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.

ME-MVS		97.97 3	98.17 4	97.75 1	99.06 5	99.08 7	98.60 8	96.48 7	97.14 3	96.47 1	98.77 1	99.29 5	97.22 4	97.29 18	96.80 21	98.66 21	98.79 14

TestfortrainingZip							98.60 8	96.48 7		96.36 2						98.66 21

MTMP										95.70 3		96.90 28

MTAPA										95.36 4		97.46 22

DVP-MVS++		98.07 1	98.46 1	97.62 2	99.08 3	99.29 2	98.84 3	96.63 4	97.89 1	95.35 5	97.83 5	99.48 3	96.98 10	97.99 2	97.14 12	98.82 11	99.60 1

SED-MVS		97.98 2	98.36 2	97.54 5	98.94 17	99.29 2	98.81 4	96.64 3	97.14 3	95.16 6	97.96 3	99.61 2	96.92 13	98.00 1	97.24 9	98.75 17	99.25 3

DVP-MVS		97.93 4	98.23 3	97.58 4	99.05 7	99.31 1	98.64 6	96.62 5	97.56 2	95.08 7	96.61 14	99.64 1	97.32 1	97.91 4	97.31 7	98.77 15	99.26 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
SF-MVS		97.20 13	97.29 16	97.10 10	98.95 16	98.51 31	97.51 32	96.48 7	96.17 17	94.64 8	97.32 7	97.57 20	96.23 27	96.78 30	96.15 44	98.79 14	98.55 31

APDe-MVS		97.79 6	97.96 7	97.60 3	99.20 2	99.10 6	98.88 2	96.68 2	96.81 8	94.64 8	97.84 4	98.02 12	97.24 3	97.74 8	97.02 15	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SD-MVS		97.35 9	97.73 9	96.90 15	97.35 46	98.66 16	97.85 28	96.25 13	96.86 7	94.54 10	96.75 12	99.13 7	96.99 8	96.94 28	96.58 25	98.39 46	99.20 5
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
DPE-MVS		97.83 5	98.13 5	97.48 6	98.83 23	99.19 4	98.99 1	96.70 1	96.05 19	94.39 11	98.30 2	99.47 4	97.02 7	97.75 7	97.02 15	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		96.05 29	95.63 33	96.55 22	98.33 30	98.17 45	96.94 39	94.61 36	94.70 40	94.37 12	89.20 54	95.96 37	96.81 14	95.57 59	97.33 6	98.24 65	98.47 35

CNVR-MVS		97.30 11	97.41 12	97.18 9	99.02 11	98.60 23	98.15 18	96.24 15	96.12 18	94.10 13	95.54 27	97.99 13	96.99 8	97.97 3	97.17 10	98.57 26	98.50 33

PLC	90.69 4	94.32 48	92.99 59	95.87 29	97.91 36	96.49 111	95.95 53	94.12 37	94.94 34	94.09 14	85.90 73	90.77 64	95.58 34	94.52 88	93.32 116	97.55 135	95.00 168
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + MP.		97.31 10	97.64 10	96.92 14	97.28 48	98.56 25	98.61 7	95.48 30	96.72 9	94.03 15	96.73 13	98.29 10	97.15 5	97.61 13	96.42 27	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSP-MVS		97.70 7	98.09 6	97.24 7	99.00 12	99.17 5	98.76 5	96.41 11	96.91 6	93.88 16	97.72 6	99.04 8	96.93 12	97.29 18	97.31 7	98.45 39	99.23 4
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
SMA-MVS		97.53 8	97.93 8	97.07 11	99.21 1	99.02 10	98.08 21	96.25 13	96.36 13	93.57 17	96.56 15	99.27 6	96.78 17	97.91 4	97.43 4	98.51 28	98.94 12
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
APD-MVS		97.12 14	97.05 20	97.19 8	99.04 8	98.63 21	98.45 10	96.54 6	94.81 38	93.50 18	96.10 21	97.40 23	96.81 14	97.05 24	96.82 20	98.80 12	98.56 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
AdaColmap		95.02 39	93.71 51	96.54 23	98.51 27	97.76 60	96.69 42	95.94 21	93.72 50	93.50 18	89.01 55	90.53 67	96.49 22	94.51 89	93.76 102	98.07 83	96.69 114

CNLPA		93.69 54	92.50 66	95.06 38	97.11 51	97.36 71	93.88 102	93.30 40	95.64 24	93.44 20	80.32 125	90.73 65	94.99 41	93.58 119	93.33 114	97.67 128	96.57 120

CSCG		95.68 32	95.46 37	95.93 28	98.71 25	99.07 8	97.13 37	93.55 39	95.48 26	93.35 21	90.61 47	93.82 48	95.16 38	94.60 85	95.57 56	97.70 124	99.08 10

HFP-MVS		97.11 15	97.19 18	97.00 13	98.97 14	98.73 14	98.37 13	95.69 23	96.60 10	93.28 22	96.87 9	96.64 30	97.27 2	96.64 36	96.33 37	98.44 40	98.56 26

HPM-MVS++		97.22 12	97.40 13	97.01 12	99.08 3	98.55 26	98.19 16	96.48 7	96.02 20	93.28 22	96.26 19	98.71 9	96.76 18	97.30 17	96.25 40	98.30 56	98.68 19

3Dnovator+	90.56 5	95.06 38	94.56 46	95.65 32	98.11 33	98.15 46	97.19 35	91.59 54	95.11 32	93.23 24	81.99 109	94.71 45	95.43 37	96.48 40	96.88 19	98.35 48	98.63 21

CP-MVS		96.68 21	96.59 28	96.77 18	98.85 22	98.58 24	98.18 17	95.51 28	95.34 27	92.94 25	95.21 30	96.25 32	96.79 16	96.44 43	95.77 52	98.35 48	98.56 26

ACMMPR		96.92 18	96.96 21	96.87 16	98.99 13	98.78 13	98.38 12	95.52 26	96.57 11	92.81 26	96.06 22	95.90 38	97.07 6	96.60 38	96.34 36	98.46 36	98.42 37

MGCNet		96.54 23	97.36 15	95.60 34	98.03 35	99.07 8	98.02 23	92.24 47	95.87 21	92.54 27	96.41 16	96.08 33	94.03 53	97.69 9	97.47 3	98.73 18	98.90 13

NCCC		96.75 20	96.67 26	96.85 17	99.03 10	98.44 35	98.15 18	96.28 12	96.32 14	92.39 28	92.16 37	97.55 21	96.68 20	97.32 15	96.65 24	98.55 27	98.26 42

CPTT-MVS		95.54 33	95.07 39	96.10 26	97.88 38	97.98 51	97.92 27	94.86 34	94.56 41	92.16 29	91.01 43	95.71 39	96.97 11	94.56 86	93.50 109	96.81 178	98.14 48

DeepC-MVS_fast	93.32 1	96.48 24	96.42 29	96.56 21	98.70 26	98.31 39	97.97 25	95.76 22	96.31 15	92.01 30	91.43 42	95.42 42	96.46 23	97.65 12	97.69 1	98.49 33	98.12 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		97.10 16	97.49 11	96.65 19	98.97 14	98.95 11	98.43 11	95.96 19	95.12 30	91.46 31	96.85 10	97.60 19	96.37 25	97.76 6	97.16 11	98.68 19	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator	90.28 7	94.70 44	94.34 49	95.11 37	98.06 34	98.21 43	96.89 40	91.03 59	94.72 39	91.45 32	82.87 96	93.10 51	94.61 43	96.24 49	97.08 14	98.63 24	98.16 46

TSAR-MVS + GP.		95.86 30	96.95 23	94.60 43	94.07 89	98.11 47	96.30 46	91.76 52	95.67 22	91.07 33	96.82 11	97.69 18	95.71 33	95.96 53	95.75 53	98.68 19	98.63 21

CANet		94.85 40	94.92 41	94.78 39	97.25 49	98.52 30	97.20 34	91.81 51	93.25 53	91.06 34	86.29 70	94.46 46	92.99 70	97.02 26	96.68 22	98.34 50	98.20 44

ACMMP_NAP		96.93 17	97.27 17	96.53 24	99.06 5	98.95 11	98.24 15	96.06 17	95.66 23	90.96 35	95.63 26	97.71 17	96.53 21	97.66 11	96.68 22	98.30 56	98.61 24

MCST-MVS		96.83 19	97.06 19	96.57 20	98.88 21	98.47 33	98.02 23	96.16 16	95.58 25	90.96 35	95.78 25	97.84 15	96.46 23	97.00 27	96.17 42	98.94 7	98.55 31

