High-res multi-view results

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

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

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

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

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

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

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

RA-MVS		95.84 1	95.93 1	95.72 1	97.35 17	98.85 3	96.83 5	92.85 6	98.01 1	96.83 2	97.58 1	91.54 8	94.99 3	94.00 18	91.86 31	95.50 57	99.68 1

MED-MVS		95.58 2	95.75 3	95.39 3	97.71 11	98.49 10	96.09 7	92.87 5	97.56 2	96.23 3	97.24 2	91.38 9	93.67 7	93.97 19	92.54 17	95.77 51	99.03 17

SED-MVS		95.53 3	95.79 2	95.23 4	97.60 12	98.92 1	95.99 8	92.05 11	97.14 3	94.19 5	94.71 9	93.25 3	95.08 1	94.32 12	92.59 16	96.49 20	99.58 4

aaEdge-Enhanced		95.35 4	95.21 7	95.51 2	97.58 14	98.09 16	95.37 15	93.61 1	96.66 7	95.96 4	97.24 2	90.86 13	93.58 9	92.95 29	91.63 35	96.96 9	99.03 17

DPE-MVS		95.10 5	95.53 4	94.60 8	97.77 9	98.64 6	96.60 6	92.45 9	96.34 9	91.41 10	96.70 5	92.26 7	93.56 10	93.68 21	91.73 33	95.79 50	99.37 8
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.06 6	95.37 6	94.70 6	97.59 13	98.89 2	95.37 15	92.04 12	96.85 5	94.00 6	92.81 17	93.02 4	92.93 11	94.22 15	92.15 23	96.30 28	99.61 3
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
DVP-MVS++		95.03 7	95.03 8	95.03 5	97.91 7	98.84 4	95.80 9	91.88 14	96.65 8	93.15 7	93.79 11	90.11 16	95.03 2	94.20 17	92.39 18	96.44 24	99.22 11

MSP-MVS		95.00 8	95.47 5	94.45 9	96.78 23	98.11 14	95.72 11	90.91 18	96.68 6	91.57 9	96.98 4	89.47 19	94.76 4	95.24 3	92.15 23	96.98 8	99.64 2
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
CNVR-MVS		94.53 9	94.85 10	94.15 11	98.03 5	98.59 8	95.56 12	92.91 4	94.86 16	88.46 18	91.32 24	90.83 14	94.03 6	95.20 4	94.16 6	95.89 41	99.01 20

SF-MVS		94.40 10	94.15 16	94.70 6	98.25 3	98.24 12	96.86 4	93.46 3	94.87 15	90.26 13	95.96 6	88.42 22	92.76 14	92.29 35	90.84 47	96.62 15	98.44 30

APDe-MVS		94.31 11	94.30 13	94.33 10	97.57 15	98.06 17	95.79 10	91.98 13	95.50 12	92.19 8	95.25 7	87.97 25	92.93 11	93.01 27	91.02 45	95.52 56	99.29 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		94.10 12	94.77 11	93.31 13	98.31 2	98.34 11	95.43 13	92.54 8	94.41 22	83.05 36	91.38 22	90.97 12	92.24 18	95.05 8	94.02 8	98.31 1	99.20 12

HPM-MVS++		94.04 13	94.96 9	92.96 15	97.93 6	97.71 23	94.65 20	91.01 17	95.91 10	87.43 20	93.52 14	92.63 6	92.29 17	94.22 15	92.34 20	94.47 87	98.37 31

NCCC		93.59 14	94.00 18	93.10 14	97.90 8	97.93 19	95.40 14	92.39 10	94.47 20	84.94 26	91.21 25	89.32 20	92.53 15	93.90 20	92.98 13	95.44 61	98.22 34

SMA-MVS		93.47 15	94.29 14	92.52 17	97.72 10	97.77 22	94.46 23	90.19 21	94.96 14	87.15 21	90.15 29	90.99 11	91.49 22	94.31 13	93.33 11	94.10 96	98.53 28
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		93.47 15	93.44 21	93.50 12	97.06 19	97.09 31	95.27 18	91.47 15	95.71 11	89.57 15	93.66 12	86.28 31	92.81 13	92.06 38	90.70 48	94.83 83	98.60 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		93.36 17	94.33 12	92.22 19	94.68 48	97.89 21	94.56 21	90.89 19	94.80 17	90.04 14	93.53 13	90.14 15	89.78 29	92.74 31	92.17 21	93.35 141	99.07 16
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
TSAR-MVS + MP.		93.07 18	93.53 20	92.53 16	94.23 51	97.54 25	94.75 19	89.87 22	95.26 13	89.20 17	93.16 15	88.19 24	92.15 20	91.79 43	89.65 75	94.99 77	99.16 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		92.86 19	93.19 23	92.47 18	95.78 39	97.40 26	97.39 1	92.56 7	92.88 30	81.84 43	81.31 44	92.95 5	91.21 23	96.54 1	97.33 1	96.01 37	93.94 143

MGCNet		92.61 20	94.18 15	90.77 27	95.62 42	98.60 7	93.09 30	83.78 49	94.44 21	85.52 25	87.49 35	89.90 17	90.25 26	95.14 6	94.49 5	96.37 27	99.19 13

SteuartSystems-ACMMP		92.31 21	93.31 22	91.15 25	96.88 21	97.36 27	93.95 27	89.44 24	92.62 31	83.20 33	94.34 10	85.55 33	88.95 36	93.07 26	91.90 28	94.51 86	98.30 32
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 22	92.91 26	91.28 24	96.95 20	97.36 27	93.66 28	89.23 26	93.33 25	83.71 31	90.53 26	86.84 28	90.39 25	93.30 25	91.56 36	93.74 109	97.43 53

HFP-MVS		92.02 23	92.13 28	91.89 22	97.16 18	96.46 44	93.57 29	87.60 29	93.79 24	88.17 19	93.15 16	83.94 43	91.19 24	90.81 53	89.83 68	93.66 115	96.94 71

train_agg		91.99 24	93.71 19	89.98 31	96.42 31	97.03 34	94.31 25	89.05 27	93.33 25	77.75 55	95.06 8	88.27 23	88.38 43	92.02 40	91.41 39	94.00 100	98.84 23

DeepC-MVS_fast	86.59 2	91.69 25	91.39 31	92.05 21	97.43 16	96.92 37	94.05 26	90.23 20	93.31 28	83.19 34	77.91 51	84.23 39	92.42 16	94.62 10	94.83 3	95.00 76	97.88 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + GP.		91.29 26	93.11 25	89.18 36	87.81 96	96.21 50	92.51 38	83.83 48	94.24 23	83.77 30	91.87 21	89.62 18	90.07 27	90.40 58	90.31 54	97.09 6	99.10 15

ACMMPR		91.15 27	91.44 30	90.81 26	96.61 25	96.25 48	93.09 30	87.08 32	93.32 27	84.78 27	92.08 20	82.10 48	89.71 30	90.24 59	89.82 69	93.61 120	96.30 95

DeepPCF-MVS	86.71 1	91.00 28	94.05 17	87.43 48	95.58 43	98.17 13	86.22 98	88.59 28	97.01 4	76.77 69	85.11 40	88.90 21	87.29 51	95.02 9	94.69 4	90.15 228	99.48 7

TSAR-MVS + ACMM		90.98 29	93.18 24	88.42 41	95.69 40	96.73 39	94.52 22	86.97 35	92.99 29	76.32 75	92.31 19	86.64 29	84.40 82	92.97 28	92.02 25	92.62 168	98.59 26

MP-MVS		90.81 30	91.45 29	90.06 30	96.59 26	96.33 47	92.46 39	87.19 31	90.27 45	82.54 39	91.38 22	84.88 36	88.27 44	90.58 56	89.30 81	93.30 143	97.44 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		90.57 31	90.68 33	90.44 28	96.13 33	95.90 56	92.77 36	86.86 36	92.12 35	84.19 28	89.18 32	82.37 46	89.43 33	89.65 74	88.43 97	93.27 144	97.13 63

MSLP-MVS++		90.33 32	88.82 43	92.10 20	96.52 29	95.93 52	94.35 24	86.26 37	88.37 60	89.24 16	75.94 59	82.60 45	89.71 30	89.45 80	92.17 21	96.51 19	97.24 58

CANet		89.98 33	90.42 38	89.47 35	94.13 52	98.05 18	91.76 44	83.27 52	90.87 42	81.90 42	72.32 67	84.82 37	88.42 41	94.52 11	93.78 10	97.34 4	98.58 27

PGM-MVS		89.97 34	90.64 35	89.18 36	96.53 28	95.90 56	93.06 32	82.48 60	90.04 47	80.37 45	92.75 18	80.96 53	88.93 37	89.88 68	89.08 86	93.69 113	95.86 107

PHI-MVS		89.88 35	92.75 27	86.52 57	94.97 45	97.57 24	89.99 56	84.56 44	92.52 33	69.72 128	90.35 28	87.11 27	84.89 72	91.82 42	92.37 19	95.02 75	97.51 49

