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.

MCST-MVS		93.81 19	94.06 22	93.53 18	96.79 23	96.85 23	95.95 17	91.69 19	92.20 28	87.17 35	90.83 30	93.41 9	91.96 16	94.49 28	93.50 34	97.61 1	97.12 25

SF-MVS		94.61 10	94.96 12	94.20 11	96.75 24	97.07 15	95.82 21	92.60 9	93.98 14	91.09 11	95.89 8	92.54 14	91.93 17	94.40 30	93.56 33	97.04 2	97.27 20

DVP-MVS++		95.79 1	96.42 1	95.06 1	97.84 2	98.17 2	97.03 4	92.84 3	96.68 1	92.83 3	95.90 7	94.38 4	92.90 7	95.98 2	94.85 6	96.93 3	98.99 1

SED-MVS		95.61 2	96.36 2	94.73 4	96.84 19	98.15 3	97.08 3	92.92 2	95.64 4	91.84 7	95.98 6	95.33 1	92.83 9	96.00 1	94.94 4	96.90 4	98.45 3

DVP-MVS		95.56 3	96.26 3	94.73 4	96.93 16	98.19 1	96.62 10	92.81 5	96.15 3	91.73 8	95.01 9	95.31 2	93.41 1	95.95 3	94.77 9	96.90 4	98.46 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
DPE-MVS		95.53 4	96.13 5	94.82 2	96.81 22	98.05 4	97.42 1	93.09 1	94.31 11	91.49 9	97.12 3	95.03 3	93.27 4	95.55 7	94.58 14	96.86 6	98.25 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MED-MVS		95.51 5	96.19 4	94.73 4	96.51 26	97.91 6	96.86 6	92.55 10	96.43 2	92.39 4	97.77 1	94.16 5	93.27 4	95.09 14	94.30 17	96.79 7	97.66 12

TSAR-MVS + GP.		92.71 30	93.91 24	91.30 37	91.96 75	96.00 43	93.43 44	87.94 44	92.53 23	86.27 43	93.57 17	91.94 21	91.44 26	93.29 47	92.89 49	96.78 8	97.15 24

TestfortrainingZip							96.76 7	92.70 6		92.16 6						96.77 9

ME-MVS		95.38 6	95.93 6	94.74 3	96.51 26	97.82 8	96.76 7	92.70 6	95.23 6	92.39 4	97.77 1	94.08 6	93.28 3	94.87 19	94.08 22	96.77 9	97.66 12

EC-MVSNet		89.96 50	90.77 46	89.01 58	90.54 97	95.15 61	91.34 66	81.43 135	85.27 70	83.08 60	82.83 51	87.22 51	90.97 31	94.79 22	93.38 38	96.73 11	96.71 37

ETV-MVS		89.22 56	89.76 53	88.60 66	91.60 80	94.61 74	89.48 104	83.46 100	85.20 73	81.58 80	82.75 52	82.59 69	88.80 44	94.57 26	93.28 42	96.68 12	95.31 61

APDe-MVS		95.23 7	95.69 8	94.70 7	97.12 10	97.81 9	97.19 2	92.83 4	95.06 8	90.98 12	96.47 4	92.77 12	93.38 2	95.34 10	94.21 19	96.68 12	98.17 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MGCNet		93.46 22	94.44 19	92.32 30	95.88 36	97.84 7	95.25 29	87.99 43	92.23 27	89.16 24	91.23 27	91.51 24	88.98 42	95.64 6	95.04 3	96.67 14	97.57 16

3Dnovator	85.17 5	90.48 44	89.90 52	91.16 39	94.88 46	95.74 51	93.82 40	85.36 59	89.28 49	87.81 31	74.34 121	87.40 50	88.56 48	93.07 50	93.74 29	96.53 15	95.71 52

TSAR-MVS + MP.		94.48 13	94.97 11	93.90 14	95.53 40	97.01 18	96.69 9	90.71 26	94.24 12	90.92 13	94.97 10	92.19 17	93.03 6	94.83 20	93.60 30	96.51 16	97.97 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS		90.34 45	90.58 47	90.07 45	93.11 62	95.82 49	90.57 75	83.62 90	87.07 60	85.35 45	82.98 50	83.47 64	91.37 28	94.94 16	93.37 40	96.37 17	96.41 42

MSP-MVS		95.12 8	95.83 7	94.30 8	96.82 21	97.94 5	96.98 5	92.37 14	95.40 5	90.59 15	96.16 5	93.71 8	92.70 10	94.80 21	94.77 9	96.37 17	97.99 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
MVSMamba_PlusPlus		90.78 42	91.67 37	89.74 48	91.80 78	96.07 40	92.21 53	85.88 54	90.36 44	82.63 68	84.71 47	85.27 56	89.59 39	95.08 15	94.64 11	96.36 19	95.58 57

QAPM		89.49 53	89.58 56	89.38 55	94.73 48	95.94 44	92.35 52	85.00 63	85.69 69	80.03 102	76.97 91	87.81 48	87.87 55	92.18 67	92.10 58	96.33 20	96.40 44

MVS_111021_HR		90.56 43	91.29 41	89.70 51	94.71 49	95.63 52	91.81 61	86.38 52	87.53 57	81.29 83	87.96 35	85.43 55	87.69 57	93.90 37	92.93 47	96.33 20	95.69 53

test1111		84.86 120	84.21 125	85.61 112	91.75 79	95.14 62	88.63 129	84.57 67	81.88 105	71.21 151	65.66 182	68.51 172	81.19 127	93.74 42	92.68 53	96.31 22	91.86 156

CANet		91.33 40	91.46 39	91.18 38	95.01 43	96.71 26	93.77 41	87.39 49	87.72 56	87.26 34	81.77 59	89.73 35	87.32 63	94.43 29	93.86 25	96.31 22	96.02 48

APD-MVS		94.37 14	94.47 18	94.26 9	97.18 8	96.99 19	96.53 11	92.68 8	92.45 25	89.96 19	94.53 13	91.63 23	92.89 8	94.58 25	93.82 26	96.31 22	97.26 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test2506		85.20 115	84.11 126	86.47 97	91.84 76	95.28 57	89.18 110	84.49 68	82.59 92	75.34 132	74.66 116	58.07 233	81.68 123	93.76 39	92.71 51	96.28 25	91.71 159

ECVR-MVS		85.25 114	84.47 122	86.16 103	91.84 76	95.28 57	89.18 110	84.49 68	82.59 92	73.49 142	66.12 172	69.28 168	81.68 123	93.76 39	92.71 51	96.28 25	91.58 166

SteuartSystems-ACMMP		94.06 16	94.65 14	93.38 20	96.97 15	97.36 12	96.12 13	91.78 17	92.05 30	87.34 33	94.42 14	90.87 28	91.87 20	95.47 9	94.59 13	96.21 27	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		92.05 34	93.74 25	90.08 44	94.96 44	97.06 16	93.11 48	87.71 47	90.71 39	80.78 90	92.40 24	91.03 26	87.68 58	94.32 31	94.48 15	96.21 27	96.16 46

CNVR-MVS		94.37 14	94.65 14	94.04 12	97.29 6	97.11 14	96.00 14	92.43 13	93.45 17	89.85 21	90.92 28	93.04 11	92.59 12	95.77 5	94.82 7	96.11 29	97.42 19

baseline1		84.54 123	84.43 123	84.67 121	90.62 93	91.16 140	88.63 129	83.75 88	79.78 135	71.16 152	75.14 110	74.10 139	77.84 172	91.56 73	90.67 83	96.04 30	88.58 189

MSLP-MVS++		92.02 36	91.40 40	92.75 25	96.01 34	95.88 47	93.73 43	89.00 36	89.89 48	90.31 17	81.28 63	88.85 41	91.45 24	92.88 54	94.24 18	96.00 31	96.76 34

NCCC		93.69 21	93.66 26	93.72 17	97.37 5	96.66 31	95.93 20	92.50 12	93.40 20	88.35 28	87.36 37	92.33 16	92.18 15	94.89 18	94.09 21	96.00 31	96.91 31

SPE-MVS-test		90.29 46	90.96 42	89.51 54	93.18 61	95.87 48	89.18 110	83.72 89	88.32 54	84.82 50	84.89 45	85.23 57	90.25 35	94.04 32	92.66 54	95.94 33	95.69 53

ACMMP		92.03 35	92.16 34	91.87 36	95.88 36	96.55 33	94.47 38	89.49 35	91.71 33	85.26 46	91.52 26	84.48 60	90.21 36	92.82 55	91.63 63	95.92 34	96.42 41
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
SMA-MVS		94.70 9	95.35 9	93.93 13	97.57 3	97.57 11	95.98 15	91.91 16	94.50 9	90.35 16	93.46 19	92.72 13	91.89 19	95.89 4	95.22 1	95.88 35	98.10 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
ACMMPR		93.72 20	93.94 23	93.48 19	97.07 11	96.93 20	95.78 23	90.66 28	93.88 15	89.24 23	93.53 18	89.08 40	92.24 14	93.89 38	93.50 34	95.88 35	96.73 35

