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		98.02 1	98.12 4	97.91 1	98.97 9	99.32 13	98.29 13	95.80 1	98.28 4	98.12 2	98.11 1	99.40 4	97.13 6	96.54 23	95.50 26	99.17 7	99.68 16

SED-MVS		97.92 2	98.27 2	97.52 2	98.88 13	99.60 1	98.80 5	95.08 9	98.57 2	95.63 4	96.98 10	99.73 1	97.67 2	97.26 11	95.86 22	99.04 16	99.89 5

MSP-MVS		97.74 3	98.32 1	97.06 8	98.66 16	99.35 8	98.66 8	94.75 15	98.22 6	93.60 8	97.99 2	98.58 9	97.41 5	98.24 2	95.95 18	99.27 4	99.91 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		97.71 4	98.01 7	97.37 3	98.98 6	99.58 3	98.79 6	95.06 10	98.24 5	94.66 5	96.35 16	99.20 5	97.63 3	97.20 13	95.68 23	99.08 14	99.84 7

DPE-MVS		97.69 5	98.16 3	97.14 6	99.01 5	99.52 5	99.12 3	95.38 4	98.00 9	93.31 11	97.71 3	99.61 3	96.94 7	96.99 17	95.45 28	99.09 13	99.81 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		97.61 6	97.87 8	97.30 4	98.94 12	99.60 1	98.21 15	95.11 6	98.39 3	95.83 3	94.40 31	99.70 2	96.79 8	97.16 14	95.95 18	98.92 28	99.90 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
CNVR-MVS		97.60 7	98.08 5	97.03 9	99.14 2	99.55 4	98.67 7	95.32 5	97.91 10	92.55 13	97.11 7	97.23 15	97.49 4	98.16 3	97.05 6	99.04 16	99.55 21

APDe-MVS		97.31 8	97.51 13	97.08 7	98.95 11	99.29 15	98.58 10	95.11 6	97.69 15	94.16 6	96.91 11	96.81 19	96.57 11	96.71 20	95.39 30	99.08 14	99.79 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.17 9	97.18 17	97.17 5	99.11 3	99.20 17	99.05 4	95.55 3	97.39 18	93.56 9	97.48 5	96.71 21	96.75 9	95.73 33	94.40 47	98.98 22	99.33 26

NCCC		97.01 10	97.74 9	96.16 12	99.02 4	99.35 8	98.63 9	95.04 11	97.84 12	88.95 26	96.83 13	97.02 18	96.39 16	97.44 7	96.51 9	98.90 30	99.16 42

SMA-MVS		96.96 11	97.65 12	96.15 13	98.98 6	99.31 14	97.91 20	94.68 17	97.52 16	90.59 20	94.54 30	99.20 5	96.54 13	97.29 9	96.48 10	98.22 72	99.19 38
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
MCST-MVS		96.93 12	98.07 6	95.61 19	98.98 6	99.44 6	98.04 16	95.04 11	98.10 7	86.55 33	97.65 4	97.56 12	95.60 24	97.67 6	96.45 11	99.43 1	99.61 20

HPM-MVS++		96.91 13	97.70 10	96.00 14	98.97 9	99.16 19	97.82 22	94.81 14	98.04 8	89.61 23	96.56 15	98.60 8	96.39 16	97.09 15	95.22 32	98.39 63	99.22 34

SD-MVS		96.87 14	97.69 11	95.92 15	96.38 49	99.25 16	97.76 23	94.75 15	97.72 13	92.46 15	95.94 17	99.09 7	96.48 15	96.01 30	96.08 16	97.68 112	99.73 13
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
APD-MVS		96.79 15	96.99 20	96.56 10	98.76 15	98.87 28	98.42 11	94.93 13	97.70 14	91.83 16	95.52 20	95.94 27	96.63 10	95.94 31	95.47 27	98.80 36	99.47 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 16	97.08 18	95.82 17	96.12 53	98.97 25	98.00 17	94.13 22	97.89 11	91.49 17	95.11 26	97.52 13	96.26 20	96.27 28	94.07 57	98.91 29	99.74 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		96.20 17	97.22 16	95.01 23	98.40 23	99.11 20	97.93 19	93.62 25	96.28 31	87.45 30	97.05 9	96.00 26	94.23 32	96.83 19	95.97 17	98.40 60	99.27 31
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 18	96.41 25	95.72 18	98.58 18	98.84 29	97.95 18	93.08 29	96.96 24	90.24 21	96.60 14	94.40 33	96.52 14	95.13 43	94.33 48	97.93 102	98.59 68

ACMMP_NAP		95.81 19	96.50 24	95.01 23	98.79 14	99.17 18	97.52 28	94.20 21	96.19 32	85.71 38	93.80 34	96.20 25	95.89 21	96.62 22	94.98 38	97.93 102	98.52 72

MGCNet		95.79 20	97.46 14	93.85 29	96.81 43	99.35 8	97.21 31	87.28 50	97.10 19	88.65 29	95.17 25	96.41 24	94.15 36	97.29 9	97.19 5	99.01 20	99.73 13

train_agg		95.72 21	97.37 15	93.80 30	97.82 32	98.92 26	97.84 21	93.50 26	96.86 26	81.35 58	97.10 8	97.71 10	94.19 33	96.02 29	95.37 31	98.07 88	99.64 18

ACMMPR		95.59 22	95.89 27	95.25 21	98.41 22	98.74 30	97.69 26	92.73 33	96.88 25	88.95 26	95.33 22	92.91 40	95.79 22	94.73 53	94.33 48	97.92 104	98.32 82

DeepC-MVS_fast	91.53 1	95.57 23	95.67 30	95.45 20	98.57 19	99.00 24	97.76 23	94.41 19	97.06 21	86.84 32	86.39 47	92.27 45	96.38 18	97.89 5	98.06 3	98.73 41	99.01 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		95.49 24	94.84 35	96.25 11	98.64 17	98.63 33	98.35 12	92.37 35	95.04 50	92.62 12	87.12 46	93.79 34	96.55 12	93.53 76	96.78 7	98.98 22	98.99 52

CP-MVS		95.43 25	95.67 30	95.14 22	98.24 28	98.60 34	97.45 29	92.80 31	95.98 35	89.21 25	95.22 23	93.60 35	95.43 25	94.37 60	93.22 86	97.68 112	98.72 59

DPM-MVS		95.36 26	95.84 28	94.82 25	96.70 45	98.49 44	99.27 1	95.09 8	96.71 27	83.87 46	86.34 49	96.44 23	95.06 27	98.35 1	98.82 1	98.89 31	95.69 156

MP-MVS		95.24 27	95.96 26	94.40 27	98.32 25	98.38 49	97.12 32	92.87 30	95.17 48	85.50 39	95.68 18	94.91 31	94.58 29	95.11 44	93.76 65	98.05 91	98.68 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 28	97.02 19	92.61 40	97.19 38	98.71 32	97.74 25	93.21 28	96.97 23	79.27 89	94.09 32	97.14 16	90.84 69	96.64 21	95.94 20	97.42 131	99.67 17

X-MVS		94.70 29	95.71 29	93.52 34	98.38 24	98.56 36	96.99 33	92.62 34	95.58 39	81.00 67	94.57 29	93.49 36	94.16 35	94.82 49	94.29 51	97.99 98	98.68 61

PGM-MVS		94.64 30	95.49 32	93.66 32	98.55 20	98.51 42	97.63 27	87.77 48	94.45 54	84.92 42	97.23 6	91.90 47	95.22 26	94.56 56	93.80 64	97.87 108	97.97 100

TSAR-MVS + GP.		94.59 31	96.60 23	92.25 41	90.25 95	98.17 56	96.22 38	86.53 55	97.49 17	87.26 31	95.21 24	97.06 17	94.07 38	94.34 62	94.20 53	99.18 5	99.71 15

PHI-MVS		94.49 32	96.72 22	91.88 43	97.06 39	98.88 27	94.99 49	89.13 43	96.15 33	79.70 76	96.91 11	95.78 28	91.87 59	94.65 54	95.68 23	98.53 51	98.98 54

AdaColmap		94.28 33	92.94 47	95.84 16	98.32 25	98.33 51	96.06 40	94.62 18	96.29 30	91.22 18	89.89 40	85.50 75	96.38 18	91.85 111	90.89 108	98.44 56	97.81 107

DeepPCF-MVS	91.00 2	94.15 34	96.87 21	90.97 51	96.82 42	99.33 12	89.40 125	92.76 32	98.76 1	82.36 53	88.74 41	95.49 30	90.58 77	98.13 4	97.80 4	93.88 224	99.88 6