CSCG		89.81 36	89.69 39	89.96 32	96.55 27	97.90 20	92.89 34	87.06 33	88.74 57	86.17 22	78.24 50	86.53 30	84.75 76	87.82 105	90.59 50	92.32 173	98.01 37

X-MVS		89.73 37	90.65 34	88.66 39	96.44 30	95.93 52	92.26 41	86.98 34	90.73 43	76.32 75	89.56 31	82.05 49	86.51 56	89.98 66	89.60 76	93.43 136	96.72 82

MVSMamba_PlusPlus		89.35 38	90.53 36	87.97 44	88.39 89	97.06 33	90.65 51	82.45 61	94.65 18	77.06 67	79.37 47	77.40 68	92.23 19	95.16 5	94.06 7	97.04 7	96.02 102

EPNet		89.30 39	90.89 32	87.44 47	95.67 41	96.81 38	91.13 47	83.12 54	91.14 39	76.31 79	87.60 34	80.40 57	84.45 79	92.13 37	91.12 44	93.96 101	97.01 67
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	84.14 3	88.80 40	88.03 49	89.71 34	94.83 46	96.56 40	92.57 37	89.38 25	89.25 53	79.59 48	70.02 75	77.05 70	88.24 45	92.44 33	92.79 14	93.65 118	98.10 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		88.76 41	90.43 37	86.81 53	96.04 35	96.53 43	92.95 33	85.95 39	90.36 44	67.93 134	85.80 39	80.69 54	83.82 89	90.81 53	91.85 32	94.18 93	96.99 68

3Dnovator+	81.14 5	88.59 42	87.49 52	89.88 33	95.83 38	96.45 46	91.94 43	82.41 62	87.09 66	85.94 24	62.80 119	85.37 34	89.46 32	91.51 45	91.89 30	93.72 110	97.30 56

ACMMP		88.48 43	88.71 44	88.22 43	94.61 49	95.53 62	90.64 52	85.60 41	90.97 40	78.62 51	89.88 30	74.20 84	86.29 58	88.16 102	86.37 124	93.57 122	95.86 107
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
AdaColmap		88.46 44	85.75 68	91.62 23	96.25 32	95.35 67	90.71 49	91.08 16	90.22 46	86.17 22	74.33 63	73.67 87	92.00 21	86.31 130	85.82 133	93.52 125	94.53 130

3Dnovator	80.58 8	88.20 45	86.53 58	90.15 29	96.86 22	96.46 44	91.97 42	83.06 55	85.16 71	83.66 32	62.28 127	82.15 47	88.98 35	90.99 50	92.65 15	96.38 26	96.03 100

CPTT-MVS		88.17 46	87.84 50	88.55 40	93.33 54	93.75 110	92.33 40	84.75 43	89.87 49	81.72 44	83.93 41	81.12 52	88.45 40	85.42 142	84.07 154	90.72 218	96.72 82

MVS_111021_HR		87.82 47	88.84 42	86.62 55	94.42 50	97.36 27	88.21 67	83.26 53	83.42 77	72.52 108	82.63 42	76.93 71	84.95 71	91.93 41	91.15 43	96.39 25	98.49 29

DELS-MVS		87.75 48	86.92 56	88.71 38	94.69 47	97.34 30	92.78 35	84.50 45	77.87 110	81.94 41	67.17 83	75.49 79	82.84 104	95.38 2	95.93 2	95.55 55	99.27 10
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
MVSTER		87.68 49	89.12 41	86.01 59	88.11 94	90.05 155	89.28 60	77.05 118	91.37 36	79.97 46	76.70 55	85.25 35	84.89 72	93.53 22	91.41 39	96.73 13	95.55 114

MVS_111021_LR		87.58 50	88.67 45	86.31 58	92.58 58	95.89 58	86.20 99	82.49 59	89.08 55	77.47 62	86.20 38	74.22 83	85.49 64	90.03 64	88.52 95	93.66 115	96.74 80

QAPM		87.06 51	86.46 59	87.75 45	96.63 24	97.09 31	91.71 45	82.62 58	80.58 94	71.28 114	66.04 92	84.24 38	87.01 52	89.93 67	89.91 65	97.26 5	97.44 51

PVSNet_BlendedMVS		86.98 52	87.05 54	86.90 50	93.03 55	96.98 35	86.57 88	81.82 64	89.78 50	82.78 37	71.54 69	66.07 126	80.73 125	93.46 23	91.97 26	96.45 22	99.53 5

PVSNet_Blended		86.98 52	87.05 54	86.90 50	93.03 55	96.98 35	86.57 88	81.82 64	89.78 50	82.78 37	71.54 69	66.07 126	80.73 125	93.46 23	91.97 26	96.45 22	99.53 5

ETV-MVS		86.94 54	89.49 40	83.95 90	87.28 103	95.61 61	83.58 140	76.37 125	92.59 32	73.20 100	80.35 45	76.42 74	87.38 50	92.20 36	90.45 52	95.90 40	98.83 24

SPE-MVS-test		86.72 55	88.35 46	84.83 74	91.78 64	96.03 51	81.71 151	76.71 119	91.19 38	77.12 66	77.64 53	75.63 78	87.59 49	90.82 52	89.11 84	94.06 98	97.99 39

CS-MVS		86.70 56	87.61 51	85.65 61	91.33 68	95.64 60	84.73 127	76.64 121	88.68 58	77.78 54	74.87 60	72.86 91	89.09 34	92.89 30	90.18 58	94.31 91	98.16 35

EC-MVSNet		86.42 57	88.31 47	84.20 85	86.61 125	94.08 99	86.20 99	72.18 162	89.06 56	76.02 80	74.48 62	80.47 56	88.90 38	92.03 39	90.07 61	95.30 63	98.00 38

OMC-MVS		86.38 58	86.21 64	86.57 56	92.30 60	94.35 92	87.60 72	83.51 51	92.32 34	77.37 63	72.27 68	77.83 62	86.59 55	87.62 110	85.95 130	92.08 177	93.11 160

HQP-MVS		86.17 59	87.35 53	84.80 75	91.41 67	92.37 130	91.05 48	84.35 47	88.52 59	64.21 141	87.05 37	68.91 107	84.80 74	89.12 83	88.16 102	92.96 158	97.31 55

sasdasda		85.93 60	86.26 62	85.54 64	88.94 81	95.44 63	89.56 57	76.01 129	87.83 61	77.70 56	76.43 56	68.66 109	87.80 47	87.02 117	91.51 37	93.25 145	96.95 69

canonicalmvs		85.93 60	86.26 62	85.54 64	88.94 81	95.44 63	89.56 57	76.01 129	87.83 61	77.70 56	76.43 56	68.66 109	87.80 47	87.02 117	91.51 37	93.25 145	96.95 69

MAR-MVS		85.65 62	86.30 61	84.88 73	95.51 44	95.89 58	86.50 91	76.71 119	89.23 54	68.59 131	70.93 73	74.49 81	88.55 39	89.40 81	90.30 55	93.42 137	93.88 148
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	82.38 4	85.52 63	84.41 73	86.81 53	91.51 66	96.23 49	90.27 53	89.81 23	77.87 110	70.67 124	69.20 77	77.86 60	85.55 63	85.92 136	86.38 123	93.03 155	97.43 53
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		85.43 64	84.24 76	86.83 52	87.69 99	93.16 121	90.01 55	82.72 57	87.17 65	79.28 50	71.43 72	65.81 129	86.02 59	87.33 113	86.96 117	95.25 69	97.83 44
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OpenMVS	77.91 11	85.09 65	83.42 80	87.03 49	96.12 34	96.55 42	89.36 59	81.59 66	79.19 104	75.20 89	55.84 168	79.04 59	84.45 79	88.47 96	89.35 80	95.48 58	95.48 115

MGCFI-Net		85.07 66	85.99 65	83.99 87	88.81 84	95.23 72	89.06 62	75.74 132	87.40 64	70.72 123	75.99 58	68.44 117	86.51 56	86.83 121	91.24 41	93.11 152	96.78 78

TSAR-MVS + COLMAP		84.93 67	85.79 67	83.92 91	90.90 70	93.57 114	89.25 61	82.00 63	91.29 37	61.66 150	88.25 33	59.46 172	86.71 54	89.79 69	87.09 114	93.01 156	91.09 184

TAPA-MVS	80.99 7	84.83 68	84.42 72	85.31 67	91.89 63	93.73 112	88.53 66	82.80 56	89.99 48	69.78 127	71.53 71	75.03 80	85.47 65	86.26 131	84.54 148	93.39 139	89.90 194
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	81.02 6	84.81 69	81.81 110	88.31 42	93.77 53	90.35 148	88.80 64	84.47 46	86.76 67	82.17 40	66.56 88	71.01 99	88.41 42	85.48 139	84.28 151	92.26 175	88.21 214
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		84.75 70	86.43 60	82.79 105	86.88 114	95.36 66	82.84 147	76.39 124	87.61 63	71.03 115	74.33 63	71.12 98	85.16 66	89.69 73	88.70 93	94.40 89	98.23 33