HFP-MVS		94.02 17	94.22 21	93.78 15	97.25 7	96.85 23	95.81 22	90.94 25	94.12 13	90.29 18	94.09 16	89.98 34	92.52 13	93.94 36	93.49 36	95.87 37	97.10 26

PVSNet_BlendedMVS		88.19 69	88.00 69	88.42 68	92.71 71	94.82 71	89.08 117	83.81 86	84.91 77	86.38 41	79.14 72	78.11 101	82.66 114	93.05 51	91.10 68	95.86 38	94.86 67

PVSNet_Blended		88.19 69	88.00 69	88.42 68	92.71 71	94.82 71	89.08 117	83.81 86	84.91 77	86.38 41	79.14 72	78.11 101	82.66 114	93.05 51	91.10 68	95.86 38	94.86 67

DeepC-MVS_fast	88.76 1	93.10 25	93.02 32	93.19 23	97.13 9	96.51 35	95.35 28	91.19 22	93.14 22	88.14 29	85.26 43	89.49 37	91.45 24	95.17 11	95.07 2	95.85 40	96.48 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PGM-MVS		92.76 28	93.03 31	92.45 29	97.03 13	96.67 30	95.73 25	87.92 45	90.15 47	86.53 39	92.97 22	88.33 46	91.69 22	93.62 44	93.03 45	95.83 41	96.41 42

SD-MVS		94.53 12	95.22 10	93.73 16	95.69 39	97.03 17	95.77 24	91.95 15	94.41 10	91.35 10	94.97 10	93.34 10	91.80 21	94.72 24	93.99 24	95.82 42	98.07 7
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
DeepC-MVS	87.86 3	92.26 33	91.86 36	92.73 26	96.18 31	96.87 22	95.19 31	91.76 18	92.17 29	86.58 38	81.79 58	85.85 53	90.88 32	94.57 26	94.61 12	95.80 43	97.18 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					93.11 62	96.70 27	91.91 57			83.95 53		88.82 42				95.79 44

X-MVStestdata					93.11 62	96.70 27	91.91 57			83.95 53		88.82 42				95.79 44

DELS-MVS		89.71 51	89.68 55	89.74 48	93.75 55	96.22 38	93.76 42	85.84 55	82.53 94	85.05 48	78.96 75	84.24 61	84.25 98	94.91 17	94.91 5	95.78 46	96.02 48
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
X-MVS		92.36 32	92.75 33	91.90 35	96.89 17	96.70 27	95.25 29	90.48 31	91.50 35	83.95 53	88.20 34	88.82 42	89.11 41	93.75 41	93.43 37	95.75 47	96.83 33

casdiffmvs		87.45 79	87.15 78	87.79 84	90.15 109	94.22 79	89.96 93	83.93 85	85.08 75	80.91 85	75.81 102	77.88 105	86.08 76	91.86 70	90.86 77	95.74 48	94.37 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVS		93.25 24	93.26 29	93.24 22	96.84 19	96.51 35	95.52 26	90.61 29	92.37 26	88.88 25	90.91 29	89.52 36	91.91 18	93.64 43	92.78 50	95.69 49	97.09 27

MVSTER		86.03 103	86.12 99	85.93 108	88.62 136	89.93 160	89.33 107	79.91 159	81.87 106	81.35 82	81.07 64	74.91 135	80.66 136	92.13 68	90.10 103	95.68 50	92.80 133

3Dnovator+	86.06 4	91.60 38	90.86 45	92.47 28	96.00 35	96.50 37	94.70 36	87.83 46	90.49 41	89.92 20	74.68 115	89.35 38	90.66 33	94.02 34	94.14 20	95.67 51	96.85 32

OpenMVS	82.53 11	87.71 73	86.84 83	88.73 62	94.42 50	95.06 64	91.02 70	83.49 96	82.50 98	82.24 72	67.62 164	85.48 54	85.56 81	91.19 80	91.30 66	95.67 51	94.75 69

EIA-MVS		87.94 72	88.05 67	87.81 82	91.46 81	95.00 66	88.67 126	82.81 112	82.53 94	80.81 88	80.04 67	80.20 80	87.48 60	92.58 58	91.61 64	95.63 53	94.36 79

ET-MVSNet_ETH3D		84.65 121	85.58 111	83.56 140	74.99 250	92.62 125	90.29 87	80.38 147	82.16 101	73.01 147	83.41 48	71.10 160	87.05 67	87.77 152	90.17 102	95.62 54	91.82 157

CDPH-MVS		91.14 41	92.01 35	90.11 43	96.18 31	96.18 39	94.89 34	88.80 40	88.76 52	77.88 117	89.18 33	87.71 49	87.29 64	93.13 49	93.31 41	95.62 54	95.84 50

hybridcas		87.61 75	87.14 79	88.16 74	90.27 108	94.38 77	90.69 74	84.23 74	85.22 72	82.04 77	75.47 107	78.20 100	86.12 74	91.78 71	90.99 73	95.61 56	93.93 93

MP-MVS		93.35 23	93.59 27	93.08 24	97.39 4	96.82 25	95.38 27	90.71 26	90.82 38	88.07 30	92.83 23	90.29 32	91.32 29	94.03 33	93.19 44	95.61 56	97.16 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
FMVSNet3		84.44 126	84.64 121	84.21 129	84.32 194	90.13 155	89.85 96	80.37 148	81.17 112	75.50 127	69.63 148	79.69 86	79.62 158	89.72 123	90.52 88	95.59 58	91.58 166

HPM-MVS++		94.60 11	94.91 13	94.24 10	97.86 1	96.53 34	96.14 12	92.51 11	93.87 16	90.76 14	93.45 20	93.84 7	92.62 11	95.11 13	94.08 22	95.58 59	97.48 17

TPM-MVS					96.31 29	96.02 41	94.89 34			86.52 40	87.18 39	92.17 18	86.76 70			95.56 60	93.85 100
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
casdiffmvs_mvg		87.97 71	87.63 76	88.37 70	90.55 96	94.42 75	91.82 60	84.69 65	84.05 83	82.08 76	76.57 95	79.00 92	85.49 82	92.35 61	92.29 57	95.55 61	94.70 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CLD-MVS		88.66 59	88.52 61	88.82 60	91.37 84	94.22 79	92.82 51	82.08 126	88.27 55	85.14 47	81.86 57	78.53 97	85.93 79	91.17 81	90.61 84	95.55 61	95.00 63
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMMP_NAP		93.94 18	94.49 17	93.30 21	97.03 13	97.31 13	95.96 16	91.30 21	93.41 19	88.55 27	93.00 21	90.33 31	91.43 27	95.53 8	94.41 16	95.53 63	97.47 18

GBi-Net		84.51 124	84.80 118	84.17 130	84.20 195	89.95 157	89.70 97	80.37 148	81.17 112	75.50 127	69.63 148	79.69 86	79.75 155	90.73 98	90.72 79	95.52 64	91.71 159

test1		84.51 124	84.80 118	84.17 130	84.20 195	89.95 157	89.70 97	80.37 148	81.17 112	75.50 127	69.63 148	79.69 86	79.75 155	90.73 98	90.72 79	95.52 64	91.71 159

FMVSNet2		83.87 131	83.73 131	84.05 134	84.20 195	89.95 157	89.70 97	80.21 153	79.17 143	74.89 134	65.91 173	77.49 109	79.75 155	90.87 94	91.00 72	95.52 64	91.71 159

Casviewmamba		88.37 66	88.02 68	88.78 61	90.62 93	94.98 67	91.00 71	85.24 60	86.70 61	83.08 60	76.96 92	78.63 96	87.25 65	92.43 60	91.85 60	95.48 67	94.60 74

viewdifsd2359ckpt09		87.46 78	86.79 86	88.25 72	89.99 116	94.91 68	90.57 75	84.20 77	82.83 90	82.29 69	76.85 93	76.34 124	86.99 69	91.42 76	90.96 74	95.48 67	94.22 86

DPM-MVS		91.72 37	91.48 38	92.00 33	95.53 40	95.75 50	95.94 18	91.07 23	91.20 36	85.58 44	81.63 61	90.74 29	88.40 50	93.40 45	93.75 28	95.45 69	93.85 100

E6new		86.44 94	85.45 113	87.59 86	89.94 120	94.05 89	90.00 90	83.35 105	80.22 128	81.75 78	73.69 127	75.92 129	85.13 90	90.17 112	90.41 91	95.40 70	93.70 110

E6		86.44 94	85.45 113	87.59 86	89.94 120	94.05 89	90.00 90	83.35 105	80.22 128	81.75 78	73.69 127	75.92 129	85.13 90	90.17 112	90.41 91	95.40 70	93.70 110