CPTT-MVS		94.11 35	93.99 40	94.25 28	96.58 46	97.66 64	97.31 30	91.94 36	94.84 51	88.72 28	92.51 35	93.04 39	95.78 23	91.51 117	89.97 125	95.15 205	98.37 79

EPNet		93.69 36	95.34 33	91.76 44	96.98 41	98.47 46	95.40 46	86.79 52	95.47 41	82.84 50	95.66 19	89.17 53	90.47 80	95.25 42	94.69 42	98.10 83	98.68 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 37	93.59 43	93.00 38	97.03 40	98.24 52	95.27 47	91.66 39	95.20 46	83.25 48	95.39 21	85.52 73	92.80 50	92.60 100	90.21 121	98.01 95	97.99 96
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
CANet		93.23 38	93.72 42	92.65 39	95.48 56	99.09 22	96.55 36	86.74 53	95.28 44	85.22 40	77.30 77	91.25 49	92.60 52	97.06 16	96.63 8	99.31 2	99.45 25

CDPH-MVS		93.22 39	95.08 34	91.04 50	97.57 35	98.49 44	96.74 35	89.35 42	95.19 47	73.57 128	90.26 38	91.59 48	90.68 74	95.09 46	96.15 14	98.31 70	98.81 57

CSCG		93.16 40	92.65 48	93.76 31	98.32 25	99.09 22	96.12 39	89.91 41	93.15 63	89.64 22	83.62 57	88.91 55	92.40 54	91.09 124	93.70 66	96.14 187	98.99 52

MVS_111021_LR		93.05 41	94.53 37	91.32 48	96.43 48	98.38 49	92.81 64	87.20 51	95.94 37	81.45 57	94.75 27	86.08 69	92.12 57	94.83 48	93.34 80	97.89 107	98.42 78

3Dnovator+	86.26 7	92.90 42	92.45 50	93.42 35	97.25 37	98.45 48	95.82 41	85.71 61	93.83 58	89.55 24	72.31 112	92.28 44	94.01 40	95.10 45	95.92 21	98.17 79	99.23 33

MVS_111021_HR		92.73 43	94.83 36	90.28 56	96.27 50	99.10 21	92.77 65	86.15 58	93.41 61	77.11 115	93.82 33	87.39 61	90.61 75	95.60 35	95.15 34	98.79 37	99.32 27

PLC	89.12 3	92.67 44	90.84 60	94.81 26	97.69 33	96.10 108	95.42 45	91.70 37	95.82 38	92.52 14	81.24 63	86.01 70	94.36 30	92.44 104	90.27 118	97.19 140	93.99 185
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 45	91.96 52	93.20 36	97.99 29	98.47 46	95.78 42	85.94 59	93.07 64	86.40 34	73.43 101	89.00 54	94.08 37	94.74 52	96.44 12	99.01 20	98.57 69

DeepC-MVS	88.77 4	92.39 46	91.74 54	93.14 37	96.21 51	98.55 39	96.30 37	93.84 23	93.06 65	81.09 64	74.69 91	85.20 79	93.48 44	95.41 38	96.13 15	97.92 104	99.18 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OMC-MVS		92.05 47	91.88 53	92.25 41	96.51 47	97.94 58	93.18 61	88.97 45	96.53 28	84.47 44	80.79 65	87.85 57	93.25 48	92.48 103	91.81 101	97.12 141	95.73 155

MVSTER		91.91 48	93.43 46	90.14 57	89.81 102	92.32 157	94.53 52	81.32 110	96.00 34	84.77 43	85.41 54	92.39 43	91.32 61	96.41 24	94.01 60	99.11 10	97.45 118

SPE-MVS-test		91.76 49	93.47 44	89.76 60	94.64 61	98.22 54	88.13 136	81.58 107	97.02 22	82.47 52	85.49 53	85.41 77	93.28 46	95.33 40	93.61 73	98.45 55	99.22 34

QAPM		91.68 50	91.97 51	91.34 47	97.86 31	98.72 31	95.60 44	85.72 60	90.86 80	77.14 114	76.06 80	90.35 50	92.69 51	94.10 65	94.60 44	99.04 16	99.09 45

CS-MVS		91.55 51	92.49 49	90.45 55	94.00 64	97.91 60	91.17 87	81.40 109	95.22 45	83.51 47	82.37 61	82.29 85	94.07 38	96.36 27	94.03 58	98.56 48	99.22 34

CNLPA		91.53 52	89.74 73	93.63 33	96.75 44	97.63 66	91.16 89	91.70 37	96.38 29	90.82 19	69.66 128	85.52 73	93.76 41	90.44 131	91.14 107	97.55 123	97.40 119

ETV-MVS		91.51 53	94.06 39	88.54 75	89.39 108	97.52 67	89.48 120	80.88 115	97.09 20	79.41 84	87.87 42	86.18 68	92.95 49	95.94 31	94.33 48	99.13 9	99.52 23

EC-MVSNet		91.25 54	93.45 45	88.68 72	88.90 116	96.18 105	91.66 74	76.70 150	95.57 40	82.00 55	84.18 55	89.28 52	94.17 34	95.64 34	94.19 54	98.68 43	99.14 43

DELS-MVS		91.09 55	90.56 68	91.71 45	95.82 54	98.59 35	95.74 43	86.68 54	85.86 115	85.12 41	72.71 106	81.36 88	88.06 116	97.31 8	98.27 2	98.86 34	99.82 8
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
TAPA-MVS	87.40 6	90.98 56	90.71 62	91.30 49	96.14 52	97.66 64	94.80 50	89.00 44	94.74 53	77.42 111	80.22 66	86.70 64	92.27 55	91.65 116	90.17 123	98.15 82	93.83 189
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 57	90.66 64	90.82 53	94.75 59	98.54 40	91.30 83	86.53 55	95.43 42	85.75 36	78.66 72	70.67 133	87.60 118	96.37 25	95.08 36	98.98 22	99.90 2

PVSNet_Blended		90.74 57	90.66 64	90.82 53	94.75 59	98.54 40	91.30 83	86.53 55	95.43 42	85.75 36	78.66 72	70.67 133	87.60 118	96.37 25	95.08 36	98.98 22	99.90 2

CHOSEN 280x420		90.61 59	94.27 38	86.35 109	93.12 69	98.16 57	89.99 114	69.62 213	92.48 69	76.89 119	87.28 45	96.72 20	90.31 82	94.81 50	92.33 96	98.17 79	98.08 93

MAR-MVS		90.44 60	91.17 58	89.59 61	97.48 36	97.92 59	90.96 96	79.80 121	95.07 49	77.03 116	80.83 64	79.10 98	94.68 28	93.16 83	94.46 46	97.59 121	97.63 111
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
PCF-MVS	88.14 5	90.42 61	89.56 79	91.41 46	94.44 62	98.18 55	94.35 53	94.33 20	84.55 132	76.61 120	75.84 83	88.47 56	91.29 62	90.37 134	90.66 114	97.46 127	98.88 56
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 62	88.89 85	90.95 52	97.63 34	98.51 42	94.64 51	85.47 64	88.14 99	78.39 102	65.06 156	85.42 76	91.04 66	93.06 86	93.70 66	98.53 51	98.37 79

EIA-MVS		89.82 63	91.48 56	87.89 93	89.16 110	97.31 69	88.99 127	80.92 114	94.29 55	77.65 109	82.16 62	79.77 96	91.90 58	94.61 55	93.03 90	98.70 42	99.21 37

sasdasda		89.62 64	89.87 71	89.33 63	90.47 88	97.02 75	93.46 58	79.67 124	92.45 70	81.05 65	82.84 58	73.00 120	93.71 42	90.38 132	94.85 39	97.65 116	98.54 70

canonicalmvs		89.62 64	89.87 71	89.33 63	90.47 88	97.02 75	93.46 58	79.67 124	92.45 70	81.05 65	82.84 58	73.00 120	93.71 42	90.38 132	94.85 39	97.65 116	98.54 70

TSAR-MVS + COLMAP		89.59 66	89.64 76	89.53 62	93.32 68	96.51 91	95.03 48	88.53 46	95.98 35	69.10 144	91.81 36	64.53 172	93.40 45	93.53 76	91.35 106	97.77 109	93.75 192

