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.

DVP-MVS++		95.79 1	96.42 1	95.06 1	97.84 2	98.17 2	97.03 4	92.84 3	96.68 1	92.83 3	95.90 5	94.38 4	92.90 5	95.98 2	94.85 6	96.93 3	98.99 1

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

DVP-MVS		95.56 3	96.26 3	94.73 3	96.93 16	98.19 1	96.62 7	92.81 5	96.15 2	91.73 5	95.01 7	95.31 2	93.41 1	95.95 3	94.77 9	96.90 4	98.46 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
DPE-MVS		95.53 4	96.13 4	94.82 2	96.81 22	98.05 4	97.42 1	93.09 1	94.31 9	91.49 6	97.12 1	95.03 3	93.27 3	95.55 7	94.58 13	96.86 6	98.25 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		95.23 5	95.69 6	94.70 5	97.12 10	97.81 7	97.19 2	92.83 4	95.06 6	90.98 9	96.47 2	92.77 10	93.38 2	95.34 10	94.21 17	96.68 9	98.17 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSP-MVS		95.12 6	95.83 5	94.30 6	96.82 21	97.94 5	96.98 5	92.37 11	95.40 4	90.59 12	96.16 3	93.71 6	92.70 8	94.80 18	94.77 9	96.37 14	97.99 8
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
SMA-MVS		94.70 7	95.35 7	93.93 11	97.57 3	97.57 9	95.98 12	91.91 13	94.50 7	90.35 13	93.46 17	92.72 11	91.89 17	95.89 4	95.22 1	95.88 31	98.10 6
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
SF-MVS		94.61 8	94.96 10	94.20 9	96.75 24	97.07 13	95.82 18	92.60 7	93.98 12	91.09 8	95.89 6	92.54 12	91.93 15	94.40 27	93.56 30	97.04 2	97.27 18

HPM-MVS++		94.60 9	94.91 11	94.24 8	97.86 1	96.53 32	96.14 9	92.51 8	93.87 14	90.76 11	93.45 18	93.84 5	92.62 9	95.11 13	94.08 20	95.58 54	97.48 15

SD-MVS		94.53 10	95.22 8	93.73 14	95.69 37	97.03 15	95.77 21	91.95 12	94.41 8	91.35 7	94.97 8	93.34 8	91.80 19	94.72 21	93.99 21	95.82 38	98.07 7
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + MP.		94.48 11	94.97 9	93.90 12	95.53 38	97.01 16	96.69 6	90.71 23	94.24 10	90.92 10	94.97 8	92.19 15	93.03 4	94.83 17	93.60 27	96.51 13	97.97 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APD-MVS		94.37 12	94.47 16	94.26 7	97.18 8	96.99 17	96.53 8	92.68 6	92.45 23	89.96 16	94.53 11	91.63 21	92.89 6	94.58 22	93.82 23	96.31 18	97.26 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		94.37 12	94.65 12	94.04 10	97.29 6	97.11 12	96.00 11	92.43 10	93.45 15	89.85 18	90.92 26	93.04 9	92.59 10	95.77 5	94.82 7	96.11 25	97.42 17

SteuartSystems-ACMMP		94.06 14	94.65 12	93.38 18	96.97 15	97.36 10	96.12 10	91.78 14	92.05 28	87.34 30	94.42 12	90.87 26	91.87 18	95.47 9	94.59 12	96.21 23	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		94.02 15	94.22 19	93.78 13	97.25 7	96.85 21	95.81 19	90.94 22	94.12 11	90.29 15	94.09 14	89.98 32	92.52 11	93.94 33	93.49 33	95.87 33	97.10 24

ACMMP_NAP		93.94 16	94.49 15	93.30 19	97.03 13	97.31 11	95.96 13	91.30 18	93.41 17	88.55 24	93.00 19	90.33 29	91.43 25	95.53 8	94.41 15	95.53 58	97.47 16

