83 168	73.52 123	61.19 213	78.37 127	76.72 178	66.80 223	62.96 119	65.50 124	34.17 243	67.19 105	69.68 117	39.20 247	79.39 144	79.44 122	85.68 164	76.73 208

FE-MVSNET		52.98 251	55.99 251	49.47 251	49.71 265	65.83 240	54.09 258	56.91 203	40.70 257	16.86 271	32.90 260	40.15 261	37.83 248	69.80 233	73.04 204	81.41 216	69.49 242

DTE-MVSNet		61.85 223	64.96 207	58.22 227	74.32 173	74.39 202	61.01 246	67.85 63	51.76 226	21.91 264	53.28 190	48.17 241	37.74 249	72.22 205	76.44 178	86.52 144	78.49 188

EU-MVSNet		54.63 246	58.69 243	49.90 250	56.99 260	62.70 255	56.41 256	50.64 241	45.95 250	23.14 260	50.42 216	46.51 247	36.63 250	65.51 248	64.85 247	75.57 241	74.91 222

Anonymous20231206		56.36 243	57.80 247	54.67 242	70.08 210	66.39 239	60.46 248	57.54 197	49.50 240	29.30 251	33.86 258	46.64 246	35.18 251	70.44 223	68.88 222	75.47 243	68.88 244

WR-MVS		63.03 205	67.40 184	57.92 229	75.14 162	77.60 171	60.56 247	66.10 75	54.11 213	23.88 257	53.94 184	53.58 208	34.50 252	73.93 196	77.71 153	87.35 117	80.94 166

usedtu_dtu_shiyan2		49.27 253	50.47 256	47.86 253	35.37 273	64.10 246	58.53 253	53.10 225	31.42 268	29.57 249	27.09 266	38.06 265	34.31 253	63.35 252	63.36 251	76.27 238	65.93 249

WR-MVS_H		61.83 225	65.87 193	57.12 232	71.72 196	76.87 175	61.45 245	66.19 73	51.97 224	22.92 261	53.13 195	52.30 225	33.80 254	71.03 217	75.00 192	86.65 140	80.78 168

PMVS	39.38 18	46.06 259	43.30 262	49.28 252	62.93 236	38.75 270	41.88 269	53.50 221	33.33 266	35.46 241	28.90 264	31.01 270	33.04 255	58.61 263	54.63 264	68.86 261	57.88 262
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test0.0.03 1		58.80 235	61.58 236	55.56 239	75.02 164	68.45 233	59.58 251	61.96 143	52.74 217	29.57 249	49.75 221	54.56 201	31.46 256	71.19 213	69.77 214	75.75 239	64.57 251

PatchmatchNet1												40.11 262	29.66 257	59.57 259	55.18 261	57.66 266	53.88 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		47.35 256	50.13 257	44.11 257	59.98 243	51.64 266	51.86 262	44.80 258	49.58 239	20.76 266	40.65 246	40.05 263	29.64 258	59.84 258	55.15 262	57.63 267	54.00 263

DeepMVS_CX						18.74 276	18.55 275	8.02 270	26.96 269	7.33 274	23.81 268	13.05 277	25.99 259	25.17 270		22.45 277	36.25 270

MIMVSNet1		49.27 253	53.25 253	44.62 256	44.61 267	61.52 258	53.61 259	52.18 231	41.62 256	18.68 268	28.14 265	41.58 258	25.50 260	68.46 242	69.04 219	73.15 251	62.37 257

Gipuma		36.38 262	35.80 264	37.07 259	45.76 266	33.90 271	29.81 271	48.47 249	39.91 259	18.02 269	8.00 276	8.14 280	25.14 261	59.29 260	61.02 254	55.19 269	40.31 267
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testgi		54.39 248	57.86 246	50.35 249	71.59 201	67.24 236	54.95 257	53.25 223	43.36 252	23.78 258	44.64 237	47.87 243	24.96 262	70.45 222	68.66 225	73.60 250	62.78 256

new_pmnet		38.40 261	42.64 263	33.44 261	37.54 272	45.00 269	36.60 270	32.72 267	40.27 258	12.72 272	29.89 262	28.90 271	24.78 263	53.17 265	52.90 265	56.31 268	48.34 265

FC-MVSNet-test		56.90 242	65.20 201	47.21 254	66.98 223	63.20 252	49.11 266	58.60 190	59.38 170	11.50 273	65.60 112	56.68 185	24.66 264	71.17 214	71.36 211	72.38 253	69.02 243

test20.03		53.93 249	56.28 250	51.19 248	72.19 193	65.83 240	53.20 260	61.08 152	42.74 253	22.08 262	37.07 253	45.76 250	24.29 265	70.44 223	69.04 219	74.31 248	63.05 255

EMVS		20.98 266	17.15 270	25.44 263	39.51 271	19.37 275	12.66 276	39.59 263	19.10 271	6.62 276	9.27 274	4.40 283	22.43 266	17.99 272	24.40 270	31.81 274	25.53 273