HQP-MVS		89.57 67	90.57 67	88.41 79	92.77 70	94.71 127	94.24 54	87.97 47	93.44 60	68.18 147	91.75 37	71.54 132	89.90 92	92.31 107	91.43 104	97.39 132	98.80 58

MGCFI-Net		89.36 68	89.66 75	89.02 68	90.40 92	96.92 78	93.26 60	79.54 128	92.10 72	80.11 73	82.55 60	72.65 123	93.26 47	90.24 136	94.69 42	97.53 125	98.46 76

MVS_Test		89.02 69	90.20 69	87.64 96	89.83 101	97.05 74	92.30 68	77.59 146	92.89 66	75.01 125	77.36 76	76.10 108	92.27 55	95.30 41	95.42 29	98.83 35	97.30 123

CLD-MVS		88.99 70	88.07 88	90.07 58	89.61 104	94.94 124	93.82 57	85.70 62	92.73 68	82.73 51	79.97 67	69.59 138	90.44 81	90.32 135	89.93 127	98.10 83	99.04 48
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
baseline		88.91 71	89.94 70	87.70 95	89.44 107	96.74 83	91.62 76	77.92 143	93.79 59	78.76 93	77.55 75	78.46 101	89.38 101	92.26 108	92.52 95	99.10 11	98.23 84

PMMVS		88.56 72	91.22 57	85.47 122	90.04 97	95.60 119	86.62 151	78.49 138	93.86 57	70.62 139	90.00 39	80.08 94	91.64 60	92.36 105	89.80 131	95.40 200	96.84 135

test2506		88.38 73	88.02 90	88.80 71	91.55 79	97.78 61	90.87 98	83.36 75	84.51 133	83.06 49	74.13 94	76.93 105	85.39 130	94.34 62	93.33 82	98.60 44	95.10 174

E2		88.25 74	87.54 96	89.08 66	88.94 115	96.72 84	90.74 100	83.41 74	86.83 110	82.08 54	72.76 105	70.33 135	90.81 70	93.83 70	94.01 60	98.48 53	98.29 83

baseline1		88.16 75	88.15 87	88.17 85	90.02 98	94.79 126	91.85 73	83.89 67	87.37 105	75.67 123	73.75 99	79.89 95	88.44 115	94.41 57	93.33 82	99.18 5	93.55 194

thisisatest0530		87.99 76	90.76 61	84.75 126	88.36 136	96.82 80	87.65 141	79.67 124	91.77 74	70.93 135	79.94 68	87.65 59	84.21 140	92.98 89	89.07 143	97.66 115	97.13 128

tttt0517		87.93 77	90.71 62	84.68 127	88.33 137	96.76 82	87.42 144	79.67 124	91.74 75	70.83 136	79.91 69	87.61 60	84.21 140	92.88 94	89.07 143	97.62 119	97.03 130

CANet_DTU		87.91 78	91.57 55	83.64 134	90.96 82	97.12 72	91.90 72	75.97 158	92.83 67	53.16 208	86.02 50	79.02 99	90.80 71	95.40 39	94.15 55	99.03 19	96.47 147

diffmvs		87.86 79	87.40 97	88.39 80	88.57 126	96.10 108	91.24 85	83.15 85	90.62 81	79.13 91	72.45 110	67.71 152	90.07 87	92.58 101	93.31 85	98.17 79	99.03 49
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IS_MVSNet		87.83 80	90.66 64	84.53 128	90.08 96	96.79 81	88.16 135	79.89 120	85.44 117	72.20 130	75.50 87	87.14 62	80.21 168	95.53 36	95.22 32	96.65 158	99.02 50

viewcassd2359sk11		87.73 81	86.79 102	88.83 70	88.87 118	96.64 85	90.66 103	83.33 80	85.05 126	81.22 63	70.85 119	69.54 139	90.50 79	93.40 80	93.86 62	98.40 60	98.21 85

EPP-MVSNet		87.72 82	89.74 73	85.37 123	89.11 111	95.57 120	86.31 154	79.44 129	85.83 116	75.73 122	77.23 78	90.05 51	84.78 136	91.22 122	90.25 119	96.83 148	98.04 94

casdiffmvs_mvg		87.64 83	86.46 108	89.01 69	89.45 106	96.09 110	92.69 66	83.42 73	84.60 131	80.01 74	68.55 134	70.29 136	90.51 78	93.93 68	93.59 75	97.96 99	98.18 86
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ET-MVSNet_ETH3D		87.63 84	91.08 59	83.59 135	67.96 241	96.30 99	92.06 70	78.47 139	91.95 73	69.87 141	87.57 44	84.14 83	94.34 31	88.58 151	92.10 98	98.88 32	96.93 131

DI_MVS_pp		87.63 84	87.13 99	88.22 82	88.61 125	95.92 114	94.09 56	81.41 108	87.00 108	78.38 103	59.70 176	80.52 92	89.08 108	94.37 60	93.34 80	97.73 110	99.05 47

casdiffmvs		87.59 86	86.69 104	88.64 73	89.06 113	96.32 98	90.18 110	83.21 84	87.74 103	80.20 71	67.99 139	68.34 148	90.79 72	93.83 70	94.08 56	98.41 59	98.50 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_Blended_VisFu		87.44 87	88.72 86	85.95 117	92.02 74	97.26 70	86.88 149	82.66 97	83.86 139	79.16 90	66.96 144	84.91 80	77.26 189	94.97 47	93.48 76	97.73 110	99.64 18

viewdifsd2359ckpt09		87.42 88	86.55 106	88.45 78	88.67 123	96.49 92	90.38 107	83.11 89	85.25 120	79.50 78	70.80 120	68.43 145	90.90 68	93.87 69	93.04 89	98.10 83	97.95 101

viewmanbaseed2359cas		87.26 89	86.56 105	88.07 89	89.09 112	96.64 85	90.52 106	83.44 71	85.33 118	76.94 118	70.09 126	68.98 142	90.04 88	92.85 95	94.02 59	98.40 60	98.03 95

diffmvs_AUTHOR		87.25 90	86.52 107	88.11 88	88.39 134	96.07 112	91.06 91	82.98 93	88.29 98	78.43 99	70.18 125	67.08 161	89.79 96	92.05 110	93.02 91	98.03 93	98.94 55

FMVSNet3		87.19 91	87.32 98	87.04 107	82.82 174	90.21 173	92.88 63	76.53 153	91.69 76	81.31 59	64.81 159	80.64 89	89.79 96	94.80 51	94.76 41	98.88 32	94.32 181

LS3D		87.19 91	85.48 118	89.18 65	94.96 58	95.47 121	92.02 71	93.36 27	88.69 94	67.01 148	70.56 122	72.10 127	92.47 53	89.96 140	89.93 127	95.25 202	91.68 210

ACMP	85.16 9	87.15 93	87.04 100	87.27 102	90.80 84	94.45 130	89.41 124	83.09 90	89.15 88	76.98 117	86.35 48	65.80 166	86.94 123	88.45 152	87.52 166	96.42 173	97.56 116
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		87.11 94	85.87 115	88.55 74	88.74 121	96.52 89	90.53 104	83.25 82	82.75 143	80.24 70	68.90 132	68.41 147	90.19 84	92.76 98	93.68 68	98.32 68	98.10 90

E3		87.08 95	85.87 115	88.49 76	88.75 120	96.52 89	90.53 104	83.25 82	82.74 144	79.93 75	68.88 133	68.46 144	90.18 85	92.76 98	93.66 70	98.32 68	98.10 90

UGNet		87.04 96	89.59 78	84.07 130	90.94 83	95.95 113	86.02 156	81.65 105	85.94 114	78.54 97	78.00 74	85.40 78	69.62 214	91.83 112	91.53 103	97.63 118	98.51 73
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
viewdifsd2359ckpt13		87.03 97	86.28 109	87.90 92	88.81 119	96.63 87	89.75 116	83.30 81	85.16 123	77.32 112	69.27 129	67.96 150	90.14 86	93.53 76	93.67 69	98.09 87	97.74 109

LGP-MVS_train		86.95 98	87.65 93	86.12 112	91.77 77	93.84 136	93.04 62	82.77 95	88.04 100	65.33 153	87.69 43	67.09 160	86.79 124	90.20 137	88.99 146	97.05 143	97.71 110

PatchMatch-RL		86.75 99	85.43 120	88.29 81	94.06 63	96.37 97	86.82 150	82.94 94	88.94 91	79.59 77	79.83 70	59.17 189	89.46 100	91.12 123	88.81 150	96.88 147	93.78 190

