High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DPE-MVS		95.53 4	96.13 4	94.82 2	96.81 22	98.05 4	97.42 1	93.09 1	94.31 10	91.49 8	97.12 2	95.03 3	93.27 4	95.55 7	94.58 13	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
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 3	91.84 6	95.98 5	95.33 1	92.83 8	96.00 1	94.94 4	96.90 4	98.45 3

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 6	94.38 4	92.90 6	95.98 2	94.85 6	96.93 3	98.99 1

APDe-MVS		95.23 6	95.69 7	94.70 6	97.12 10	97.81 8	97.19 2	92.83 4	95.06 7	90.98 11	96.47 3	92.77 11	93.38 2	95.34 10	94.21 17	96.68 11	98.17 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		95.56 3	96.26 3	94.73 4	96.93 16	98.19 1	96.62 9	92.81 5	96.15 2	91.73 7	95.01 8	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
TestfortrainingZip							96.76 6	92.70 6		92.16 5						96.77 8

ME-MVS		95.38 5	95.93 5	94.74 3	96.51 26	97.82 7	96.76 6	92.70 6	95.23 5	92.39 4	97.77 1	94.08 5	93.28 3	94.87 17	94.08 20	96.77 8	97.66 12

APD-MVS		94.37 13	94.47 17	94.26 8	97.18 8	96.99 18	96.53 10	92.68 8	92.45 24	89.96 18	94.53 12	91.63 22	92.89 7	94.58 23	93.82 24	96.31 20	97.26 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		94.61 9	94.96 11	94.20 10	96.75 24	97.07 14	95.82 20	92.60 9	93.98 13	91.09 10	95.89 7	92.54 13	91.93 16	94.40 28	93.56 31	97.04 2	97.27 19

HPM-MVS++		94.60 10	94.91 12	94.24 9	97.86 1	96.53 33	96.14 11	92.51 10	93.87 15	90.76 13	93.45 19	93.84 6	92.62 10	95.11 13	94.08 20	95.58 56	97.48 16

NCCC		93.69 20	93.66 25	93.72 16	97.37 5	96.66 30	95.93 19	92.50 11	93.40 19	88.35 27	87.36 36	92.33 15	92.18 14	94.89 16	94.09 19	96.00 29	96.91 30

CNVR-MVS		94.37 13	94.65 13	94.04 11	97.29 6	97.11 13	96.00 13	92.43 12	93.45 16	89.85 20	90.92 27	93.04 10	92.59 11	95.77 5	94.82 7	96.11 27	97.42 18

MSP-MVS		95.12 7	95.83 6	94.30 7	96.82 21	97.94 5	96.98 5	92.37 13	95.40 4	90.59 14	96.16 4	93.71 7	92.70 9	94.80 19	94.77 9	96.37 16	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
SD-MVS		94.53 11	95.22 9	93.73 15	95.69 38	97.03 16	95.77 23	91.95 14	94.41 9	91.35 9	94.97 9	93.34 9	91.80 20	94.72 22	93.99 22	95.82 40	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
SMA-MVS		94.70 8	95.35 8	93.93 12	97.57 3	97.57 10	95.98 14	91.91 15	94.50 8	90.35 15	93.46 18	92.72 12	91.89 18	95.89 4	95.22 1	95.88 33	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
SteuartSystems-ACMMP		94.06 15	94.65 13	93.38 19	96.97 15	97.36 11	96.12 12	91.78 16	92.05 29	87.34 32	94.42 13	90.87 27	91.87 19	95.47 9	94.59 12	96.21 25	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS	87.86 3	92.26 32	91.86 35	92.73 25	96.18 30	96.87 21	95.19 30	91.76 17	92.17 28	86.58 37	81.79 56	85.85 52	90.88 31	94.57 24	94.61 11	95.80 41	97.18 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MCST-MVS		93.81 18	94.06 21	93.53 17	96.79 23	96.85 22	95.95 16	91.69 18	92.20 27	87.17 34	90.83 29	93.41 8	91.96 15	94.49 26	93.50 32	97.61 1	97.12 24

AdaColmap		90.29 44	88.38 61	92.53 26	96.10 32	95.19 58	92.98 48	91.40 19	89.08 49	88.65 25	78.35 75	81.44 72	91.30 29	90.81 92	90.21 96	94.72 115	93.59 108

ACMMP_NAP		93.94 17	94.49 16	93.30 20	97.03 13	97.31 12	95.96 15	91.30 20	93.41 18	88.55 26	93.00 20	90.33 30	91.43 26	95.53 8	94.41 15	95.53 60	97.47 17

DeepC-MVS_fast	88.76 1	93.10 24	93.02 31	93.19 22	97.13 9	96.51 34	95.35 27	91.19 21	93.14 21	88.14 28	85.26 42	89.49 36	91.45 23	95.17 11	95.07 2	95.85 38	96.48 38
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DPM-MVS		91.72 36	91.48 36	92.00 32	95.53 39	95.75 48	95.94 17	91.07 22	91.20 35	85.58 43	81.63 59	90.74 28	88.40 48	93.40 43	93.75 26	95.45 65	93.85 94

SR-MVS					96.58 25			90.99 23				92.40 14

HFP-MVS		94.02 16	94.22 20	93.78 14	97.25 7	96.85 22	95.81 21	90.94 24	94.12 12	90.29 17	94.09 15	89.98 33	92.52 12	93.94 34	93.49 34	95.87 35	97.10 25

TSAR-MVS + MP.		94.48 12	94.97 10	93.90 13	95.53 39	97.01 17	96.69 8	90.71 25	94.24 11	90.92 12	94.97 9	92.19 16	93.03 5	94.83 18	93.60 28	96.51 15	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
MP-MVS		93.35 22	93.59 26	93.08 23	97.39 4	96.82 24	95.38 26	90.71 25	90.82 37	88.07 29	92.83 22	90.29 31	91.32 28	94.03 31	93.19 42	95.61 54	97.16 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMPR		93.72 19	93.94 22	93.48 18	97.07 11	96.93 19	95.78 22	90.66 27	93.88 14	89.24 22	93.53 17	89.08 39	92.24 13	93.89 36	93.50 32	95.88 33	96.73 34

CP-MVS		93.25 23	93.26 28	93.24 21	96.84 19	96.51 34	95.52 25	90.61 28	92.37 25	88.88 24	90.91 28	89.52 35	91.91 17	93.64 41	92.78 48	95.69 47	97.09 26

train_agg		92.87 26	93.53 27	92.09 31	96.88 18	95.38 53	95.94 17	90.59 29	90.65 39	83.65 56	94.31 14	91.87 21	90.30 33	93.38 44	92.42 53	95.17 91	96.73 34

X-MVS		92.36 31	92.75 32	91.90 34	96.89 17	96.70 26	95.25 28	90.48 30	91.50 34	83.95 52	88.20 33	88.82 41	89.11 39	93.75 39	93.43 35	95.75 45	96.83 32

TSAR-MVS + ACMM		92.97 25	94.51 15	91.16 38	95.88 35	96.59 31	95.09 31	90.45 31	93.42 17	83.01 60	94.68 11	90.74 28	88.74 44	94.75 21	93.78 25	93.82 157	97.63 13

PCF-MVS	84.60 6	88.66 57	87.75 71	89.73 48	93.06 64	96.02 39	93.22 46	90.00 32	82.44 91	80.02 94	77.96 78	85.16 56	87.36 60	88.54 136	88.54 139	94.72 115	95.61 55
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DeepPCF-MVS	88.51 2	92.64 30	94.42 19	90.56 41	94.84 46	96.92 20	91.31 65	89.61 33	95.16 6	84.55 50	89.91 31	91.45 24	90.15 36	95.12 12	94.81 8	92.90 178	97.58 14

ACMMP		92.03 34	92.16 33	91.87 35	95.88 35	96.55 32	94.47 37	89.49 34	91.71 32	85.26 45	91.52 25	84.48 58	90.21 35	92.82 53	91.63 60	95.92 32	96.42 40
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
MSLP-MVS++		92.02 35	91.40 38	92.75 24	96.01 33	95.88 45	93.73 42	89.00 35	89.89 46	90.31 16	81.28 61	88.85 40	91.45 23	92.88 52	94.24 16	96.00 29	96.76 33

LS3D		85.96 96	84.37 115	87.81 78	94.13 51	93.27 104	90.26 84	89.00 35	84.91 70	72.84 139	71.74 129	72.47 144	87.45 59	89.53 124	89.09 129	93.20 174	89.60 174