OPM-MVS		87.56 76	85.80 104	89.62 52	93.90 54	94.09 86	94.12 39	88.18 41	75.40 164	77.30 120	76.41 96	77.93 104	88.79 45	92.20 65	90.82 78	95.40 70	93.72 109
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CSCG		92.76 28	93.16 30	92.29 31	96.30 30	97.74 10	94.67 37	88.98 38	92.46 24	89.73 22	86.67 40	92.15 20	88.69 47	92.26 63	92.92 48	95.40 70	97.89 10

E4		86.66 89	85.61 110	87.87 81	89.94 120	94.00 93	90.47 82	84.16 78	80.46 127	82.16 75	74.11 122	76.35 123	85.14 89	90.04 116	90.45 90	95.37 74	93.86 99

E3new		87.09 83	86.27 96	88.05 76	90.04 114	94.08 87	90.53 77	84.16 78	82.52 96	82.94 63	75.92 99	76.91 118	85.29 87	90.27 109	90.34 94	95.36 75	93.82 102

E3		87.08 84	86.27 96	88.04 77	90.04 114	94.08 87	90.53 77	84.16 78	82.52 96	82.86 64	75.91 100	76.93 116	85.27 88	90.27 109	90.33 95	95.36 75	93.82 102

sasdasda		89.36 54	89.92 49	88.70 63	91.38 82	95.92 45	91.81 61	82.61 121	90.37 42	82.73 66	82.09 54	79.28 89	88.30 51	91.17 81	93.59 31	95.36 75	97.04 28

canonicalmvs		89.36 54	89.92 49	88.70 63	91.38 82	95.92 45	91.81 61	82.61 121	90.37 42	82.73 66	82.09 54	79.28 89	88.30 51	91.17 81	93.59 31	95.36 75	97.04 28

IB-MVS	79.09 12	82.60 142	82.19 141	83.07 144	91.08 87	93.55 102	80.90 225	81.35 137	76.56 156	80.87 86	64.81 191	69.97 164	68.87 226	85.64 187	90.06 106	95.36 75	94.74 70
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
viewcassd2359sk11		87.35 81	86.67 90	88.14 75	90.08 112	94.12 84	90.51 79	84.13 81	83.71 85	83.42 58	76.99 89	77.46 110	85.33 86	90.40 107	90.21 100	95.34 80	93.81 105

gg-mvs-nofinetune		75.64 225	77.26 199	73.76 234	87.92 150	92.20 129	87.32 147	64.67 258	51.92 261	35.35 268	46.44 253	77.05 115	71.97 215	92.64 57	91.02 71	95.34 80	89.53 184

E5new		86.71 87	85.64 107	87.96 78	89.95 118	93.99 94	90.75 72	84.39 70	80.71 123	82.22 73	74.36 119	76.30 126	85.12 92	89.86 119	90.30 96	95.33 82	93.93 93

E5		86.71 87	85.64 107	87.96 78	89.95 118	93.99 94	90.75 72	84.39 70	80.71 123	82.22 73	74.36 119	76.30 126	85.12 92	89.86 119	90.30 96	95.33 82	93.93 93

Vis-MVSNet		84.38 128	86.68 89	81.70 158	87.65 155	94.89 69	88.14 135	80.90 141	74.48 170	68.23 168	77.53 87	80.72 77	69.98 222	92.68 56	91.90 59	95.33 82	94.58 75
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		87.53 77	86.95 81	88.20 73	90.10 110	94.13 83	90.50 81	84.09 83	84.43 81	83.82 56	77.92 85	77.84 107	85.37 85	90.43 106	90.08 104	95.32 85	93.79 106

TAPA-MVS	84.37 7	88.91 58	88.93 59	88.89 59	93.00 66	94.85 70	92.00 56	84.84 64	91.68 34	80.05 100	79.77 69	84.56 59	88.17 53	90.11 115	89.00 137	95.30 86	92.57 143
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_Test		86.93 85	87.24 77	86.56 96	90.10 110	93.47 103	90.31 84	80.12 154	83.55 86	78.12 113	79.58 70	79.80 84	85.45 83	90.17 112	90.59 85	95.29 87	93.53 115

LGP-MVS_train		88.25 68	88.55 60	87.89 80	92.84 69	93.66 100	93.35 45	85.22 62	85.77 67	74.03 139	86.60 41	76.29 128	86.62 72	91.20 79	90.58 86	95.29 87	95.75 51

FA-MVS(training)		85.65 108	85.79 105	85.48 114	90.44 102	93.47 103	88.66 128	73.11 222	83.34 87	82.26 70	71.79 137	78.39 99	83.14 108	91.00 89	89.47 124	95.28 89	93.06 126

UniMVSNet_NR-MVSNet		81.87 148	81.33 149	82.50 149	85.31 181	91.30 138	85.70 174	84.25 73	75.89 160	64.21 196	66.95 167	64.65 192	80.22 145	87.07 160	89.18 132	95.27 90	94.29 80

viewmacassd2359aftdt		86.41 97	85.73 106	87.21 92	89.86 125	94.03 92	90.30 85	83.22 108	80.76 122	79.59 106	73.51 131	76.32 125	85.06 94	90.24 111	91.13 67	95.23 91	94.11 88

MGCFI-Net		88.38 65	89.72 54	86.83 95	91.21 85	95.59 53	91.14 69	82.37 124	90.25 45	75.33 133	81.89 56	79.13 91	85.69 80	90.98 92	93.23 43	95.23 91	96.94 30

viewmanbaseed2359cas		87.17 82	86.90 82	87.48 90	90.08 112	94.14 82	90.30 85	83.19 109	84.17 82	80.68 92	76.78 94	77.43 111	85.43 84	90.78 97	90.92 75	95.21 93	94.10 89

IS_MVSNet		86.18 100	88.18 65	83.85 136	91.02 88	94.72 73	87.48 143	82.46 123	81.05 116	70.28 156	76.98 90	82.20 72	76.65 180	93.97 35	93.38 38	95.18 94	94.97 64

train_agg		92.87 27	93.53 28	92.09 32	96.88 18	95.38 55	95.94 18	90.59 30	90.65 40	83.65 57	94.31 15	91.87 22	90.30 34	93.38 46	92.42 55	95.17 95	96.73 35

NR-MVSNet		80.25 164	79.98 167	80.56 176	85.20 183	90.94 144	85.65 176	83.58 94	75.74 161	61.36 220	65.30 186	56.75 240	72.38 214	88.46 145	88.80 141	95.16 96	93.87 97

PVSNet_Blended_VisFu		87.40 80	87.80 71	86.92 94	92.86 67	95.40 54	88.56 132	83.45 101	79.55 138	82.26 70	74.49 117	84.03 62	79.24 163	92.97 53	91.53 65	95.15 97	96.65 38

EPP-MVSNet		86.55 91	87.76 73	85.15 116	90.52 98	94.41 76	87.24 150	82.32 125	81.79 107	73.60 141	78.57 78	82.41 70	82.07 120	91.23 77	90.39 93	95.14 98	95.48 59

thisisatest0530		85.15 117	85.86 102	84.33 126	89.19 132	92.57 126	87.22 151	80.11 155	82.15 103	74.41 136	78.15 81	73.80 145	79.90 151	90.99 90	89.58 119	95.13 99	93.75 108

TranMVSNet+NR-MVSNet		80.52 161	79.84 171	81.33 166	84.92 190	90.39 149	85.53 180	84.22 76	74.27 173	60.68 225	64.93 190	59.96 221	77.48 174	86.75 169	89.28 127	95.12 100	93.29 119

tttt0517		85.11 118	85.81 103	84.30 127	89.24 130	92.68 122	87.12 156	80.11 155	81.98 104	74.31 138	78.08 82	73.57 147	79.90 151	91.01 88	89.58 119	95.11 101	93.77 107

casdiffseed414692147		85.57 109	83.88 129	87.54 88	89.98 117	93.88 98	90.07 89	83.49 96	79.40 139	80.57 96	68.32 159	71.85 157	86.11 75	89.45 129	90.56 87	95.00 102	93.69 112

viewdifsd2359ckpt13		86.88 86	86.35 95	87.50 89	89.91 124	94.19 81	89.89 95	83.43 102	82.94 89	80.82 87	75.76 103	76.45 122	85.95 78	90.72 101	90.49 89	95.00 102	93.88 96

UniMVSNet (Re)		81.22 156	81.08 152	81.39 164	85.35 180	91.76 136	84.93 186	82.88 110	76.13 159	65.02 191	64.94 189	63.09 203	75.17 197	87.71 154	89.04 135	94.97 104	94.88 66

usedtu_dtu_shiyan1		79.85 168	79.89 169	79.80 185	77.40 242	89.77 166	85.31 183	80.48 146	77.76 151	64.71 193	61.69 202	67.04 183	75.92 187	87.76 153	87.67 155	94.96 105	87.52 208