FA-MVS(training)		86.74 100	88.01 91	85.26 124	89.86 99	96.99 77	88.54 132	64.26 231	89.04 89	81.30 62	66.74 146	81.52 87	89.11 107	94.04 66	90.37 117	98.47 54	97.37 120

viewmambaseed2359dif		86.69 101	85.42 121	88.17 85	88.54 127	95.67 116	90.98 95	82.71 96	86.36 113	80.14 72	68.41 135	68.31 149	89.91 91	87.78 159	92.27 97	96.75 152	99.13 44

baseline2		86.51 102	89.35 82	83.19 137	85.70 159	94.88 125	85.75 161	77.13 148	89.87 85	70.65 138	79.03 71	79.14 97	81.51 161	93.70 72	90.22 120	98.38 64	98.60 67

viewdifsd2359ckpt07		86.50 103	85.45 119	87.72 94	88.88 117	96.19 104	89.63 117	83.34 79	81.97 149	78.44 98	67.87 141	68.43 145	87.74 117	93.68 73	93.13 88	98.27 71	96.88 133

thres100view900		86.48 104	85.08 124	88.12 87	90.54 85	96.90 79	92.39 67	84.82 65	84.16 137	71.65 131	70.86 117	60.49 184	91.23 64	93.65 74	90.19 122	98.10 83	99.32 27

ACMM	84.23 10	86.40 105	84.64 131	88.46 77	91.90 75	91.93 163	88.11 137	85.59 63	88.61 95	79.13 91	75.31 88	66.25 164	89.86 95	89.88 141	87.64 163	96.16 186	92.86 199
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E5new		86.34 106	84.76 128	88.20 83	88.52 128	96.26 100	90.68 101	83.36 75	79.90 161	78.40 100	66.52 147	67.18 158	90.01 89	91.82 113	93.64 71	98.22 72	97.98 98

E5		86.34 106	84.76 128	88.20 83	88.52 128	96.26 100	90.68 101	83.36 75	79.90 161	78.40 100	66.52 147	67.18 158	90.01 89	91.82 113	93.64 71	98.22 72	97.98 98

GBi-Net		86.16 108	86.00 112	86.35 109	81.81 180	89.52 182	91.40 79	76.53 153	91.69 76	81.31 59	64.81 159	80.64 89	88.72 110	90.54 128	90.72 110	98.34 65	94.08 182

test1		86.16 108	86.00 112	86.35 109	81.81 180	89.52 182	91.40 79	76.53 153	91.69 76	81.31 59	64.81 159	80.64 89	88.72 110	90.54 128	90.72 110	98.34 65	94.08 182

E4		86.15 110	84.60 132	87.96 91	88.52 128	96.25 102	90.25 109	83.05 92	79.58 164	78.14 105	66.12 150	67.23 156	89.62 98	91.68 115	93.43 78	98.20 75	97.93 102

tfpn200view9		86.07 111	84.76 128	87.61 97	90.54 85	96.39 94	91.35 82	83.15 85	84.16 137	71.65 131	70.86 117	60.49 184	90.91 67	92.89 91	89.34 134	98.05 91	99.17 40

DCV-MVSNet		85.90 112	85.88 114	85.93 118	87.86 142	88.37 199	89.45 123	77.46 147	87.33 106	77.51 110	76.06 80	75.76 110	88.48 114	87.40 162	88.89 149	94.80 211	97.37 120

Vis-MVSNet (Re-imp)		85.89 113	89.62 77	81.55 149	89.85 100	96.08 111	87.55 142	79.80 121	84.80 128	66.55 150	73.70 100	86.71 63	68.25 221	94.40 58	94.53 45	97.32 135	97.09 129

MSDG		85.81 114	82.29 159	89.93 59	95.52 55	92.61 152	91.51 78	91.46 40	85.12 124	78.56 95	63.25 165	69.01 141	85.31 133	88.45 152	88.23 155	97.21 139	89.33 222

thres200		85.80 115	84.38 134	87.46 100	90.51 87	96.39 94	91.64 75	83.15 85	81.59 153	71.54 133	70.24 123	60.41 186	89.88 93	92.89 91	89.85 130	98.06 89	99.26 32

E6new		85.77 116	84.30 136	87.49 98	88.49 132	96.18 105	89.47 121	81.93 103	79.29 165	77.66 107	65.72 151	66.80 162	89.17 104	91.36 119	92.90 93	98.19 77	97.84 105

E6		85.77 116	84.30 136	87.49 98	88.49 132	96.18 105	89.47 121	81.93 103	79.29 165	77.66 107	65.72 151	66.80 162	89.17 104	91.36 119	92.90 93	98.19 77	97.84 105

ECVR-MVS		85.74 118	83.80 144	88.00 90	91.55 79	97.78 61	90.87 98	83.36 75	84.51 133	78.21 104	58.65 181	62.75 178	85.39 130	94.34 62	93.33 82	98.60 44	95.25 167

viewmacassd2359aftdt		85.71 119	84.41 133	87.22 103	88.63 124	96.25 102	90.16 111	83.07 91	79.77 163	74.57 127	65.34 153	67.22 157	88.71 113	90.93 125	93.61 73	98.20 75	97.77 108

OPM-MVS		85.69 120	82.79 152	89.06 67	93.42 66	94.21 134	94.21 55	87.61 49	72.68 186	70.79 137	71.09 115	67.27 155	90.74 73	91.29 121	89.05 145	97.61 120	93.94 187
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 121	84.08 139	87.36 101	90.45 90	96.60 88	90.95 97	83.67 70	80.99 157	71.17 134	69.08 131	60.25 187	89.88 93	93.14 84	89.34 134	98.02 94	99.17 40

0.3-1-1-0.015		85.55 122	85.15 123	86.02 115	78.77 201	93.03 147	91.14 90	80.95 113	88.71 93	79.50 78	73.18 103	73.11 114	89.48 99	83.59 195	88.42 153	96.29 179	96.01 151

0.4-1-1-0.2		85.51 123	85.07 125	86.02 115	78.76 202	93.04 146	91.17 87	81.04 112	88.53 96	79.46 83	72.62 109	73.05 118	89.37 102	83.67 194	88.56 152	96.31 176	96.03 150

CostFormer		85.47 124	86.98 101	83.71 133	88.70 122	94.02 135	88.07 138	62.72 233	89.78 86	78.68 94	72.69 107	78.37 102	87.35 120	85.96 175	89.32 138	96.73 155	98.72 59

0.4-1-1-0.1		85.32 125	84.89 126	85.83 120	78.73 203	93.00 148	90.99 94	80.42 117	88.43 97	79.41 84	72.22 113	73.05 118	89.17 104	83.43 199	88.14 156	96.24 182	95.94 153

test1111		85.17 126	83.46 147	87.17 104	91.36 81	97.75 63	90.06 113	83.44 71	83.41 141	75.25 124	58.08 184	62.19 180	84.39 139	94.39 59	93.38 79	98.54 50	95.00 176

thres600view7		85.14 127	83.58 146	86.96 108	90.37 94	96.39 94	90.33 108	83.15 85	80.46 158	70.60 140	67.96 140	60.04 188	89.22 103	92.89 91	88.28 154	98.06 89	99.08 46

test-LLR		85.11 128	89.49 80	80.00 158	85.32 163	94.49 128	82.27 192	74.18 167	87.83 101	56.70 186	75.55 85	86.26 65	82.75 154	93.06 86	90.60 115	98.77 38	98.65 65

FMVSNet2		84.89 129	84.02 141	85.91 119	81.81 180	89.52 182	91.40 79	75.79 159	84.45 135	79.39 86	58.75 179	74.35 112	88.72 110	93.51 79	93.46 77	98.34 65	94.08 182

FC-MVSNet-train		84.88 130	84.08 139	85.82 121	89.21 109	91.74 164	85.87 157	81.20 111	81.71 152	74.66 126	73.38 102	64.99 170	86.60 125	90.75 126	88.08 157	97.36 133	97.90 103

EPNet_dtu		84.87 131	89.01 83	80.05 157	95.25 57	92.88 150	88.84 129	84.11 66	91.69 76	49.28 224	85.69 51	78.95 100	65.39 226	92.22 109	91.66 102	97.43 130	89.95 218
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 132	85.71 117	83.73 132	87.94 141	95.76 115	90.08 112	73.45 182	85.12 124	62.66 162	72.39 111	64.97 171	90.59 76	92.95 90	90.69 113	97.67 114	98.12 88