CPTT-MVS		91.39 38	90.95 41	91.91 33	95.06 41	95.24 57	95.02 32	88.98 37	91.02 36	86.71 36	84.89 44	88.58 44	91.60 22	90.82 91	89.67 114	94.08 144	96.45 39

CSCG		92.76 27	93.16 29	92.29 30	96.30 29	97.74 9	94.67 36	88.98 37	92.46 23	89.73 21	86.67 39	92.15 19	88.69 45	92.26 60	92.92 46	95.40 66	97.89 10

CDPH-MVS		91.14 40	92.01 34	90.11 42	96.18 30	96.18 38	94.89 33	88.80 39	88.76 50	77.88 108	89.18 32	87.71 48	87.29 62	93.13 47	93.31 39	95.62 52	95.84 49

OPM-MVS		87.56 72	85.80 96	89.62 50	93.90 53	94.09 82	94.12 38	88.18 40	75.40 155	77.30 111	76.41 89	77.93 98	88.79 43	92.20 62	90.82 74	95.40 66	93.72 103
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EPNet		89.60 50	89.91 49	89.24 55	96.45 27	93.61 97	92.95 49	88.03 41	85.74 62	83.36 58	87.29 37	83.05 65	80.98 121	92.22 61	91.85 58	93.69 162	95.58 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MGCNet		93.46 21	94.44 18	92.32 29	95.88 35	97.84 6	95.25 28	87.99 42	92.23 26	89.16 23	91.23 26	91.51 23	88.98 40	95.64 6	95.04 3	96.67 13	97.57 15

TSAR-MVS + GP.		92.71 29	93.91 23	91.30 36	91.96 74	96.00 41	93.43 43	87.94 43	92.53 22	86.27 42	93.57 16	91.94 20	91.44 25	93.29 45	92.89 47	96.78 7	97.15 23

PGM-MVS		92.76 27	93.03 30	92.45 28	97.03 13	96.67 29	95.73 24	87.92 44	90.15 45	86.53 38	92.97 21	88.33 45	91.69 21	93.62 42	93.03 43	95.83 39	96.41 41

3Dnovator+	86.06 4	91.60 37	90.86 43	92.47 27	96.00 34	96.50 36	94.70 35	87.83 45	90.49 40	89.92 19	74.68 107	89.35 37	90.66 32	94.02 32	94.14 18	95.67 49	96.85 31

PHI-MVS		92.05 33	93.74 24	90.08 43	94.96 43	97.06 15	93.11 47	87.71 46	90.71 38	80.78 84	92.40 23	91.03 25	87.68 56	94.32 29	94.48 14	96.21 25	96.16 45

HQP-MVS		89.13 55	89.58 54	88.60 63	93.53 56	93.67 95	93.29 45	87.58 47	88.53 51	75.50 118	87.60 35	80.32 77	87.07 63	90.66 99	89.95 106	94.62 121	96.35 44

CANet		91.33 39	91.46 37	91.18 37	95.01 42	96.71 25	93.77 40	87.39 48	87.72 54	87.26 33	81.77 57	89.73 34	87.32 61	94.43 27	93.86 23	96.31 20	96.02 47

PLC	83.76 9	88.61 59	86.83 80	90.70 40	94.22 50	92.63 117	91.50 62	87.19 49	89.16 48	86.87 35	75.51 99	80.87 74	89.98 37	90.01 113	89.20 127	94.41 134	90.45 171
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMM	83.27 10	87.68 71	86.09 92	89.54 51	93.26 58	92.19 123	91.43 63	86.74 50	86.02 60	82.85 63	75.63 97	75.14 124	88.41 47	90.68 98	89.99 103	94.59 122	92.97 119
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS_111021_HR		90.56 41	91.29 39	89.70 49	94.71 48	95.63 50	91.81 59	86.38 51	87.53 55	81.29 78	87.96 34	85.43 54	87.69 55	93.90 35	92.93 45	96.33 18	95.69 52

OMC-MVS		90.23 46	90.40 46	90.03 45	93.45 57	95.29 54	91.89 57	86.34 52	93.25 20	84.94 48	81.72 58	86.65 51	88.90 41	91.69 68	90.27 95	94.65 119	93.95 88

DELS-MVS		89.71 49	89.68 53	89.74 47	93.75 54	96.22 37	93.76 41	85.84 53	82.53 86	85.05 47	78.96 72	84.24 59	84.25 94	94.91 15	94.91 5	95.78 44	96.02 47
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
CNLPA		88.40 60	87.00 76	90.03 45	93.73 55	94.28 74	89.56 98	85.81 54	91.87 30	87.55 31	69.53 143	81.49 71	89.23 38	89.45 125	88.59 138	94.31 138	93.82 96

MSDG		83.87 122	81.02 144	87.19 89	92.17 73	89.80 155	89.15 108	85.72 55	80.61 116	79.24 99	66.66 160	68.75 161	82.69 106	87.95 143	87.44 150	94.19 140	85.92 214

TSAR-MVS + COLMAP		88.40 60	89.09 56	87.60 81	92.72 69	93.92 93	92.21 52	85.57 56	91.73 31	73.72 131	91.75 24	73.22 142	87.64 57	91.49 70	89.71 113	93.73 160	91.82 148

3Dnovator	85.17 5	90.48 42	89.90 50	91.16 38	94.88 45	95.74 49	93.82 39	85.36 57	89.28 47	87.81 30	74.34 112	87.40 49	88.56 46	93.07 48	93.74 27	96.53 14	95.71 51

ACMP	83.90 8	88.32 64	88.06 64	88.62 62	92.18 72	93.98 92	91.28 66	85.24 58	86.69 58	81.23 79	85.62 41	75.13 125	87.01 65	89.83 117	89.77 111	94.79 109	95.43 58
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		88.25 65	88.55 58	87.89 76	92.84 68	93.66 96	93.35 44	85.22 59	85.77 61	74.03 130	86.60 40	76.29 119	86.62 69	91.20 75	90.58 82	95.29 83	95.75 50

QAPM		89.49 51	89.58 54	89.38 53	94.73 47	95.94 42	92.35 51	85.00 60	85.69 63	80.03 93	76.97 85	87.81 47	87.87 53	92.18 64	92.10 56	96.33 18	96.40 43

TAPA-MVS	84.37 7	88.91 56	88.93 57	88.89 57	93.00 65	94.85 67	92.00 54	84.84 61	91.68 33	80.05 91	79.77 67	84.56 57	88.17 51	90.11 111	89.00 133	95.30 82	92.57 134
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
casdiffmvs_mvg		87.97 68	87.63 73	88.37 67	90.55 93	94.42 72	91.82 58	84.69 62	84.05 75	82.08 73	76.57 88	79.00 90	85.49 78	92.35 58	92.29 55	95.55 58	94.70 69
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_111021_LR		90.14 47	90.89 42	89.26 54	93.23 59	94.05 85	90.43 79	84.65 63	90.16 44	84.52 51	90.14 30	83.80 61	87.99 52	92.50 57	90.92 71	94.74 113	94.70 69

test1111		84.86 111	84.21 116	85.61 103	91.75 77	95.14 60	88.63 120	84.57 64	81.88 97	71.21 142	65.66 173	68.51 162	81.19 118	93.74 40	92.68 51	96.31 20	91.86 147

test2506		85.20 106	84.11 117	86.47 93	91.84 75	95.28 55	89.18 104	84.49 65	82.59 84	75.34 123	74.66 108	58.07 222	81.68 114	93.76 37	92.71 49	96.28 23	91.71 150

ECVR-MVS		85.25 105	84.47 113	86.16 97	91.84 75	95.28 55	89.18 104	84.49 65	82.59 84	73.49 133	66.12 163	69.28 158	81.68 114	93.76 37	92.71 49	96.28 23	91.58 157

E5new		86.71 83	85.64 99	87.96 74	89.95 114	93.99 90	90.75 69	84.39 67	80.71 114	82.22 70	74.36 110	76.30 117	85.12 88	89.86 115	90.30 92	95.33 78	93.93 89

E5		86.71 83	85.64 99	87.96 74	89.95 114	93.99 90	90.75 69	84.39 67	80.71 114	82.22 70	74.36 110	76.30 117	85.12 88	89.86 115	90.30 92	95.33 78	93.93 89

UA-Net		86.07 94	87.78 69	84.06 124	92.85 67	95.11 61	87.73 131	84.38 69	73.22 176	73.18 135	79.99 66	89.22 38	71.47 208	93.22 46	93.03 43	94.76 112	90.69 165