MCST-MVS		93.81 17	94.06 20	93.53 16	96.79 23	96.85 21	95.95 14	91.69 16	92.20 26	87.17 32	90.83 28	93.41 7	91.96 14	94.49 25	93.50 31	97.61 1	97.12 23

ACMMPR		93.72 18	93.94 21	93.48 17	97.07 11	96.93 18	95.78 20	90.66 25	93.88 13	89.24 20	93.53 16	89.08 38	92.24 12	93.89 35	93.50 31	95.88 31	96.73 33

NCCC		93.69 19	93.66 24	93.72 15	97.37 5	96.66 29	95.93 17	92.50 9	93.40 18	88.35 25	87.36 35	92.33 14	92.18 13	94.89 16	94.09 19	96.00 27	96.91 29

MVS_0304		93.46 20	94.44 17	92.32 28	95.88 34	97.84 6	95.25 26	87.99 40	92.23 25	89.16 21	91.23 25	91.51 22	88.98 39	95.64 6	95.04 3	96.67 11	97.57 14

MP-MVS		93.35 21	93.59 25	93.08 22	97.39 4	96.82 23	95.38 24	90.71 23	90.82 36	88.07 27	92.83 21	90.29 30	91.32 27	94.03 30	93.19 41	95.61 52	97.16 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		93.25 22	93.26 27	93.24 20	96.84 19	96.51 33	95.52 23	90.61 26	92.37 24	88.88 22	90.91 27	89.52 34	91.91 16	93.64 40	92.78 47	95.69 45	97.09 25

DeepC-MVS_fast	88.76 1	93.10 23	93.02 30	93.19 21	97.13 9	96.51 33	95.35 25	91.19 19	93.14 20	88.14 26	85.26 41	89.49 35	91.45 22	95.17 11	95.07 2	95.85 36	96.48 37
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + ACMM		92.97 24	94.51 14	91.16 37	95.88 34	96.59 30	95.09 29	90.45 29	93.42 16	83.01 57	94.68 10	90.74 27	88.74 43	94.75 20	93.78 24	93.82 143	97.63 12

train_agg		92.87 25	93.53 26	92.09 30	96.88 18	95.38 52	95.94 15	90.59 27	90.65 38	83.65 53	94.31 13	91.87 20	90.30 32	93.38 43	92.42 52	95.17 80	96.73 33

PGM-MVS		92.76 26	93.03 29	92.45 27	97.03 13	96.67 28	95.73 22	87.92 42	90.15 44	86.53 36	92.97 20	88.33 44	91.69 20	93.62 41	93.03 42	95.83 37	96.41 40

CSCG		92.76 26	93.16 28	92.29 29	96.30 28	97.74 8	94.67 34	88.98 35	92.46 22	89.73 19	86.67 38	92.15 18	88.69 44	92.26 59	92.92 45	95.40 63	97.89 10

TSAR-MVS + GP.		92.71 28	93.91 22	91.30 35	91.96 73	96.00 40	93.43 41	87.94 41	92.53 21	86.27 40	93.57 15	91.94 19	91.44 24	93.29 44	92.89 46	96.78 7	97.15 22

DeepPCF-MVS	88.51 2	92.64 29	94.42 18	90.56 40	94.84 45	96.92 19	91.31 63	89.61 31	95.16 5	84.55 48	89.91 30	91.45 23	90.15 35	95.12 12	94.81 8	92.90 163	97.58 13

X-MVS		92.36 30	92.75 31	91.90 33	96.89 17	96.70 25	95.25 26	90.48 28	91.50 33	83.95 50	88.20 32	88.82 40	89.11 38	93.75 38	93.43 34	95.75 43	96.83 31