MP-MVS		96.56 22	96.72 25	96.37 25	98.93 19	98.48 32	98.04 22	95.55 25	94.32 42	90.95 37	95.88 24	97.02 27	96.29 26	96.77 31	96.01 50	98.47 34	98.56 26
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PVSNet_BlendedMVS		92.80 59	92.44 68	93.23 56	96.02 63	97.83 57	93.74 108	90.58 61	91.86 65	90.69 38	85.87 75	82.04 112	90.01 120	96.39 44	95.26 61	98.34 50	97.81 64

PVSNet_Blended		92.80 59	92.44 68	93.23 56	96.02 63	97.83 57	93.74 108	90.58 61	91.86 65	90.69 38	85.87 75	82.04 112	90.01 120	96.39 44	95.26 61	98.34 50	97.81 64

PGM-MVS		96.16 26	96.33 30	95.95 27	99.04 8	98.63 21	98.32 14	92.76 44	93.42 51	90.49 40	96.30 18	95.31 43	96.71 19	96.46 41	96.02 49	98.38 47	98.19 45

OMC-MVS		94.49 47	94.36 48	94.64 41	97.17 50	97.73 62	95.49 57	92.25 46	96.18 16	90.34 41	88.51 57	92.88 52	94.90 42	94.92 71	94.17 90	97.69 126	96.15 138

CS-MVS		94.53 46	94.73 44	94.31 44	96.30 61	98.53 28	94.98 65	89.24 96	93.37 52	90.24 42	88.96 56	89.76 72	96.09 29	97.48 14	96.42 27	98.99 2	98.59 25

TPM-MVS					98.33 30	97.85 55	97.06 38			89.97 43	93.26 33	97.16 26	93.12 69			97.79 114	95.95 146
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
DELS-MVS		93.71 53	93.47 53	94.00 46	96.82 55	98.39 37	96.80 41	91.07 58	89.51 108	89.94 44	83.80 87	89.29 73	90.95 108	97.32 15	97.65 2	98.42 42	98.32 40
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
SPE-MVS-test		94.63 45	95.28 38	93.88 51	96.56 58	98.67 15	93.41 119	89.31 93	94.27 43	89.64 45	90.84 45	91.64 58	95.58 34	97.04 25	96.17 42	98.77 15	98.32 40

ACMMP		95.54 33	95.49 36	95.61 33	98.27 32	98.53 28	97.16 36	94.86 34	94.88 36	89.34 46	95.36 29	91.74 56	95.50 36	95.51 60	94.16 91	98.50 31	98.22 43
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
DeepPCF-MVS	92.65 2	95.50 35	96.96 21	93.79 52	96.44 59	98.21 43	93.51 116	94.08 38	96.94 5	89.29 47	93.08 34	96.77 29	93.82 58	97.68 10	97.40 5	95.59 201	98.65 20

EPNet		93.92 51	94.40 47	93.36 55	97.89 37	96.55 109	96.08 49	92.14 48	91.65 68	89.16 48	94.07 32	90.17 71	87.78 149	95.24 65	94.97 68	97.09 154	98.15 47
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CLD-MVS		92.50 65	91.96 76	93.13 60	93.93 95	96.24 117	95.69 54	88.77 104	92.92 54	89.01 49	88.19 60	81.74 115	93.13 68	93.63 118	93.08 124	98.23 66	97.91 61
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DPM-MVS		95.07 37	94.84 42	95.34 36	97.44 45	97.49 69	97.76 29	95.52 26	94.88 36	88.92 50	87.25 63	96.44 31	94.41 45	95.78 56	96.11 46	97.99 102	95.95 146

DeepC-MVS	92.10 3	95.22 36	94.77 43	95.75 31	97.77 40	98.54 27	97.63 31	95.96 19	95.07 33	88.85 51	85.35 77	91.85 55	95.82 31	96.88 29	97.10 13	98.44 40	98.63 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_111021_LR		94.84 41	95.57 34	94.00 46	97.11 51	97.72 64	94.88 68	91.16 57	95.24 29	88.74 52	96.03 23	91.52 60	94.33 49	95.96 53	95.01 67	97.79 114	97.49 75

EC-MVSNet		94.19 49	95.05 40	93.18 59	93.56 105	97.65 65	95.34 61	86.37 140	92.05 62	88.71 53	89.91 50	93.32 49	96.14 28	97.29 18	96.42 27	98.98 3	98.70 17

MVSTER		91.73 78	91.61 81	91.86 93	93.18 117	94.56 135	94.37 74	87.90 120	90.16 92	88.69 54	89.23 53	81.28 119	88.92 142	95.75 57	93.95 98	98.12 76	96.37 129

IB-MVS	85.10 14	87.98 140	87.97 141	87.99 145	94.55 81	96.86 103	84.52 229	88.21 115	86.48 149	88.54 55	74.41 171	77.74 155	74.10 236	89.65 194	92.85 130	98.06 86	97.80 66
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
test2506		90.93 99	89.20 122	92.95 65	94.97 76	98.30 40	94.53 70	90.25 66	89.91 99	88.39 56	83.23 92	64.17 226	90.69 113	96.75 33	96.10 47	98.87 8	95.97 145

E2		92.03 69	91.47 84	92.69 70	93.29 110	97.27 74	94.14 89	89.63 84	91.02 73	88.25 57	83.68 88	82.18 110	92.84 74	94.51 89	94.62 82	98.00 100	97.00 97

FA-MVS(training)		90.79 105	91.33 85	90.17 121	93.76 101	97.22 83	92.74 128	77.79 226	90.60 80	88.03 58	78.80 137	87.41 75	91.00 107	95.40 63	93.43 112	97.70 124	96.46 125

XVS					95.68 65	98.66 16	94.96 66			88.03 58		96.06 34				98.46 36

X-MVStestdata					95.68 65	98.66 16	94.96 66			88.03 58		96.06 34				98.46 36

X-MVS		96.07 28	96.33 30	95.77 30	98.94 17	98.66 16	97.94 26	95.41 32	95.12 30	88.03 58	93.00 35	96.06 34	95.85 30	96.65 35	96.35 33	98.47 34	98.48 34

PHI-MVS		95.86 30	96.93 24	94.61 42	97.60 44	98.65 20	96.49 43	93.13 42	94.07 45	87.91 62	97.12 8	97.17 25	93.90 57	96.46 41	96.93 18	98.64 23	98.10 52

viewcassd2359sk11		91.81 76	91.13 90	92.61 71	93.28 111	97.26 75	94.16 86	89.64 82	90.27 86	87.79 63	82.51 103	81.72 116	92.78 75	94.43 93	94.69 80	98.01 98	96.99 99

train_agg		96.15 27	96.64 27	95.58 35	98.44 28	98.03 49	98.14 20	95.40 33	93.90 48	87.72 64	96.26 19	98.10 11	95.75 32	96.25 48	95.45 58	98.01 98	98.47 35

ETV-MVS		93.80 52	94.57 45	92.91 67	93.98 91	97.50 68	93.62 112	88.70 105	91.95 63	87.57 65	90.21 49	90.79 63	94.56 44	97.20 21	96.35 33	99.02 1	97.98 54

sasdasda		93.08 56	93.09 56	93.07 63	94.24 83	97.86 53	95.45 59	87.86 124	94.00 46	87.47 66	88.32 58	82.37 106	95.13 39	93.96 109	96.41 30	98.27 60	98.73 15

canonicalmvs		93.08 56	93.09 56	93.07 63	94.24 83	97.86 53	95.45 59	87.86 124	94.00 46	87.47 66	88.32 58	82.37 106	95.13 39	93.96 109	96.41 30	98.27 60	98.73 15

PVSNet_Blended_VisFu		91.92 73	92.39 70	91.36 108	95.45 73	97.85 55	92.25 137	89.54 88	88.53 123	87.47 66	79.82 127	90.53 67	85.47 179	96.31 47	95.16 64	97.99 102	98.56 26

E3new		91.52 83	90.67 98	92.51 73	93.24 112	97.23 80	94.16 86	89.65 80	89.19 111	87.26 69	81.25 116	81.00 121	92.71 77	94.26 96	94.75 75	98.03 89	96.99 99