E-PMN		21.77 265	18.24 268	25.89 262	40.22 270	19.58 274	12.46 277	39.87 262	18.68 272	6.71 275	9.57 273	4.31 284	22.36 267	19.89 271	27.28 269	33.73 273	28.34 272

new-patchmatchnet		46.97 257	49.47 259	44.05 258	62.82 237	56.55 262	45.35 268	52.01 232	42.47 254	17.04 270	35.73 256	35.21 266	21.84 268	61.27 256	54.83 263	65.26 264	60.26 258

test_method		22.26 264	25.94 266	17.95 266	3.24 278	7.17 278	23.83 273	7.27 271	37.35 262	20.44 267	21.87 270	39.16 264	18.67 269	34.56 267	20.84 271	34.28 272	20.64 275

MVE	19.12 19	20.47 267	23.27 267	17.20 267	12.66 276	25.41 273	10.52 278	34.14 266	14.79 275	6.53 277	8.79 275	4.68 282	16.64 270	29.49 269	41.63 266	22.73 276	38.11 268
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		11.35 268	17.29 269	4.42 269	6.68 277	7.99 277	2.60 281	0.92 273	16.92 273	0.48 281	22.62 269	12.56 278	9.83 271	17.93 273	14.55 272	6.00 278	28.50 271

MVS_clip		8.39 269	13.78 271	2.10 270	1.74 280	3.70 280	1.20 282	0.34 274	14.88 274	0.07 283	20.38 271	11.54 279	7.32 272	13.39 274	11.44 273	1.94 279	21.14 274

WB-MVS		40.01 260	45.06 261	34.13 260	58.84 254	53.28 265	28.60 272	58.10 195	32.93 267	4.65 278	40.92 244	28.33 272	7.26 273	58.86 262	56.09 259	47.36 270	44.98 266

PMMVS2		25.60 263	29.75 265	20.76 265	28.00 274	30.93 272	23.10 274	29.18 269	23.14 270	1.46 279	18.23 272	16.54 275	5.08 274	40.22 266	41.40 267	37.76 271	37.79 269

tmp_tt				14.50 268	14.68 275	7.17 278	10.46 279	2.21 272	37.73 261	28.71 252	25.26 267	16.98 274	4.37 275	31.49 268	29.77 268	26.56 275

VLMVS		3.55 270	5.54 272	1.24 271	1.79 279	2.25 281	0.89 283	0.17 275	6.40 276	0.53 280	5.78 277	7.21 281	2.77 276	3.56 275	2.98 274	1.27 280	10.57 277

MVS_baseline		2.20 271	3.80 273	0.33 272	0.11 281	0.12 282	0.03 285	0.00 279	3.77 277	0.00 285	5.12 278	3.54 285	1.81 277	1.56 276	1.72 275	0.01 281	10.79 276

GG-mvs-BLEND		46.86 258	67.51 182	22.75 264	0.05 282	76.21 183	64.69 233	0.04 276	61.90 152	0.09 282	55.57 166	71.32 99	0.08 278	70.54 221	67.19 241	71.58 254	69.86 239

test123		0.09 272	0.14 275	0.02 273	0.00 284	0.02 283	0.02 286	0.01 277	0.09 279	0.00 285	0.30 279	0.00 287	0.08 278	0.03 278	0.09 277	0.01 281	0.45 278

testmvs		0.09 272	0.15 274	0.02 273	0.01 283	0.02 283	0.05 284	0.01 277	0.11 278	0.01 284	0.26 280	0.01 286	0.06 280	0.10 277	0.10 276	0.01 281	0.43 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 284	0.00 285	0.00 287	0.00 279	0.00 280	0.00 285	0.00 281	0.00 287	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 284	0.00 285	0.00 287	0.00 279	0.00 280	0.00 285	0.00 281	0.00 287	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 284	0.00 285	0.00 287	0.00 279	0.00 280	0.00 285	0.00 281	0.00 287	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

PatchmatchNet2					59.93 244	50.56 267	52.11 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										20.85 265	40.60 247
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							91.33 8	75.06 16		80.35 17						91.03 7

RE-MVS-def										46.24 209

9.14												86.88 19

SR-MVS					88.99 38			73.57 28				87.54 17

our_test_3					67.93 220	70.99 221	66.89 221

MTAPA										83.48 1		86.45 22

MTMP										82.66 6		84.91 30

Patchmatch-RL test							2.85 280

XVS					86.63 50	88.68 30	85.00 52			71.81 51		81.92 41				90.47 27

X-MVStestdata					86.63 50	88.68 30	85.00 52			71.81 51		81.92 41				90.47 27

mPP-MVS					89.90 29							81.29 46

NP-MVS									80.10 51

Patchmtry						65.80 242	65.97 228	52.74 228		52.65 168

High-resolution multi-view benchmark