UA-Net		84.69 133	87.64 94	81.25 151	90.38 93	95.67 116	87.33 145	79.41 130	72.07 190	66.48 151	75.09 89	92.48 42	66.88 222	94.03 67	94.25 52	97.01 146	89.88 219

TESTMET0.1,1		84.62 134	89.49 80	78.94 168	82.18 177	94.49 128	82.27 192	70.94 202	87.83 101	56.70 186	75.55 85	86.26 65	82.75 154	93.06 86	90.60 115	98.77 38	98.65 65

CHOSEN 1792x2688		84.59 135	84.30 136	84.93 125	93.71 65	98.23 53	89.91 115	77.96 142	84.81 127	65.93 152	45.19 232	71.76 131	83.13 152	95.46 37	95.13 35	98.94 27	99.53 22

casdiffseed414692147		84.37 136	81.97 163	87.16 106	88.39 134	95.36 122	89.17 126	81.64 106	78.81 169	77.31 113	60.13 174	61.16 182	88.91 109	89.68 143	91.85 100	97.54 124	96.81 136

Anonymous20231211		84.23 137	81.71 167	87.17 104	87.38 151	93.59 139	88.95 128	82.14 101	83.82 140	78.56 95	48.09 226	73.89 113	91.25 63	86.38 169	88.06 159	94.74 212	98.14 87

MDTV_nov1_ep13		84.17 138	88.03 89	79.66 160	86.00 157	94.41 131	85.05 163	66.01 227	90.36 82	64.34 158	77.13 79	84.56 81	82.71 156	87.12 166	88.92 147	93.84 226	93.69 193

test-mter		84.06 139	89.00 84	78.29 173	81.92 178	94.23 133	81.07 202	70.38 207	87.12 107	56.10 195	74.75 90	85.80 71	81.81 160	92.52 102	90.10 124	98.43 57	98.49 75

viewdifsd2359ckpt11		83.97 140	82.19 160	86.05 113	87.69 146	93.13 143	86.43 152	82.38 99	82.00 148	79.38 87	68.06 137	64.36 175	87.13 121	83.72 193	86.86 172	93.31 232	97.22 124

viewmsd2359difaftdt		83.97 140	82.19 160	86.04 114	87.69 146	93.13 143	86.43 152	82.37 100	81.93 150	79.33 88	68.06 137	64.40 174	87.12 122	83.73 192	86.86 172	93.31 232	97.22 124

IB-MVS	79.58 12	83.83 142	84.81 127	82.68 141	91.85 76	97.35 68	75.75 227	82.57 98	86.55 111	84.01 45	70.90 116	65.43 168	63.18 232	84.19 189	89.92 129	98.74 40	99.31 29
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
EPMVS		83.71 143	86.76 103	80.16 156	89.72 103	95.64 118	84.68 164	59.73 238	89.61 87	62.67 161	72.65 108	81.80 86	86.22 127	86.23 171	88.03 160	97.96 99	93.35 195

HyFIR lowres test		83.43 144	82.94 150	84.01 131	93.41 67	97.10 73	87.21 146	74.04 170	80.15 160	64.98 154	41.09 240	76.61 107	86.51 126	93.31 81	93.01 92	97.91 106	99.30 30

PatchmatchNet		83.28 145	87.57 95	78.29 173	87.46 149	94.95 123	83.36 174	59.43 241	90.20 84	58.10 181	74.29 93	86.20 67	84.13 142	85.27 181	87.39 167	97.25 138	94.67 179
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 146	87.76 92	78.00 179	87.45 150	92.20 158	82.63 188	58.42 243	90.30 83	58.23 179	75.74 84	87.75 58	83.97 145	86.10 174	87.64 163	97.30 136	94.62 180

GeoE		83.17 147	82.86 151	83.53 136	87.24 152	93.78 137	87.94 139	72.75 187	82.19 147	69.76 142	60.54 172	65.95 165	86.01 128	89.41 146	89.72 132	97.47 126	98.43 77

CDS-MVSNet		83.13 148	83.73 145	82.43 147	84.52 168	92.92 149	88.26 134	77.67 145	72.08 189	69.08 145	66.96 144	74.66 111	78.61 175	90.70 127	91.96 99	96.46 172	96.86 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 149	81.86 164	84.13 129	88.25 138	88.32 200	87.67 140	80.86 116	84.78 129	76.57 121	85.56 52	76.00 109	84.61 137	78.20 230	76.52 234	86.81 249	83.63 241

Vis-MVSNet		82.88 150	86.04 111	79.20 166	87.77 145	96.42 93	86.10 155	76.70 150	74.82 180	61.38 165	70.70 121	77.91 103	64.83 228	93.22 82	93.19 87	98.43 57	96.01 151
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 151	82.64 155	82.62 143	87.81 144	92.81 151	84.39 166	61.96 234	86.43 112	81.63 56	69.72 127	67.60 154	84.42 138	82.51 208	83.90 206	95.52 196	95.50 164

IterMVS-LS		82.62 152	82.75 154	82.48 144	87.09 153	87.48 213	87.19 147	72.85 185	79.09 167	66.63 149	65.22 154	72.14 126	84.06 144	88.33 155	91.39 105	97.03 145	95.60 163
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 153	82.51 157	82.72 140	85.49 162	93.06 145	87.17 148	71.39 199	84.18 136	64.59 156	63.03 166	58.89 190	90.22 83	91.39 118	90.83 109	97.44 128	96.21 149

tpm cat1		82.39 154	82.32 158	82.47 145	88.13 139	92.42 156	87.43 143	62.79 232	85.30 119	78.05 106	60.14 173	72.10 127	83.20 151	82.26 211	85.67 185	95.23 203	98.35 81

dmvs_re		82.31 155	81.55 168	83.19 137	83.15 173	93.17 142	88.68 131	83.72 68	82.73 145	61.70 163	67.43 143	55.43 203	83.35 150	87.51 161	89.27 141	98.56 48	95.31 166

MS-PatchMatch		82.16 156	82.18 162	82.12 148	91.65 78	93.50 140	89.51 119	71.95 193	81.48 154	64.45 157	59.58 178	77.54 104	77.23 190	89.88 141	85.62 186	97.94 101	87.68 226

blend_shiyan4		81.76 157	80.92 172	82.74 139	79.07 198	85.29 225	91.60 77	74.15 169	89.00 90	79.50 78	73.82 96	73.11 114	77.73 183	77.73 232	75.18 237	94.37 215	92.34 202

tpmrst		81.71 158	83.87 143	79.20 166	89.01 114	93.67 138	84.22 167	60.14 236	87.45 104	59.49 169	64.97 157	71.86 130	85.30 134	84.72 185	86.30 177	97.04 144	98.09 92

RPMNet		81.47 159	86.24 110	75.90 198	86.72 154	92.12 160	82.82 186	55.76 250	85.21 121	53.73 206	63.45 163	83.16 84	80.13 169	92.34 106	89.52 133	96.23 184	97.90 103

CR-MVSNet		81.44 160	85.29 122	76.94 189	86.53 155	92.12 160	83.86 168	58.37 244	85.21 121	56.28 190	59.60 177	80.39 93	80.50 166	92.77 96	89.32 138	96.12 188	97.59 114

Effi-MVS+-dtu		81.18 161	82.77 153	79.33 164	84.70 167	92.54 154	85.81 158	71.55 197	78.84 168	57.06 185	71.98 114	63.77 176	85.09 135	88.94 148	87.62 165	91.79 242	95.68 158

test0.0.03 1		80.99 162	84.37 135	77.05 187	85.32 163	89.79 178	78.43 218	74.18 167	84.78 129	57.98 184	76.06 80	72.88 122	69.14 218	88.02 157	87.70 161	97.27 137	91.37 211

Fast-Effi-MVS+-dtu		80.57 163	83.44 148	77.22 185	83.98 171	91.52 166	85.78 160	64.54 230	80.38 159	50.28 220	74.06 95	62.89 177	82.00 159	89.10 147	88.91 148	96.75 152	97.21 127

FMVSNet5		80.56 164	82.53 156	78.26 175	73.80 234	81.52 241	82.26 194	68.36 219	88.85 92	64.21 159	69.09 130	84.38 82	83.49 149	87.13 165	86.76 174	97.44 128	79.95 245

ADS-MVSNet		80.25 165	82.96 149	77.08 186	87.86 142	92.60 153	81.82 199	56.19 249	86.95 109	56.16 193	68.19 136	72.42 125	83.70 148	82.05 212	85.45 191	96.75 152	93.08 198