ACMM	88.76 10	91.70 80	90.43 101	93.19 58	95.56 68	95.14 132	93.35 121	91.48 55	92.26 61	87.12 70	84.02 85	79.34 140	93.99 54	94.07 102	92.68 133	97.62 133	95.50 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E3		91.50 85	90.67 98	92.48 75	93.24 112	97.23 80	94.16 86	89.65 80	89.18 112	87.08 71	81.24 117	81.04 120	92.71 77	94.26 96	94.75 75	98.03 89	96.99 99

dps		85.00 177	83.21 195	87.08 157	90.73 163	92.55 192	89.34 185	75.29 233	84.94 157	87.01 72	79.27 132	67.69 206	87.27 157	84.22 226	83.56 229	92.83 234	90.25 224

PatchMatch-RL		90.30 114	88.93 126	91.89 92	95.41 74	95.68 126	90.94 155	88.67 107	89.80 103	86.95 73	85.90 73	72.51 178	92.46 87	93.56 121	92.18 142	96.93 169	92.89 194

EIA-MVS		92.72 62	92.96 61	92.44 78	93.86 98	97.76 60	93.13 123	88.65 108	89.78 104	86.68 74	86.69 67	87.57 74	93.74 59	96.07 52	95.32 59	98.58 25	97.53 73

viewdifsd2359ckpt09		91.65 81	90.91 94	92.51 73	93.35 109	97.36 71	93.95 97	89.64 82	89.83 102	86.67 75	82.25 106	80.77 125	93.37 65	94.71 80	94.48 84	98.07 83	96.99 99

TSAR-MVS + ACMM		96.19 25	97.39 14	94.78 39	97.70 42	98.41 36	97.72 30	95.49 29	96.47 12	86.66 76	96.35 17	97.85 14	93.99 54	97.19 22	96.37 32	97.12 152	99.13 7

OpenMVS	88.18 11	92.51 64	91.61 81	93.55 54	97.74 41	98.02 50	95.66 55	90.46 63	89.14 113	86.50 77	75.80 159	90.38 70	92.69 79	94.99 68	95.30 60	98.27 60	97.63 68

casdiffmvs_mvg		91.94 72	91.25 87	92.75 69	93.41 107	97.19 85	95.48 58	89.77 72	89.86 101	86.41 78	81.02 119	82.23 109	92.93 71	95.44 62	95.61 55	98.51 28	97.40 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MSDG		90.42 113	88.25 136	92.94 66	96.67 57	94.41 141	93.96 96	92.91 43	89.59 106	86.26 79	76.74 149	80.92 124	90.43 118	92.60 139	92.08 146	97.44 140	91.41 212

E5new		91.10 91	90.03 110	92.35 81	93.15 121	97.13 93	94.28 79	89.76 73	87.71 128	86.24 80	79.61 128	80.18 133	92.62 81	93.77 114	94.80 72	98.02 95	97.01 95

E5		91.10 91	90.03 110	92.35 81	93.15 121	97.13 93	94.28 79	89.76 73	87.71 128	86.24 80	79.61 128	80.18 133	92.62 81	93.77 114	94.80 72	98.02 95	97.01 95

viewdifsd2359ckpt11		89.68 123	88.67 129	90.86 112	92.35 141	95.23 128	91.72 152	88.40 112	88.84 117	86.14 82	80.75 121	78.17 150	90.95 108	90.02 187	91.15 164	95.59 201	96.50 122

viewmsd2359difaftdt		89.67 125	88.66 130	90.85 113	92.35 141	95.23 128	91.72 152	88.40 112	88.80 118	86.12 83	80.75 121	78.20 149	90.94 110	90.02 187	91.15 164	95.59 201	96.50 122

viewmambaseed2359dif		90.70 109	89.81 117	91.73 96	92.66 139	96.10 121	93.97 95	88.69 106	89.92 98	86.12 83	80.79 120	80.73 126	91.92 93	91.13 167	92.81 131	97.06 156	97.20 88

E4		91.04 95	90.00 112	92.25 84	93.15 121	97.14 91	94.09 90	89.62 85	87.54 133	86.08 85	79.38 130	80.24 130	92.53 83	93.89 111	94.82 71	98.04 88	96.99 99

casdiffmvs		91.72 79	91.16 89	92.38 80	93.16 119	97.15 88	93.95 97	89.49 90	91.58 70	86.03 86	80.75 121	80.95 123	93.16 67	95.25 64	95.22 63	98.50 31	97.23 85
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_HR		94.84 41	95.91 32	93.60 53	97.35 46	98.46 34	95.08 64	91.19 56	94.18 44	85.97 87	95.38 28	92.56 53	93.61 61	96.61 37	96.25 40	98.40 44	97.92 59

TAPA-MVS	90.35 6	93.69 54	93.52 52	93.90 49	96.89 54	97.62 66	96.15 47	91.67 53	94.94 34	85.97 87	87.72 62	91.96 54	94.40 46	93.76 116	93.06 126	98.30 56	95.58 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DI_MVS_pp		91.05 94	90.15 106	92.11 86	92.67 138	96.61 106	96.03 50	88.44 110	90.25 87	85.92 89	73.73 172	84.89 90	91.92 93	94.17 100	94.07 95	97.68 127	97.31 82

Anonymous20231211		89.82 121	88.18 137	91.74 95	92.52 140	96.09 122	93.38 120	89.30 94	88.95 115	85.90 90	64.55 228	84.39 91	92.41 89	92.24 147	93.06 126	96.93 169	97.95 56

UGNet		91.52 83	93.41 54	89.32 129	94.13 86	97.15 88	91.83 150	89.01 97	90.62 78	85.86 91	86.83 64	91.73 57	77.40 224	94.68 82	94.43 85	97.71 122	98.40 39
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
E6new		90.91 100	89.94 114	92.04 88	93.14 124	97.16 86	93.76 105	88.98 98	87.44 134	85.85 92	79.15 133	79.96 137	92.48 85	94.04 103	94.75 75	98.03 89	97.06 93

E6		90.91 100	89.94 114	92.04 88	93.14 124	97.16 86	93.76 105	88.98 98	87.44 134	85.85 92	79.15 133	79.96 137	92.48 85	94.04 103	94.75 75	98.03 89	97.06 93

ECVR-MVS		90.77 106	89.27 120	92.52 72	94.97 76	98.30 40	94.53 70	90.25 66	89.91 99	85.80 94	73.64 173	74.31 169	90.69 113	96.75 33	96.10 47	98.87 8	95.91 149

MAR-MVS		92.71 63	92.63 64	92.79 68	97.70 42	97.15 88	93.75 107	87.98 118	90.71 75	85.76 95	86.28 71	86.38 80	94.35 48	94.95 69	95.49 57	97.22 145	97.44 76
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
baseline		91.19 90	91.89 77	90.38 114	92.76 133	95.04 133	93.55 115	84.54 158	92.92 54	85.71 96	86.68 68	86.96 77	89.28 133	92.00 151	92.62 135	96.46 183	96.99 99

QAPM		94.13 50	94.33 50	93.90 49	97.82 39	98.37 38	96.47 44	90.89 60	92.73 58	85.63 97	85.35 77	93.87 47	94.17 50	95.71 58	95.90 51	98.40 44	98.42 37

DCV-MVSNet		91.24 88	91.26 86	91.22 109	92.84 132	93.44 164	93.82 103	86.75 136	91.33 72	85.61 98	84.00 86	85.46 87	91.27 101	92.91 133	93.62 104	97.02 159	98.05 53

viewdifsd2359ckpt07		90.96 98	90.40 102	91.62 99	93.22 115	96.95 99	93.49 117	89.26 95	88.94 116	85.56 99	80.56 124	80.99 122	91.25 102	94.88 75	94.01 96	96.92 171	96.49 124

GBi-Net		90.21 115	90.11 107	90.32 116	88.66 182	93.65 160	94.25 81	85.78 145	90.03 93	85.56 99	77.38 142	86.13 81	89.38 130	93.97 106	94.16 91	98.31 53	95.47 158

test1		90.21 115	90.11 107	90.32 116	88.66 182	93.65 160	94.25 81	85.78 145	90.03 93	85.56 99	77.38 142	86.13 81	89.38 130	93.97 106	94.16 91	98.31 53	95.47 158

FMVSNet3		90.19 117	90.06 109	90.34 115	88.69 181	93.85 152	94.58 69	85.78 145	90.03 93	85.56 99	77.38 142	86.13 81	89.22 136	93.29 130	94.36 87	98.20 69	95.40 162