CNLPA		84.72 71	82.14 102	87.73 46	92.85 57	93.83 106	84.70 128	85.07 42	90.90 41	83.16 35	56.28 163	71.53 95	88.14 46	84.19 150	84.00 159	92.48 170	94.26 137

MVS_Test		84.60 72	85.13 71	83.99 87	88.17 92	95.27 71	88.21 67	73.15 153	84.30 74	70.55 125	68.67 81	68.78 108	86.99 53	91.71 44	91.90 28	96.84 12	95.27 120

E2		84.16 73	82.96 86	85.55 62	87.24 107	94.92 75	86.60 87	79.90 75	78.46 108	78.56 52	65.58 97	64.57 136	84.77 75	90.00 65	90.43 53	96.22 30	96.77 79

Casviewmamba		84.10 74	82.75 90	85.67 60	87.27 104	94.54 88	86.53 90	80.07 72	80.60 93	79.92 47	63.36 114	65.36 131	85.98 60	89.75 72	89.72 72	94.25 92	95.93 106

casdiffmvs_mvg		83.97 75	82.62 93	85.54 64	87.71 97	94.38 90	88.93 63	80.11 71	77.34 114	77.57 61	63.01 117	65.95 128	84.96 70	90.69 55	90.23 57	93.95 102	96.74 80
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs		83.84 76	82.65 92	85.22 69	87.25 106	94.62 84	86.01 105	79.62 80	79.48 101	77.59 60	61.92 130	64.34 140	85.57 62	90.55 57	90.51 51	95.26 67	97.14 62
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		83.83 77	84.38 74	83.18 104	86.65 121	94.59 86	85.79 111	73.78 150	85.83 69	72.94 101	69.28 76	70.80 101	83.45 95	86.80 122	87.59 109	96.47 21	95.77 111

diffmvs		83.69 78	83.17 84	84.31 81	85.45 141	93.92 100	86.89 77	78.62 92	82.71 83	75.95 81	66.78 87	63.90 143	83.84 88	87.90 104	89.16 82	95.10 72	97.82 45
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		83.64 79	82.24 100	85.27 68	87.13 108	94.82 78	86.47 92	79.81 76	76.49 122	77.69 59	64.03 107	63.90 143	84.40 82	89.49 78	90.26 56	96.12 31	96.68 85

hybridcas		83.63 80	81.98 104	85.55 62	87.09 109	94.43 89	86.68 83	79.77 77	78.10 109	79.32 49	61.40 133	64.87 133	84.99 69	89.59 76	89.40 78	95.46 60	96.08 99

hybridnocas07		83.51 81	82.86 88	84.26 83	85.51 140	93.82 107	85.90 110	78.82 91	83.91 75	77.18 65	67.15 84	64.53 138	83.24 100	85.43 141	88.30 99	94.90 79	96.92 73

hybrid		83.39 82	82.89 87	83.97 89	85.35 145	93.76 109	85.67 112	78.58 93	83.51 76	76.87 68	66.86 86	65.10 132	82.60 109	85.71 137	88.11 103	94.73 84	97.17 60

CANet_DTU		83.33 83	86.59 57	79.53 134	88.88 83	94.87 76	86.63 86	68.85 193	85.45 70	50.54 203	77.86 52	69.94 104	85.62 61	92.63 32	90.88 46	96.63 14	94.46 131

DI_MVS_pp		83.32 84	82.53 97	84.25 84	86.26 133	93.66 113	90.23 54	77.16 117	77.05 119	74.06 96	53.74 177	74.33 82	83.61 94	91.40 47	89.82 69	94.17 94	97.73 46

viewmanbaseed2359cas		83.27 85	82.21 101	84.51 79	87.27 104	94.83 77	86.41 93	79.61 81	77.03 120	73.99 97	63.66 110	63.85 145	84.06 85	88.94 86	90.63 49	95.72 53	96.56 88

viewdifsd2359ckpt09		83.21 86	81.85 108	84.79 76	86.60 126	94.61 85	86.12 102	79.22 84	76.41 123	76.76 70	64.54 101	62.66 155	85.00 68	89.79 69	88.69 94	95.03 74	96.29 96

viewmamba		83.12 87	82.57 95	83.76 95	85.45 141	93.77 108	85.29 116	78.87 88	84.43 73	75.48 84	65.83 94	64.57 136	83.33 98	84.73 147	87.97 104	94.16 95	96.68 85

onestephybrid01		83.11 88	82.62 93	83.69 97	85.53 137	93.84 105	85.06 123	78.84 89	82.40 85	77.70 56	65.60 95	65.49 130	81.53 117	85.34 143	87.83 108	93.48 132	97.84 43

diffmvs_AUTHOR		83.09 89	82.28 99	84.04 86	85.22 148	93.85 104	86.75 79	78.41 96	79.81 99	75.32 86	64.61 100	63.57 147	83.62 93	87.60 111	88.86 92	94.93 78	97.68 47

E3new		82.99 90	81.31 114	84.95 71	86.95 112	94.63 82	86.33 95	79.69 78	73.85 142	76.69 71	62.37 125	63.02 151	84.04 86	88.73 92	90.04 63	95.99 38	96.53 90

E3		82.98 91	81.31 114	84.92 72	86.95 112	94.63 82	86.32 96	79.69 78	73.86 141	76.54 73	62.35 126	63.05 150	84.01 87	88.73 92	90.03 64	95.99 38	96.52 91

viewdifsd2359ckpt13		82.93 92	81.75 113	84.30 82	87.00 111	94.76 79	85.59 114	79.57 82	76.32 125	74.15 93	62.74 121	62.67 153	84.44 81	89.49 78	90.15 59	95.06 73	96.13 98

baseline1		82.63 93	82.02 103	83.34 102	88.30 91	91.89 134	88.03 70	80.86 68	75.05 130	65.96 136	64.27 104	72.20 93	80.01 129	91.32 48	89.56 77	96.90 11	89.85 195

PVSNet_Blended_VisFu		82.55 94	83.70 79	81.21 118	89.66 74	95.15 74	82.41 148	77.36 116	72.53 152	73.64 98	61.15 135	77.19 69	70.35 190	91.31 49	89.72 72	93.84 105	98.85 22

ET-MVSNet_ETH3D		82.37 95	85.68 69	78.51 144	62.90 254	94.66 80	87.06 74	73.57 151	83.13 79	61.52 152	78.37 49	76.01 76	89.99 28	84.14 151	89.03 87	96.03 36	94.42 132

PMMVS		82.26 96	85.48 70	78.51 144	85.92 136	91.92 133	78.30 183	70.77 170	86.30 68	61.11 154	82.46 43	70.88 100	84.70 77	88.05 103	84.78 143	90.24 227	93.98 141

E5new		82.25 97	80.16 121	84.68 77	86.67 117	94.33 93	86.64 84	79.95 73	70.44 160	75.30 87	60.18 141	62.15 156	83.73 90	87.82 105	89.87 66	95.80 46	96.32 92

E5		82.25 97	80.16 121	84.68 77	86.67 117	94.33 93	86.64 84	79.95 73	70.44 160	75.30 87	60.18 141	62.15 156	83.73 90	87.82 105	89.87 66	95.80 46	96.32 92

ACMP	79.58 9	82.23 99	81.82 109	82.71 106	88.15 93	90.95 144	85.23 119	78.52 95	81.70 86	72.52 108	78.41 48	60.63 167	80.48 127	82.88 164	83.44 164	91.37 196	94.70 127
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewmambaseed2359dif		82.18 100	80.85 117	83.72 96	85.36 144	93.20 120	86.29 97	77.89 105	77.11 118	76.48 74	62.40 123	63.42 148	83.28 99	84.01 153	87.92 105	93.04 154	97.91 40

CHOSEN 280x420		82.15 101	85.87 66	77.80 149	86.54 128	93.42 116	81.74 150	59.96 240	78.99 106	63.99 142	74.50 61	83.95 42	80.99 120	89.53 77	85.01 138	93.56 124	95.71 113

LGP-MVS_train		82.12 102	82.57 95	81.59 112	89.26 78	90.23 151	88.76 65	78.05 97	81.26 89	61.64 151	79.52 46	62.11 160	79.59 133	85.20 144	84.68 145	92.27 174	95.02 124

E4		82.02 103	79.99 129	84.39 80	86.67 117	94.32 95	86.01 105	79.43 83	69.96 167	75.10 90	59.77 144	62.13 158	83.38 96	87.74 109	89.71 74	95.77 51	96.31 94

viewdifsd2359ckpt07		81.95 104	80.38 120	83.79 94	86.81 115	94.23 96	84.62 129	79.22 84	71.88 154	75.48 84	61.13 136	62.70 152	81.05 119	88.84 88	89.15 83	95.57 54	94.70 127