FC-MVSNet-train		85.18 116	85.31 115	85.03 119	90.67 92	91.62 137	87.66 141	83.61 91	79.75 136	74.37 137	78.69 77	71.21 159	78.91 164	91.23 77	89.96 109	94.96 105	94.69 73

GeoE		84.62 122	83.98 128	85.35 115	89.34 129	92.83 118	88.34 133	78.95 169	79.29 141	77.16 121	68.10 161	74.56 136	83.40 106	89.31 132	89.23 130	94.92 107	94.57 76

tfpn200view9		82.86 138	81.46 146	84.48 123	90.30 106	93.09 110	89.05 119	82.71 114	75.14 165	69.56 159	65.72 179	63.13 201	80.38 144	91.15 84	89.51 121	94.91 108	92.50 147

thres600view7		82.53 144	81.02 153	84.28 128	90.61 95	93.05 111	88.57 131	82.67 116	74.12 176	68.56 167	65.09 188	62.13 212	80.40 143	91.15 84	89.02 136	94.88 109	92.59 141

thres200		82.77 140	81.25 150	84.54 122	90.38 103	93.05 111	89.13 116	82.67 116	74.40 171	69.53 161	65.69 181	63.03 204	80.63 137	91.15 84	89.42 125	94.88 109	92.04 153

Effi-MVS+		85.33 113	85.08 116	85.63 111	89.69 127	93.42 105	89.90 94	80.31 152	79.32 140	72.48 150	73.52 130	74.03 140	86.55 73	90.99 90	89.98 108	94.83 111	94.27 84

dmvs_re		81.08 158	79.92 168	82.44 151	86.66 165	87.70 197	87.91 138	83.30 107	72.86 190	65.29 190	65.76 175	63.43 200	76.69 179	88.93 136	89.50 122	94.80 112	91.23 171

thres400		82.68 141	81.15 151	84.47 124	90.52 98	92.89 116	88.95 122	82.71 114	74.33 172	69.22 164	65.31 185	62.61 207	80.63 137	90.96 93	89.50 122	94.79 113	92.45 149

ACMP	83.90 8	88.32 67	88.06 66	88.62 65	92.18 73	93.98 96	91.28 68	85.24 60	86.69 62	81.23 84	85.62 42	75.13 134	87.01 68	89.83 121	89.77 115	94.79 113	95.43 60
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DU-MVS		81.20 157	80.30 161	82.25 153	84.98 188	90.94 144	85.70 174	83.58 94	75.74 161	64.21 196	65.30 186	59.60 226	80.22 145	86.89 164	89.31 126	94.77 115	94.29 80

UA-Net		86.07 102	87.78 72	84.06 133	92.85 68	95.11 63	87.73 140	84.38 72	73.22 186	73.18 144	79.99 68	89.22 39	71.47 218	93.22 48	93.03 45	94.76 116	90.69 174

MVS_111021_LR		90.14 49	90.89 44	89.26 56	93.23 60	94.05 89	90.43 83	84.65 66	90.16 46	84.52 52	90.14 31	83.80 63	87.99 54	92.50 59	90.92 75	94.74 117	94.70 71

thres100view900		82.55 143	81.01 155	84.34 125	90.30 106	92.27 128	89.04 120	82.77 113	75.14 165	69.56 159	65.72 179	63.13 201	79.62 158	89.97 118	89.26 129	94.73 118	91.61 165

AdaColmap		90.29 46	88.38 63	92.53 27	96.10 33	95.19 60	92.98 49	91.40 20	89.08 51	88.65 26	78.35 80	81.44 74	91.30 30	90.81 96	90.21 100	94.72 119	93.59 114

PCF-MVS	84.60 6	88.66 59	87.75 74	89.73 50	93.06 65	96.02 41	93.22 47	90.00 33	82.44 99	80.02 103	77.96 83	85.16 58	87.36 62	88.54 141	88.54 146	94.72 119	95.61 56
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DI_MVS_pp		86.41 97	85.54 112	87.42 91	89.24 130	93.13 109	92.16 55	82.65 118	82.30 100	80.75 91	68.30 160	80.41 78	85.01 95	90.56 104	90.07 105	94.70 121	94.01 90

Fast-Effi-MVS+		83.77 133	82.98 136	84.69 120	87.98 149	91.87 135	88.10 136	77.70 183	78.10 149	73.04 146	69.13 154	68.51 172	86.66 71	90.49 105	89.85 113	94.67 122	92.88 130

WR-MVS_H		75.84 223	76.93 205	74.57 233	82.86 214	89.50 174	78.34 238	79.36 166	66.90 224	52.51 244	60.20 214	59.71 223	59.73 246	83.61 211	85.77 190	94.65 123	92.84 131

OMC-MVS		90.23 48	90.40 48	90.03 46	93.45 58	95.29 56	91.89 59	86.34 53	93.25 21	84.94 49	81.72 60	86.65 52	88.90 43	91.69 72	90.27 99	94.65 123	93.95 92

HQP-MVS		89.13 57	89.58 56	88.60 66	93.53 57	93.67 99	93.29 46	87.58 48	88.53 53	75.50 127	87.60 36	80.32 79	87.07 66	90.66 103	89.95 110	94.62 125	96.35 45

PEN-MVS		76.02 220	76.07 214	75.95 223	83.17 208	87.97 194	79.65 229	80.07 158	66.57 226	51.45 248	60.94 208	55.47 245	66.81 235	82.72 217	86.80 169	94.59 126	92.03 154

ACMM	83.27 10	87.68 74	86.09 100	89.54 53	93.26 59	92.19 130	91.43 65	86.74 51	86.02 65	82.85 65	75.63 104	75.14 133	88.41 49	90.68 102	89.99 107	94.59 126	92.97 128
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		85.43 111	87.72 75	82.76 147	90.95 91	93.01 113	89.99 92	75.46 209	82.67 91	64.91 192	83.14 49	80.09 81	80.68 134	92.03 69	91.03 70	94.57 128	92.08 151

CP-MVSNet		76.36 217	76.41 210	76.32 220	82.73 217	88.64 187	79.39 232	79.62 161	67.21 222	53.70 240	60.72 210	55.22 246	67.91 231	83.52 212	86.34 179	94.55 129	93.19 121

EG-PatchMatch MVS		76.40 216	75.47 225	77.48 204	85.86 173	90.22 153	82.45 211	73.96 220	59.64 252	59.60 229	52.75 244	62.20 211	68.44 228	88.23 148	87.50 158	94.55 129	87.78 204

tfpnnormal		77.46 201	74.86 229	80.49 177	86.34 169	88.92 185	84.33 193	81.26 139	61.39 246	61.70 217	51.99 246	53.66 252	74.84 200	88.63 140	87.38 161	94.50 131	92.08 151

baseline2		82.80 139	82.86 138	82.73 148	87.68 154	90.50 148	84.92 187	78.93 170	78.07 150	73.06 145	75.08 111	69.77 165	77.31 175	88.90 138	86.94 167	94.50 131	90.74 173

Vis-MVSNet (Re-imp)		83.65 134	86.81 85	79.96 182	90.46 101	92.71 120	84.84 188	82.00 127	80.93 118	62.44 209	76.29 97	82.32 71	65.54 239	92.29 62	91.66 62	94.49 133	91.47 168

PS-CasMVS		75.90 222	75.86 219	75.96 222	82.59 218	88.46 191	79.23 235	79.56 163	66.00 229	52.77 243	59.48 218	54.35 250	67.14 234	83.37 213	86.23 180	94.47 134	93.10 125

Baseline_NR-MVSNet		79.84 169	78.37 186	81.55 162	84.98 188	86.66 206	85.06 184	83.49 96	75.57 163	63.31 203	58.22 231	60.97 216	78.00 170	86.89 164	87.13 163	94.47 134	93.15 124

FMVSNet1		81.64 153	80.61 158	82.84 146	82.36 220	89.20 179	88.67 126	79.58 162	70.79 201	72.63 149	58.95 222	72.26 154	79.34 161	90.73 98	90.72 79	94.47 134	91.62 164

DTE-MVSNet		75.14 232	75.44 226	74.80 230	83.18 207	87.19 203	78.25 240	80.11 155	66.05 228	48.31 254	60.88 209	54.67 247	64.54 240	82.57 219	86.17 181	94.43 137	90.53 178

PLC	83.76 9	88.61 61	86.83 84	90.70 41	94.22 51	92.63 123	91.50 64	87.19 50	89.16 50	86.87 36	75.51 106	80.87 76	89.98 38	90.01 117	89.20 131	94.41 138	90.45 180
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UGNet		85.90 106	88.23 64	83.18 143	88.96 134	94.10 85	87.52 142	83.60 92	81.66 108	77.90 116	80.76 65	83.19 66	66.70 236	91.13 87	90.71 82	94.39 139	96.06 47
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
TransMVSNet (Re)		76.57 211	75.16 228	78.22 201	85.60 177	87.24 202	82.46 210	81.23 140	59.80 251	59.05 233	57.07 233	59.14 230	66.60 237	88.09 149	86.82 168	94.37 140	87.95 201

gm-plane-assit		70.29 244	70.65 245	69.88 245	85.03 186	78.50 257	58.41 266	65.47 254	50.39 263	40.88 263	49.60 249	50.11 257	75.14 198	91.43 75	89.78 114	94.32 141	84.73 230