DeepC-MVS	87.86 3	92.26 31	91.86 34	92.73 24	96.18 29	96.87 20	95.19 28	91.76 15	92.17 27	86.58 35	81.79 55	85.85 51	90.88 30	94.57 23	94.61 11	95.80 39	97.18 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		92.05 32	93.74 23	90.08 42	94.96 42	97.06 14	93.11 45	87.71 44	90.71 37	80.78 73	92.40 22	91.03 24	87.68 55	94.32 28	94.48 14	96.21 23	96.16 44

ACMMP		92.03 33	92.16 32	91.87 34	95.88 34	96.55 31	94.47 35	89.49 32	91.71 31	85.26 43	91.52 24	84.48 57	90.21 34	92.82 52	91.63 59	95.92 30	96.42 39
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MSLP-MVS++		92.02 34	91.40 37	92.75 23	96.01 32	95.88 44	93.73 40	89.00 33	89.89 45	90.31 14	81.28 60	88.85 39	91.45 22	92.88 51	94.24 16	96.00 27	96.76 32

DPM-MVS		91.72 35	91.48 35	92.00 31	95.53 38	95.75 47	95.94 15	91.07 20	91.20 34	85.58 41	81.63 58	90.74 27	88.40 47	93.40 42	93.75 25	95.45 62	93.85 89

3Dnovator+	86.06 4	91.60 36	90.86 42	92.47 26	96.00 33	96.50 35	94.70 33	87.83 43	90.49 39	89.92 17	74.68 101	89.35 36	90.66 31	94.02 31	94.14 18	95.67 47	96.85 30

CPTT-MVS		91.39 37	90.95 40	91.91 32	95.06 40	95.24 56	95.02 30	88.98 35	91.02 35	86.71 34	84.89 43	88.58 43	91.60 21	90.82 89	89.67 103	94.08 130	96.45 38

CANet		91.33 38	91.46 36	91.18 36	95.01 41	96.71 24	93.77 38	87.39 46	87.72 53	87.26 31	81.77 56	89.73 33	87.32 60	94.43 26	93.86 22	96.31 18	96.02 46

CDPH-MVS		91.14 39	92.01 33	90.11 41	96.18 29	96.18 37	94.89 31	88.80 37	88.76 49	77.88 95	89.18 31	87.71 47	87.29 61	93.13 46	93.31 38	95.62 50	95.84 48

MVS_111021_HR		90.56 40	91.29 38	89.70 48	94.71 47	95.63 49	91.81 57	86.38 49	87.53 54	81.29 67	87.96 33	85.43 53	87.69 54	93.90 34	92.93 44	96.33 16	95.69 51

3Dnovator	85.17 5	90.48 41	89.90 49	91.16 37	94.88 44	95.74 48	93.82 37	85.36 55	89.28 46	87.81 28	74.34 104	87.40 48	88.56 45	93.07 47	93.74 26	96.53 12	95.71 50

CS-MVS		90.34 42	90.58 44	90.07 43	93.11 60	95.82 46	90.57 67	83.62 77	87.07 56	85.35 42	82.98 47	83.47 61	91.37 26	94.94 14	93.37 37	96.37 14	96.41 40

SPE-MVS-test		90.29 43	90.96 39	89.51 51	93.18 59	95.87 45	89.18 92	83.72 76	88.32 51	84.82 47	84.89 43	85.23 54	90.25 33	94.04 29	92.66 51	95.94 29	95.69 51

AdaColmap		90.29 43	88.38 60	92.53 25	96.10 31	95.19 57	92.98 46	91.40 17	89.08 48	88.65 23	78.35 74	81.44 71	91.30 28	90.81 90	90.21 86	94.72 102	93.59 97

OMC-MVS		90.23 45	90.40 45	90.03 44	93.45 56	95.29 53	91.89 55	86.34 50	93.25 19	84.94 46	81.72 57	86.65 50	88.90 40	91.69 67	90.27 85	94.65 106	93.95 86