FMVSNet3		81.93 105	81.98 104	81.88 111	79.49 185	87.02 172	88.15 69	72.57 156	83.02 80	72.63 105	56.55 159	73.48 88	82.34 114	91.49 46	91.20 42	96.07 32	91.13 183

test2506		81.91 106	81.78 112	82.06 110	89.09 79	95.32 68	84.61 131	77.54 110	74.61 134	68.77 130	63.80 109	67.53 120	77.09 142	90.19 61	89.01 88	95.27 64	92.00 175

dtuplus		81.70 107	80.04 125	83.63 100	85.25 147	93.26 119	85.98 107	78.03 98	73.89 140	76.64 72	60.83 139	63.39 149	83.12 102	83.91 157	87.41 110	92.77 164	97.63 48

thisisatest0530		81.67 108	84.27 75	78.63 140	85.53 137	93.88 103	81.77 149	73.84 147	81.35 88	63.85 144	68.79 79	77.64 64	73.02 171	88.73 92	85.73 134	93.76 108	93.80 152

viewmacassd2359aftdt		81.60 109	79.90 131	83.58 101	86.67 117	94.36 91	86.02 104	79.17 86	70.40 162	71.64 112	58.95 148	62.12 159	82.55 111	87.08 116	90.14 60	95.41 62	96.24 97

tttt0517		81.51 110	84.12 78	78.47 146	85.33 146	93.74 111	81.42 154	73.84 147	81.21 90	63.59 145	68.73 80	77.46 67	73.02 171	88.47 96	85.73 134	93.63 119	93.49 156

E6new		81.43 111	79.49 134	83.69 97	86.62 123	94.23 96	84.87 124	77.93 103	69.39 172	74.14 94	59.07 146	61.48 161	82.80 106	87.23 114	89.01 88	95.80 46	96.01 103

E6		81.43 111	79.49 134	83.69 97	86.62 123	94.23 96	84.87 124	77.93 103	69.39 172	74.14 94	59.07 146	61.48 161	82.80 106	87.23 114	89.01 88	95.80 46	96.01 103

FA-MVS(training)		81.41 113	81.98 104	80.76 127	87.58 100	94.59 86	83.09 142	61.18 237	79.80 100	74.74 91	58.46 151	69.76 105	82.12 115	88.90 87	87.00 115	95.83 44	95.33 117

OPM-MVS		81.34 114	78.18 143	85.02 70	91.27 69	91.78 135	90.66 50	83.62 50	62.39 193	65.91 137	63.35 115	64.33 141	85.03 67	87.77 108	85.88 132	93.66 115	91.75 179
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		81.21 115	83.36 83	78.70 138	83.22 163	92.71 123	80.32 163	74.25 146	80.39 96	63.94 143	68.89 78	68.44 117	74.67 157	89.61 75	86.68 121	95.83 44	96.81 77

IS_MVSNet		80.92 116	84.14 77	77.16 153	87.43 101	93.90 102	80.44 159	74.64 140	75.05 130	61.10 155	65.59 96	76.89 72	67.39 206	90.88 51	90.05 62	91.95 182	96.62 87

ACMM	78.09 10	80.91 117	78.39 140	83.86 92	89.61 77	87.71 169	85.16 120	80.67 70	79.04 105	74.18 92	63.82 108	60.84 166	82.59 110	84.33 148	83.59 162	90.96 212	89.39 200
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		80.82 118	82.79 89	78.52 142	86.31 132	92.37 130	79.83 166	74.51 141	73.79 144	64.46 140	67.01 85	80.63 55	74.33 160	85.63 138	84.35 150	91.68 189	95.79 110

CostFormer		80.72 119	81.81 110	79.44 136	86.50 129	91.65 136	84.31 133	59.84 241	80.86 91	72.69 103	62.46 122	73.74 85	79.93 130	82.58 169	84.50 149	93.37 140	96.90 75

GBi-Net		80.72 119	80.49 118	81.00 123	78.18 189	86.19 186	86.73 80	72.57 156	83.02 80	72.63 105	56.55 159	73.48 88	80.99 120	86.57 124	86.83 118	94.89 80	90.77 187

test1		80.72 119	80.49 118	81.00 123	78.18 189	86.19 186	86.73 80	72.57 156	83.02 80	72.63 105	56.55 159	73.48 88	80.99 120	86.57 124	86.83 118	94.89 80	90.77 187

UGNet		80.71 122	83.09 85	77.93 148	87.02 110	92.71 123	80.28 164	76.53 122	73.83 143	71.35 113	70.07 74	73.71 86	58.93 227	87.39 112	86.97 116	93.48 132	96.94 71
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
0.3-1-1-0.015		80.56 123	80.14 123	81.04 122	76.03 208	91.03 143	86.78 78	76.11 127	80.64 92	70.88 116	62.86 118	68.56 111	82.79 108	80.60 189	84.02 158	93.67 114	93.30 158

0.4-1-1-0.2		80.56 123	80.09 124	81.10 120	76.02 209	91.04 141	86.90 76	76.23 126	80.57 95	70.87 120	62.39 124	68.47 115	82.82 105	80.69 188	84.19 152	93.72 110	93.32 157

0.4-1-1-0.1		80.27 125	79.82 133	80.80 126	75.96 211	90.95 144	86.41 93	75.70 133	80.30 97	70.74 122	61.89 131	68.45 116	82.38 113	80.37 193	83.53 163	93.60 121	93.22 159

CHOSEN 1792x2688		80.23 126	79.16 137	81.48 114	91.97 61	96.56 40	86.18 101	75.40 136	76.17 126	61.32 153	37.43 247	61.08 165	76.52 148	92.35 34	91.64 34	97.46 3	98.86 21

casdiffseed414692147		79.95 127	77.08 152	83.29 103	86.42 131	93.30 118	85.12 121	77.72 106	69.61 170	73.32 99	52.68 183	56.35 186	83.20 101	84.96 145	87.92 105	93.95 102	94.75 125

thres100view900		79.83 128	77.79 147	82.21 107	88.42 87	93.54 115	87.07 73	81.11 67	70.15 163	61.01 156	56.65 157	51.22 194	81.78 116	89.77 71	85.95 130	93.84 105	97.26 57

Effi-MVS+		79.80 129	80.04 125	79.52 135	85.53 137	93.31 117	85.28 117	70.68 172	74.15 136	58.79 165	62.03 129	60.51 168	83.37 97	88.41 98	86.09 129	93.49 131	95.80 109

ECVR-MVS		79.76 130	78.27 141	81.50 113	89.09 79	95.32 68	84.61 131	77.54 110	74.61 134	65.38 138	50.22 191	56.31 187	77.09 142	90.19 61	89.01 88	95.27 64	92.25 169

DCV-MVSNet		79.76 130	79.17 136	80.44 130	84.65 152	84.51 211	84.20 134	72.36 161	75.17 129	70.81 121	66.21 91	66.56 123	80.99 120	82.89 163	84.56 147	89.65 233	94.30 136

FC-MVSNet-train		79.54 132	78.20 142	81.09 121	86.55 127	88.63 164	79.96 165	78.53 94	70.90 158	68.24 132	65.87 93	56.45 185	80.29 128	86.20 134	84.08 153	92.97 157	95.31 119

test-LLR		79.52 133	83.42 80	74.97 162	81.79 168	91.26 137	76.17 204	70.57 173	77.71 112	52.14 188	66.26 89	77.47 65	73.10 167	87.02 117	87.16 112	96.05 34	97.02 65

FMVSNet2		79.24 134	78.14 144	80.53 129	78.18 189	86.19 186	86.73 80	71.91 163	72.97 147	70.48 126	50.63 189	66.55 124	80.99 120	90.10 63	89.77 71	94.89 80	90.77 187

TESTMET0.1,1		79.15 135	83.42 80	74.18 169	79.81 183	91.26 137	76.17 204	67.83 207	77.71 112	52.14 188	66.26 89	77.47 65	73.10 167	87.02 117	87.16 112	96.05 34	97.02 65

tfpn200view9		79.05 136	77.21 151	81.18 119	88.42 87	92.55 128	85.12 121	77.94 100	70.15 163	61.01 156	56.65 157	51.22 194	81.11 118	88.23 99	84.80 142	93.50 130	96.90 75

test1111		78.99 137	77.77 148	80.42 131	88.64 85	95.31 70	83.39 141	77.67 108	72.76 150	61.91 148	49.58 194	55.59 189	75.67 153	90.23 60	89.09 85	95.23 70	91.83 178

viewdifsd2359ckpt11		78.83 138	76.68 156	81.33 116	84.03 160	90.13 153	80.89 157	77.43 114	70.01 165	75.72 82	60.97 137	59.03 177	79.67 131	79.81 198	81.58 187	90.25 225	95.22 121

viewmsd2359difaftdt		78.82 139	76.68 156	81.33 116	84.03 160	90.13 153	80.89 157	77.43 114	70.00 166	75.68 83	60.97 137	59.01 178	79.67 131	79.82 197	81.58 187	90.25 225	95.22 121

PatchMatch-RL		78.75 140	76.47 161	81.41 115	88.53 86	91.10 139	78.09 184	77.51 113	77.33 115	71.98 110	64.38 103	48.10 212	82.55 111	84.06 152	82.35 174	89.78 230	87.97 216