CNLPA		88.40 62	87.00 80	90.03 46	93.73 56	94.28 78	89.56 102	85.81 56	91.87 31	87.55 32	69.53 152	81.49 73	89.23 40	89.45 129	88.59 145	94.31 142	93.82 102

MAR-MVS		88.39 64	88.44 62	88.33 71	94.90 45	95.06 64	90.51 79	83.59 93	85.27 70	79.07 109	77.13 88	82.89 68	87.70 56	92.19 66	92.32 56	94.23 143	94.20 87
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
MSDG		83.87 131	81.02 153	87.19 93	92.17 74	89.80 164	89.15 115	85.72 57	80.61 125	79.24 108	66.66 169	68.75 171	82.69 113	87.95 151	87.44 159	94.19 144	85.92 223

pm-mvs1		78.51 192	77.75 194	79.40 186	84.83 191	89.30 176	83.55 199	79.38 165	62.64 242	63.68 201	58.73 227	64.68 191	70.78 221	89.79 122	87.84 152	94.17 145	91.28 170

FE-MVSNET2		71.00 242	70.45 247	71.65 241	66.32 261	85.00 230	76.33 243	76.20 196	61.03 247	52.47 245	41.50 261	50.21 256	64.44 241	84.97 201	85.46 194	94.16 146	84.97 226

diffmvs_AUTHOR		86.44 94	86.59 92	86.26 101	88.33 143	92.74 119	89.66 100	81.74 130	85.17 74	80.04 101	77.70 86	77.20 113	83.68 99	89.66 125	89.28 127	94.14 147	94.37 77

CPTT-MVS		91.39 39	90.95 43	91.91 34	95.06 42	95.24 59	95.02 33	88.98 38	91.02 37	86.71 37	84.89 45	88.58 45	91.60 23	90.82 95	89.67 118	94.08 148	96.45 40

v144192		78.81 186	77.22 200	80.67 174	82.95 211	89.79 165	86.40 167	77.42 184	68.26 215	63.13 204	59.50 217	58.13 232	80.08 150	85.93 183	86.08 183	94.06 149	92.83 132

diffmvs		86.52 93	86.76 87	86.23 102	88.31 144	92.63 123	89.58 101	81.61 133	86.14 64	80.26 98	79.00 74	77.27 112	83.58 102	88.94 135	89.06 134	94.05 150	94.29 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
v1921920		78.57 191	76.99 203	80.41 180	82.93 212	89.63 172	86.38 168	77.14 187	68.31 214	61.80 216	58.89 223	56.79 239	80.19 148	86.50 176	86.05 185	94.02 151	92.76 135

ACMH	78.52 14	81.86 149	80.45 160	83.51 142	90.51 100	91.22 139	85.62 178	84.23 74	70.29 206	62.21 210	69.04 156	64.05 198	84.48 97	87.57 155	88.45 148	94.01 152	92.54 145
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		76.63 210	78.02 191	75.02 228	84.14 198	89.76 167	78.34 238	80.64 145	69.56 207	52.32 246	61.26 204	61.24 215	60.66 245	84.45 206	87.07 164	93.99 153	92.77 134

viewmamba		86.59 90	86.74 88	86.42 99	88.44 140	92.86 117	89.26 109	82.63 120	87.39 59	80.58 95	78.43 79	77.87 106	83.66 100	88.44 146	88.75 142	93.96 154	93.45 116

v10		79.62 172	78.19 187	81.28 167	83.73 201	89.69 169	87.27 149	76.86 190	70.50 204	65.46 185	60.58 212	60.47 218	80.44 141	86.91 163	86.63 173	93.93 155	92.55 144

hybridnocas07		86.29 99	86.58 93	85.96 107	88.15 145	92.31 127	88.95 122	81.61 133	86.15 63	80.80 89	79.24 71	77.78 108	82.33 118	88.53 142	88.60 144	93.92 156	93.42 117

anonymousdsp		77.94 196	79.00 178	76.71 215	79.03 234	87.83 196	79.58 230	72.87 223	65.80 231	58.86 234	65.82 174	62.48 209	75.99 186	86.77 168	88.66 143	93.92 156	95.68 55

v1240		78.15 194	76.53 208	80.04 181	82.85 215	89.48 175	85.61 179	76.77 191	67.05 223	61.18 223	58.37 230	56.16 243	79.89 153	86.11 182	86.08 183	93.92 156	92.47 148

v8		79.90 167	78.39 185	81.66 159	83.97 199	89.81 163	87.16 153	77.40 185	71.49 196	67.71 169	61.24 205	62.49 208	79.83 154	85.48 191	86.17 181	93.89 159	92.02 155

v2v482		79.84 169	78.07 189	81.90 156	83.75 200	90.21 154	87.17 152	79.85 160	70.65 202	65.93 182	61.93 201	60.07 220	80.82 131	85.25 193	86.71 170	93.88 160	91.70 163

thisisatest0515		79.76 171	80.59 159	78.80 192	84.40 193	88.91 186	79.48 231	76.94 189	72.29 193	67.33 171	67.82 163	65.99 186	70.80 220	88.50 144	87.84 152	93.86 161	92.75 136

IterMVS-LS		83.28 137	82.95 137	83.65 137	88.39 141	88.63 188	86.80 164	78.64 174	76.56 156	73.43 143	72.52 136	75.35 132	80.81 132	86.43 177	88.51 147	93.84 162	92.66 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + ACMM		92.97 26	94.51 16	91.16 39	95.88 36	96.59 32	95.09 32	90.45 32	93.42 18	83.01 62	94.68 12	90.74 29	88.74 46	94.75 23	93.78 27	93.82 163	97.63 14

v1144		79.38 179	77.83 192	81.18 169	83.62 202	90.23 152	87.15 155	78.35 176	69.13 209	64.02 199	60.20 214	59.41 227	80.14 149	86.78 167	86.57 174	93.81 164	92.53 146

v1192		78.94 184	77.33 197	80.82 172	83.25 206	89.90 161	86.91 160	77.72 182	68.63 213	62.61 208	59.17 219	57.53 236	80.62 139	86.89 164	86.47 176	93.79 165	92.75 136

onestephybrid01		86.53 92	86.61 91	86.44 98	88.53 137	92.94 115	89.16 114	82.82 111	84.73 80	81.56 81	77.96 83	78.49 98	82.84 110	88.93 136	89.00 137	93.74 166	94.23 85

TSAR-MVS + COLMAP		88.40 62	89.09 58	87.60 85	92.72 70	93.92 97	92.21 53	85.57 58	91.73 32	73.72 140	91.75 25	73.22 151	87.64 59	91.49 74	89.71 117	93.73 167	91.82 157

UniMVSNet_ETH3D		79.24 180	76.47 209	82.48 150	85.66 176	90.97 143	86.08 171	81.63 132	64.48 237	68.94 166	54.47 238	57.65 235	78.83 165	85.20 197	88.91 140	93.72 168	93.60 113

EPNet		89.60 52	89.91 51	89.24 57	96.45 28	93.61 101	92.95 50	88.03 42	85.74 68	83.36 59	87.29 38	83.05 67	80.98 130	92.22 64	91.85 60	93.69 169	95.58 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		81.62 155	79.45 177	84.14 132	91.00 89	93.38 107	88.27 134	78.19 177	76.28 158	70.18 157	48.78 250	73.69 146	83.52 104	87.05 161	87.83 154	93.68 170	89.15 186

hybrid		86.13 101	86.45 94	85.75 109	88.02 148	92.17 131	88.79 125	81.32 138	85.86 66	80.67 93	78.80 76	78.11 101	82.06 121	88.52 143	88.29 149	93.66 171	93.38 118

V42		79.59 173	78.43 184	80.94 171	82.79 216	89.71 168	86.66 165	76.73 192	71.38 197	67.42 170	61.01 207	62.30 210	78.39 167	85.56 189	86.48 175	93.65 172	92.60 140

DCV-MVSNet		85.88 107	86.17 98	85.54 113	89.10 133	89.85 162	89.34 106	80.70 142	83.04 88	78.08 115	76.19 98	79.00 92	82.42 117	89.67 124	90.30 96	93.63 173	95.12 62

v7n		77.22 203	76.23 212	78.38 200	81.89 223	89.10 183	82.24 216	76.36 193	65.96 230	61.21 222	56.56 234	55.79 244	75.07 199	86.55 173	86.68 171	93.52 174	92.95 129

viewdifsd2359ckpt07		85.95 105	85.62 109	86.34 100	89.73 126	93.40 106	89.18 110	81.99 128	81.53 109	80.19 99	75.17 109	76.65 120	83.45 105	90.32 108	89.00 137	93.51 175	93.26 120