ACMP	89.13 9	92.03 69	91.70 80	92.41 79	94.92 78	96.44 115	93.95 97	89.96 69	91.81 67	85.48 103	90.97 44	79.12 141	92.42 88	93.28 131	92.55 136	97.76 118	97.74 67
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
0.4-1-1-0.1		85.56 168	83.44 188	88.04 143	83.51 229	92.54 193	92.35 134	82.48 183	82.48 181	85.45 104	76.70 150	73.34 172	89.71 123	81.68 241	84.56 224	94.73 225	92.79 200

tpm cat1		84.13 190	81.99 210	86.63 164	91.74 148	91.50 216	90.68 158	75.69 232	86.12 150	85.44 105	72.39 183	70.72 186	85.16 181	80.89 245	81.56 233	91.07 244	90.71 219

diffmvs		91.37 86	91.09 91	91.70 97	92.71 136	96.47 112	94.03 92	88.78 103	92.74 57	85.43 106	83.63 90	80.37 128	91.76 98	93.39 126	93.78 101	97.50 137	97.23 85
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
0.3-1-1-0.015		85.24 174	82.99 198	87.87 149	83.27 231	92.15 201	92.14 142	82.29 188	81.93 186	85.41 107	76.15 157	73.18 174	89.63 124	81.11 244	84.26 227	94.50 226	92.12 207

usedtu_blend_shiyan5		83.61 198	81.81 213	85.71 172	74.05 245	89.88 229	91.99 147	82.09 192	78.96 207	85.41 107	75.60 161	73.18 174	85.67 173	82.18 235	80.05 242	95.03 218	92.85 197

blend_shiyan4		84.25 188	82.04 208	86.82 160	82.33 233	89.89 228	90.94 155	81.51 206	81.22 191	85.41 107	75.60 161	73.18 174	85.67 173	81.60 242	79.96 246	95.08 214	92.85 197

FE-MVSNET3		83.34 203	81.82 212	85.12 180	74.05 245	89.88 229	88.48 199	82.09 192	78.96 207	85.41 107	75.60 161	73.18 174	85.67 173	82.18 235	80.05 242	95.03 218	92.87 195

casdiffseed414692147		89.97 118	88.31 133	91.90 91	93.03 126	96.77 105	93.66 111	88.85 101	86.52 146	85.39 111	74.87 167	75.76 166	92.53 83	93.35 128	94.26 88	97.97 106	96.67 115

0.4-1-1-0.2		85.17 175	82.95 199	87.75 150	83.20 232	92.00 208	91.99 147	82.20 190	81.62 187	85.34 112	76.38 155	73.33 173	89.43 127	81.21 243	84.14 228	94.36 227	92.00 208

CostFormer		86.78 151	86.05 163	87.62 154	92.15 144	93.20 173	91.55 154	75.83 231	88.11 126	85.29 113	81.76 110	76.22 163	87.80 148	84.45 225	85.21 221	93.12 231	93.42 189

MGCFI-Net		92.75 61	92.98 60	92.48 75	94.18 85	97.77 59	95.28 63	87.77 126	93.88 49	85.28 114	88.19 60	82.17 111	94.14 51	93.86 112	96.32 38	98.20 69	98.69 18

viewdifsd2359ckpt13		91.32 87	90.71 97	92.04 88	93.21 116	97.23 80	93.57 114	89.54 88	89.94 97	85.21 115	81.31 115	80.56 127	92.78 75	94.56 86	94.57 83	97.95 107	96.80 110

RPSCF		89.68 123	89.24 121	90.20 119	92.97 129	92.93 182	92.30 135	87.69 128	90.44 84	85.12 116	91.68 41	85.84 86	90.69 113	87.34 212	86.07 215	92.46 237	90.37 222

PCF-MVS	90.19 8	92.98 58	92.07 74	94.04 45	96.39 60	97.87 52	96.03 50	95.47 31	87.16 137	85.09 117	84.81 81	93.21 50	93.46 64	91.98 152	91.98 149	97.78 116	97.51 74
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
diffmvs_AUTHOR		91.22 89	90.82 96	91.68 98	92.69 137	96.56 108	94.05 91	88.87 100	91.87 64	85.08 118	82.26 105	80.04 136	91.84 95	93.80 113	93.93 99	97.56 134	97.26 83

FMVSNet2		89.61 126	89.14 123	90.16 122	88.66 182	93.65 160	94.25 81	85.44 149	88.57 122	84.96 119	73.53 175	83.82 93	89.38 130	94.23 98	94.68 81	98.31 53	95.47 158

viewmanbaseed2359cas		91.57 82	91.09 91	92.12 85	93.36 108	97.26 75	94.02 93	89.62 85	90.50 82	84.95 120	82.00 108	81.36 117	92.69 79	94.47 92	95.04 66	98.09 81	97.00 97

CHOSEN 280x420		90.77 106	92.14 73	89.17 131	93.86 98	92.81 186	93.16 122	80.22 215	90.21 89	84.67 121	89.89 51	91.38 61	90.57 117	94.94 70	92.11 144	92.52 236	93.65 186

test1111		90.47 112	89.10 124	92.07 87	94.92 78	98.30 40	94.17 85	90.30 65	89.56 107	83.92 122	73.25 180	73.66 170	90.26 119	96.77 31	96.14 45	98.87 8	96.04 142

viewmacassd2359aftdt		90.80 104	89.95 113	91.78 94	93.17 118	97.14 91	93.99 94	89.56 87	87.66 130	83.65 123	78.82 136	80.23 131	92.23 91	93.74 117	95.11 65	98.10 79	96.97 105

EPP-MVSNet		92.13 68	93.06 58	91.05 110	93.66 104	97.30 73	92.18 138	87.90 120	90.24 88	83.63 124	86.14 72	90.52 69	90.76 112	94.82 77	94.38 86	98.18 72	97.98 54

MVS_Test		91.81 76	92.19 72	91.37 107	93.24 112	96.95 99	94.43 72	86.25 141	91.45 71	83.45 125	86.31 69	85.15 88	92.93 71	93.99 105	94.71 79	97.92 108	96.77 112

FC-MVSNet-train		90.55 110	90.19 105	90.97 111	93.78 100	95.16 131	92.11 143	88.85 101	87.64 131	83.38 126	84.36 84	78.41 147	89.53 126	94.69 81	93.15 123	98.15 73	97.92 59

CDPH-MVS		94.80 43	95.50 35	93.98 48	98.34 29	98.06 48	97.41 33	93.23 41	92.81 56	82.98 127	92.51 36	94.82 44	93.53 62	96.08 51	96.30 39	98.42 42	97.94 57

baseline1		90.81 102	90.29 103	91.42 104	93.67 103	95.86 125	93.94 100	89.69 78	89.29 110	82.85 128	82.91 95	80.30 129	89.60 125	95.05 67	94.79 74	98.80 12	93.82 184

FMVSNet1		87.33 145	86.00 166	88.89 132	87.13 208	92.83 185	93.08 125	84.46 159	81.35 190	82.20 129	66.33 214	77.96 152	88.96 139	93.97 106	94.16 91	97.54 136	95.38 163

OPM-MVS		91.08 93	89.34 119	93.11 62	96.18 62	96.13 120	96.39 45	92.39 45	82.97 178	81.74 130	82.55 102	80.20 132	93.97 56	94.62 83	93.23 117	98.00 100	95.73 152
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thisisatest0530		91.04 95	91.74 78	90.21 118	92.93 131	97.00 97	92.06 144	87.63 131	90.74 74	81.51 131	86.81 65	82.48 103	89.23 134	94.81 78	93.03 128	97.90 109	97.33 81

tttt0517		91.01 97	91.71 79	90.19 120	92.98 127	97.07 96	91.96 149	87.63 131	90.61 79	81.42 132	86.76 66	82.26 108	89.23 134	94.86 76	93.03 128	97.90 109	97.36 79

GeoE		89.29 132	88.68 128	89.99 124	92.75 135	96.03 123	93.07 126	83.79 167	86.98 139	81.34 133	74.72 168	78.92 142	91.22 103	93.31 129	93.21 120	97.78 116	97.60 72

thres200		89.49 128	87.72 144	91.55 101	93.95 93	97.25 78	94.34 76	89.74 75	85.66 154	81.18 134	76.12 158	70.19 195	91.80 96	94.92 71	93.51 106	98.27 60	96.40 128

thres100view900		89.36 130	87.61 147	91.39 105	93.90 96	96.86 103	94.35 75	89.66 79	85.87 151	81.15 135	76.46 152	70.38 189	91.17 104	94.09 101	93.43 112	98.13 75	96.16 137

tfpn200view9		89.55 127	87.86 142	91.53 102	93.90 96	97.26 75	94.31 78	89.74 75	85.87 151	81.15 135	76.46 152	70.38 189	91.76 98	94.92 71	93.51 106	98.28 59	96.61 117

thres400		89.40 129	87.58 149	91.53 102	94.06 90	97.21 84	94.19 84	89.83 71	85.69 153	81.08 137	75.50 164	69.76 196	91.80 96	94.79 79	93.51 106	98.20 69	96.60 118

pmmvs4		86.00 162	84.28 181	88.00 144	87.80 193	92.01 207	89.94 176	84.91 153	86.79 142	80.98 138	73.41 178	66.34 214	88.12 147	89.31 197	88.90 207	96.24 188	93.20 192

baseline2		88.97 134	89.50 118	88.36 138	91.14 157	95.30 127	90.13 171	85.17 152	87.24 136	80.80 139	84.46 83	78.44 146	85.60 176	93.54 122	91.87 150	97.31 142	95.66 153