MVS_111021_LR		90.14 46	90.89 41	89.26 53	93.23 58	94.05 80	90.43 70	84.65 61	90.16 43	84.52 49	90.14 29	83.80 60	87.99 51	92.50 56	90.92 69	94.74 100	94.70 68

EC-MVSNet		89.96 47	90.77 43	89.01 55	90.54 93	95.15 58	91.34 62	81.43 114	85.27 63	83.08 56	82.83 48	87.22 49	90.97 29	94.79 19	93.38 35	96.73 8	96.71 35

DELS-MVS		89.71 48	89.68 52	89.74 46	93.75 53	96.22 36	93.76 39	85.84 51	82.53 83	85.05 45	78.96 71	84.24 58	84.25 83	94.91 15	94.91 5	95.78 42	96.02 46
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
EPNet		89.60 49	89.91 48	89.24 54	96.45 26	93.61 86	92.95 47	88.03 39	85.74 61	83.36 55	87.29 36	83.05 64	80.98 109	92.22 60	91.85 57	93.69 148	95.58 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		89.49 50	89.58 53	89.38 52	94.73 46	95.94 41	92.35 49	85.00 58	85.69 62	80.03 80	76.97 83	87.81 46	87.87 52	92.18 63	92.10 55	96.33 16	96.40 42

sasdasda		89.36 51	89.92 46	88.70 59	91.38 79	95.92 42	91.81 57	82.61 103	90.37 40	82.73 59	82.09 51	79.28 86	88.30 48	91.17 75	93.59 28	95.36 65	97.04 26

canonicalmvs		89.36 51	89.92 46	88.70 59	91.38 79	95.92 42	91.81 57	82.61 103	90.37 40	82.73 59	82.09 51	79.28 86	88.30 48	91.17 75	93.59 28	95.36 65	97.04 26

ETV-MVS		89.22 53	89.76 50	88.60 62	91.60 77	94.61 69	89.48 88	83.46 86	85.20 65	81.58 65	82.75 49	82.59 66	88.80 41	94.57 23	93.28 39	96.68 9	95.31 58

HQP-MVS		89.13 54	89.58 53	88.60 62	93.53 55	93.67 84	93.29 43	87.58 45	88.53 50	75.50 100	87.60 34	80.32 76	87.07 62	90.66 97	89.95 95	94.62 108	96.35 43

TAPA-MVS	84.37 7	88.91 55	88.93 56	88.89 56	93.00 64	94.85 65	92.00 52	84.84 59	91.68 32	80.05 78	79.77 66	84.56 56	88.17 50	90.11 103	89.00 122	95.30 71	92.57 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PCF-MVS	84.60 6	88.66 56	87.75 70	89.73 47	93.06 63	96.02 38	93.22 44	90.00 30	82.44 86	80.02 81	77.96 77	85.16 55	87.36 59	88.54 124	88.54 127	94.72 102	95.61 54
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		88.66 56	88.52 58	88.82 57	91.37 81	94.22 73	92.82 48	82.08 108	88.27 52	85.14 44	81.86 54	78.53 93	85.93 72	91.17 75	90.61 78	95.55 56	95.00 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PLC	83.76 9	88.61 58	86.83 78	90.70 39	94.22 49	92.63 105	91.50 60	87.19 47	89.16 47	86.87 33	75.51 94	80.87 73	89.98 36	90.01 104	89.20 116	94.41 121	90.45 158
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + COLMAP		88.40 59	89.09 55	87.60 73	92.72 68	93.92 83	92.21 50	85.57 54	91.73 30	73.72 112	91.75 23	73.22 131	87.64 56	91.49 69	89.71 102	93.73 146	91.82 136

CNLPA		88.40 59	87.00 75	90.03 44	93.73 54	94.28 72	89.56 86	85.81 52	91.87 29	87.55 29	69.53 132	81.49 70	89.23 37	89.45 114	88.59 126	94.31 125	93.82 91