Anonymous20231211		84.42 127	83.02 135	86.05 106	88.85 135	92.70 121	88.92 124	83.40 103	79.99 131	78.31 112	55.83 236	78.92 94	83.33 107	89.06 134	89.76 116	93.50 176	94.90 65

ACMH+	79.08 13	81.84 150	80.06 165	83.91 135	89.92 123	90.62 146	86.21 169	83.48 99	73.88 178	65.75 183	66.38 171	65.30 189	84.63 96	85.90 184	87.25 162	93.45 177	91.13 172

pmmvs5		76.93 207	76.33 211	77.62 203	81.97 222	88.40 192	81.32 221	74.35 218	65.42 235	61.42 219	63.07 197	57.95 234	73.23 212	85.60 188	85.35 196	93.41 178	88.55 190

Anonymous202405211			82.75 139		89.58 128	92.97 114	89.04 120	84.13 81	78.72 145		57.18 232	76.64 121	83.13 109	89.55 127	89.92 111	93.38 179	94.28 83

viewmambaseed2359dif		85.52 110	85.01 117	86.12 105	88.39 141	91.96 133	89.39 105	81.43 135	82.16 101	80.47 97	75.52 105	76.85 119	83.66 100	87.03 162	87.60 157	93.37 180	93.98 91

dtuplus		85.37 112	84.69 120	86.16 103	88.46 138	91.91 134	89.32 108	81.64 131	80.88 119	80.66 94	74.38 118	76.92 117	83.58 102	87.28 157	87.61 156	93.33 181	93.87 97

USDC		80.69 160	79.89 169	81.62 161	86.48 167	89.11 182	86.53 166	78.86 171	81.15 115	63.48 202	72.98 133	59.12 231	81.16 128	87.10 159	85.01 198	93.23 182	84.77 229

LS3D		85.96 104	84.37 124	87.81 82	94.13 52	93.27 108	90.26 88	89.00 36	84.91 77	72.84 148	71.74 138	72.47 153	87.45 61	89.53 128	89.09 133	93.20 183	89.60 183

MS-PatchMatch		81.79 151	81.44 147	82.19 155	90.35 104	89.29 177	88.08 137	75.36 210	77.60 152	69.00 165	64.37 194	78.87 95	77.14 178	88.03 150	85.70 191	93.19 184	86.24 220

Fast-Effi-MVS+-dtu		79.95 166	80.69 157	79.08 189	86.36 168	89.14 181	85.85 172	72.28 225	72.85 191	59.32 230	70.43 146	68.42 174	77.57 173	86.14 181	86.44 177	93.11 185	91.39 169

GA-MVS		79.52 174	79.71 174	79.30 188	85.68 175	90.36 150	84.55 190	78.44 175	70.47 205	57.87 235	68.52 158	61.38 214	76.21 185	89.40 131	87.89 151	93.04 186	89.96 182

DeepPCF-MVS	88.51 2	92.64 31	94.42 20	90.56 42	94.84 47	96.92 21	91.31 67	89.61 34	95.16 7	84.55 51	89.91 32	91.45 25	90.15 37	95.12 12	94.81 8	92.90 187	97.58 15

CDS-MVSNet		81.63 154	82.09 142	81.09 170	87.21 160	90.28 151	87.46 145	80.33 151	69.06 210	70.66 153	71.30 139	73.87 143	67.99 229	89.58 126	89.87 112	92.87 188	90.69 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		82.05 146	81.76 143	82.38 152	87.72 152	90.56 147	86.90 161	78.05 179	73.85 179	66.85 173	71.29 140	71.90 156	82.00 122	86.64 172	85.48 193	92.76 189	92.58 142

v148		78.59 190	76.84 207	80.62 175	83.61 203	89.16 180	83.65 198	79.24 167	69.38 208	69.34 163	59.88 216	60.41 219	75.19 196	83.81 210	84.63 203	92.70 190	90.63 176

pmmvs4		79.99 165	78.08 188	82.22 154	83.04 210	87.16 204	84.95 185	78.80 173	78.64 146	74.53 135	64.61 192	59.41 227	79.45 160	84.13 208	84.54 205	92.53 191	88.08 195

viewdifsd2359ckpt11		84.31 129	83.65 132	85.08 117	88.07 146	91.03 141	86.86 162	80.65 143	79.92 132	79.63 104	75.08 111	73.99 141	82.74 111	86.40 178	85.98 188	92.51 192	93.16 122

viewmsd2359difaftdt		84.31 129	83.65 132	85.07 118	88.07 146	91.03 141	86.86 162	80.65 143	79.92 132	79.61 105	75.08 111	73.98 142	82.74 111	86.40 178	85.99 186	92.51 192	93.16 122

blended_shiyan8		75.62 226	74.39 233	77.05 208	69.20 254	86.13 209	83.05 205	75.65 203	68.14 216	66.18 177	58.73 227	64.21 194	75.71 191	78.65 238	76.92 240	92.50 194	87.96 199

blended_shiyan6		75.62 226	74.41 232	77.03 209	69.20 254	86.12 210	83.03 206	75.65 203	68.09 221	66.14 178	58.83 226	64.22 193	75.70 192	78.65 238	76.94 239	92.49 195	88.01 197

RPMNet		77.07 206	77.63 195	76.42 217	85.56 178	85.15 227	81.37 219	65.27 255	74.71 168	60.29 226	63.71 196	66.59 185	73.64 208	82.71 218	82.12 220	92.38 196	88.39 191

blend_shiyan4		78.17 193	76.23 212	80.43 179	77.49 241	85.96 218	85.63 177	74.87 212	72.02 194	75.60 123	65.73 176	67.75 179	76.63 181	77.82 246	76.48 247	92.34 197	87.87 202

CR-MVSNet		78.71 188	78.86 179	78.55 197	85.85 174	85.15 227	82.30 214	68.23 242	74.71 168	65.37 187	64.39 193	69.59 167	77.18 176	85.10 199	84.87 199	92.34 197	88.21 193

wanda-best-256-512		75.51 228	74.25 234	76.99 211	69.08 256	86.01 212	83.06 202	75.62 205	68.11 218	66.14 178	58.89 223	64.15 195	75.77 189	78.43 240	76.54 243	92.29 199	87.59 206

FE-blended-shiyan7		75.51 228	74.25 234	76.99 211	69.08 256	86.01 212	83.06 202	75.62 205	68.12 217	66.14 178	58.89 223	64.15 195	75.77 189	78.43 240	76.54 243	92.29 199	87.59 206

usedtu_blend_shiyan5		77.43 202	75.78 221	79.36 187	69.08 256	86.01 212	86.97 158	75.62 205	68.11 218	75.60 123	65.73 176	67.75 179	76.63 181	78.43 240	76.54 243	92.29 199	87.87 202

FE-MVSNET3		77.14 204	75.80 220	78.71 195	69.08 256	86.01 212	83.06 202	75.62 205	68.11 218	75.60 123	65.73 176	67.75 179	76.63 181	78.43 240	76.54 243	92.29 199	88.01 197

gbinet_0.2-2-1-0.02		75.42 231	74.57 231	76.42 217	67.86 260	86.00 216	82.79 208	76.24 194	65.77 232	65.59 184	58.60 229	65.11 190	73.76 207	79.11 236	76.90 241	92.27 203	90.47 179

COLMAP_ROB	76.78 15	80.50 162	78.49 182	82.85 145	90.96 90	89.65 171	86.20 170	83.40 103	77.15 154	66.54 174	62.27 199	65.62 188	77.89 171	85.23 194	84.70 202	92.11 204	84.83 228
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchMatch-RL		83.34 136	81.36 148	85.65 110	90.33 105	89.52 173	84.36 192	81.82 129	80.87 121	79.29 107	74.04 123	62.85 206	86.05 77	88.40 147	87.04 166	92.04 205	86.77 214

PMMVS		81.65 152	84.05 127	78.86 191	78.56 237	82.63 242	83.10 200	67.22 247	81.39 110	70.11 158	84.91 44	79.74 85	82.12 119	87.31 156	85.70 191	92.03 206	86.67 217

IterMVS-SCA-FT		79.41 178	80.20 163	78.49 198	85.88 171	86.26 208	83.95 195	71.94 226	73.55 184	61.94 213	70.48 145	70.50 161	75.23 195	85.81 186	84.61 204	91.99 207	90.18 181

0.4-1-1-0.1		79.43 177	77.51 196	81.66 159	79.11 233	88.57 190	87.37 146	75.16 211	73.57 183	75.70 122	67.26 166	67.91 177	80.67 135	78.11 244	79.88 225	91.94 208	87.30 210

baseline		84.89 119	86.06 101	83.52 141	87.25 159	89.67 170	87.76 139	75.68 202	84.92 76	78.40 111	80.10 66	80.98 75	80.20 147	86.69 171	87.05 165	91.86 209	92.99 127