ET-MVSNet_ETH3D		89.93 119	90.84 95	88.87 133	79.60 240	96.19 118	94.43 72	86.56 137	90.63 77	80.75 140	90.71 46	77.78 154	93.73 60	91.36 161	93.45 111	98.15 73	95.77 151

thres600view7		89.28 133	87.47 152	91.39 105	94.12 87	97.25 78	93.94 100	89.74 75	85.62 156	80.63 141	75.24 166	69.33 198	91.66 100	94.92 71	93.23 117	98.27 60	96.72 113

PMMVS		89.88 120	91.19 88	88.35 139	89.73 172	91.97 209	90.62 160	81.92 200	90.57 81	80.58 142	92.16 37	86.85 79	91.17 104	92.31 144	91.35 160	96.11 189	93.11 193

TSAR-MVS + COLMAP		92.39 66	92.31 71	92.47 77	95.35 75	96.46 113	96.13 48	92.04 50	95.33 28	80.11 143	94.95 31	77.35 158	94.05 52	94.49 91	93.08 124	97.15 149	94.53 172

IS_MVSNet		91.87 74	93.35 55	90.14 123	94.09 88	97.73 62	93.09 124	88.12 116	88.71 120	79.98 144	84.49 82	90.63 66	87.49 154	97.07 23	96.96 17	98.07 83	97.88 63

HQP-MVS		92.39 66	92.49 67	92.29 83	95.65 67	95.94 124	95.64 56	92.12 49	92.46 60	79.65 145	91.97 39	82.68 102	92.92 73	93.47 124	92.77 132	97.74 120	98.12 50

CDS-MVSNet		88.34 138	88.71 127	87.90 147	90.70 165	94.54 136	92.38 132	86.02 142	80.37 195	79.42 146	79.30 131	83.43 95	82.04 207	93.39 126	94.01 96	96.86 176	95.93 148
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LS3D		91.97 71	90.98 93	93.12 61	97.03 53	97.09 95	95.33 62	95.59 24	92.47 59	79.26 147	81.60 112	82.77 101	94.39 47	94.28 94	94.23 89	97.14 151	94.45 174

UA-Net		90.81 102	92.58 65	88.74 135	94.87 80	97.44 70	92.61 130	88.22 114	82.35 183	78.93 148	85.20 79	95.61 40	79.56 219	96.52 39	96.57 26	98.23 66	94.37 176

IterMVS-LS		88.60 135	88.45 131	88.78 134	92.02 146	92.44 197	92.00 146	83.57 171	86.52 146	78.90 149	78.61 139	81.34 118	89.12 137	90.68 175	93.18 121	97.10 153	96.35 130
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LGP-MVS_train		91.83 75	92.04 75	91.58 100	95.46 71	96.18 119	95.97 52	89.85 70	90.45 83	77.76 150	91.92 40	80.07 135	92.34 90	94.27 95	93.47 110	98.11 78	97.90 62

Fast-Effi-MVS+		88.56 137	87.99 140	89.22 130	91.56 152	95.21 130	92.29 136	82.69 178	86.82 141	77.73 151	76.24 156	73.39 171	93.36 66	94.22 99	93.64 103	97.65 130	96.43 127

UniMVSNet_ETH3D		84.57 181	81.40 218	88.28 140	89.34 176	94.38 143	90.33 163	86.50 139	74.74 234	77.52 152	59.90 238	62.04 234	88.78 145	88.82 205	92.65 134	97.22 145	97.24 84

CHOSEN 1792x2688		88.57 136	87.82 143	89.44 128	95.46 71	96.89 102	93.74 108	85.87 144	89.63 105	77.42 153	61.38 234	83.31 96	88.80 144	93.44 125	93.16 122	95.37 209	96.95 107

HyFIR lowres test		87.87 141	86.42 158	89.57 126	95.56 68	96.99 98	92.37 133	84.15 162	86.64 143	77.17 154	57.65 240	83.97 92	91.08 106	92.09 150	92.44 137	97.09 154	95.16 165

MDTV_nov1_ep13		86.64 153	87.50 151	85.65 173	90.73 163	93.69 158	89.96 175	78.03 225	89.48 109	76.85 155	84.92 80	82.42 105	86.14 169	86.85 216	86.15 214	92.17 238	88.97 232

Effi-MVS+		89.79 122	89.83 116	89.74 125	92.98 127	96.45 114	93.48 118	84.24 160	87.62 132	76.45 156	81.76 110	77.56 157	93.48 63	94.61 84	93.59 105	97.82 113	97.22 87

MS-PatchMatch		87.63 142	87.61 147	87.65 152	93.95 93	94.09 147	92.60 131	81.52 205	86.64 143	76.41 157	73.46 177	85.94 84	85.01 187	92.23 148	90.00 192	96.43 185	90.93 218

Vis-MVSNet (Re-imp)		90.54 111	92.76 63	87.94 146	93.73 102	96.94 101	92.17 140	87.91 119	88.77 119	76.12 158	83.68 88	90.80 62	79.49 220	96.34 46	96.35 33	98.21 68	96.46 125

COLMAP_ROB	84.39 15	87.61 143	86.03 164	89.46 127	95.54 70	94.48 138	91.77 151	90.14 68	87.16 137	75.50 159	73.41 178	76.86 161	87.33 156	90.05 186	89.76 198	96.48 182	90.46 221
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Vis-MVSNet		89.36 130	91.49 83	86.88 159	92.10 145	97.60 67	92.16 141	85.89 143	84.21 167	75.20 160	82.58 100	87.13 76	77.40 224	95.90 55	95.63 54	98.51 28	97.36 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dmvs_re		87.31 146	86.10 162	88.74 135	89.84 169	94.28 144	92.66 129	89.41 91	82.61 180	74.69 161	74.69 169	69.47 197	87.78 149	92.38 143	93.23 117	98.03 89	96.02 144

UniMVSNet (Re)		86.22 156	85.46 174	87.11 156	88.34 186	94.42 140	89.65 183	87.10 135	84.39 164	74.61 162	70.41 193	68.10 203	85.10 182	91.17 165	91.79 152	97.84 112	97.94 57

EPMVS		85.77 163	86.24 160	85.23 179	92.76 133	93.78 154	89.91 177	73.60 239	90.19 90	74.22 163	82.18 107	78.06 151	87.55 153	85.61 222	85.38 220	93.32 230	88.48 236

Baseline_NR-MVSNet		85.28 172	83.42 190	87.46 155	87.77 195	90.80 224	89.90 179	87.69 128	83.93 172	74.16 164	64.72 226	66.43 213	87.48 155	90.14 181	90.83 167	97.73 121	97.11 91

FMVSNet5		84.47 186	84.72 178	84.18 194	83.30 230	88.43 239	88.09 207	79.42 219	84.25 166	74.14 165	73.15 181	78.74 143	83.65 197	91.19 164	91.19 163	96.46 183	86.07 242

v148		83.61 198	82.10 206	85.37 175	87.34 202	92.94 181	87.48 211	85.72 148	78.92 210	73.87 166	65.71 219	64.69 224	81.78 211	87.82 208	89.35 202	96.01 190	95.26 164

TAMVS		84.94 179	84.95 175	84.93 183	88.82 178	93.18 174	88.44 204	81.28 208	77.16 221	73.76 167	75.43 165	76.57 162	82.04 207	90.59 176	90.79 168	95.22 211	90.94 217

gbinet_0.2-2-1-0.02		81.58 223	80.59 224	82.73 217	73.97 249	89.77 233	88.25 205	82.49 182	77.59 218	73.56 168	67.87 205	71.56 184	83.06 199	82.77 231	80.22 239	95.04 216	94.38 175

blended_shiyan8		81.65 221	80.43 226	83.06 209	74.09 243	89.98 226	88.48 199	81.99 198	79.15 204	73.52 169	67.98 204	70.34 193	85.09 183	82.39 233	80.39 238	95.19 212	92.81 199