UniMVSNet_NR-MVSNet		81.87 139	81.33 140	82.50 140	85.31 172	91.30 129	85.70 165	84.25 70	75.89 151	64.21 186	66.95 158	64.65 182	80.22 136	87.07 151	89.18 128	95.27 86	94.29 77

ACMH	78.52 14	81.86 140	80.45 151	83.51 133	90.51 97	91.22 130	85.62 169	84.23 71	70.29 196	62.21 200	69.04 147	64.05 188	84.48 93	87.57 147	88.45 141	94.01 148	92.54 136
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TranMVSNet+NR-MVSNet		80.52 152	79.84 162	81.33 157	84.92 181	90.39 140	85.53 171	84.22 72	74.27 164	60.68 215	64.93 180	59.96 210	77.48 165	86.75 160	89.28 123	95.12 96	93.29 110

viewdifsd2359ckpt09		87.46 74	86.79 82	88.25 69	89.99 112	94.91 65	90.57 71	84.20 73	82.83 82	82.29 66	76.85 86	76.34 115	86.99 66	91.42 72	90.96 70	95.48 64	94.22 82

E4		86.66 85	85.61 102	87.87 77	89.94 116	94.00 89	90.47 78	84.16 74	80.46 118	82.16 72	74.11 113	76.35 114	85.14 85	90.04 112	90.45 86	95.37 70	93.86 93

E3new		87.09 79	86.27 88	88.05 72	90.04 110	94.08 83	90.53 73	84.16 74	82.52 88	82.94 61	75.92 92	76.91 109	85.29 83	90.27 105	90.34 90	95.36 71	93.82 96

E3		87.08 80	86.27 88	88.04 73	90.04 110	94.08 83	90.53 73	84.16 74	82.52 88	82.86 62	75.91 93	76.93 108	85.27 84	90.27 105	90.33 91	95.36 71	93.82 96

viewcassd2359sk11		87.35 77	86.67 85	88.14 71	90.08 108	94.12 80	90.51 75	84.13 77	83.71 77	83.42 57	76.99 83	77.46 102	85.33 82	90.40 103	90.21 96	95.34 76	93.81 99

Anonymous202405211			82.75 130		89.58 124	92.97 110	89.04 113	84.13 77	78.72 136		57.18 222	76.64 112	83.13 103	89.55 123	89.92 107	93.38 171	94.28 80

E2		87.53 73	86.95 77	88.20 70	90.10 106	94.13 79	90.50 77	84.09 79	84.43 73	83.82 55	77.92 79	77.84 100	85.37 81	90.43 102	90.08 100	95.32 81	93.79 100

EPNet_dtu		81.98 138	83.82 121	79.83 175	94.10 52	85.97 208	87.29 139	84.08 80	80.61 116	59.96 217	81.62 60	77.19 106	62.91 233	87.21 149	86.38 169	90.66 217	87.77 196
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
casdiffmvs		87.45 75	87.15 75	87.79 80	90.15 105	94.22 75	89.96 89	83.93 81	85.08 68	80.91 80	75.81 95	77.88 99	86.08 72	91.86 67	90.86 73	95.74 46	94.37 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		88.19 66	88.00 66	88.42 65	92.71 70	94.82 68	89.08 110	83.81 82	84.91 70	86.38 40	79.14 69	78.11 96	82.66 107	93.05 49	91.10 65	95.86 36	94.86 65

PVSNet_Blended		88.19 66	88.00 66	88.42 65	92.71 70	94.82 68	89.08 110	83.81 82	84.91 70	86.38 40	79.14 69	78.11 96	82.66 107	93.05 49	91.10 65	95.86 36	94.86 65

baseline1		84.54 114	84.43 114	84.67 112	90.62 91	91.16 131	88.63 120	83.75 84	79.78 126	71.16 143	75.14 102	74.10 130	77.84 163	91.56 69	90.67 79	96.04 28	88.58 180

SPE-MVS-test		90.29 44	90.96 40	89.51 52	93.18 60	95.87 46	89.18 104	83.72 85	88.32 52	84.82 49	84.89 44	85.23 55	90.25 34	94.04 30	92.66 52	95.94 31	95.69 52

CS-MVS		90.34 43	90.58 45	90.07 44	93.11 61	95.82 47	90.57 71	83.62 86	87.07 57	85.35 44	82.98 48	83.47 62	91.37 27	94.94 14	93.37 38	96.37 16	96.41 41

FC-MVSNet-train		85.18 107	85.31 107	85.03 110	90.67 90	91.62 128	87.66 132	83.61 87	79.75 127	74.37 128	78.69 73	71.21 149	78.91 155	91.23 73	89.96 105	94.96 101	94.69 71

UGNet		85.90 98	88.23 62	83.18 134	88.96 130	94.10 81	87.52 133	83.60 88	81.66 100	77.90 107	80.76 63	83.19 64	66.70 225	91.13 83	90.71 78	94.39 135	96.06 46
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
MAR-MVS		88.39 62	88.44 60	88.33 68	94.90 44	95.06 62	90.51 75	83.59 89	85.27 64	79.07 100	77.13 82	82.89 66	87.70 54	92.19 63	92.32 54	94.23 139	94.20 83
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
DU-MVS		81.20 148	80.30 152	82.25 144	84.98 179	90.94 135	85.70 165	83.58 90	75.74 152	64.21 186	65.30 176	59.60 215	80.22 136	86.89 155	89.31 122	94.77 111	94.29 77

NR-MVSNet		80.25 155	79.98 158	80.56 167	85.20 174	90.94 135	85.65 167	83.58 90	75.74 152	61.36 210	65.30 176	56.75 229	72.38 204	88.46 138	88.80 136	95.16 92	93.87 92

casdiffseed414692147		85.57 101	83.88 120	87.54 84	89.98 113	93.88 94	90.07 85	83.49 92	79.40 130	80.57 87	68.32 150	71.85 147	86.11 71	89.45 125	90.56 83	95.00 98	93.69 106

Baseline_NR-MVSNet		79.84 160	78.37 177	81.55 153	84.98 179	86.66 197	85.06 174	83.49 92	75.57 154	63.31 193	58.22 221	60.97 205	78.00 161	86.89 155	87.13 154	94.47 130	93.15 115

OpenMVS	82.53 11	87.71 70	86.84 79	88.73 59	94.42 49	95.06 62	91.02 68	83.49 92	82.50 90	82.24 69	67.62 155	85.48 53	85.56 77	91.19 76	91.30 63	95.67 49	94.75 67

ACMH+	79.08 13	81.84 141	80.06 156	83.91 126	89.92 119	90.62 137	86.21 160	83.48 95	73.88 168	65.75 174	66.38 162	65.30 179	84.63 92	85.90 175	87.25 153	93.45 169	91.13 163

ETV-MVS		89.22 54	89.76 51	88.60 63	91.60 78	94.61 71	89.48 100	83.46 96	85.20 66	81.58 76	82.75 50	82.59 67	88.80 42	94.57 24	93.28 40	96.68 11	95.31 59

PVSNet_Blended_VisFu		87.40 76	87.80 68	86.92 90	92.86 66	95.40 52	88.56 123	83.45 97	79.55 129	82.26 67	74.49 109	84.03 60	79.24 154	92.97 51	91.53 62	95.15 93	96.65 37

viewdifsd2359ckpt13		86.88 82	86.35 87	87.50 85	89.91 120	94.19 77	89.89 91	83.43 98	82.94 81	80.82 82	75.76 96	76.45 113	85.95 74	90.72 97	90.49 85	95.00 98	93.88 91

Anonymous20231211		84.42 118	83.02 126	86.05 99	88.85 131	92.70 115	88.92 116	83.40 99	79.99 122	78.31 103	55.83 226	78.92 92	83.33 101	89.06 130	89.76 112	93.50 168	94.90 63

COLMAP_ROB	76.78 15	80.50 153	78.49 173	82.85 136	90.96 88	89.65 162	86.20 161	83.40 99	77.15 145	66.54 165	62.27 189	65.62 178	77.89 162	85.23 185	84.70 193	92.11 195	84.83 219
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
E6new		86.44 88	85.45 105	87.59 82	89.94 116	94.05 85	90.00 86	83.35 101	80.22 119	81.75 74	73.69 118	75.92 120	85.13 86	90.17 108	90.41 87	95.40 66	93.70 104