FMVSNet1		80.18 166	78.07 181	82.65 142	78.55 208	87.57 212	88.41 133	73.93 175	70.16 195	73.57 128	49.80 215	64.45 173	85.35 132	90.54 128	90.72 110	96.10 189	93.21 196

USDC		80.10 167	79.33 177	81.00 153	86.36 156	91.71 165	88.74 130	75.77 160	81.90 151	54.90 200	67.67 142	52.05 208	83.94 146	88.44 154	86.25 178	96.31 176	87.28 230

COLMAP_ROB	75.69 15	79.47 168	76.90 190	82.46 146	92.20 71	90.53 169	85.30 162	83.69 69	78.27 172	61.47 164	58.26 182	62.75 178	78.28 178	82.41 209	82.13 219	93.83 228	83.98 240
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs4		79.32 169	77.78 185	81.11 152	80.18 189	88.96 194	83.39 172	76.07 156	81.27 155	69.35 143	58.66 180	51.19 211	82.01 158	87.16 164	84.39 203	95.66 193	92.82 200

PatchT		79.28 170	83.88 142	73.93 211	85.54 161	90.95 167	66.14 245	56.53 248	83.21 142	56.28 190	56.50 187	76.80 106	80.50 166	92.77 96	89.32 138	98.57 47	97.59 114

ACMH	78.51 14	79.27 171	78.08 180	80.65 154	89.52 105	90.40 170	80.45 209	79.77 123	69.54 200	54.85 201	64.83 158	56.16 201	83.94 146	84.58 187	86.01 182	95.41 199	95.03 175
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 172	78.95 179	79.56 161	81.89 179	92.52 155	82.97 181	73.70 176	67.27 213	64.97 155	61.66 171	65.06 169	78.61 175	87.12 166	88.07 158	95.23 203	90.95 213

ACMH+	79.09 13	79.12 173	77.22 189	81.35 150	88.50 131	90.36 171	82.14 196	79.38 132	72.78 185	58.59 176	62.31 170	56.44 200	84.10 143	82.03 213	84.05 204	95.40 200	92.55 201

usedtu_dtu_shiyan1		79.10 174	79.87 174	78.20 177	71.16 236	90.83 168	84.41 165	78.54 137	81.24 156	58.78 175	56.79 186	61.56 181	78.74 174	90.08 138	87.70 161	97.59 121	90.90 214

UniMVSNet_NR-MVSNet		78.89 175	78.04 182	79.88 159	79.40 195	89.70 179	82.92 183	80.17 118	76.37 178	58.56 177	57.10 185	54.92 204	81.44 162	83.51 198	87.12 169	96.76 151	97.60 112

tpm		78.87 176	81.33 171	76.00 196	85.57 160	90.19 174	82.81 187	59.66 239	78.35 171	51.40 215	66.30 149	67.92 151	80.94 164	83.28 202	85.73 183	95.65 194	97.56 116

GA-MVS		78.86 177	80.42 173	77.05 187	83.27 172	92.17 159	83.24 176	75.73 161	73.75 182	46.27 234	62.43 168	57.12 193	76.94 192	93.14 84	89.34 134	96.83 148	95.00 176

IterMVS		78.85 178	81.36 169	75.93 197	84.27 170	85.74 219	83.83 170	66.35 225	76.82 173	50.48 218	63.48 162	68.82 143	73.99 201	89.68 143	89.34 134	96.63 161	95.67 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 179	81.34 170	75.64 202	84.31 169	85.67 220	83.51 171	66.14 226	76.67 174	50.38 219	63.45 163	69.02 140	73.23 204	89.66 145	89.22 142	96.24 182	95.67 159

usedtu_blend_shiyan5		78.69 180	77.98 183	79.53 162	60.42 245	84.96 228	91.21 86	73.97 171	69.27 202	79.50 78	73.82 96	73.11 114	77.73 183	77.31 236	75.07 238	94.33 218	92.34 202

UniMVSNet (Re)		78.00 181	77.52 186	78.57 171	79.66 194	90.36 171	82.09 197	77.86 144	76.38 177	60.26 166	54.63 193	52.07 207	75.31 199	84.97 184	86.10 180	96.22 185	98.11 89

DU-MVS		77.98 182	76.71 191	79.46 163	78.68 205	89.26 188	82.92 183	79.06 134	76.52 175	58.56 177	54.89 191	48.35 225	81.44 162	83.16 204	87.21 168	96.08 190	97.60 112

FC-MVSNet-test		77.95 183	81.85 165	73.39 217	82.31 175	88.99 193	79.33 214	74.24 166	78.75 170	47.40 232	70.22 124	72.09 129	60.78 239	86.66 168	85.62 186	96.30 178	90.61 215

FE-MVSNET3		77.89 184	77.94 184	77.83 181	60.42 245	84.96 228	81.04 203	73.97 171	69.27 202	79.50 78	73.82 96	73.11 114	77.73 183	77.31 236	75.07 238	94.33 218	92.02 206

NR-MVSNet		77.21 185	76.41 192	78.14 178	80.18 189	89.26 188	83.38 173	79.06 134	76.52 175	56.59 188	54.89 191	45.32 235	72.89 206	85.39 180	86.12 179	96.71 156	97.36 122

thisisatest0515		77.13 186	79.36 176	74.52 204	79.79 193	89.65 180	73.54 232	73.69 177	74.10 181	58.14 180	62.79 167	60.57 183	66.49 224	88.08 156	85.16 196	95.49 198	95.15 171

gg-mvs-nofinetune		77.08 187	79.79 175	73.92 212	85.95 158	97.23 71	92.18 69	52.65 253	46.19 254	27.79 260	38.27 244	85.63 72	85.67 129	96.95 18	95.62 25	99.30 3	98.67 64

TranMVSNet+NR-MVSNet		77.02 188	75.76 194	78.49 172	78.46 211	88.24 201	83.03 180	79.97 119	73.49 184	54.73 202	54.00 196	48.74 220	78.15 180	82.36 210	86.90 171	96.59 163	96.55 141

CVMVSNet		76.86 189	79.09 178	74.26 207	85.29 165	89.44 185	79.91 213	78.47 139	68.94 209	44.45 241	62.35 169	69.70 137	64.50 229	85.82 176	87.03 170	92.94 237	90.33 216

Baseline_NR-MVSNet		76.71 190	74.56 201	79.23 165	78.68 205	84.15 236	82.45 190	78.87 136	75.83 179	60.05 167	47.92 227	50.18 217	79.06 173	83.16 204	83.86 207	96.26 180	96.80 137

v2v482		76.25 191	74.78 198	77.96 180	78.50 210	89.14 191	83.05 179	76.02 157	68.78 210	54.11 203	51.36 207	48.59 222	79.49 171	83.53 197	85.60 189	96.59 163	96.49 146

V42		76.21 192	75.04 197	77.58 182	78.68 205	89.33 187	82.93 182	74.64 164	69.84 197	56.13 194	50.42 212	50.93 212	76.30 198	83.32 200	84.89 200	96.83 148	96.54 142

v8		75.89 193	74.74 199	77.23 184	79.09 197	88.00 204	83.19 177	71.08 201	70.03 196	56.29 189	50.50 210	50.88 213	77.06 191	83.32 200	84.99 198	96.68 157	95.49 165

TinyColmap		75.75 194	73.19 212	78.74 170	84.82 166	87.69 208	81.59 200	74.62 165	71.81 191	54.01 204	55.79 190	44.42 240	82.89 153	84.61 186	83.76 208	94.50 213	84.22 239

MIMVSNet		75.71 195	77.26 187	73.90 213	70.93 237	88.71 197	79.98 212	57.67 247	73.58 183	58.08 183	53.93 197	58.56 191	79.41 172	90.04 139	89.97 125	97.34 134	86.04 231

UniMVSNet_ETH3D		75.63 196	71.59 226	80.35 155	81.03 184	89.90 177	83.25 175	76.58 152	60.08 234	64.19 160	42.89 239	45.01 236	82.14 157	80.20 223	86.75 175	94.90 208	96.29 148

pm-mvs1		75.61 197	74.19 203	77.26 183	80.16 191	88.79 195	81.49 201	75.49 163	59.49 236	58.09 182	48.32 223	55.53 202	72.35 207	88.61 150	85.48 190	95.99 191	93.12 197

v10		75.57 198	74.67 200	76.62 192	78.73 203	87.46 214	83.14 178	69.41 214	69.27 202	53.44 207	49.73 216	49.21 219	78.44 177	86.17 173	85.18 195	96.53 168	95.65 162

v1144		75.54 199	74.55 202	76.69 190	78.33 214	88.77 196	82.89 185	72.76 186	67.18 215	51.73 212	49.34 218	48.37 223	78.10 181	86.22 172	85.24 193	96.35 175	96.74 138