UniMVSNet_NR-MVSNet		86.80 150	85.86 169	87.89 148	88.17 188	94.07 148	90.15 169	88.51 109	84.20 168	73.45 170	72.38 184	70.30 194	88.95 140	90.25 180	92.21 141	98.12 76	97.62 70

DU-MVS		86.12 158	84.81 177	87.66 151	87.77 195	93.78 154	90.15 169	87.87 122	84.40 162	73.45 170	70.59 190	64.82 223	88.95 140	90.14 181	92.33 138	97.76 118	97.62 70

wanda-best-256-512		81.56 224	80.31 227	83.02 211	74.05 245	89.88 229	88.48 199	82.09 192	78.96 207	73.38 172	68.19 200	70.37 191	85.08 184	82.18 235	80.05 242	95.03 218	92.52 205

FE-blended-shiyan7		81.56 224	80.31 227	83.02 211	74.05 245	89.88 229	88.48 199	82.09 192	78.97 206	73.38 172	68.19 200	70.35 192	85.08 184	82.18 235	80.05 242	95.03 218	92.52 205

blended_shiyan6		81.63 222	80.44 225	83.02 211	74.06 244	89.96 227	88.46 203	81.98 199	79.01 205	73.38 172	68.03 203	70.41 188	85.03 186	82.38 234	80.40 237	95.18 213	92.87 195

usedtu_dtu_shiyan1		86.08 161	86.20 161	85.93 168	81.88 237	93.87 151	90.68 158	86.54 138	86.84 140	72.93 175	71.70 185	75.39 167	85.90 172	91.74 155	91.33 161	97.66 129	92.56 204

thisisatest0515		85.70 164	87.00 153	84.19 193	88.16 189	93.67 159	84.20 231	84.14 163	83.39 176	72.91 176	76.79 148	74.75 168	78.82 222	92.57 140	91.26 162	96.94 166	96.56 121

SCA		86.25 154	87.52 150	84.77 184	91.59 150	93.90 150	89.11 190	73.25 243	90.38 85	72.84 177	83.26 91	83.79 94	88.49 146	86.07 219	85.56 218	93.33 229	89.67 228

tpmrst		83.72 197	83.45 187	84.03 196	92.21 143	91.66 213	88.74 196	73.58 240	88.14 125	72.67 178	77.37 145	72.11 181	86.34 165	82.94 230	82.05 232	90.63 247	89.86 227

PatchmatchNet		85.70 164	86.65 155	84.60 187	91.79 147	93.40 165	89.27 186	73.62 238	90.19 90	72.63 179	82.74 99	81.93 114	87.64 151	84.99 223	84.29 226	92.64 235	89.00 231
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pm-mvs1		84.55 182	83.46 186	85.82 169	88.16 189	93.39 166	89.05 192	85.36 151	74.03 235	72.43 180	65.08 222	71.11 185	82.30 206	93.48 123	91.70 154	97.64 131	95.43 161

ACMH+	85.75 12	87.19 148	86.02 165	88.56 137	93.42 106	94.41 141	89.91 177	87.66 130	83.45 175	72.25 181	76.42 154	71.99 182	90.78 111	89.86 189	90.94 166	97.32 141	95.11 167

NR-MVSNet		85.46 170	84.54 179	86.52 165	88.33 187	93.78 154	90.45 162	87.87 122	84.40 162	71.61 182	70.59 190	62.09 233	82.79 203	91.75 154	91.75 153	98.10 79	97.44 76

Effi-MVS+-dtu		87.51 144	88.13 138	86.77 162	91.10 158	94.90 134	90.91 157	82.67 179	83.47 174	71.55 183	81.11 118	77.04 159	89.41 129	92.65 138	91.68 156	95.00 223	96.09 140

v8		84.45 187	83.30 194	85.80 170	87.53 200	92.95 180	90.31 165	82.46 185	80.46 194	71.43 184	66.99 209	67.16 208	86.14 169	89.26 199	90.22 184	96.94 166	96.06 141

pmmvs-eth3d		79.78 231	77.58 236	82.34 222	81.57 238	87.46 243	82.92 233	81.28 208	75.33 233	71.34 185	61.88 232	52.41 252	81.59 213	87.56 210	86.90 213	95.36 210	91.48 211

TDRefinement		84.97 178	83.39 191	86.81 161	92.97 129	94.12 146	92.18 138	87.77 126	82.78 179	71.31 186	68.43 199	68.07 204	81.10 215	89.70 193	89.03 205	95.55 205	91.62 210

V42		84.48 185	83.36 193	85.79 171	87.14 207	93.28 170	90.03 172	83.98 165	80.30 196	71.20 187	66.90 211	67.17 207	85.55 177	89.35 195	90.27 182	96.82 177	96.27 135

CR-MVSNet		85.48 169	86.29 159	84.53 189	91.08 160	92.10 202	89.18 188	73.30 241	84.75 158	71.08 188	73.12 182	77.91 153	86.27 167	91.48 158	90.75 171	96.27 187	93.94 181

Patchmtry						92.39 198	89.18 188	73.30 241		71.08 188

PatchT		83.86 194	85.51 173	81.94 224	88.41 185	91.56 215	78.79 244	71.57 246	84.08 170	71.08 188	70.62 189	76.13 164	86.27 167	91.48 158	90.75 171	95.52 207	93.94 181

USDC		86.73 152	85.96 167	87.63 153	91.64 149	93.97 149	92.76 127	84.58 157	88.19 124	70.67 191	80.10 126	67.86 205	89.43 127	91.81 153	89.77 197	96.69 180	90.05 226

tfpnnormal		83.80 196	81.26 220	86.77 162	89.60 173	93.26 172	89.72 182	87.60 133	72.78 236	70.44 192	60.53 237	61.15 238	85.55 177	92.72 135	91.44 158	97.71 122	96.92 108

pmmvs6		80.90 226	78.77 232	83.38 204	85.84 220	91.61 214	86.01 224	82.54 181	64.17 250	70.43 193	54.14 247	67.06 209	80.73 216	90.50 178	89.17 204	94.74 224	94.75 170

ACMH	85.51 13	87.31 146	86.59 156	88.14 142	93.96 92	94.51 137	89.00 193	87.99 117	81.58 188	70.15 194	78.41 140	71.78 183	90.60 116	91.30 162	91.99 148	97.17 148	96.58 119
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TranMVSNet+NR-MVSNet		85.57 167	84.41 180	86.92 158	87.67 198	93.34 167	90.31 165	88.43 111	83.07 177	70.11 195	69.99 196	65.28 218	86.96 159	89.73 191	92.27 139	98.06 86	97.17 90

TinyColmap		84.04 192	82.01 209	86.42 166	90.87 161	91.84 210	88.89 195	84.07 164	82.11 185	69.89 196	71.08 188	60.81 239	89.04 138	90.52 177	89.19 203	95.76 193	88.50 235

v2v482		84.51 183	83.05 197	86.20 167	87.25 204	93.28 170	90.22 167	85.40 150	79.94 201	69.78 197	67.74 206	65.15 220	87.57 152	89.12 201	90.55 177	96.97 162	95.60 155

MIMVSNet		82.97 209	84.00 183	81.77 226	82.23 235	92.25 200	87.40 214	72.73 244	81.48 189	69.55 198	68.79 198	72.42 179	81.82 210	92.23 148	92.25 140	96.89 173	88.61 234

ADS-MVSNet		84.08 191	84.95 175	83.05 210	91.53 154	91.75 212	88.16 206	70.70 248	89.96 96	69.51 199	78.83 135	76.97 160	86.29 166	84.08 227	84.60 223	92.13 240	88.48 236

test-LLR		86.88 149	88.28 134	85.24 178	91.22 155	92.07 204	87.41 212	83.62 169	84.58 160	69.33 200	83.00 93	82.79 99	84.24 191	92.26 145	89.81 195	95.64 199	93.44 187

TESTMET0.1,1		86.11 159	88.28 134	83.59 200	87.80 193	92.07 204	87.41 212	77.12 228	84.58 160	69.33 200	83.00 93	82.79 99	84.24 191	92.26 145	89.81 195	95.64 199	93.44 187

v10		84.18 189	83.17 196	85.37 175	87.34 202	92.68 188	90.32 164	81.33 207	79.93 202	69.23 202	66.33 214	65.74 216	87.03 158	90.84 170	90.38 179	96.97 162	96.29 134