MAR-MVS		88.39 61	88.44 59	88.33 67	94.90 43	95.06 61	90.51 68	83.59 80	85.27 63	79.07 87	77.13 80	82.89 65	87.70 53	92.19 62	92.32 53	94.23 126	94.20 81
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
MGCFI-Net		88.38 62	89.72 51	86.83 80	91.21 82	95.59 50	91.14 65	82.37 106	90.25 42	75.33 105	81.89 53	79.13 88	85.69 73	90.98 86	93.23 40	95.23 76	96.94 28

ACMP	83.90 8	88.32 63	88.06 63	88.62 61	92.18 71	93.98 82	91.28 64	85.24 56	86.69 57	81.23 68	85.62 40	75.13 114	87.01 64	89.83 106	89.77 100	94.79 96	95.43 57
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		88.25 64	88.55 57	87.89 69	92.84 67	93.66 85	93.35 42	85.22 57	85.77 60	74.03 111	86.60 39	76.29 110	86.62 67	91.20 73	90.58 80	95.29 72	95.75 49

PVSNet_BlendedMVS		88.19 65	88.00 65	88.42 64	92.71 69	94.82 66	89.08 97	83.81 73	84.91 69	86.38 38	79.14 68	78.11 95	82.66 95	93.05 48	91.10 64	95.86 34	94.86 64

PVSNet_Blended		88.19 65	88.00 65	88.42 64	92.71 69	94.82 66	89.08 97	83.81 73	84.91 69	86.38 38	79.14 68	78.11 95	82.66 95	93.05 48	91.10 64	95.86 34	94.86 64

casdiffmvs_mvg		87.97 67	87.63 72	88.37 66	90.55 92	94.42 70	91.82 56	84.69 60	84.05 73	82.08 64	76.57 85	79.00 89	85.49 75	92.35 57	92.29 54	95.55 56	94.70 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		87.94 68	88.05 64	87.81 70	91.46 78	95.00 63	88.67 104	82.81 95	82.53 83	80.81 72	80.04 64	80.20 77	87.48 57	92.58 55	91.61 60	95.63 49	94.36 75

OpenMVS	82.53 11	87.71 69	86.84 77	88.73 58	94.42 48	95.06 61	91.02 66	83.49 83	82.50 85	82.24 63	67.62 143	85.48 52	85.56 74	91.19 74	91.30 62	95.67 47	94.75 66

ACMM	83.27 10	87.68 70	86.09 87	89.54 50	93.26 57	92.19 111	91.43 61	86.74 48	86.02 59	82.85 58	75.63 92	75.14 113	88.41 46	90.68 96	89.99 92	94.59 109	92.97 107
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		87.56 71	85.80 91	89.62 49	93.90 52	94.09 79	94.12 36	88.18 38	75.40 142	77.30 98	76.41 86	77.93 97	88.79 42	92.20 61	90.82 72	95.40 63	93.72 95
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
casdiffmvs		87.45 72	87.15 74	87.79 72	90.15 104	94.22 73	89.96 77	83.93 72	85.08 67	80.91 69	75.81 90	77.88 98	86.08 69	91.86 66	90.86 71	95.74 44	94.37 73
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		87.40 73	87.80 67	86.92 79	92.86 65	95.40 51	88.56 110	83.45 87	79.55 118	82.26 61	74.49 103	84.03 59	79.24 139	92.97 50	91.53 61	95.15 82	96.65 36

viewcassd2359sk11		87.35 74	86.67 82	88.14 68	90.08 106	94.12 77	90.51 68	84.13 69	83.71 75	83.42 54	76.99 81	77.46 100	85.33 78	90.40 100	90.21 86	95.34 68	93.81 92

viewmanbaseed2359cas		87.17 75	86.90 76	87.48 75	90.08 106	94.14 76	90.30 72	83.19 93	84.17 72	80.68 75	76.78 84	77.43 101	85.43 77	90.78 91	90.92 69	95.21 78	94.10 83