E6		86.44 88	85.45 105	87.59 82	89.94 116	94.05 85	90.00 86	83.35 101	80.22 119	81.75 74	73.69 118	75.92 120	85.13 86	90.17 108	90.41 87	95.40 66	93.70 104

dmvs_re		81.08 149	79.92 159	82.44 142	86.66 156	87.70 188	87.91 129	83.30 103	72.86 180	65.29 181	65.76 166	63.43 190	76.69 170	88.93 132	89.50 118	94.80 108	91.23 162

viewmacassd2359aftdt		86.41 91	85.73 98	87.21 88	89.86 121	94.03 88	90.30 81	83.22 104	80.76 113	79.59 97	73.51 122	76.32 116	85.06 90	90.24 107	91.13 64	95.23 87	94.11 84

viewmanbaseed2359cas		87.17 78	86.90 78	87.48 86	90.08 108	94.14 78	90.30 81	83.19 105	84.17 74	80.68 86	76.78 87	77.43 103	85.43 80	90.78 93	90.92 71	95.21 89	94.10 85

UniMVSNet (Re)		81.22 147	81.08 143	81.39 155	85.35 171	91.76 127	84.93 176	82.88 106	76.13 150	65.02 182	64.94 179	63.09 193	75.17 187	87.71 146	89.04 131	94.97 100	94.88 64

EIA-MVS		87.94 69	88.05 65	87.81 78	91.46 79	95.00 64	88.67 117	82.81 107	82.53 86	80.81 83	80.04 65	80.20 78	87.48 58	92.58 56	91.61 61	95.63 51	94.36 76

thres100view900		82.55 134	81.01 146	84.34 116	90.30 103	92.27 121	89.04 113	82.77 108	75.14 156	69.56 150	65.72 170	63.13 191	79.62 149	89.97 114	89.26 125	94.73 114	91.61 156

tfpn200view9		82.86 129	81.46 137	84.48 114	90.30 103	93.09 106	89.05 112	82.71 109	75.14 156	69.56 150	65.72 170	63.13 191	80.38 135	91.15 80	89.51 117	94.91 104	92.50 138

thres400		82.68 132	81.15 142	84.47 115	90.52 95	92.89 111	88.95 115	82.71 109	74.33 163	69.22 155	65.31 175	62.61 197	80.63 128	90.96 89	89.50 118	94.79 109	92.45 140

thres600view7		82.53 135	81.02 144	84.28 119	90.61 92	93.05 107	88.57 122	82.67 111	74.12 166	68.56 158	65.09 178	62.13 202	80.40 134	91.15 80	89.02 132	94.88 105	92.59 132

thres200		82.77 131	81.25 141	84.54 113	90.38 100	93.05 107	89.13 109	82.67 111	74.40 162	69.53 152	65.69 172	63.03 194	80.63 128	91.15 80	89.42 121	94.88 105	92.04 144

DI_MVS_pp		86.41 91	85.54 104	87.42 87	89.24 126	93.13 105	92.16 53	82.65 113	82.30 92	80.75 85	68.30 151	80.41 76	85.01 91	90.56 100	90.07 101	94.70 117	94.01 86

TDRefinement		79.05 173	77.05 192	81.39 155	88.45 133	89.00 175	86.92 150	82.65 113	74.21 165	64.41 185	59.17 209	59.16 218	74.52 193	85.23 185	85.09 188	91.37 209	87.51 200

sasdasda		89.36 52	89.92 47	88.70 60	91.38 80	95.92 43	91.81 59	82.61 115	90.37 41	82.73 64	82.09 52	79.28 87	88.30 49	91.17 77	93.59 29	95.36 71	97.04 27

canonicalmvs		89.36 52	89.92 47	88.70 60	91.38 80	95.92 43	91.81 59	82.61 115	90.37 41	82.73 64	82.09 52	79.28 87	88.30 49	91.17 77	93.59 29	95.36 71	97.04 27

IS_MVSNet		86.18 93	88.18 63	83.85 127	91.02 86	94.72 70	87.48 134	82.46 117	81.05 108	70.28 147	76.98 84	82.20 70	76.65 171	93.97 33	93.38 36	95.18 90	94.97 62

MGCFI-Net		88.38 63	89.72 52	86.83 91	91.21 83	95.59 51	91.14 67	82.37 118	90.25 43	75.33 124	81.89 54	79.13 89	85.69 76	90.98 88	93.23 41	95.23 87	96.94 29

EPP-MVSNet		86.55 86	87.76 70	85.15 107	90.52 95	94.41 73	87.24 141	82.32 119	81.79 99	73.60 132	78.57 74	82.41 68	82.07 112	91.23 73	90.39 89	95.14 94	95.48 57

CLD-MVS		88.66 57	88.52 59	88.82 58	91.37 82	94.22 75	92.82 50	82.08 120	88.27 53	85.14 46	81.86 55	78.53 94	85.93 75	91.17 77	90.61 80	95.55 58	95.00 61
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Vis-MVSNet (Re-imp)		83.65 125	86.81 81	79.96 173	90.46 98	92.71 114	84.84 178	82.00 121	80.93 110	62.44 199	76.29 90	82.32 69	65.54 228	92.29 59	91.66 59	94.49 129	91.47 159

viewdifsd2359ckpt07		85.95 97	85.62 101	86.34 94	89.73 122	93.40 102	89.18 104	81.99 122	81.53 101	80.19 90	75.17 101	76.65 111	83.45 99	90.32 104	89.00 133	93.51 167	93.26 111

PatchMatch-RL		83.34 127	81.36 139	85.65 101	90.33 102	89.52 164	84.36 182	81.82 123	80.87 112	79.29 98	74.04 114	62.85 196	86.05 73	88.40 139	87.04 157	92.04 196	86.77 205

diffmvs_AUTHOR		86.44 88	86.59 86	86.26 95	88.33 136	92.74 113	89.66 96	81.74 124	85.17 67	80.04 92	77.70 80	77.20 105	83.68 95	89.66 121	89.28 123	94.14 143	94.37 74

UniMVSNet_ETH3D		79.24 171	76.47 199	82.48 141	85.66 167	90.97 134	86.08 162	81.63 125	64.48 227	68.94 157	54.47 228	57.65 224	78.83 156	85.20 188	88.91 135	93.72 161	93.60 107

diffmvs		86.52 87	86.76 83	86.23 96	88.31 137	92.63 117	89.58 97	81.61 126	86.14 59	80.26 89	79.00 71	77.27 104	83.58 97	88.94 131	89.06 130	94.05 146	94.29 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
viewmambaseed2359dif		85.52 102	85.01 109	86.12 98	88.39 134	91.96 125	89.39 101	81.43 127	82.16 93	80.47 88	75.52 98	76.85 110	83.66 96	87.03 153	87.60 148	93.37 172	93.98 87

EC-MVSNet		89.96 48	90.77 44	89.01 56	90.54 94	95.15 59	91.34 64	81.43 127	85.27 64	83.08 59	82.83 49	87.22 50	90.97 30	94.79 20	93.38 36	96.73 10	96.71 36

IB-MVS	79.09 12	82.60 133	82.19 132	83.07 135	91.08 85	93.55 98	80.90 215	81.35 129	76.56 147	80.87 81	64.81 181	69.97 154	68.87 215	85.64 178	90.06 102	95.36 71	94.74 68
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
tfpnnormal		77.46 192	74.86 219	80.49 168	86.34 160	88.92 176	84.33 183	81.26 130	61.39 235	61.70 207	51.99 236	53.66 241	74.84 190	88.63 135	87.38 152	94.50 127	92.08 142

TransMVSNet (Re)		76.57 201	75.16 218	78.22 192	85.60 168	87.24 193	82.46 200	81.23 131	59.80 240	59.05 223	57.07 223	59.14 219	66.60 226	88.09 141	86.82 159	94.37 136	87.95 192

Vis-MVSNet		84.38 119	86.68 84	81.70 149	87.65 146	94.89 66	88.14 126	80.90 132	74.48 161	68.23 159	77.53 81	80.72 75	69.98 212	92.68 54	91.90 57	95.33 78	94.58 72
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DCV-MVSNet		85.88 99	86.17 90	85.54 104	89.10 129	89.85 153	89.34 102	80.70 133	83.04 80	78.08 106	76.19 91	79.00 90	82.42 110	89.67 120	90.30 92	93.63 165	95.12 60

viewdifsd2359ckpt11		84.31 120	83.65 123	85.08 108	88.07 138	91.03 132	86.86 153	80.65 134	79.92 123	79.63 95	75.08 103	73.99 132	82.74 104	86.40 169	85.98 179	92.51 183	93.16 113

viewmsd2359difaftdt		84.31 120	83.65 123	85.07 109	88.07 138	91.03 132	86.86 153	80.65 134	79.92 123	79.61 96	75.08 103	73.98 133	82.74 104	86.40 169	85.99 177	92.51 183	93.16 113