RPMNet		84.82 180	85.90 168	83.56 201	91.10 158	92.10 202	88.73 197	71.11 247	84.75 158	68.79 203	73.56 174	77.62 156	85.33 180	90.08 185	89.43 201	96.32 186	93.77 185

CANet_DTU		90.74 108	92.93 62	88.19 141	94.36 82	96.61 106	94.34 76	84.66 155	90.66 76	68.75 204	90.41 48	86.89 78	89.78 122	95.46 61	94.87 69	97.25 144	95.62 154

CMPMVS	61.19 17	79.86 230	77.46 238	82.66 219	91.54 153	91.82 211	83.25 232	81.57 204	70.51 244	68.64 205	59.89 239	66.77 211	79.63 218	84.00 228	84.30 225	91.34 242	84.89 245
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test-mter		86.09 160	88.38 132	83.43 203	87.89 192	92.61 190	86.89 217	77.11 229	84.30 165	68.62 206	82.57 101	82.45 104	84.34 190	92.40 142	90.11 189	95.74 194	94.21 179

tmp_tt				50.24 252	68.55 254	46.86 261	48.90 261	18.28 260	86.51 148	68.32 207	70.19 194	65.33 217	26.69 258	74.37 251	66.80 253	70.72 260

TransMVSNet (Re)		82.67 212	80.93 223	84.69 186	88.71 180	91.50 216	87.90 208	87.15 134	71.54 241	68.24 208	63.69 230	64.67 225	78.51 223	91.65 157	90.73 173	97.64 131	92.73 203

WR-MVS_H		82.86 211	82.66 202	83.10 207	87.44 201	93.33 168	85.71 227	83.20 176	77.36 220	68.20 209	66.37 213	65.23 219	76.05 230	89.35 195	90.13 185	97.99 102	96.89 109

v1144		84.03 193	82.88 200	85.37 175	87.17 206	93.15 177	90.18 168	83.31 174	78.83 211	67.85 210	65.99 216	64.99 221	86.79 161	90.75 172	90.33 181	96.90 172	96.15 138

test0.0.03 1		85.58 166	87.69 146	83.11 206	91.22 155	92.54 193	85.60 228	83.62 169	85.66 154	67.84 211	82.79 98	79.70 139	73.51 238	91.15 166	90.79 168	96.88 174	91.23 215

CP-MVSNet		83.11 208	82.15 205	84.23 192	87.20 205	92.70 187	86.42 221	83.53 172	77.83 217	67.67 212	66.89 212	60.53 241	82.47 204	89.23 200	90.65 175	98.08 82	97.20 88

MVS-HIRNet		78.16 233	77.57 237	78.83 232	85.83 221	87.76 241	76.67 246	70.22 249	75.82 231	67.39 213	55.61 242	70.52 187	81.96 209	86.67 217	85.06 222	90.93 245	81.58 248

v144192		83.48 201	82.23 204	84.94 182	86.65 214	92.84 183	89.63 184	82.48 183	77.87 216	67.36 214	65.33 221	63.50 227	86.51 163	89.72 192	89.99 193	97.03 158	96.35 130

pmmvs5		83.37 202	82.68 201	84.18 194	87.13 208	93.18 174	86.74 218	82.08 196	76.48 225	67.28 215	71.26 187	62.70 230	84.71 188	90.77 171	90.12 188	97.15 149	94.24 177

PM-MVS		80.29 228	79.30 231	81.45 227	81.91 236	88.23 240	82.61 234	79.01 220	79.99 200	67.15 216	69.07 197	51.39 254	82.92 202	87.55 211	85.59 217	95.08 214	93.28 190

tpm		83.16 205	83.64 184	82.60 220	90.75 162	91.05 219	88.49 198	73.99 236	82.36 182	67.08 217	78.10 141	68.79 199	84.17 193	85.95 221	85.96 216	91.09 243	93.23 191

v1192		83.56 200	82.35 203	84.98 181	86.84 213	92.84 183	90.01 174	82.70 177	78.54 212	66.48 218	64.88 224	62.91 228	86.91 160	90.72 173	90.25 183	96.94 166	96.32 132

WR-MVS		83.14 206	83.38 192	82.87 215	87.55 199	93.29 169	86.36 222	84.21 161	80.05 199	66.41 219	66.91 210	66.92 210	75.66 232	88.96 203	90.56 176	97.05 157	96.96 106

IterMVS-SCA-FT		85.44 171	86.71 154	83.97 197	90.59 166	90.84 222	89.73 181	78.34 222	84.07 171	66.40 220	77.27 147	78.66 144	83.06 199	91.20 163	90.10 190	95.72 196	94.78 169

IterMVS		85.25 173	86.49 157	83.80 198	90.42 167	90.77 225	90.02 173	78.04 224	84.10 169	66.27 221	77.28 146	78.41 147	83.01 201	90.88 169	89.72 199	95.04 216	94.24 177
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v7n		82.25 216	81.54 216	83.07 208	85.55 223	92.58 191	86.68 220	81.10 211	76.54 224	65.97 222	62.91 231	60.56 240	82.36 205	91.07 168	90.35 180	96.77 179	96.80 110

v1921920		83.30 204	82.09 207	84.70 185	86.59 217	92.67 189	89.82 180	82.23 189	78.32 213	65.76 223	64.64 227	62.35 231	86.78 162	90.34 179	90.02 191	97.02 159	96.31 133

PS-CasMVS		82.53 213	81.54 216	83.68 199	87.08 210	92.54 193	86.20 223	83.46 173	76.46 226	65.73 224	65.71 219	59.41 246	81.61 212	89.06 202	90.55 177	98.03 89	97.07 92

EPNet_dtu		88.32 139	90.61 100	85.64 174	96.79 56	92.27 199	92.03 145	90.31 64	89.05 114	65.44 225	89.43 52	85.90 85	74.22 234	92.76 134	92.09 145	95.02 222	92.76 201
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		86.25 154	87.70 145	84.56 188	90.37 168	93.70 157	90.54 161	78.14 223	83.50 173	65.37 226	81.59 113	75.83 165	86.09 171	91.70 156	91.70 154	96.88 174	95.84 150

v1240		82.88 210	81.66 214	84.29 191	86.46 218	92.52 196	89.06 191	81.82 202	77.16 221	65.09 227	64.17 229	61.50 236	86.36 164	90.12 183	90.13 185	96.95 165	96.04 142

PEN-MVS		82.49 214	81.58 215	83.56 201	86.93 211	92.05 206	86.71 219	83.84 166	76.94 223	64.68 228	67.24 207	60.11 242	81.17 214	87.78 209	90.70 174	98.02 95	96.21 136

SixPastTwentyTwo		83.12 207	83.44 188	82.74 216	87.71 197	93.11 178	82.30 236	82.33 186	79.24 203	64.33 229	78.77 138	62.75 229	84.11 195	88.11 207	87.89 209	95.70 197	94.21 179

MDTV_nov1_ep13_2view		80.43 227	80.94 222	79.84 229	84.82 226	90.87 221	84.23 230	73.80 237	80.28 197	64.33 229	70.05 195	68.77 200	79.67 217	84.83 224	83.50 230	92.17 238	88.25 238

EG-PatchMatch MVS		81.70 220	81.31 219	82.15 223	88.75 179	93.81 153	87.14 215	78.89 221	71.57 239	64.12 231	61.20 236	68.46 201	76.73 228	91.48 158	90.77 170	97.28 143	91.90 209

anonymousdsp		84.51 183	85.85 170	82.95 214	86.30 219	93.51 163	85.77 226	80.38 214	78.25 215	63.42 232	73.51 176	72.20 180	84.64 189	93.21 132	92.16 143	97.19 147	98.14 48

DTE-MVSNet		81.76 219	81.04 221	82.60 220	86.63 215	91.48 218	85.97 225	83.70 168	76.45 227	62.44 233	67.16 208	59.98 243	78.98 221	87.15 213	89.93 194	97.88 111	95.12 166

GA-MVS		85.08 176	85.65 171	84.42 190	89.77 171	94.25 145	89.26 187	84.62 156	81.19 192	62.25 234	75.72 160	68.44 202	84.14 194	93.57 120	91.68 156	96.49 181	94.71 171

FC-MVSNet-test		86.15 157	89.10 124	82.71 218	89.83 170	93.18 174	87.88 209	84.69 154	86.54 145	62.18 235	82.39 104	83.31 96	74.18 235	92.52 141	91.86 151	97.50 137	93.88 183