MVS_Test		86.93 76	87.24 73	86.56 81	90.10 105	93.47 88	90.31 71	80.12 131	83.55 76	78.12 91	79.58 67	79.80 81	85.45 76	90.17 102	90.59 79	95.29 72	93.53 98

viewdifsd2359ckpt13		86.88 77	86.35 84	87.50 74	89.91 109	94.19 75	89.89 79	83.43 88	82.94 79	80.82 71	75.76 91	76.45 108	85.95 71	90.72 95	90.49 82	95.00 87	93.88 87

EPP-MVSNet		86.55 78	87.76 69	85.15 95	90.52 94	94.41 71	87.24 127	82.32 107	81.79 94	73.60 113	78.57 73	82.41 67	82.07 100	91.23 71	90.39 83	95.14 83	95.48 56

diffmvs		86.52 79	86.76 80	86.23 84	88.31 125	92.63 105	89.58 85	81.61 113	86.14 58	80.26 77	79.00 70	77.27 102	83.58 86	88.94 119	89.06 119	94.05 132	94.29 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		86.44 80	86.59 83	86.26 83	88.33 124	92.74 101	89.66 84	81.74 111	85.17 66	80.04 79	77.70 78	77.20 103	83.68 84	89.66 110	89.28 112	94.14 129	94.37 73

viewmacassd2359aftdt		86.41 81	85.73 93	87.21 77	89.86 110	94.03 81	90.30 72	83.22 92	80.76 107	79.59 84	73.51 111	76.32 109	85.06 79	90.24 101	91.13 63	95.23 76	94.11 82

DI_MVS_pp		86.41 81	85.54 95	87.42 76	89.24 114	93.13 93	92.16 51	82.65 101	82.30 87	80.75 74	68.30 139	80.41 75	85.01 80	90.56 98	90.07 90	94.70 104	94.01 84

IS_MVSNet		86.18 83	88.18 62	83.85 115	91.02 85	94.72 68	87.48 121	82.46 105	81.05 102	70.28 128	76.98 82	82.20 69	76.65 156	93.97 32	93.38 35	95.18 79	94.97 61

UA-Net		86.07 84	87.78 68	84.06 112	92.85 66	95.11 60	87.73 118	84.38 65	73.22 162	73.18 116	79.99 65	89.22 37	71.47 184	93.22 45	93.03 42	94.76 99	90.69 153

MVSTER		86.03 85	86.12 86	85.93 88	88.62 120	89.93 139	89.33 91	79.91 136	81.87 93	81.35 66	81.07 61	74.91 115	80.66 114	92.13 64	90.10 89	95.68 46	92.80 112

LS3D		85.96 86	84.37 104	87.81 70	94.13 50	93.27 92	90.26 75	89.00 33	84.91 69	72.84 120	71.74 118	72.47 133	87.45 58	89.53 113	89.09 118	93.20 159	89.60 161

UGNet		85.90 87	88.23 61	83.18 122	88.96 118	94.10 78	87.52 120	83.60 79	81.66 95	77.90 94	80.76 62	83.19 63	66.70 201	91.13 81	90.71 76	94.39 122	96.06 45
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
DCV-MVSNet		85.88 88	86.17 85	85.54 92	89.10 117	89.85 141	89.34 90	80.70 120	83.04 78	78.08 93	76.19 88	79.00 89	82.42 98	89.67 109	90.30 84	93.63 151	95.12 59

FA-MVS(training)		85.65 89	85.79 92	85.48 93	90.44 98	93.47 88	88.66 106	73.11 187	83.34 77	82.26 61	71.79 117	78.39 94	83.14 90	91.00 83	89.47 109	95.28 74	93.06 105

viewmambaseed2359dif		85.52 90	85.01 98	86.12 86	88.39 122	91.96 113	89.39 89	81.43 114	82.16 88	80.47 76	75.52 93	76.85 106	83.66 85	87.03 140	87.60 135	93.37 157	93.98 85