LS3D		78.72 141	75.79 167	82.15 108	91.91 62	89.39 160	83.66 138	85.88 40	76.81 121	59.22 164	57.67 154	58.53 179	83.72 92	82.07 174	81.63 185	88.50 241	84.39 228

thres200		78.69 142	76.71 155	80.99 125	88.35 90	92.56 126	86.03 103	77.94 100	66.27 178	60.66 158	56.08 164	51.11 196	79.45 134	88.23 99	85.54 137	93.52 125	97.20 59

Anonymous20231211		78.61 143	75.57 170	82.15 108	84.43 156	90.26 149	84.08 136	77.68 107	71.09 156	72.90 102	39.24 241	66.21 125	84.23 84	82.15 172	84.04 155	89.61 234	96.03 100

IB-MVS	74.10 12	78.52 144	78.51 139	78.52 142	90.15 72	95.39 65	71.95 230	77.53 112	74.95 132	77.25 64	58.93 149	55.92 188	58.37 229	79.01 204	87.89 107	95.88 42	97.47 50
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
EPNet_dtu		78.49 145	81.96 107	74.45 168	92.57 59	88.74 163	82.98 143	78.83 90	83.28 78	44.64 234	77.40 54	67.73 119	53.98 239	85.44 140	84.91 139	93.71 112	86.22 223
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres400		78.39 146	76.39 162	80.73 128	88.02 95	92.94 122	84.77 126	78.88 87	65.20 186	59.70 162	55.20 171	50.85 197	79.45 134	88.81 89	84.81 141	93.57 122	96.91 74

UA-Net		78.30 147	80.92 116	75.25 161	87.42 102	92.48 129	79.54 169	75.49 135	60.47 197	60.52 159	68.44 82	84.08 41	57.54 231	88.54 95	88.45 96	90.96 212	83.97 230

Vis-MVSNet (Re-imp)		78.28 148	82.68 91	73.16 181	86.64 122	92.68 125	78.07 185	74.48 142	74.05 137	53.47 176	64.22 105	76.52 73	54.28 235	88.96 85	88.29 100	92.03 179	94.00 140

MSDG		78.11 149	73.17 185	83.86 92	91.78 64	86.83 174	85.25 118	86.02 38	72.84 149	69.69 129	51.43 185	54.00 191	77.61 138	81.95 177	82.27 176	92.83 163	82.91 235

HyFIR lowres test		78.08 150	76.81 153	79.56 133	90.77 71	94.64 81	82.97 144	69.85 183	69.81 169	59.53 163	33.52 255	64.66 134	78.97 136	88.77 91	88.38 98	95.27 64	97.86 42

GeoE		78.04 151	77.52 150	78.65 139	84.51 154	90.84 146	80.94 156	69.24 191	72.86 148	66.06 135	53.45 178	60.46 169	77.37 139	84.20 149	84.85 140	93.78 107	96.00 105

test-mter		77.90 152	82.44 98	72.60 187	78.52 187	90.24 150	73.85 223	65.31 223	76.37 124	51.29 194	65.58 97	75.94 77	71.36 181	85.98 135	86.26 125	95.26 67	96.71 84

thres600view7		77.66 153	75.67 168	79.98 132	87.71 97	92.56 126	83.79 137	77.94 100	64.41 188	58.69 166	54.32 176	50.54 199	78.23 137	88.23 99	83.06 167	93.52 125	96.55 89

MS-PatchMatch		77.47 154	76.48 160	78.63 140	89.89 73	90.42 147	85.42 115	69.53 187	70.79 159	60.43 160	50.05 192	70.62 103	70.66 187	86.71 123	82.54 171	95.86 43	84.23 229

Fast-Effi-MVS+		77.37 155	76.68 156	78.17 147	82.84 165	89.94 156	81.47 153	68.01 202	72.99 146	60.26 161	55.07 172	53.20 192	82.99 103	86.47 129	86.12 128	93.46 134	92.98 163

dmvs_re		77.25 156	75.86 165	78.86 137	81.08 174	89.36 161	84.15 135	80.73 69	73.02 145	55.58 172	58.33 152	48.97 208	75.32 155	83.92 156	86.25 126	96.29 29	91.20 182

Vis-MVSNet		77.24 157	79.99 129	74.02 171	84.62 153	93.92 100	80.33 162	72.55 159	62.58 192	55.25 174	64.45 102	69.49 106	57.00 233	88.78 90	88.21 101	94.36 90	92.54 166
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MDTV_nov1_ep13		77.20 158	80.04 125	73.90 173	82.22 166	90.14 152	79.25 173	61.52 235	78.63 107	56.98 167	65.52 99	72.80 92	73.05 169	80.93 185	83.20 165	90.36 222	89.05 203

EPMVS		77.16 159	79.08 138	74.92 163	86.73 116	91.98 132	78.62 178	55.44 249	79.43 102	56.59 169	61.24 134	70.73 102	76.97 145	80.59 190	81.43 193	95.15 71	88.17 215

tpm cat1		76.93 160	76.19 164	77.79 150	85.08 151	88.58 165	82.96 145	59.33 242	75.72 128	72.64 104	51.25 186	64.41 139	75.74 152	77.90 212	80.10 209	90.97 211	95.35 116

PatchmatchNet		76.85 161	80.03 128	73.15 182	84.08 158	91.04 141	77.76 189	55.85 248	79.43 102	52.74 182	62.08 128	76.02 75	74.56 158	79.92 196	81.41 194	93.92 104	90.29 192
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		76.80 162	76.33 163	77.35 152	84.07 159	84.11 212	81.54 152	68.52 195	66.17 179	61.74 149	57.84 153	64.31 142	74.88 156	83.48 160	86.21 127	93.34 142	92.16 171
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blend_shiyan4		76.72 163	75.85 166	77.73 151	76.42 206	82.48 222	87.78 71	70.39 176	81.47 87	70.88 116	63.45 111	68.56 111	69.59 193	73.85 230	72.21 239	91.32 197	88.93 205

CDS-MVSNet		76.57 164	76.78 154	76.32 156	80.94 176	89.75 157	82.94 146	72.64 155	59.01 203	62.95 147	58.60 150	62.67 153	66.91 208	86.26 131	87.20 111	91.57 191	93.97 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		76.41 165	79.90 131	72.35 191	84.26 157	85.24 201	75.57 211	54.56 251	79.95 98	52.72 183	64.22 105	77.84 61	73.73 164	80.48 191	81.37 195	93.25 145	90.20 193

tpmrst		76.27 166	77.65 149	74.66 165	86.13 135	89.53 159	79.31 172	54.91 250	77.19 117	56.27 170	55.87 167	64.58 135	77.25 140	80.85 186	80.21 206	94.07 97	95.32 118

dps		75.76 167	75.02 172	76.63 155	84.51 154	88.12 166	77.51 190	58.33 244	75.91 127	71.98 110	57.37 155	57.85 180	76.81 147	77.89 213	78.40 218	90.63 219	89.63 197

CR-MVSNet		74.84 168	77.91 145	71.26 205	81.77 170	85.52 197	78.32 181	54.14 253	74.05 137	51.09 197	50.00 193	71.38 97	70.77 185	86.48 127	84.03 156	91.46 195	93.92 145

Effi-MVS+-dtu		74.57 169	74.60 176	74.53 166	81.38 172	86.74 176	80.39 161	67.70 208	67.36 177	53.06 178	59.86 143	57.50 181	75.84 151	80.19 194	78.62 216	88.79 240	91.95 177

dtuonly		74.50 170	74.47 178	74.53 166	77.49 195	85.14 203	81.27 155	67.90 205	67.39 176	53.07 177	50.95 188	59.33 173	75.45 154	82.73 166	82.83 169	91.98 181	92.94 164

RPSCF		74.27 171	73.24 184	75.48 160	81.01 175	80.18 242	76.24 203	72.37 160	74.84 133	68.24 132	72.47 66	67.39 121	73.89 161	71.05 246	69.38 255	81.14 263	77.37 250

FMVSNet1		74.26 172	71.95 192	76.95 154	74.28 226	83.94 214	83.61 139	69.99 177	57.08 209	65.08 139	42.39 230	57.41 182	76.98 144	86.57 124	86.83 118	91.77 188	89.42 198

GA-MVS		73.62 173	74.52 177	72.58 188	79.93 181	89.29 162	78.02 186	71.67 166	60.79 196	42.68 239	54.41 175	49.07 207	70.07 191	89.39 82	86.55 122	93.13 151	92.12 172

Fast-Effi-MVS+-dtu		73.56 174	75.32 171	71.50 201	80.35 178	86.83 174	79.72 167	58.07 245	67.64 175	44.83 231	60.28 140	54.07 190	73.59 166	81.90 179	82.30 175	92.46 171	94.18 138

tpm		73.50 175	74.85 173	71.93 195	83.19 164	86.84 173	78.61 179	55.91 247	65.64 181	48.90 210	56.30 162	61.09 164	72.31 173	79.10 203	80.61 205	92.68 166	94.35 135

RPMNet		73.46 176	77.85 146	68.34 219	81.71 171	85.52 197	73.83 224	50.54 261	74.05 137	46.10 225	53.03 181	71.91 94	66.31 210	83.55 158	82.18 178	91.55 193	94.71 126