WR-MVS		76.63 200	78.02 182	75.02 218	84.14 189	89.76 158	78.34 228	80.64 136	69.56 197	52.32 236	61.26 194	61.24 204	60.66 234	84.45 197	87.07 155	93.99 149	92.77 125

usedtu_dtu_shiyan1		79.85 159	79.89 160	79.80 176	77.40 232	89.77 157	85.31 173	80.48 137	77.76 142	64.71 184	61.69 192	67.04 173	75.92 178	87.76 145	87.67 147	94.96 101	87.52 199

ET-MVSNet_ETH3D		84.65 112	85.58 103	83.56 131	74.99 240	92.62 119	90.29 83	80.38 138	82.16 93	73.01 138	83.41 46	71.10 150	87.05 64	87.77 144	90.17 98	95.62 52	91.82 148

GBi-Net		84.51 115	84.80 110	84.17 121	84.20 186	89.95 148	89.70 93	80.37 139	81.17 104	75.50 118	69.63 139	79.69 84	79.75 146	90.73 94	90.72 75	95.52 61	91.71 150

test1		84.51 115	84.80 110	84.17 121	84.20 186	89.95 148	89.70 93	80.37 139	81.17 104	75.50 118	69.63 139	79.69 84	79.75 146	90.73 94	90.72 75	95.52 61	91.71 150

FMVSNet3		84.44 117	84.64 112	84.21 120	84.32 185	90.13 146	89.85 92	80.37 139	81.17 104	75.50 118	69.63 139	79.69 84	79.62 149	89.72 119	90.52 84	95.59 55	91.58 157

CDS-MVSNet		81.63 145	82.09 133	81.09 161	87.21 151	90.28 142	87.46 136	80.33 142	69.06 200	70.66 144	71.30 130	73.87 134	67.99 218	89.58 122	89.87 108	92.87 179	90.69 165
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+		85.33 104	85.08 108	85.63 102	89.69 123	93.42 101	89.90 90	80.31 143	79.32 131	72.48 141	73.52 121	74.03 131	86.55 70	90.99 86	89.98 104	94.83 107	94.27 81

FMVSNet2		83.87 122	83.73 122	84.05 125	84.20 186	89.95 148	89.70 93	80.21 144	79.17 134	74.89 125	65.91 164	77.49 101	79.75 146	90.87 90	91.00 69	95.52 61	91.71 150

MVS_Test		86.93 81	87.24 74	86.56 92	90.10 106	93.47 99	90.31 80	80.12 145	83.55 78	78.12 104	79.58 68	79.80 82	85.45 79	90.17 108	90.59 81	95.29 83	93.53 109

thisisatest0530		85.15 108	85.86 94	84.33 117	89.19 128	92.57 120	87.22 142	80.11 146	82.15 95	74.41 127	78.15 76	73.80 136	79.90 142	90.99 86	89.58 115	95.13 95	93.75 102

tttt0517		85.11 109	85.81 95	84.30 118	89.24 126	92.68 116	87.12 147	80.11 146	81.98 96	74.31 129	78.08 77	73.57 138	79.90 142	91.01 84	89.58 115	95.11 97	93.77 101

DTE-MVSNet		75.14 222	75.44 216	74.80 220	83.18 198	87.19 194	78.25 230	80.11 146	66.05 218	48.31 243	60.88 199	54.67 236	64.54 229	82.57 209	86.17 172	94.43 133	90.53 169

PEN-MVS		76.02 210	76.07 204	75.95 213	83.17 199	87.97 185	79.65 219	80.07 149	66.57 216	51.45 238	60.94 198	55.47 234	66.81 224	82.72 207	86.80 160	94.59 122	92.03 145

MVSTER		86.03 95	86.12 91	85.93 100	88.62 132	89.93 151	89.33 103	79.91 150	81.87 98	81.35 77	81.07 62	74.91 126	80.66 127	92.13 65	90.10 99	95.68 48	92.80 124

v2v482		79.84 160	78.07 180	81.90 147	83.75 191	90.21 145	87.17 143	79.85 151	70.65 192	65.93 173	61.93 191	60.07 209	80.82 122	85.25 184	86.71 161	93.88 154	91.70 154

CP-MVSNet		76.36 207	76.41 200	76.32 210	82.73 208	88.64 178	79.39 222	79.62 152	67.21 212	53.70 230	60.72 200	55.22 235	67.91 220	83.52 203	86.34 170	94.55 125	93.19 112

FMVSNet1		81.64 144	80.61 149	82.84 137	82.36 211	89.20 170	88.67 117	79.58 153	70.79 191	72.63 140	58.95 212	72.26 145	79.34 152	90.73 94	90.72 75	94.47 130	91.62 155

PS-CasMVS		75.90 212	75.86 209	75.96 212	82.59 209	88.46 182	79.23 225	79.56 154	66.00 219	52.77 233	59.48 208	54.35 239	67.14 223	83.37 204	86.23 171	94.47 130	93.10 116

RPSCF		83.46 126	83.36 125	83.59 130	87.75 142	87.35 192	84.82 179	79.46 155	83.84 76	78.12 104	82.69 51	79.87 80	82.60 109	82.47 210	81.13 214	88.78 228	86.13 212

pm-mvs1		78.51 183	77.75 185	79.40 177	84.83 182	89.30 167	83.55 189	79.38 156	62.64 231	63.68 191	58.73 217	64.68 181	70.78 211	89.79 118	87.84 144	94.17 141	91.28 161

WR-MVS_H		75.84 213	76.93 195	74.57 223	82.86 205	89.50 165	78.34 228	79.36 157	66.90 214	52.51 234	60.20 204	59.71 212	59.73 235	83.61 202	85.77 181	94.65 119	92.84 122

v148		78.59 181	76.84 197	80.62 166	83.61 194	89.16 171	83.65 188	79.24 158	69.38 198	69.34 154	59.88 206	60.41 208	75.19 186	83.81 201	84.63 194	92.70 181	90.63 167

CHOSEN 1792x2688		82.16 136	80.91 147	83.61 129	91.14 84	92.01 124	89.55 99	79.15 159	79.87 125	70.29 146	52.51 235	72.56 143	81.39 116	88.87 134	88.17 142	90.15 221	92.37 141

GeoE		84.62 113	83.98 119	85.35 106	89.34 125	92.83 112	88.34 124	78.95 160	79.29 132	77.16 112	68.10 152	74.56 127	83.40 100	89.31 128	89.23 126	94.92 103	94.57 73

baseline2		82.80 130	82.86 129	82.73 139	87.68 145	90.50 139	84.92 177	78.93 161	78.07 141	73.06 136	75.08 103	69.77 155	77.31 166	88.90 133	86.94 158	94.50 127	90.74 164

USDC		80.69 151	79.89 160	81.62 152	86.48 158	89.11 173	86.53 157	78.86 162	81.15 107	63.48 192	72.98 124	59.12 220	81.16 119	87.10 150	85.01 189	93.23 173	84.77 220

FC-MVSNet-test		76.53 203	81.62 136	70.58 233	84.99 178	85.73 212	74.81 237	78.85 163	77.00 146	39.13 254	75.90 94	73.50 139	54.08 242	86.54 165	85.99 177	91.65 204	86.68 206

pmmvs4		79.99 156	78.08 179	82.22 145	83.04 201	87.16 195	84.95 175	78.80 164	78.64 137	74.53 126	64.61 182	59.41 216	79.45 151	84.13 199	84.54 196	92.53 182	88.08 186

IterMVS-LS		83.28 128	82.95 128	83.65 128	88.39 134	88.63 179	86.80 155	78.64 165	76.56 147	73.43 134	72.52 127	75.35 123	80.81 123	86.43 168	88.51 140	93.84 156	92.66 129
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GA-MVS		79.52 165	79.71 165	79.30 179	85.68 166	90.36 141	84.55 180	78.44 166	70.47 195	57.87 225	68.52 149	61.38 203	76.21 176	89.40 127	87.89 143	93.04 177	89.96 173

v1144		79.38 170	77.83 183	81.18 160	83.62 193	90.23 143	87.15 146	78.35 167	69.13 199	64.02 189	60.20 204	59.41 216	80.14 140	86.78 158	86.57 165	93.81 158	92.53 137