MIMVSNet		74.69 234	75.60 224	73.62 235	76.02 247	85.31 226	81.21 224	67.43 246	71.02 199	59.07 232	54.48 237	64.07 197	66.14 238	86.52 175	86.64 172	91.83 210	81.17 246

FE-MVSNET		66.05 251	67.24 250	64.66 252	59.88 265	79.66 254	69.18 258	74.46 216	55.47 259	37.02 267	41.66 260	48.62 261	55.72 248	80.54 227	83.09 213	91.68 211	81.66 242

0.3-1-1-0.015		79.02 183	76.98 204	81.41 163	78.71 236	88.07 193	87.16 153	74.71 213	72.89 189	75.60 123	66.54 170	67.75 179	80.60 140	77.49 248	79.58 228	91.66 212	86.56 218

FC-MVSNet-test		76.53 213	81.62 145	70.58 244	84.99 187	85.73 221	74.81 248	78.85 172	77.00 155	39.13 265	75.90 101	73.50 148	54.08 253	86.54 174	85.99 186	91.65 213	86.68 215

pmmvs-eth3d		74.32 236	71.96 242	77.08 207	77.33 243	82.71 241	78.41 237	76.02 199	66.65 225	65.98 181	54.23 240	49.02 260	73.14 213	82.37 221	82.69 217	91.61 214	86.05 222

0.4-1-1-0.2		78.93 185	76.93 205	81.25 168	78.56 237	87.86 195	86.98 157	74.58 214	72.54 192	75.49 131	66.85 168	67.89 178	80.44 141	77.55 247	79.41 231	91.49 215	86.44 219

SixPastTwentyTwo		76.02 220	75.72 222	76.36 219	83.38 204	87.54 199	75.50 246	76.22 195	65.50 234	57.05 236	70.64 142	53.97 251	74.54 202	80.96 225	82.12 220	91.44 216	89.35 185

pmmvs6		74.83 233	72.89 240	77.09 206	82.11 221	87.50 200	80.88 226	76.97 188	52.79 260	61.91 215	46.66 252	60.49 217	69.28 224	86.74 170	85.46 194	91.39 217	90.56 177

test-mter		77.79 197	80.02 166	75.18 227	81.18 229	82.85 240	80.52 228	62.03 262	73.62 182	62.16 211	73.55 129	73.83 144	73.81 206	84.67 203	83.34 211	91.37 218	88.31 192

TDRefinement		79.05 182	77.05 202	81.39 164	88.45 139	89.00 184	86.92 159	82.65 118	74.21 174	64.41 194	59.17 219	59.16 229	74.52 203	85.23 194	85.09 197	91.37 218	87.51 209

test-LLR		79.47 176	79.84 171	79.03 190	87.47 156	82.40 245	81.24 222	78.05 179	73.72 180	62.69 206	73.76 125	74.42 137	73.49 209	84.61 204	82.99 215	91.25 220	87.01 212

TESTMET0.1,1		77.78 198	79.84 171	75.38 226	80.86 230	82.40 245	81.24 222	62.72 261	73.72 180	62.69 206	73.76 125	74.42 137	73.49 209	84.61 204	82.99 215	91.25 220	87.01 212

TinyColmap		76.73 208	73.95 237	79.96 182	85.16 185	85.64 223	82.34 213	78.19 177	70.63 203	62.06 212	60.69 211	49.61 258	80.81 132	85.12 198	83.69 210	91.22 222	82.27 239

FMVSNet5		75.50 230	76.07 214	74.83 229	76.16 245	81.19 248	81.34 220	70.21 234	73.20 187	61.59 218	58.97 221	68.33 175	68.50 227	85.87 185	85.85 189	91.18 223	79.11 252

IterMVS		78.79 187	79.71 174	77.71 202	85.26 182	85.91 219	84.54 191	69.84 237	73.38 185	61.25 221	70.53 144	70.35 162	74.43 204	85.21 196	83.80 209	90.95 224	88.77 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchT		76.42 214	77.81 193	74.80 230	78.46 239	84.30 233	71.82 254	65.03 257	73.89 177	65.37 187	61.58 203	66.70 184	77.18 176	85.10 199	84.87 199	90.94 225	88.21 193

EPNet_dtu		81.98 147	83.82 130	79.83 184	94.10 53	85.97 217	87.29 148	84.08 84	80.61 125	59.96 227	81.62 62	77.19 114	62.91 244	87.21 158	86.38 178	90.66 226	87.77 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PM-MVS		74.17 237	73.10 238	75.41 225	76.07 246	82.53 243	77.56 241	71.69 227	71.04 198	61.92 214	61.23 206	47.30 262	74.82 201	81.78 223	79.80 226	90.42 227	88.05 196

test0.0.03 1		76.03 219	78.51 181	73.12 238	87.47 156	85.13 229	76.32 244	78.05 179	73.19 188	50.98 251	70.64 142	69.28 168	55.53 249	85.33 192	84.38 206	90.39 228	81.63 243

Anonymous20231206		70.80 243	70.59 246	71.04 242	81.60 226	82.49 244	74.64 249	75.87 200	64.17 238	49.27 253	44.85 256	53.59 253	54.68 252	83.07 215	82.34 219	90.17 229	83.65 233

CHOSEN 1792x2688		82.16 145	80.91 156	83.61 138	91.14 86	92.01 132	89.55 103	79.15 168	79.87 134	70.29 155	52.51 245	72.56 152	81.39 125	88.87 139	88.17 150	90.15 230	92.37 150

MIMVSNet1		65.00 252	66.24 253	63.55 254	58.41 267	80.01 253	69.00 259	74.03 219	55.81 257	41.88 262	36.81 263	49.48 259	47.89 259	81.32 224	82.40 218	90.08 231	77.88 254

LTVRE_ROB	74.41 16	75.78 224	74.72 230	77.02 210	85.88 171	89.22 178	82.44 212	77.17 186	50.57 262	45.45 258	65.44 183	52.29 254	81.25 126	85.50 190	87.42 160	89.94 232	92.62 139
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
GG-mvs-BLEND		57.56 258	82.61 140	28.34 266	0.22 275	90.10 156	79.37 233	0.14 273	79.56 137	0.40 277	71.25 141	83.40 65	0.30 273	86.27 180	83.87 207	89.59 233	83.83 232

CVMVSNet		76.70 209	78.46 183	74.64 232	83.34 205	84.48 232	81.83 218	74.58 214	68.88 211	51.23 250	69.77 147	70.05 163	67.49 232	84.27 207	83.81 208	89.38 234	87.96 199

TAMVS		76.42 214	77.16 201	75.56 224	83.05 209	85.55 224	80.58 227	71.43 228	65.40 236	61.04 224	67.27 165	69.22 170	67.99 229	84.88 202	84.78 201	89.28 235	83.01 237

CostFormer		80.94 159	80.21 162	81.79 157	87.69 153	88.58 189	87.47 144	70.66 231	80.02 130	77.88 117	73.03 132	71.40 158	78.24 168	79.96 230	79.63 227	88.82 236	88.84 187

RPSCF		83.46 135	83.36 134	83.59 139	87.75 151	87.35 201	84.82 189	79.46 164	83.84 84	78.12 113	82.69 53	79.87 82	82.60 116	82.47 220	81.13 224	88.78 237	86.13 221

test20.03		68.31 248	70.05 248	66.28 251	82.41 219	80.84 249	67.35 260	76.11 198	58.44 254	40.80 264	53.77 242	54.54 248	42.28 261	83.07 215	81.96 222	88.73 238	77.76 255

SCA		79.51 175	80.15 164	78.75 193	86.58 166	87.70 197	83.07 201	68.53 241	81.31 111	66.40 175	73.83 124	75.38 131	79.30 162	80.49 228	79.39 232	88.63 239	82.96 238

testgi		71.92 241	74.20 236	69.27 246	84.58 192	83.06 237	73.40 251	74.39 217	64.04 239	46.17 257	68.90 157	57.15 238	48.89 258	84.07 209	83.08 214	88.18 240	79.09 253

dps		78.02 195	75.94 218	80.44 178	86.06 170	86.62 207	82.58 209	69.98 235	75.14 165	77.76 119	69.08 155	59.93 222	78.47 166	79.47 232	77.96 236	87.78 241	83.40 234

PatchmatchNet		78.67 189	78.85 180	78.46 199	86.85 164	86.03 211	83.77 197	68.11 245	80.88 119	66.19 176	72.90 134	73.40 149	78.06 169	79.25 234	77.71 237	87.75 242	81.75 241
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		73.21 239	72.91 239	73.56 236	80.01 231	84.28 234	78.62 236	66.43 252	68.64 212	59.12 231	60.39 213	59.69 225	69.81 223	78.82 237	77.43 238	87.36 243	81.11 247