USDC		73.43 177	72.31 188	74.73 164	80.86 177	86.21 184	80.42 160	71.83 165	71.69 155	46.94 218	59.60 145	42.58 234	76.47 149	82.66 168	81.22 198	91.88 184	82.24 241

pmmvs4		73.38 178	71.53 195	75.55 159	75.95 212	85.24 201	77.25 194	71.59 167	71.03 157	63.10 146	49.09 199	44.22 224	73.73 164	82.04 175	80.18 207	91.68 189	88.89 207

usedtu_dtu_shiyan1		73.19 179	73.51 183	72.82 183	67.62 245	88.00 168	78.54 180	74.77 138	69.96 167	51.51 193	46.24 206	52.09 193	69.99 192	86.25 133	84.58 146	94.46 88	87.44 218

UniMVSNet_NR-MVSNet		73.11 180	72.59 186	73.71 176	76.90 199	86.58 180	77.01 195	75.82 131	65.59 182	48.82 211	50.97 187	48.42 210	71.61 177	79.19 202	83.03 168	92.11 176	94.37 133

usedtu_blend_shiyan5		73.04 181	72.10 190	74.14 170	56.36 256	82.07 224	86.93 75	69.94 178	56.27 212	70.88 116	63.45 111	68.56 111	69.59 193	73.35 232	72.06 241	91.17 202	88.93 205

FMVSNet5		72.83 182	73.89 181	71.59 199	67.42 246	76.28 252	75.88 208	63.74 228	77.27 116	54.59 175	53.32 179	71.48 96	73.85 162	81.95 177	81.69 183	94.06 98	75.20 256

PatchT		72.66 183	76.58 159	68.09 221	79.02 186	86.09 190	59.81 255	51.78 259	72.00 153	51.09 197	46.84 204	66.70 122	70.77 185	86.48 127	84.03 156	96.07 32	93.92 145

ACMH	71.22 14	72.65 184	70.13 200	75.59 158	86.19 134	86.14 189	75.76 209	77.63 109	54.79 223	46.16 224	53.28 180	47.28 214	77.24 141	78.91 205	81.18 199	90.57 220	89.33 201
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		72.43 185	74.05 179	70.55 209	80.34 179	81.17 236	77.44 191	61.00 239	63.57 191	46.82 220	55.88 166	59.09 176	65.03 212	83.15 161	83.83 160	92.67 167	91.65 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH+	72.14 13	72.38 186	69.34 207	75.93 157	85.21 149	84.89 206	76.96 198	76.04 128	59.76 198	51.63 192	50.37 190	48.69 209	76.90 146	76.06 222	78.69 214	88.85 239	86.90 221

DU-MVS		72.19 187	71.35 196	73.17 180	75.95 212	86.02 191	77.01 195	74.42 143	65.39 184	48.82 211	49.10 197	42.81 232	71.61 177	78.67 206	83.10 166	91.22 200	94.37 133

IterMVS-SCA-FT		72.18 188	73.96 180	70.11 211	80.15 180	81.11 237	77.42 192	61.09 238	63.67 190	46.73 221	55.77 169	59.15 175	63.95 216	82.83 165	83.70 161	91.31 198	91.49 181

UniMVSNet (Re)		72.12 189	72.28 189	71.93 195	76.77 200	87.38 171	75.73 210	73.51 152	65.76 180	50.24 205	48.65 200	46.49 215	63.85 217	80.10 195	82.47 172	91.49 194	95.13 123

ADS-MVSNet		72.11 190	73.72 182	70.24 210	81.24 173	86.59 179	74.75 219	50.56 260	72.58 151	49.17 208	55.40 170	61.46 163	73.80 163	76.01 223	78.14 219	91.93 183	85.86 224

FE-MVSNET3		72.10 191	72.04 191	72.18 192	56.36 256	82.07 224	75.15 212	69.94 178	56.27 212	70.88 116	63.45 111	68.56 111	69.59 193	73.35 232	72.06 241	91.17 202	88.50 211

gg-mvs-nofinetune		72.10 191	74.79 174	68.97 214	83.31 162	95.22 73	85.66 113	48.77 262	35.68 264	22.17 273	30.49 259	77.73 63	76.37 150	94.30 14	93.03 12	97.55 2	97.05 64

TAMVS		72.06 193	71.76 194	72.41 190	76.68 201	88.12 166	74.82 216	68.09 200	53.52 228	56.91 168	52.94 182	56.93 184	66.91 208	81.37 182	82.44 173	91.07 208	86.99 220

v2v482		71.73 194	69.80 202	73.99 172	75.88 216	86.66 178	79.58 168	71.90 164	57.58 207	50.41 204	45.35 209	43.24 230	73.05 169	79.69 199	82.18 178	93.08 153	93.87 149

test0.0.03 1		71.70 195	74.68 175	68.23 220	81.79 168	83.81 215	68.64 234	70.57 173	68.81 174	43.47 236	62.77 120	60.09 171	51.77 248	82.48 170	81.67 184	93.16 149	83.13 233

V42		71.58 196	70.11 201	73.30 179	75.66 219	86.68 177	79.17 175	69.92 182	59.29 202	52.80 181	44.36 213	45.66 218	68.83 196	79.48 201	81.49 190	93.44 135	93.82 151

NR-MVSNet		71.47 197	71.11 197	71.90 197	77.73 194	86.02 191	76.88 199	74.42 143	65.39 184	46.09 226	49.10 197	39.87 247	64.27 215	81.40 181	82.24 177	91.99 180	93.75 153

v8		71.42 198	69.69 203	73.43 178	76.45 204	85.12 205	79.53 170	67.47 211	59.34 201	52.90 180	44.60 211	45.82 217	71.05 183	79.56 200	81.45 192	93.17 148	91.96 176

TranMVSNet+NR-MVSNet		71.12 199	70.24 199	72.15 193	76.01 210	84.80 208	76.55 201	75.65 134	61.99 194	45.29 229	48.42 201	43.07 231	67.55 204	78.28 209	82.83 169	91.85 185	92.29 167

v10		70.97 200	69.44 204	72.75 184	75.90 215	84.58 210	79.43 171	66.45 216	58.07 205	49.93 206	43.87 219	43.68 225	71.91 175	82.04 175	81.70 182	92.89 161	92.11 173

v1144		70.93 201	69.42 206	72.70 185	75.48 220	86.26 182	79.22 174	69.39 189	55.61 220	48.05 216	43.47 222	42.55 235	71.51 179	82.11 173	81.74 181	92.56 169	94.17 139

thisisatest0515		70.62 202	71.94 193	69.07 213	76.48 203	85.59 196	68.03 235	68.02 201	59.70 199	52.94 179	52.19 184	50.36 200	58.10 230	83.15 161	81.63 185	90.87 215	90.99 185

Baseline_NR-MVSNet		70.61 203	68.87 210	72.65 186	75.95 212	80.49 240	75.92 207	74.75 139	65.10 187	48.78 213	41.28 236	44.28 223	68.45 197	78.67 206	79.64 210	92.04 178	92.62 165

v148		70.34 204	68.46 213	72.54 189	76.04 207	86.38 181	74.83 215	72.73 154	55.88 219	55.26 173	43.32 225	43.49 226	64.52 214	76.93 220	80.11 208	91.85 185	93.11 160

v1192		70.32 205	68.77 211	72.12 194	74.76 222	85.62 195	78.73 176	68.53 194	55.08 222	46.34 223	42.39 230	40.67 242	71.90 176	82.27 171	81.53 189	92.43 172	93.86 150

v144192		70.10 206	68.55 212	71.90 197	74.55 223	85.67 194	77.81 187	68.22 199	54.65 224	46.91 219	42.76 228	41.27 239	70.95 184	80.48 191	81.11 203	92.96 158	93.90 147

pmmvs5		70.01 207	69.31 208	70.82 208	75.80 218	86.26 182	72.94 225	67.91 203	53.84 227	47.22 217	47.31 203	41.47 238	67.61 203	83.93 155	81.93 180	93.42 137	90.42 191

COLMAP_ROB	66.31 15	69.91 208	66.61 218	73.76 174	86.44 130	82.76 219	76.59 200	76.46 123	63.82 189	50.92 201	45.60 208	49.13 206	65.87 211	74.96 228	74.45 236	86.30 252	75.57 255
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1921920		69.85 209	68.38 214	71.58 200	74.35 224	85.39 199	77.78 188	67.88 206	54.64 225	45.39 228	42.11 233	39.97 246	71.10 182	81.68 180	81.17 201	92.96 158	93.69 155

pm-mvs1		69.62 210	68.07 216	71.44 202	77.21 197	85.32 200	76.11 206	71.05 168	46.55 250	51.17 196	41.83 234	48.20 211	61.81 223	84.00 154	81.14 202	91.28 199	89.42 198