HyFIR lowres test		81.62 146	79.45 168	84.14 123	91.00 87	93.38 103	88.27 125	78.19 168	76.28 149	70.18 148	48.78 239	73.69 137	83.52 98	87.05 152	87.83 146	93.68 163	89.15 177

TinyColmap		76.73 198	73.95 227	79.96 173	85.16 176	85.64 214	82.34 203	78.19 168	70.63 193	62.06 202	60.69 201	49.61 247	80.81 123	85.12 189	83.69 201	91.22 213	82.27 228

Effi-MVS+-dtu		82.05 137	81.76 134	82.38 143	87.72 143	90.56 138	86.90 152	78.05 170	73.85 169	66.85 164	71.29 131	71.90 146	82.00 113	86.64 163	85.48 184	92.76 180	92.58 133

test-LLR		79.47 167	79.84 162	79.03 181	87.47 147	82.40 235	81.24 212	78.05 170	73.72 170	62.69 196	73.76 116	74.42 128	73.49 199	84.61 195	82.99 206	91.25 211	87.01 203

test0.0.03 1		76.03 209	78.51 172	73.12 228	87.47 147	85.13 220	76.32 234	78.05 170	73.19 178	50.98 241	70.64 133	69.28 158	55.53 238	85.33 183	84.38 197	90.39 219	81.63 232

v1192		78.94 175	77.33 188	80.82 163	83.25 197	89.90 152	86.91 151	77.72 173	68.63 203	62.61 198	59.17 209	57.53 225	80.62 130	86.89 155	86.47 167	93.79 159	92.75 127

Fast-Effi-MVS+		83.77 124	82.98 127	84.69 111	87.98 140	91.87 126	88.10 127	77.70 174	78.10 140	73.04 137	69.13 145	68.51 162	86.66 68	90.49 101	89.85 109	94.67 118	92.88 121

v144192		78.81 177	77.22 190	80.67 165	82.95 202	89.79 156	86.40 158	77.42 175	68.26 205	63.13 194	59.50 207	58.13 221	80.08 141	85.93 174	86.08 174	94.06 145	92.83 123

v8		79.90 158	78.39 176	81.66 150	83.97 190	89.81 154	87.16 144	77.40 176	71.49 186	67.71 160	61.24 195	62.49 198	79.83 145	85.48 182	86.17 172	93.89 153	92.02 146

LTVRE_ROB	74.41 16	75.78 214	74.72 220	77.02 201	85.88 162	89.22 169	82.44 202	77.17 177	50.57 251	45.45 247	65.44 174	52.29 243	81.25 117	85.50 181	87.42 151	89.94 223	92.62 130
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
v1921920		78.57 182	76.99 193	80.41 171	82.93 203	89.63 163	86.38 159	77.14 178	68.31 204	61.80 206	58.89 213	56.79 228	80.19 139	86.50 167	86.05 176	94.02 147	92.76 126

pmmvs6		74.83 223	72.89 230	77.09 197	82.11 212	87.50 191	80.88 216	76.97 179	52.79 249	61.91 205	46.66 241	60.49 206	69.28 214	86.74 161	85.46 185	91.39 208	90.56 168

thisisatest0515		79.76 162	80.59 150	78.80 183	84.40 184	88.91 177	79.48 221	76.94 180	72.29 183	67.33 162	67.82 154	65.99 176	70.80 210	88.50 137	87.84 144	93.86 155	92.75 127

v10		79.62 163	78.19 178	81.28 158	83.73 192	89.69 160	87.27 140	76.86 181	70.50 194	65.46 176	60.58 202	60.47 207	80.44 132	86.91 154	86.63 164	93.93 150	92.55 135

v1240		78.15 185	76.53 198	80.04 172	82.85 206	89.48 166	85.61 170	76.77 182	67.05 213	61.18 213	58.37 220	56.16 232	79.89 144	86.11 173	86.08 174	93.92 151	92.47 139

V42		79.59 164	78.43 175	80.94 162	82.79 207	89.71 159	86.66 156	76.73 183	71.38 187	67.42 161	61.01 197	62.30 200	78.39 158	85.56 180	86.48 166	93.65 164	92.60 131

v7n		77.22 194	76.23 202	78.38 191	81.89 214	89.10 174	82.24 206	76.36 184	65.96 220	61.21 212	56.56 224	55.79 233	75.07 189	86.55 164	86.68 162	93.52 166	92.95 120

gbinet_0.2-2-1-0.02		75.42 221	74.57 221	76.42 207	67.86 249	86.00 207	82.79 198	76.24 185	65.77 222	65.59 175	58.60 219	65.11 180	73.76 197	79.11 226	76.90 231	92.27 194	90.47 170

SixPastTwentyTwo		76.02 210	75.72 212	76.36 209	83.38 195	87.54 190	75.50 236	76.22 186	65.50 224	57.05 226	70.64 133	53.97 240	74.54 192	80.96 215	82.12 211	91.44 207	89.35 176

FE-MVSNET2		71.00 232	70.45 237	71.65 231	66.32 250	85.00 221	76.33 233	76.20 187	61.03 236	52.47 235	41.50 250	50.21 245	64.44 230	84.97 192	85.46 185	94.16 142	84.97 217

MDA-MVSNet-bldmvs		66.22 239	64.49 243	68.24 236	61.67 252	82.11 237	70.07 246	76.16 188	59.14 242	47.94 244	54.35 229	35.82 260	67.33 222	64.94 252	75.68 239	86.30 242	79.36 240

test20.03		68.31 237	70.05 238	66.28 240	82.41 210	80.84 239	67.35 249	76.11 189	58.44 243	40.80 253	53.77 232	54.54 237	42.28 250	83.07 205	81.96 213	88.73 229	77.76 244

pmmvs-eth3d		74.32 226	71.96 232	77.08 198	77.33 233	82.71 231	78.41 227	76.02 190	66.65 215	65.98 172	54.23 230	49.02 249	73.14 203	82.37 211	82.69 208	91.61 205	86.05 213

Anonymous20231206		70.80 233	70.59 236	71.04 232	81.60 216	82.49 234	74.64 238	75.87 191	64.17 228	49.27 242	44.85 245	53.59 242	54.68 241	83.07 205	82.34 210	90.17 220	83.65 223

WB-MVS		52.27 249	57.26 250	46.45 249	75.64 239	65.62 255	40.45 261	75.80 192	47.10 254	9.11 264	53.83 231	38.98 259	14.47 258	69.44 248	68.29 250	63.24 257	57.56 255

baseline		84.89 110	86.06 93	83.52 132	87.25 150	89.67 161	87.76 130	75.68 193	84.92 69	78.40 102	80.10 64	80.98 73	80.20 138	86.69 162	87.05 156	91.86 200	92.99 118

blended_shiyan8		75.62 216	74.39 223	77.05 199	69.20 243	86.13 200	83.05 195	75.65 194	68.14 206	66.18 168	58.73 217	64.21 184	75.71 182	78.65 228	76.92 230	92.50 185	87.96 190

blended_shiyan6		75.62 216	74.41 222	77.03 200	69.20 243	86.12 201	83.03 196	75.65 194	68.09 211	66.14 169	58.83 216	64.22 183	75.70 183	78.65 228	76.94 229	92.49 186	88.01 188

wanda-best-256-512		75.51 218	74.25 224	76.99 202	69.08 245	86.01 203	83.06 192	75.62 196	68.11 208	66.14 169	58.89 213	64.15 185	75.77 180	78.43 230	76.54 233	92.29 190	87.59 197

FE-blended-shiyan7		75.51 218	74.25 224	76.99 202	69.08 245	86.01 203	83.06 192	75.62 196	68.12 207	66.14 169	58.89 213	64.15 185	75.77 180	78.43 230	76.54 233	92.29 190	87.59 197

usedtu_blend_shiyan5		77.43 193	75.78 211	79.36 178	69.08 245	86.01 203	86.97 149	75.62 196	68.11 208	75.60 114	65.73 167	67.75 169	76.63 172	78.43 230	76.54 233	92.29 190	87.87 193

FE-MVSNET3		77.14 195	75.80 210	78.71 186	69.08 245	86.01 203	83.06 192	75.62 196	68.11 208	75.60 114	65.73 167	67.75 169	76.63 172	78.43 230	76.54 233	92.29 190	88.01 188

CANet_DTU		85.43 103	87.72 72	82.76 138	90.95 89	93.01 109	89.99 88	75.46 200	82.67 83	64.91 183	83.14 47	80.09 79	80.68 125	92.03 66	91.03 67	94.57 124	92.08 142