TDRefinement		75.54 199	73.22 210	78.25 176	87.65 148	89.65 180	85.81 158	79.28 133	71.14 193	56.06 196	52.17 205	51.96 209	68.74 220	81.60 214	80.58 222	91.94 240	85.45 232

pmmvs5		75.46 201	75.12 196	75.87 199	79.39 196	89.44 185	78.12 220	72.27 191	65.98 220	51.54 213	55.83 189	46.23 230	76.80 195	88.77 149	85.73 183	97.07 142	93.84 188

tfpnnormal		75.27 202	72.12 223	78.94 168	82.30 176	88.52 198	82.41 191	79.41 130	58.03 237	55.59 198	43.83 238	44.71 237	77.35 187	87.70 160	85.45 191	96.60 162	96.61 140

anonymousdsp		75.14 203	77.25 188	72.69 220	76.68 224	89.26 188	75.26 229	68.44 218	65.53 223	46.65 233	58.16 183	56.67 195	73.96 202	87.84 158	86.05 181	95.13 206	97.22 124

v148		74.98 204	73.52 208	76.69 190	78.84 200	89.02 192	78.78 216	76.82 149	67.22 214	59.61 168	49.18 219	47.94 227	70.57 213	80.76 218	83.99 205	95.52 196	96.52 144

v1192		74.96 205	73.92 204	76.17 193	77.76 217	88.19 203	82.54 189	71.94 194	66.84 216	50.07 222	48.10 225	46.14 231	78.28 178	86.30 170	85.23 194	96.41 174	96.67 139

v144192		74.76 206	73.64 205	76.06 195	77.58 218	88.23 202	81.87 198	71.63 196	66.03 219	51.08 216	48.63 222	46.77 229	77.59 186	84.53 188	84.76 201	96.64 160	96.54 142

v1921920		74.60 207	73.56 207	75.81 200	77.43 220	87.94 205	82.18 195	71.33 200	66.48 218	49.23 226	47.84 228	45.56 233	78.03 182	85.70 178	84.92 199	96.65 158	96.50 145

v1240		74.04 208	73.04 214	75.20 203	77.19 222	87.69 208	80.93 206	70.72 206	65.08 224	48.47 227	47.31 229	44.71 237	77.33 188	85.50 179	85.07 197	96.59 163	95.94 153

wanda-best-256-512		73.38 209	72.60 217	74.28 205	60.42 245	84.96 228	81.04 203	73.97 171	69.27 202	59.09 172	52.95 200	56.56 196	76.85 193	77.31 236	75.07 238	94.33 218	92.05 204

FE-blended-shiyan7		73.37 210	72.59 218	74.28 205	60.42 245	84.96 228	81.04 203	73.97 171	69.28 201	59.09 172	52.95 200	56.54 197	76.85 193	77.31 236	75.07 238	94.33 218	92.05 204

blended_shiyan8		73.25 211	72.48 219	74.14 209	60.35 249	84.93 232	80.84 207	73.55 180	69.25 206	59.22 171	52.62 203	56.47 199	76.66 196	77.19 241	74.92 243	94.23 222	91.94 208

blended_shiyan6		73.22 212	72.48 219	74.09 210	60.31 250	84.90 233	80.80 208	73.54 181	69.06 208	59.06 174	52.69 202	56.53 198	76.59 197	77.20 240	74.94 242	94.22 223	92.02 206

testgi		73.22 212	75.84 193	70.16 231	81.67 183	85.50 223	71.45 234	70.81 204	69.56 199	44.74 240	74.52 92	49.25 218	58.45 240	84.10 191	83.37 212	93.86 225	84.56 238

gbinet_0.2-2-1-0.02		73.19 214	72.88 215	73.56 215	60.07 251	84.50 235	80.22 211	73.59 179	67.33 212	59.36 170	52.21 204	58.21 192	73.76 203	77.60 233	75.19 236	94.37 215	95.12 172

CP-MVSNet		73.19 214	72.37 221	74.15 208	77.54 219	86.77 217	76.34 223	72.05 192	65.66 222	51.47 214	50.49 211	43.66 241	70.90 209	80.93 217	83.40 211	96.59 163	95.66 161

WR-MVS		72.93 216	73.57 206	72.19 223	78.14 215	87.71 207	76.21 225	73.02 184	67.78 211	50.09 221	50.35 213	50.53 215	61.27 238	80.42 221	83.10 215	94.43 214	95.11 173

TransMVSNet (Re)		72.90 217	70.51 230	75.69 201	80.88 185	85.26 226	79.25 215	78.43 141	56.13 244	52.81 209	46.81 230	48.20 226	66.77 223	85.18 183	83.70 209	95.98 192	88.28 225

WR-MVS_H		72.69 218	72.80 216	72.56 222	77.94 216	87.83 206	75.26 229	71.53 198	64.75 225	52.19 211	49.83 214	48.62 221	61.96 236	81.12 216	82.44 217	96.50 169	95.00 176

SixPastTwentyTwo		72.65 219	73.22 210	71.98 226	78.40 212	87.64 210	70.09 237	70.37 208	66.49 217	47.60 230	65.09 155	45.94 232	73.09 205	78.94 225	78.66 229	92.33 238	89.82 220

LTVRE_ROB	71.82 16	72.62 220	71.77 224	73.62 214	80.74 186	87.59 211	80.42 210	70.37 208	49.73 249	37.12 253	59.76 175	42.52 246	80.92 165	83.20 203	85.61 188	92.13 239	93.95 186
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
PS-CasMVS		72.37 221	71.47 228	73.43 216	77.32 221	86.43 218	75.99 226	71.94 194	63.37 228	49.24 225	49.07 220	42.42 247	69.60 215	80.59 220	83.18 214	96.48 171	95.23 169

MVS-HIRNet		72.32 222	73.45 209	71.00 229	80.58 187	89.97 175	68.51 242	55.28 251	70.89 194	52.27 210	39.09 242	57.11 194	75.02 200	85.76 177	86.33 176	94.36 217	85.00 235

PEN-MVS		72.24 223	71.30 229	73.33 218	77.08 223	85.57 221	76.75 221	72.52 189	63.89 227	48.12 228	50.79 208	43.09 244	69.03 219	78.54 227	83.46 210	96.50 169	93.76 191

v7n		72.11 224	71.66 225	72.63 221	75.26 229	86.85 215	76.74 222	68.77 217	62.70 231	49.40 223	45.92 231	43.51 242	70.63 212	84.16 190	83.21 213	94.99 207	95.25 167

EG-PatchMatch MVS		71.81 225	71.54 227	72.12 224	80.53 188	89.94 176	78.51 217	66.56 224	57.38 239	47.46 231	44.28 237	52.22 206	63.10 233	85.22 182	84.42 202	96.56 167	87.35 229

CMPMVS	54.54 17	71.74 226	67.94 235	76.16 194	90.41 91	93.25 141	78.32 219	75.60 162	59.81 235	53.95 205	44.64 235	51.22 210	70.70 210	74.59 245	75.88 235	88.01 246	76.23 248
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 227	73.08 213	69.97 232	75.22 230	86.81 216	73.98 231	59.61 240	69.75 198	48.01 229	54.21 195	53.06 205	69.19 217	78.50 228	80.43 223	93.84 226	88.79 223

pmnet_mix02		71.64 228	72.36 222	70.81 230	78.39 213	85.57 221	68.64 240	73.65 178	72.13 187	45.07 239	56.01 188	50.61 214	65.34 227	76.21 242	76.60 233	93.75 229	89.35 221

gm-plane-assit		71.33 229	75.18 195	66.83 235	79.06 199	75.57 249	48.05 258	60.33 235	48.28 250	34.67 257	44.34 236	67.70 153	79.78 170	97.25 12	96.21 13	99.10 11	96.92 132

DTE-MVSNet		71.19 230	70.45 231	72.06 225	76.61 225	84.59 234	75.61 228	72.32 190	63.12 230	45.70 237	50.72 209	43.02 245	65.89 225	77.53 235	82.23 218	96.26 180	91.93 209

pmmvs6		70.29 231	67.90 236	73.07 219	76.17 226	85.31 224	76.29 224	70.75 205	47.39 252	55.33 199	37.15 248	50.49 216	69.55 216	82.96 206	80.85 221	90.34 245	91.18 212