MDTV_nov1_ep13		79.14 181	79.49 176	78.74 194	85.40 179	86.89 205	84.32 194	70.29 233	78.85 144	69.42 162	75.37 108	73.29 150	75.64 193	80.61 226	79.48 230	87.36 243	81.91 240

EPMVS		77.53 200	78.07 189	76.90 214	86.89 163	84.91 231	82.18 217	66.64 251	81.00 117	64.11 198	72.75 135	69.68 166	74.42 205	79.36 233	78.13 235	87.14 245	80.68 249

EU-MVSNet		69.98 245	72.30 241	67.28 249	75.67 248	79.39 255	73.12 252	69.94 236	63.59 241	42.80 261	62.93 198	56.71 241	55.07 251	79.13 235	78.55 234	87.06 246	85.82 224

usedtu_dtu_shiyan2		62.45 255	61.54 258	63.50 255	49.14 270	78.26 258	71.51 255	67.18 248	43.16 267	53.22 241	33.68 266	45.76 263	53.15 254	74.24 255	74.13 254	86.83 247	81.56 244

new-patchmatchnet		63.80 253	63.31 255	64.37 253	76.49 244	75.99 259	63.73 263	70.99 230	57.27 255	43.08 260	45.86 254	43.80 264	45.13 260	73.20 256	70.68 259	86.80 248	76.34 257

pmnet_mix02		71.95 240	71.83 243	72.10 239	81.40 228	80.63 252	73.78 250	72.85 224	70.90 200	54.89 238	62.17 200	57.42 237	62.92 243	76.80 250	73.98 255	86.74 249	80.87 248

dtuonlycased		69.72 246	68.74 249	70.86 243	74.97 251	83.54 236	75.33 247	68.22 244	63.98 240	50.82 252	50.34 248	62.09 213	69.26 225	68.11 260	69.75 260	86.54 250	83.37 235

CMPMVS	56.49 17	73.84 238	71.73 244	76.31 221	85.20 183	85.67 222	75.80 245	73.23 221	62.26 243	65.40 186	53.40 243	59.70 224	71.77 217	80.25 229	79.56 229	86.45 251	81.28 245
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDA-MVSNet-bldmvs		66.22 250	64.49 254	68.24 247	61.67 263	82.11 247	70.07 257	76.16 197	59.14 253	47.94 255	54.35 239	35.82 271	67.33 233	64.94 263	75.68 249	86.30 252	79.36 251

MVS-HIRNet		68.83 247	66.39 252	71.68 240	77.58 240	75.52 260	66.45 261	65.05 256	62.16 244	62.84 205	44.76 257	56.60 242	71.96 216	78.04 245	75.06 252	86.18 253	72.56 259

CHOSEN 280x420		80.28 163	81.66 144	78.67 196	82.92 213	79.24 256	85.36 182	66.79 250	78.11 148	70.32 154	75.03 114	79.87 82	81.09 129	89.07 133	83.16 212	85.54 254	87.17 211

tpm cat1		77.78 198	75.28 227	80.70 173	87.14 161	85.84 220	85.81 173	70.40 232	77.44 153	78.80 110	63.72 195	64.01 199	76.55 184	75.60 253	75.21 251	85.51 255	85.12 225

dtuonly		77.14 204	77.32 198	76.92 213	81.74 225	80.84 249	85.46 181	68.93 240	74.15 175	64.33 195	65.39 184	71.91 155	75.62 194	83.27 214	81.21 223	85.47 256	84.45 231

tpm		76.30 218	76.05 216	76.59 216	86.97 162	83.01 239	83.83 196	67.06 249	71.83 195	63.87 200	69.56 151	62.88 205	73.41 211	79.79 231	78.59 233	84.41 257	86.68 215

tpmrst		76.55 212	75.99 217	77.20 205	87.32 158	83.05 238	82.86 207	65.62 253	78.61 147	67.22 172	69.19 153	65.71 187	75.87 188	76.75 251	75.33 250	84.31 258	83.28 236

pmmvs3		61.89 256	61.74 257	62.06 256	64.30 262	70.83 264	64.22 262	52.14 266	48.78 264	44.47 259	41.67 259	41.70 268	63.03 242	76.06 252	76.02 248	84.18 259	77.14 256

ADS-MVSNet		74.53 235	75.69 223	73.17 237	81.57 227	80.71 251	79.27 234	63.03 260	79.27 142	59.94 228	67.86 162	68.32 176	71.08 219	77.33 249	76.83 242	84.12 260	79.53 250

ambc			61.92 256		70.98 253	73.54 262	63.64 264		60.06 249	52.23 247	38.44 262	19.17 274	57.12 247	82.33 222	75.03 253	83.21 261	84.89 227

FPMVS		63.63 254	60.08 260	67.78 248	80.01 231	71.50 263	72.88 253	69.41 239	61.82 245	53.11 242	45.12 255	42.11 267	50.86 256	66.69 261	63.84 262	80.41 262	69.46 261

N_pmnet		66.85 249	66.63 251	67.11 250	78.73 235	74.66 261	70.53 256	71.07 229	66.46 227	46.54 256	51.68 247	51.91 255	55.48 250	74.68 254	72.38 256	80.29 263	74.65 258

new_pmnet		59.28 257	61.47 259	56.73 258	61.66 264	68.29 265	59.57 265	54.91 263	60.83 248	34.38 269	44.66 258	43.65 265	49.90 257	71.66 257	71.56 258	79.94 264	69.67 260

PMVS	50.48 18	55.81 259	51.93 262	60.33 257	72.90 252	49.34 268	48.78 267	69.51 238	43.49 266	54.25 239	36.26 264	41.04 269	39.71 263	65.07 262	60.70 263	76.85 265	67.58 262
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		49.17 261	47.05 264	51.65 259	59.67 266	48.39 269	41.98 270	63.47 259	55.64 258	33.33 270	14.90 268	13.78 275	41.34 262	69.31 259	72.30 257	70.11 266	55.00 267
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.68 263	44.74 265	38.10 261	46.97 271	52.32 267	40.63 271	48.08 267	35.51 268	7.36 276	26.86 267	24.64 273	16.72 268	55.24 266	59.03 264	68.85 267	59.59 265

WB-MVS		52.27 260	57.26 261	46.45 260	75.64 249	65.62 266	40.45 272	75.80 201	47.10 265	9.11 275	53.83 241	38.98 270	14.47 269	69.44 258	68.29 261	63.24 268	57.56 266

test_method		41.78 262	48.10 263	34.42 264	10.74 274	19.78 275	44.64 269	17.73 270	59.83 250	38.67 266	35.82 265	54.41 249	34.94 264	62.87 264	43.13 267	59.81 269	60.82 264

DeepMVS_CX						48.31 270	48.03 268	26.08 269	56.42 256	25.77 271	47.51 251	31.31 272	51.30 255	48.49 267		53.61 270	61.52 263

tmp_tt				32.73 265	43.96 272	21.15 274	26.71 273	8.99 271	65.67 233	51.39 249	56.01 235	42.64 266	11.76 270	56.60 265	50.81 266	53.55 271

E-PMN		31.40 264	26.80 267	36.78 262	51.39 269	29.96 272	20.20 274	54.17 264	25.93 270	12.75 273	14.73 269	8.58 277	34.10 266	27.36 269	37.83 268	48.07 272	43.18 269

EMVS		30.49 266	25.44 268	36.39 263	51.47 268	29.89 273	20.17 275	54.00 265	26.49 269	12.02 274	13.94 271	8.84 276	34.37 265	25.04 270	34.37 269	46.29 273	39.53 270

MVE	30.17 19	30.88 265	33.52 266	27.80 267	23.78 273	39.16 271	18.69 276	46.90 268	21.88 271	15.39 272	14.37 270	7.31 278	24.41 267	41.63 268	56.22 265	37.64 274	54.07 268
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		1.03 267	1.63 269	0.34 268	0.09 276	0.35 276	0.61 278	0.16 272	1.49 272	0.10 278	3.15 272	0.15 279	0.86 272	1.32 271	1.18 270	0.20 275	3.76 272

test123		0.87 268	1.40 270	0.25 269	0.03 277	0.25 277	0.35 279	0.08 274	1.21 273	0.05 279	2.84 273	0.03 280	0.89 271	0.43 272	1.16 271	0.13 276	3.87 271

uanet_test		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet-low-res		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

RE-MVS-def										56.08 237

9.14												92.16 19

SR-MVS					96.58 25			90.99 24				92.40 15

our_test_3					81.81 224	83.96 235	76.61 242

MTAPA										92.97 2		91.03 26

MTMP										93.14 1		90.21 33

Patchmatch-RL test							8.55 277

mPP-MVS					97.06 12							88.08 47

NP-MVS									87.47 58

Patchmtry						85.54 225	82.30 214	68.23 242		65.37 187

High-resolution multi-view benchmark