MS-PatchMatch		81.79 142	81.44 138	82.19 146	90.35 101	89.29 168	88.08 128	75.36 201	77.60 143	69.00 156	64.37 184	78.87 93	77.14 169	88.03 142	85.70 182	93.19 175	86.24 211

0.4-1-1-0.1		79.43 168	77.51 187	81.66 150	79.11 223	88.57 181	87.37 137	75.16 202	73.57 173	75.70 113	67.26 157	67.91 167	80.67 126	78.11 234	79.88 215	91.94 199	87.30 201

blend_shiyan4		78.17 184	76.23 202	80.43 170	77.49 231	85.96 209	85.63 168	74.87 203	72.02 184	75.60 114	65.73 167	67.75 169	76.63 172	77.82 236	76.48 237	92.34 188	87.87 193

0.3-1-1-0.015		79.02 174	76.98 194	81.41 154	78.71 226	88.07 184	87.16 144	74.71 204	72.89 179	75.60 114	66.54 161	67.75 169	80.60 131	77.49 238	79.58 218	91.66 203	86.56 209

0.4-1-1-0.2		78.93 176	76.93 195	81.25 159	78.56 227	87.86 186	86.98 148	74.58 205	72.54 182	75.49 122	66.85 159	67.89 168	80.44 132	77.55 237	79.41 221	91.49 206	86.44 210

CVMVSNet		76.70 199	78.46 174	74.64 222	83.34 196	84.48 223	81.83 208	74.58 205	68.88 201	51.23 240	69.77 138	70.05 153	67.49 221	84.27 198	83.81 199	89.38 225	87.96 190

FE-MVSNET		66.05 240	67.24 239	64.66 241	59.88 254	79.66 243	69.18 247	74.46 207	55.47 248	37.02 256	41.66 249	48.62 250	55.72 237	80.54 217	83.09 204	91.68 202	81.66 231

testgi		71.92 231	74.20 226	69.27 235	84.58 183	83.06 227	73.40 240	74.39 208	64.04 229	46.17 246	68.90 148	57.15 227	48.89 247	84.07 200	83.08 205	88.18 231	79.09 242

pmmvs5		76.93 197	76.33 201	77.62 194	81.97 213	88.40 183	81.32 211	74.35 209	65.42 225	61.42 209	63.07 187	57.95 223	73.23 202	85.60 179	85.35 187	93.41 170	88.55 181

MIMVSNet1		65.00 241	66.24 242	63.55 243	58.41 256	80.01 242	69.00 248	74.03 210	55.81 246	41.88 251	36.81 252	49.48 248	47.89 248	81.32 214	82.40 209	90.08 222	77.88 243

EG-PatchMatch MVS		76.40 206	75.47 215	77.48 195	85.86 164	90.22 144	82.45 201	73.96 211	59.64 241	59.60 219	52.75 234	62.20 201	68.44 217	88.23 140	87.50 149	94.55 125	87.78 195

CMPMVS	56.49 17	73.84 228	71.73 234	76.31 211	85.20 174	85.67 213	75.80 235	73.23 212	62.26 232	65.40 177	53.40 233	59.70 213	71.77 207	80.25 219	79.56 219	86.45 241	81.28 234
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FA-MVS(training)		85.65 100	85.79 97	85.48 105	90.44 99	93.47 99	88.66 119	73.11 213	83.34 79	82.26 67	71.79 128	78.39 95	83.14 102	91.00 85	89.47 120	95.28 85	93.06 117

anonymousdsp		77.94 187	79.00 169	76.71 205	79.03 224	87.83 187	79.58 220	72.87 214	65.80 221	58.86 224	65.82 165	62.48 199	75.99 177	86.77 159	88.66 137	93.92 151	95.68 54

pmnet_mix02		71.95 230	71.83 233	72.10 229	81.40 218	80.63 241	73.78 239	72.85 215	70.90 190	54.89 228	62.17 190	57.42 226	62.92 232	76.80 240	73.98 245	86.74 240	80.87 237

Fast-Effi-MVS+-dtu		79.95 157	80.69 148	79.08 180	86.36 159	89.14 172	85.85 163	72.28 216	72.85 181	59.32 220	70.43 137	68.42 164	77.57 164	86.14 172	86.44 168	93.11 176	91.39 160

IterMVS-SCA-FT		79.41 169	80.20 154	78.49 189	85.88 162	86.26 199	83.95 185	71.94 217	73.55 174	61.94 203	70.48 136	70.50 151	75.23 185	85.81 177	84.61 195	91.99 198	90.18 172

PM-MVS		74.17 227	73.10 228	75.41 215	76.07 236	82.53 233	77.56 231	71.69 218	71.04 188	61.92 204	61.23 196	47.30 251	74.82 191	81.78 213	79.80 216	90.42 218	88.05 187

TAMVS		76.42 204	77.16 191	75.56 214	83.05 200	85.55 215	80.58 217	71.43 219	65.40 226	61.04 214	67.27 156	69.22 160	67.99 218	84.88 193	84.78 192	89.28 226	83.01 226

N_pmnet		66.85 238	66.63 240	67.11 239	78.73 225	74.66 250	70.53 245	71.07 220	66.46 217	46.54 245	51.68 237	51.91 244	55.48 239	74.68 244	72.38 246	80.29 252	74.65 247

new-patchmatchnet		63.80 242	63.31 244	64.37 242	76.49 234	75.99 248	63.73 252	70.99 221	57.27 244	43.08 249	45.86 243	43.80 253	45.13 249	73.20 246	70.68 249	86.80 239	76.34 246

CostFormer		80.94 150	80.21 153	81.79 148	87.69 144	88.58 180	87.47 135	70.66 222	80.02 121	77.88 108	73.03 123	71.40 148	78.24 159	79.96 220	79.63 217	88.82 227	88.84 178

tpm cat1		77.78 189	75.28 217	80.70 164	87.14 152	85.84 211	85.81 164	70.40 223	77.44 144	78.80 101	63.72 185	64.01 189	76.55 175	75.60 243	75.21 241	85.51 245	85.12 216

MDTV_nov1_ep13		79.14 172	79.49 167	78.74 185	85.40 170	86.89 196	84.32 184	70.29 224	78.85 135	69.42 153	75.37 100	73.29 141	75.64 184	80.61 216	79.48 220	87.36 234	81.91 229

FMVSNet5		75.50 220	76.07 204	74.83 219	76.16 235	81.19 238	81.34 210	70.21 225	73.20 177	61.59 208	58.97 211	68.33 165	68.50 216	85.87 176	85.85 180	91.18 214	79.11 241

dps		78.02 186	75.94 208	80.44 169	86.06 161	86.62 198	82.58 199	69.98 226	75.14 156	77.76 110	69.08 146	59.93 211	78.47 157	79.47 222	77.96 226	87.78 232	83.40 224

EU-MVSNet		69.98 235	72.30 231	67.28 238	75.67 238	79.39 244	73.12 241	69.94 227	63.59 230	42.80 250	62.93 188	56.71 230	55.07 240	79.13 225	78.55 224	87.06 237	85.82 215

IterMVS		78.79 178	79.71 165	77.71 193	85.26 173	85.91 210	84.54 181	69.84 228	73.38 175	61.25 211	70.53 135	70.35 152	74.43 194	85.21 187	83.80 200	90.95 215	88.77 179
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PMVS	50.48 18	55.81 248	51.93 251	60.33 246	72.90 241	49.34 257	48.78 256	69.51 229	43.49 255	54.25 229	36.26 253	41.04 258	39.71 252	65.07 251	60.70 252	76.85 254	67.58 251
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		63.63 243	60.08 249	67.78 237	80.01 221	71.50 252	72.88 242	69.41 230	61.82 234	53.11 232	45.12 244	42.11 256	50.86 245	66.69 250	63.84 251	80.41 251	69.46 250

SCA		79.51 166	80.15 155	78.75 184	86.58 157	87.70 188	83.07 191	68.53 231	81.31 103	66.40 166	73.83 115	75.38 122	79.30 153	80.49 218	79.39 222	88.63 230	82.96 227

CR-MVSNet		78.71 179	78.86 170	78.55 188	85.85 165	85.15 218	82.30 204	68.23 232	74.71 159	65.37 178	64.39 183	69.59 157	77.18 167	85.10 190	84.87 190	92.34 188	88.21 184