UniMVSNet_ETH3D		69.49 211	65.86 225	73.72 175	76.51 202	85.88 193	78.65 177	70.52 175	48.08 247	55.71 171	37.64 244	40.56 243	71.38 180	75.05 227	81.49 190	89.57 236	92.29 167

tfpnnormal		69.29 212	65.58 226	73.62 177	79.87 182	84.82 207	76.97 197	75.12 137	45.29 251	49.03 209	35.57 251	37.20 255	68.02 201	82.70 167	81.24 197	92.69 165	92.20 170

v1240		69.28 213	67.82 217	71.00 207	74.09 228	85.13 204	76.54 202	67.28 213	53.17 230	44.70 232	41.55 235	39.38 248	70.51 189	81.29 183	81.18 199	92.88 162	93.02 162

CVMVSNet		68.95 214	70.79 198	66.79 228	79.69 184	83.75 216	72.05 229	70.90 169	56.20 215	36.30 254	54.94 174	59.22 174	54.03 238	78.33 208	78.65 215	87.77 247	84.44 227

MIMVSNet		68.66 215	69.43 205	67.76 222	64.92 250	84.68 209	74.16 220	54.10 255	60.85 195	51.27 195	39.47 240	49.48 201	67.48 205	84.86 146	85.57 136	94.63 85	81.10 242

TDRefinement		67.82 216	64.91 232	71.22 206	82.08 167	81.45 231	77.42 192	73.79 149	59.62 200	48.35 215	42.35 232	42.40 236	60.87 225	74.69 229	74.64 235	84.83 257	79.20 247

wanda-best-256-512		67.61 217	66.46 221	68.94 215	56.36 256	82.07 224	75.15 212	69.94 178	56.27 212	52.66 184	43.54 220	49.41 202	68.38 198	73.35 232	72.06 241	91.17 202	88.53 209

FE-blended-shiyan7		67.61 217	66.46 221	68.94 215	56.36 256	82.07 224	75.15 212	69.94 178	56.28 211	52.66 184	43.54 220	49.41 202	68.38 198	73.35 232	72.06 241	91.17 202	88.53 209

anonymousdsp		67.61 217	68.94 209	66.04 229	71.44 240	83.97 213	66.45 239	63.53 230	50.54 239	42.42 240	49.39 195	45.63 219	62.84 220	77.99 211	81.34 196	89.59 235	93.75 153

blended_shiyan8		67.43 220	66.30 224	68.74 217	56.30 261	82.00 228	74.80 217	69.62 185	55.94 216	52.60 186	43.24 226	49.40 204	68.00 202	73.19 238	71.88 246	91.09 207	88.46 213

blended_shiyan6		67.43 220	66.32 223	68.72 218	56.29 262	81.99 229	74.78 218	69.62 185	55.89 218	52.55 187	43.36 223	49.38 205	68.03 200	73.20 237	71.89 245	91.07 208	88.50 211

TinyColmap		67.16 222	63.51 239	71.42 203	77.94 192	79.54 246	72.80 226	69.78 184	56.58 210	45.52 227	44.53 212	33.53 262	74.45 159	76.91 221	77.06 226	88.03 246	76.41 251

FC-MVSNet-test		67.04 223	72.47 187	60.70 247	76.92 198	81.41 232	61.52 251	69.45 188	65.58 183	26.74 268	61.79 132	60.40 170	41.17 258	77.60 216	77.78 222	88.41 242	82.70 237

gbinet_0.2-2-1-0.02		67.03 224	66.53 220	67.63 223	54.59 264	81.34 235	73.95 221	69.35 190	53.34 229	51.93 190	42.82 227	50.76 198	64.78 213	73.34 236	72.07 240	91.16 206	92.01 174

TransMVSNet (Re)		66.87 225	64.30 234	69.88 212	78.32 188	81.35 234	73.88 222	74.34 145	43.19 256	45.20 230	40.12 238	42.37 237	55.97 234	80.85 186	79.15 211	91.56 192	83.06 234

CMPMVS	50.59 17	66.74 226	62.72 243	71.42 203	85.40 143	89.72 158	72.69 227	70.72 171	51.24 235	51.75 191	38.91 242	44.40 221	63.74 218	70.84 248	71.52 248	84.19 258	72.45 260
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 227	65.51 227	67.51 224	71.63 239	83.10 217	70.89 233	65.02 224	50.13 242	44.68 233	39.59 239	38.77 249	62.57 221	77.59 217	78.91 212	90.29 224	90.44 190

EG-PatchMatch MVS		66.23 228	65.20 229	67.43 225	77.74 193	86.20 185	72.51 228	63.68 229	43.95 254	43.44 237	36.22 250	45.43 220	54.04 237	81.00 184	80.95 204	93.15 150	82.67 238

WR-MVS		64.98 229	66.59 219	63.09 239	74.34 225	82.68 220	64.98 245	69.17 192	54.42 226	36.18 255	44.32 214	44.35 222	44.65 251	73.60 231	77.83 221	89.21 238	88.96 204

gm-plane-assit		64.86 230	68.15 215	61.02 246	76.44 205	68.29 263	41.60 270	53.37 256	34.68 266	26.19 270	33.22 257	57.09 183	71.97 174	95.12 7	93.97 9	96.54 18	94.66 129

CP-MVSNet		64.84 231	64.97 230	64.69 234	72.09 235	81.04 238	66.66 238	67.53 210	52.45 232	37.40 249	44.00 218	38.37 251	53.54 241	72.26 242	76.93 227	90.94 214	89.75 196

MDTV_nov1_ep13_2view		64.72 232	64.94 231	64.46 235	71.14 241	81.94 230	67.53 236	54.54 252	55.92 217	43.29 238	44.02 217	43.27 229	59.87 226	71.85 244	74.77 234	90.36 222	82.82 236

MVS-HIRNet		64.63 233	64.03 238	65.33 231	75.01 221	82.84 218	58.54 259	52.10 258	55.42 221	49.29 207	29.83 262	43.48 227	66.97 207	78.28 209	78.81 213	90.07 229	79.52 246

pmnet_mix02		64.58 234	64.11 237	65.12 232	74.16 227	80.17 243	63.24 248	67.91 203	57.87 206	41.69 241	45.86 207	40.99 241	53.97 240	69.92 251	71.67 247	89.77 231	82.29 240

LTVRE_ROB	63.07 16	64.49 235	63.16 242	66.04 229	77.47 196	82.64 221	70.98 232	65.02 224	34.01 267	29.61 264	49.12 196	35.58 260	70.57 188	75.10 226	78.45 217	82.60 261	87.24 219
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
PEN-MVS		64.35 236	64.29 235	64.42 236	72.67 231	79.83 244	66.97 237	68.24 198	51.21 236	35.29 257	44.09 215	38.51 250	52.36 245	71.06 245	77.65 223	90.99 210	87.68 217

pmmvs6		64.24 237	61.77 247	67.12 226	72.39 234	81.39 233	71.33 231	65.95 222	36.05 263	48.48 214	30.55 258	43.45 228	58.75 228	77.88 214	76.36 230	85.83 253	86.70 222

pmmvs-eth3d		64.24 237	61.96 245	66.90 227	66.35 247	76.04 255	66.09 241	66.31 218	52.59 231	50.94 200	37.61 245	32.79 264	62.43 222	75.78 224	75.48 232	89.27 237	83.39 232

PS-CasMVS		64.22 239	64.19 236	64.25 237	71.86 237	80.67 239	66.42 240	67.43 212	50.64 238	36.48 252	42.60 229	37.46 254	52.56 243	71.98 243	76.69 229	90.76 216	89.29 202

WR-MVS_H		64.14 240	65.36 228	62.71 242	72.47 233	82.33 223	65.13 242	66.99 214	51.81 234	36.47 253	43.33 224	42.77 233	43.99 253	72.41 241	75.99 231	91.20 201	88.86 208

SixPastTwentyTwo		63.75 241	63.42 240	64.13 238	72.91 230	80.34 241	61.29 252	63.90 227	49.58 244	40.42 244	54.99 173	37.13 256	60.90 224	68.46 252	70.80 249	85.37 255	82.65 239

PM-MVS		63.52 242	62.51 244	64.70 233	64.79 252	76.08 254	65.07 243	62.08 233	58.13 204	46.56 222	44.98 210	31.31 266	62.89 219	72.58 240	69.93 254	86.81 249	84.55 226

DTE-MVSNet		63.26 243	63.41 241	63.08 240	72.59 232	78.56 247	65.03 244	68.28 197	50.53 240	32.38 261	44.03 216	37.79 253	49.48 249	70.83 249	76.73 228	90.73 217	85.42 225

testgi		63.11 244	64.88 233	61.05 245	75.83 217	78.51 248	60.42 253	66.20 219	48.77 245	34.56 258	56.96 156	40.35 244	40.95 259	77.46 218	77.22 225	88.37 244	74.86 258

GG-mvs-BLEND		62.08 245	88.31 47	31.46 264	0.16 282	98.10 15	91.57 46	0.09 276	85.07 72	0.21 283	73.90 65	83.74 44	0.19 280	88.98 84	89.39 79	96.58 16	99.02 19

Anonymous20231206		62.05 246	61.83 246	62.30 244	72.09 235	77.84 249	63.10 249	67.62 209	50.20 241	36.68 251	29.59 263	37.05 257	43.90 254	77.33 219	77.31 224	90.41 221	83.49 231