FE-MVSNET2		76.99 237	76.02 240	78.12 234	71.26 253	89.46 236	81.92 237	80.87 212	71.48 242	61.96 236	47.82 251	54.83 250	75.73 231	89.29 198	88.91 206	97.00 161	90.36 223

usedtu_dtu_shiyan2		69.49 246	68.33 247	70.84 246	57.31 261	83.43 250	77.39 245	72.63 245	54.43 255	61.92 237	40.25 255	52.40 253	65.07 246	79.46 247	79.03 248	90.69 246	89.29 229

pmnet_mix02		80.14 229	80.21 230	80.06 228	86.61 216	89.66 235	80.40 241	82.20 190	82.29 184	61.35 238	71.52 186	66.67 212	76.75 227	82.55 232	80.18 240	93.05 232	88.62 233

N_pmnet		77.55 236	76.68 239	78.56 233	85.43 224	87.30 244	78.84 243	81.88 201	78.30 214	60.61 239	61.46 233	62.15 232	74.03 237	82.04 239	80.69 236	90.59 248	84.81 246

RE-MVS-def										60.19 240

CVMVSNet		83.83 195	85.53 172	81.85 225	89.60 173	90.92 220	87.81 210	83.21 175	80.11 198	60.16 241	76.47 151	78.57 145	76.79 226	89.76 190	90.13 185	93.51 228	92.75 202

ambc			67.96 248		73.69 250	79.79 253	73.82 251		71.61 238	59.80 242	46.00 252	20.79 263	66.15 245	86.92 215	80.11 241	89.13 252	90.50 220

testgi		81.94 217	84.09 182	79.43 231	89.53 175	90.83 223	82.49 235	81.75 203	80.59 193	59.46 243	82.82 97	65.75 215	67.97 240	90.10 184	89.52 200	95.39 208	89.03 230

PMVS	56.77 18	61.27 248	58.64 252	64.35 247	75.66 241	54.60 259	53.62 259	74.23 235	53.69 256	58.37 244	44.27 254	49.38 256	44.16 255	69.51 254	65.35 254	80.07 255	73.66 253
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		78.09 234	78.11 235	78.07 235	85.19 225	89.17 237	80.99 239	81.24 210	75.46 232	58.25 245	54.78 246	59.90 244	66.73 244	88.94 204	88.26 208	96.01 190	90.25 224

FPMVS		69.87 245	67.10 249	73.10 241	84.09 227	78.35 254	79.40 242	76.41 230	71.92 237	57.71 246	54.06 248	50.04 255	56.72 249	71.19 252	68.70 252	84.25 253	75.43 252

MIMVSNet1		73.19 241	73.70 242	72.60 242	65.42 256	86.69 246	75.56 249	79.65 217	67.87 247	55.30 247	45.24 253	56.41 248	63.79 247	86.98 214	87.66 210	95.85 192	85.04 244

MDA-MVSNet-bldmvs		73.81 239	72.56 244	75.28 238	72.52 252	88.87 238	74.95 250	82.67 179	71.57 239	55.02 248	65.96 217	42.84 261	76.11 229	70.61 253	81.47 234	90.38 249	86.59 240

new-patchmatchnet		72.32 242	71.09 245	73.74 240	81.17 239	84.86 249	72.21 253	77.48 227	68.32 246	54.89 249	55.10 244	49.31 257	63.68 248	79.30 248	76.46 249	93.03 233	84.32 247

EU-MVSNet		78.43 232	80.25 229	76.30 237	83.81 228	87.27 245	80.99 239	79.52 218	76.01 228	54.12 250	70.44 192	64.87 222	67.40 242	86.23 218	85.54 219	91.95 241	91.41 212

LTVRE_ROB	81.71 16	82.44 215	81.84 211	83.13 205	89.01 177	92.99 179	88.90 194	82.32 187	66.26 249	54.02 251	74.68 170	59.62 245	88.87 143	90.71 174	92.02 147	95.68 198	96.62 116
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
pmmvs3		71.13 244	71.06 246	71.21 244	73.54 251	80.19 252	71.69 254	64.86 253	62.04 254	52.10 252	54.92 245	48.00 259	75.03 233	83.75 229	83.24 231	90.04 250	85.27 243

test_method		58.10 251	64.61 251	50.51 251	28.26 263	41.71 262	61.28 257	32.07 259	75.92 230	52.04 253	47.94 250	61.83 235	51.80 252	79.83 246	63.95 256	77.60 257	81.05 249

gm-plane-assit		77.65 235	78.50 233	76.66 236	87.96 191	85.43 247	64.70 256	74.50 234	64.15 251	51.26 254	61.32 235	58.17 247	84.11 195	95.16 66	93.83 100	97.45 139	91.41 212

test20.03		76.41 238	78.49 234	73.98 239	85.64 222	87.50 242	75.89 248	80.71 213	70.84 243	51.07 255	68.06 202	61.40 237	54.99 251	88.28 206	87.20 212	95.58 204	86.15 241

FE-MVSNET		73.24 240	74.06 241	72.28 243	64.92 257	85.32 248	76.06 247	79.75 216	67.71 248	50.14 256	49.61 249	54.40 251	67.26 243	85.97 220	87.33 211	95.53 206	88.10 239

new_pmnet		72.29 243	73.25 243	71.16 245	75.35 242	81.38 251	73.72 252	69.27 250	75.97 229	49.84 257	56.27 241	56.12 249	69.08 239	81.73 240	80.86 235	89.72 251	80.44 250

DeepMVS_CX						71.82 256	68.37 255	48.05 258	77.38 219	46.88 258	65.77 218	47.03 260	67.48 241	64.27 256		76.89 258	76.72 251

Gipuma		58.52 250	56.17 253	61.27 248	67.14 255	58.06 258	52.16 260	68.40 252	69.00 245	45.02 259	22.79 257	20.57 264	55.11 250	76.27 249	79.33 247	79.80 256	67.16 255
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
gg-mvs-nofinetune		81.83 218	83.58 185	79.80 230	91.57 151	96.54 110	93.79 104	68.80 251	62.71 253	43.01 260	55.28 243	85.06 89	83.65 197	96.13 50	94.86 70	97.98 105	94.46 173

MVE	39.81 19	39.52 254	41.58 255	37.11 255	33.93 262	49.06 260	26.45 265	54.22 257	29.46 260	24.15 261	20.77 259	10.60 267	34.42 256	51.12 257	65.27 255	49.49 263	64.81 257
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		53.68 252	55.72 254	51.30 250	58.84 258	67.02 257	54.23 258	60.97 256	47.50 257	19.42 262	34.81 256	31.97 262	30.88 257	65.84 255	69.99 251	83.47 254	72.92 254

E-PMN		40.00 253	35.74 256	44.98 253	57.69 260	39.15 264	28.05 263	62.70 254	35.52 259	17.78 263	20.90 258	14.36 266	44.47 254	35.89 258	47.86 257	59.15 261	56.47 258

EMVS		39.04 255	34.32 257	44.54 254	58.25 259	39.35 263	27.61 264	62.55 255	35.99 258	16.40 264	20.04 260	14.77 265	44.80 253	33.12 259	44.10 258	57.61 262	52.89 259

WB-MVS		60.76 249	66.86 250	53.64 249	82.24 234	72.70 255	48.70 262	82.04 197	63.91 252	12.91 265	64.77 225	49.00 258	22.74 259	75.95 250	75.36 250	73.22 259	66.33 256

GG-mvs-BLEND		62.84 247	90.21 104	30.91 256	0.57 265	94.45 139	86.99 216	0.34 263	88.71 120	0.98 266	81.55 114	91.58 59	0.86 262	92.66 137	91.43 159	95.73 195	91.11 216

testmvs		4.35 256	6.54 258	1.79 257	0.60 264	1.82 265	3.06 267	0.95 261	7.22 261	0.88 267	12.38 261	1.25 268	3.87 261	6.09 260	5.58 259	1.40 264	11.42 261

test123		3.48 257	5.31 259	1.34 258	0.20 266	1.52 266	2.17 268	0.58 262	6.13 262	0.31 268	9.85 262	0.31 269	3.90 260	2.65 261	5.28 260	0.87 265	11.46 260

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

9.14												97.28 24

SR-MVS					98.93 19			96.00 18				97.75 16

Anonymous202405211			88.00 139		93.16 119	96.38 116	93.58 113	89.34 92	87.92 127		65.04 223	83.03 98	92.07 92	92.67 136	93.33 114	96.96 164	97.63 68

our_test_3					86.93 211	89.77 233	81.61 238

Patchmatch-RL test							18.47 266

mPP-MVS					98.76 24							95.49 41

NP-MVS									91.63 69

High-resolution multi-view benchmark