Patchmtry						85.54 216	82.30 204	68.23 232		65.37 178

PatchmatchNet		78.67 180	78.85 171	78.46 190	86.85 155	86.03 202	83.77 187	68.11 234	80.88 111	66.19 167	72.90 125	73.40 140	78.06 160	79.25 224	77.71 227	87.75 233	81.75 230
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		74.69 224	75.60 214	73.62 225	76.02 237	85.31 217	81.21 214	67.43 235	71.02 189	59.07 222	54.48 227	64.07 187	66.14 227	86.52 166	86.64 163	91.83 201	81.17 235

PMMVS		81.65 143	84.05 118	78.86 182	78.56 227	82.63 232	83.10 190	67.22 236	81.39 102	70.11 149	84.91 43	79.74 83	82.12 111	87.31 148	85.70 182	92.03 197	86.67 208

usedtu_dtu_shiyan2		62.45 244	61.54 247	63.50 244	49.14 259	78.26 247	71.51 244	67.18 237	43.16 256	53.22 231	33.68 255	45.76 252	53.15 243	74.24 245	74.13 244	86.83 238	81.56 233

tpm		76.30 208	76.05 206	76.59 206	86.97 153	83.01 229	83.83 186	67.06 238	71.83 185	63.87 190	69.56 142	62.88 195	73.41 201	79.79 221	78.59 223	84.41 246	86.68 206

CHOSEN 280x420		80.28 154	81.66 135	78.67 187	82.92 204	79.24 245	85.36 172	66.79 239	78.11 139	70.32 145	75.03 106	79.87 80	81.09 120	89.07 129	83.16 203	85.54 244	87.17 202

EPMVS		77.53 191	78.07 180	76.90 204	86.89 154	84.91 222	82.18 207	66.64 240	81.00 109	64.11 188	72.75 126	69.68 156	74.42 195	79.36 223	78.13 225	87.14 236	80.68 238

MDTV_nov1_ep13_2view		73.21 229	72.91 229	73.56 226	80.01 221	84.28 225	78.62 226	66.43 241	68.64 202	59.12 221	60.39 203	59.69 214	69.81 213	78.82 227	77.43 228	87.36 234	81.11 236

tpmrst		76.55 202	75.99 207	77.20 196	87.32 149	83.05 228	82.86 197	65.62 242	78.61 138	67.22 163	69.19 144	65.71 177	75.87 179	76.75 241	75.33 240	84.31 247	83.28 225

gm-plane-assit		70.29 234	70.65 235	69.88 234	85.03 177	78.50 246	58.41 255	65.47 243	50.39 252	40.88 252	49.60 238	50.11 246	75.14 188	91.43 71	89.78 110	94.32 137	84.73 221

RPMNet		77.07 196	77.63 186	76.42 207	85.56 169	85.15 218	81.37 209	65.27 244	74.71 159	60.29 216	63.71 186	66.59 175	73.64 198	82.71 208	82.12 211	92.38 187	88.39 182

MVS-HIRNet		68.83 236	66.39 241	71.68 230	77.58 230	75.52 249	66.45 250	65.05 245	62.16 233	62.84 195	44.76 246	56.60 231	71.96 206	78.04 235	75.06 242	86.18 243	72.56 248

PatchT		76.42 204	77.81 184	74.80 220	78.46 229	84.30 224	71.82 243	65.03 246	73.89 167	65.37 178	61.58 193	66.70 174	77.18 167	85.10 190	84.87 190	90.94 216	88.21 184

gg-mvs-nofinetune		75.64 215	77.26 189	73.76 224	87.92 141	92.20 122	87.32 138	64.67 247	51.92 250	35.35 257	46.44 242	77.05 107	71.97 205	92.64 55	91.02 68	95.34 76	89.53 175

Gipuma		49.17 250	47.05 253	51.65 248	59.67 255	48.39 258	41.98 259	63.47 248	55.64 247	33.33 259	14.90 257	13.78 264	41.34 251	69.31 249	72.30 247	70.11 255	55.00 256
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ADS-MVSNet		74.53 225	75.69 213	73.17 227	81.57 217	80.71 240	79.27 224	63.03 249	79.27 133	59.94 218	67.86 153	68.32 166	71.08 209	77.33 239	76.83 232	84.12 249	79.53 239

TESTMET0.1,1		77.78 189	79.84 162	75.38 216	80.86 220	82.40 235	81.24 212	62.72 250	73.72 170	62.69 196	73.76 116	74.42 128	73.49 199	84.61 195	82.99 206	91.25 211	87.01 203

test-mter		77.79 188	80.02 157	75.18 217	81.18 219	82.85 230	80.52 218	62.03 251	73.62 172	62.16 201	73.55 120	73.83 135	73.81 196	84.67 194	83.34 202	91.37 209	88.31 183

new_pmnet		59.28 246	61.47 248	56.73 247	61.66 253	68.29 254	59.57 254	54.91 252	60.83 237	34.38 258	44.66 247	43.65 254	49.90 246	71.66 247	71.56 248	79.94 253	69.67 249

E-PMN		31.40 253	26.80 256	36.78 251	51.39 258	29.96 261	20.20 263	54.17 253	25.93 259	12.75 262	14.73 258	8.58 266	34.10 255	27.36 258	37.83 257	48.07 261	43.18 258

EMVS		30.49 255	25.44 257	36.39 252	51.47 257	29.89 262	20.17 264	54.00 254	26.49 258	12.02 263	13.94 260	8.84 265	34.37 254	25.04 259	34.37 258	46.29 262	39.53 259

pmmvs3		61.89 245	61.74 246	62.06 245	64.30 251	70.83 253	64.22 251	52.14 255	48.78 253	44.47 248	41.67 248	41.70 257	63.03 231	76.06 242	76.02 238	84.18 248	77.14 245

PMMVS2		41.68 252	44.74 254	38.10 250	46.97 260	52.32 256	40.63 260	48.08 256	35.51 257	7.36 265	26.86 256	24.64 262	16.72 257	55.24 255	59.03 253	68.85 256	59.59 254

MVE	30.17 19	30.88 254	33.52 255	27.80 256	23.78 262	39.16 260	18.69 265	46.90 257	21.88 260	15.39 261	14.37 259	7.31 267	24.41 256	41.63 257	56.22 254	37.64 263	54.07 257
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						48.31 259	48.03 257	26.08 258	56.42 245	25.77 260	47.51 240	31.31 261	51.30 244	48.49 256		53.61 259	61.52 252

test_method		41.78 251	48.10 252	34.42 253	10.74 263	19.78 264	44.64 258	17.73 259	59.83 239	38.67 255	35.82 254	54.41 238	34.94 253	62.87 253	43.13 256	59.81 258	60.82 253

tmp_tt				32.73 254	43.96 261	21.15 263	26.71 262	8.99 260	65.67 223	51.39 239	56.01 225	42.64 255	11.76 259	56.60 254	50.81 255	53.55 260

testmvs		1.03 256	1.63 258	0.34 257	0.09 265	0.35 265	0.61 267	0.16 261	1.49 261	0.10 267	3.15 261	0.15 268	0.86 261	1.32 260	1.18 259	0.20 264	3.76 261

GG-mvs-BLEND		57.56 247	82.61 131	28.34 255	0.22 264	90.10 147	79.37 223	0.14 262	79.56 128	0.40 266	71.25 132	83.40 63	0.30 262	86.27 171	83.87 198	89.59 224	83.83 222

test123		0.87 257	1.40 259	0.25 258	0.03 266	0.25 266	0.35 268	0.08 263	1.21 262	0.05 268	2.84 262	0.03 269	0.89 260	0.43 261	1.16 260	0.13 265	3.87 260

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TPM-MVS					96.31 28	96.02 39	94.89 33			86.52 39	87.18 38	92.17 17	86.76 67			95.56 57	93.85 94
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										56.08 227

9.14												92.16 18

our_test_3					81.81 215	83.96 226	76.61 232

ambc			61.92 245		70.98 242	73.54 251	63.64 253		60.06 238	52.23 237	38.44 251	19.17 263	57.12 236	82.33 212	75.03 243	83.21 250	84.89 218

MTAPA										92.97 2		91.03 25

MTMP										93.14 1		90.21 32

Patchmatch-RL test							8.55 266

XVS					93.11 61	96.70 26	91.91 55			83.95 52		88.82 41				95.79 42

X-MVStestdata					93.11 61	96.70 26	91.91 55			83.95 52		88.82 41				95.79 42

mPP-MVS					97.06 12							88.08 46

NP-MVS									87.47 56

High-resolution multi-view benchmark