PM-MVS		70.17 232	69.42 233	71.04 228	70.82 238	81.26 243	71.25 235	67.80 220	69.16 207	51.04 217	53.15 199	34.93 254	72.19 208	80.30 222	76.95 232	93.16 236	90.21 217

pmmvs-eth3d		69.59 233	67.57 238	71.95 227	70.04 239	80.05 244	71.48 233	70.00 212	62.57 232	55.99 197	44.92 233	35.73 252	70.64 211	81.56 215	79.69 224	93.55 230	88.43 224

N_pmnet		68.54 234	67.83 237	69.38 233	75.77 227	81.90 240	66.21 244	72.53 188	65.91 221	46.09 235	44.67 234	45.48 234	63.82 231	74.66 244	77.39 231	91.87 241	84.77 237

Anonymous20231206		68.09 235	68.68 234	67.39 234	75.16 231	82.55 237	69.33 239	70.06 211	63.34 229	42.28 244	37.91 246	43.12 243	52.67 243	83.56 196	82.71 216	94.84 210	87.59 227

EU-MVSNet		68.07 236	70.25 232	65.52 237	74.68 233	81.30 242	68.53 241	70.31 210	62.40 233	37.43 252	54.62 194	48.36 224	51.34 245	78.32 229	79.27 226	90.84 243	87.47 228

FE-MVSNET2		65.87 237	65.40 241	66.41 236	56.18 254	82.03 239	69.83 238	68.97 215	56.64 242	45.42 238	31.48 251	37.87 250	62.52 235	82.96 206	81.55 220	95.56 195	85.28 233

GG-mvs-BLEND		65.67 238	93.78 41	32.89 253	0.47 264	99.35 8	96.92 34	0.22 263	93.28 62	0.51 266	84.07 56	92.50 41	0.62 262	93.59 75	93.86 62	98.59 46	99.79 10

test20.03		65.17 239	67.41 239	62.55 239	75.35 228	79.31 245	62.22 247	68.83 216	56.50 243	35.35 256	51.97 206	44.70 239	40.01 251	80.69 219	79.25 227	93.55 230	79.47 247

MDA-MVSNet-bldmvs		62.23 240	61.13 245	63.52 238	58.94 252	82.44 238	60.71 251	73.28 183	57.22 240	38.42 250	49.63 217	27.64 261	62.83 234	54.98 253	74.16 244	86.96 248	81.83 244

new_pmnet		61.60 241	62.68 242	60.35 242	63.02 242	74.93 250	60.97 250	58.86 242	64.21 226	35.38 255	39.51 241	39.89 248	57.37 241	72.78 246	72.56 246	86.49 250	74.85 250

FE-MVSNET		61.22 242	62.61 243	59.59 244	48.81 256	75.79 248	61.96 248	67.51 221	52.39 247	34.04 258	33.16 250	37.64 251	52.00 244	77.89 231	79.39 225	93.22 234	82.04 243

new-patchmatchnet		60.74 243	59.78 247	61.87 240	69.52 240	76.67 247	57.99 254	65.78 228	52.63 246	38.47 249	38.08 245	32.92 257	48.88 248	68.50 247	69.87 247	90.56 244	79.75 246

pmmvs3		60.52 244	60.87 246	60.12 243	61.38 243	71.62 252	57.42 255	53.94 252	48.09 251	35.95 254	38.62 243	32.19 260	64.12 230	75.33 243	77.99 230	87.89 247	82.28 242

MIMVSNet1		60.51 245	61.43 244	59.44 245	48.75 257	77.21 246	60.98 249	66.84 223	52.09 248	38.74 248	29.29 253	39.40 249	48.08 249	77.60 233	78.87 228	93.22 234	75.56 249

test_method		60.40 246	66.30 240	53.52 248	37.48 262	64.10 256	55.56 256	42.45 258	71.79 192	41.87 245	33.74 249	46.80 228	61.71 237	79.18 224	73.33 245	82.01 253	95.17 170

FPMVS		56.54 247	52.82 250	60.87 241	74.90 232	67.58 255	67.69 243	65.38 229	57.86 238	41.51 246	37.83 247	34.19 255	41.21 250	55.88 252	53.09 254	74.55 256	63.31 253

usedtu_dtu_shiyan2		56.32 248	55.74 249	57.01 247	40.29 261	72.50 251	63.80 246	57.88 246	37.70 255	45.71 236	25.31 255	35.59 253	49.97 247	67.09 248	67.03 249	84.41 251	84.92 236

WB-MVS		47.20 249	51.37 251	42.35 251	71.55 235	57.66 258	32.77 262	70.86 203	47.39 252	6.95 265	48.14 224	32.52 258	12.95 259	61.73 251	61.27 251	59.00 260	50.85 257

PMVS	42.57 18	45.71 250	42.61 253	49.32 249	61.35 244	37.82 261	36.96 260	60.10 237	37.20 256	41.50 247	28.53 254	33.11 256	28.82 256	53.45 254	48.70 256	67.22 258	59.42 254
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 251	42.62 252	45.50 250	50.79 255	41.20 260	35.55 261	52.51 254	52.95 245	29.09 259	12.92 257	11.48 264	38.15 252	62.01 250	66.62 250	66.89 259	51.17 255
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 252	42.55 254	39.74 252	43.25 258	55.05 259	38.15 259	47.11 257	31.78 257	11.83 262	21.16 256	19.12 262	20.98 258	49.95 256	56.09 253	77.09 254	64.68 252

E-PMN		27.87 253	24.36 256	31.97 254	41.27 260	25.56 264	16.62 264	49.16 255	22.00 259	9.90 263	11.75 259	7.86 266	29.57 255	22.22 258	34.70 257	45.27 261	46.41 258

MVE	32.98 19	27.61 254	29.89 255	24.94 256	21.97 263	37.22 262	15.56 266	38.83 259	17.49 260	14.72 261	11.64 261	5.62 267	21.26 257	35.20 257	50.95 255	37.29 263	51.13 256
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 255	22.96 257	31.63 255	41.91 259	25.73 263	16.30 265	49.10 256	22.38 258	9.03 264	11.22 262	8.12 265	29.93 254	20.16 259	31.04 258	43.49 262	42.04 259

testmvs		5.16 256	8.14 258	1.69 257	0.36 265	1.65 265	3.02 267	0.66 261	7.17 261	0.50 267	12.58 258	0.69 268	4.67 260	5.42 260	5.65 259	0.92 264	23.86 261

test123		4.39 257	7.11 259	1.21 258	0.11 266	1.16 266	1.67 268	0.35 262	5.91 262	0.16 268	11.65 260	0.16 269	4.45 261	1.72 261	4.92 260	0.51 265	24.28 260

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

TestfortrainingZip							98.29 13	95.80 1		98.47 1						99.17 7

TPM-MVS					99.19 1	99.43 7	99.16 2			85.97 35	94.75 27	97.40 14	97.76 1			98.95 26	95.69 156
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										43.17 242

9.14												97.59 11

SR-MVS					98.52 21			93.70 24				96.63 22

Anonymous202405211			81.72 166		88.09 140	94.27 132	89.62 118	82.14 101	82.27 146		48.83 221	72.58 124	91.08 65	87.40 162	88.70 151	94.90 208	97.99 96

our_test_3					78.55 208	84.98 227	70.12 236

ambc			57.08 248		58.68 253	67.71 254	60.07 252		57.13 241	42.79 243	30.00 252	11.64 263	50.18 246	78.89 226	69.14 248	82.64 252	85.02 234

MTAPA										93.37 10		95.71 29

MTMP										93.84 7		94.86 32

Patchmatch-RL test							19.65 263

tmp_tt				57.89 246	79.94 192	59.29 257	52.84 257	36.65 260	94.77 52	68.22 146	72.96 104	65.62 167	33.65 253	66.20 249	58.02 252	76.06 255

XVS					92.16 72	98.56 36	91.04 92			81.00 67		93.49 36				98.00 96

X-MVStestdata					92.16 72	98.56 36	91.04 92			81.00 67		93.49 36				98.00 96

mPP-MVS					97.95 30							92.24 46

NP-MVS									94.12 56

Patchmtry						92.08 162	83.86 168	58.37 244		56.28 190

DeepMVS_CX						70.68 253	59.61 253	67.36 222	72.12 188	38.41 251	53.88 198	32.44 259	55.15 242	50.88 255		74.35 257	68.42 251

High-resolution multi-view benchmark