N_pmnet		60.52 247	58.83 251	62.50 243	68.97 244	75.61 256	59.72 257	66.47 215	51.90 233	41.26 242	35.42 253	35.63 259	52.25 246	67.07 255	70.08 253	86.35 250	76.10 252

FE-MVSNET2		60.10 248	59.87 249	60.37 248	51.97 267	77.72 250	63.63 247	66.11 220	45.14 252	36.89 250	26.42 267	33.72 261	51.78 247	77.68 215	78.09 220	91.85 185	80.29 243

dtuonlycased		59.74 249	57.09 252	62.83 241	64.59 253	76.76 251	62.72 250	62.48 232	49.65 243	44.54 235	34.46 254	45.96 216	57.26 232	54.43 262	58.78 261	85.36 256	79.58 245

EU-MVSNet		58.73 250	60.92 248	56.17 251	66.17 249	72.39 259	58.85 258	61.24 236	48.47 246	27.91 266	46.70 205	40.06 245	39.07 261	68.27 253	70.34 251	83.77 259	80.23 244

test20.03		57.93 251	59.22 250	56.44 250	71.84 238	73.78 258	53.55 264	65.96 221	43.02 257	28.46 265	37.50 246	38.17 252	30.41 265	75.25 225	74.42 237	88.41 242	72.37 261

MDA-MVSNet-bldmvs		54.99 252	52.66 257	57.71 249	52.74 266	74.87 257	55.61 261	68.41 196	43.65 255	32.54 259	37.93 243	22.11 275	54.11 236	48.85 266	67.34 256	82.85 260	73.88 259

FE-MVSNET		54.54 253	55.85 253	53.01 254	44.64 269	70.42 262	54.91 262	64.61 226	39.64 260	23.66 272	26.69 266	32.48 265	41.99 255	71.03 247	74.94 233	88.27 245	75.74 253

new-patchmatchnet		53.91 254	52.69 256	55.33 253	64.83 251	70.90 260	52.24 265	61.75 234	41.09 258	30.82 262	29.90 261	28.22 269	36.69 262	61.52 259	65.08 257	85.64 254	72.14 262

MIMVSNet1		52.76 255	53.95 255	51.38 256	41.96 271	70.79 261	53.56 263	63.03 231	39.36 261	27.83 267	22.73 270	33.07 263	34.47 264	70.49 250	72.69 238	87.41 248	68.51 263

pmmvs3		52.59 256	52.43 258	52.78 255	54.53 265	64.49 266	50.07 266	46.89 265	35.31 265	30.19 263	27.27 265	26.96 271	53.02 242	67.28 254	70.54 250	81.96 262	75.20 256

new_pmnet		50.32 257	51.36 259	49.11 258	49.19 268	64.89 265	48.66 268	47.99 264	47.55 248	26.27 269	29.51 264	28.66 268	44.89 250	61.12 260	62.74 259	77.66 265	65.03 264

FPMVS		50.25 258	45.67 262	55.58 252	70.48 242	60.12 267	59.78 256	59.33 242	46.66 249	37.94 247	30.22 260	27.51 270	35.94 263	50.98 265	47.90 265	70.02 267	56.31 265

usedtu_dtu_shiyan2		50.22 259	49.72 261	50.80 257	33.02 275	67.71 264	57.83 260	52.96 257	27.83 272	39.36 246	20.55 272	29.77 267	40.68 260	61.53 258	62.06 260	80.93 264	78.57 248

test_method		47.92 260	55.39 254	39.21 261	19.90 276	49.24 270	39.29 271	34.65 270	57.37 208	32.54 259	25.11 268	41.02 240	44.31 252	66.58 257	57.57 263	64.59 270	90.82 186

PMVS	36.83 18	40.62 261	36.39 264	45.56 259	58.40 255	33.20 273	32.62 273	56.02 246	28.25 271	37.92 248	22.29 271	26.15 272	25.29 267	48.49 267	43.82 268	63.13 271	52.53 268
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		39.74 262	42.23 263	36.84 262	66.24 248	50.82 269	26.18 276	66.39 217	31.14 269	4.85 278	37.06 248	24.28 273	7.95 276	54.48 261	54.23 264	49.46 274	43.61 271

Gipuma		35.20 263	33.96 265	36.65 263	43.30 270	32.51 274	26.96 275	48.31 263	38.87 262	20.08 274	8.08 275	7.41 281	26.44 266	53.60 263	58.43 262	54.81 272	38.79 274
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		32.52 264	33.92 266	30.88 265	34.15 274	44.70 272	27.79 274	39.69 269	22.21 273	4.31 279	15.73 273	14.13 279	12.45 273	40.11 268	47.00 266	66.88 268	53.54 266

E-PMN		21.42 265	17.56 271	25.94 266	36.25 273	19.02 277	11.56 277	43.72 267	15.25 275	6.99 276	8.04 276	4.53 284	21.77 269	16.13 274	26.16 270	35.34 275	33.77 275

MVE	25.07 19	21.25 266	23.51 270	18.62 268	15.07 277	29.77 276	10.67 279	34.60 271	12.51 276	9.46 275	7.84 277	3.82 285	14.38 271	27.45 270	42.42 269	27.56 277	40.74 272
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 267	16.32 272	25.62 267	36.41 272	18.93 278	11.51 278	43.75 266	15.65 274	6.53 277	7.56 278	4.68 283	22.03 268	14.56 275	23.10 271	33.51 276	29.77 276

VLMVS		19.18 268	30.41 267	6.08 270	4.08 279	8.55 280	5.11 282	0.41 275	40.06 259	2.99 280	55.93 165	23.93 274	9.07 275	20.26 273	19.06 273	14.85 278	45.09 270

VLMVS_CLIP		18.77 269	29.38 268	6.40 269	5.19 278	9.75 279	6.18 281	0.73 273	32.15 268	0.96 281	47.91 202	17.70 277	11.68 274	24.94 271	21.30 272	13.63 279	51.95 269

MVS_clip		14.93 270	23.85 269	4.53 271	3.12 280	7.65 281	3.59 283	0.52 274	30.26 270	0.46 282	33.40 256	16.95 278	12.84 272	21.07 272	17.62 274	6.61 280	40.02 273

MVS_baseline		3.69 271	6.36 273	0.57 272	0.17 281	0.30 282	0.08 286	0.00 279	7.51 277	0.00 286	9.54 274	5.03 282	3.12 277	3.94 276	3.76 275	0.03 283	14.47 277

testmvs		0.76 272	1.23 274	0.21 273	0.05 283	0.21 283	0.38 284	0.09 276	0.94 278	0.05 284	2.13 280	0.08 286	0.60 279	0.82 277	0.77 276	0.11 281	3.62 279

test123		0.67 273	1.11 275	0.16 274	0.01 284	0.14 284	0.20 285	0.04 278	0.77 279	0.02 285	2.15 279	0.02 287	0.61 278	0.23 278	0.72 277	0.07 282	3.76 278

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					98.20 4	98.52 9	96.93 2		94.55 19	78.23 53	87.10 36	93.26 2	93.66 8			95.47 59	97.16 61

PatchmatchNet2					69.65 243	76.10 253	60.12 254
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												35.72 258	52.39 244	67.05 256	70.24 252	86.34 251	75.74 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										41.18 243	35.45 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							95.37 15	93.61 1		96.88 1						96.96 9

TPM-MVS					98.35 1	98.66 5	96.92 3			83.78 29	90.39 27	94.36 1	94.48 5			96.58 16	93.94 143
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										39.41 245

9.14												91.16 10

SR-MVS					96.04 35			87.51 30				87.60 26

Anonymous202405211			75.59 169		85.13 150	91.06 140	84.62 129	77.96 99	69.47 171		40.79 237	63.84 146	84.57 78	83.55 158	84.69 144	89.69 232	95.75 112

our_test_3					73.80 229	79.57 245	64.47 246

ambc			50.35 260		55.61 263	59.93 268	48.73 267		44.08 253	35.81 256	24.01 269	10.64 280	41.57 257	72.83 239	63.35 258	74.99 266	77.61 249

MTAPA										91.14 11		85.84 32

MTMP										90.95 12		84.13 40

Patchmatch-RL test							8.17 280

tmp_tt				39.78 260	56.31 260	31.71 275	35.84 272	15.08 272	82.57 84	50.83 202	63.07 116	47.51 213	15.28 270	52.23 264	44.24 267	65.35 269

XVS					89.65 75	95.93 52	85.97 108			76.32 75		82.05 49				93.51 128

X-MVStestdata					89.65 75	95.93 52	85.97 108			76.32 75		82.05 49				93.51 128

mPP-MVS					95.90 37							80.22 58

NP-MVS									89.55 52

Patchmtry						87.41 170	78.32 181	54.14 253		51.09 197

DeepMVS_CX						48.96 271	43.77 269	40.58 268	50.93 237	24.67 271	36.95 249	20.18 276	41.60 256	38.92 269		52.37 273	53.31 267

High-resolution multi-view benchmark