CANet_DTU		85.43 91	87.72 71	82.76 126	90.95 88	93.01 97	89.99 76	75.46 178	82.67 80	64.91 159	83.14 46	80.09 78	80.68 113	92.03 65	91.03 66	94.57 111	92.08 130

Effi-MVS+		85.33 92	85.08 97	85.63 90	89.69 111	93.42 90	89.90 78	80.31 129	79.32 119	72.48 122	73.52 110	74.03 120	86.55 68	90.99 84	89.98 93	94.83 94	94.27 80

ECVR-MVS		85.25 93	84.47 102	86.16 85	91.84 74	95.28 54	89.18 92	84.49 63	82.59 81	73.49 114	66.12 148	69.28 146	81.68 102	93.76 36	92.71 48	96.28 21	91.58 145

test2506		85.20 94	84.11 106	86.47 82	91.84 74	95.28 54	89.18 92	84.49 63	82.59 81	75.34 104	74.66 102	58.07 198	81.68 102	93.76 36	92.71 48	96.28 21	91.71 138

FC-MVSNet-train		85.18 95	85.31 96	85.03 98	90.67 89	91.62 116	87.66 119	83.61 78	79.75 116	74.37 109	78.69 72	71.21 137	78.91 140	91.23 71	89.96 94	94.96 89	94.69 70

thisisatest0530		85.15 96	85.86 89	84.33 105	89.19 116	92.57 108	87.22 128	80.11 132	82.15 90	74.41 108	78.15 75	73.80 125	79.90 127	90.99 84	89.58 104	95.13 84	93.75 94

tttt0517		85.11 97	85.81 90	84.30 106	89.24 114	92.68 104	87.12 132	80.11 132	81.98 91	74.31 110	78.08 76	73.57 127	79.90 127	91.01 82	89.58 104	95.11 86	93.77 93

baseline		84.89 98	86.06 88	83.52 120	87.25 138	89.67 148	87.76 117	75.68 177	84.92 68	78.40 89	80.10 63	80.98 72	80.20 123	86.69 149	87.05 143	91.86 176	92.99 106

test1111		84.86 99	84.21 105	85.61 91	91.75 76	95.14 59	88.63 107	84.57 62	81.88 92	71.21 123	65.66 155	68.51 150	81.19 106	93.74 39	92.68 50	96.31 18	91.86 135

ET-MVSNet_ETH3D		84.65 100	85.58 94	83.56 119	74.99 223	92.62 107	90.29 74	80.38 124	82.16 88	73.01 119	83.41 45	71.10 138	87.05 63	87.77 132	90.17 88	95.62 50	91.82 136

GeoE		84.62 101	83.98 108	85.35 94	89.34 113	92.83 100	88.34 111	78.95 146	79.29 120	77.16 99	68.10 140	74.56 116	83.40 88	89.31 116	89.23 115	94.92 90	94.57 72

baseline1		84.54 102	84.43 103	84.67 100	90.62 90	91.16 119	88.63 107	83.75 75	79.78 115	71.16 124	75.14 96	74.10 119	77.84 148	91.56 68	90.67 77	96.04 26	88.58 167

GBi-Net		84.51 103	84.80 99	84.17 109	84.20 174	89.95 136	89.70 81	80.37 125	81.17 98	75.50 100	69.63 128	79.69 83	79.75 131	90.73 92	90.72 73	95.52 59	91.71 138

test1		84.51 103	84.80 99	84.17 109	84.20 174	89.95 136	89.70 81	80.37 125	81.17 98	75.50 100	69.63 128	79.69 83	79.75 131	90.73 92	90.72 73	95.52 59	91.71 138

FMVSNet3		84.44 105	84.64 101	84.21 108	84.32 173	90.13 134	89.85 80	80.37 125	81.17 98	75.50 100	69.63 128	79.69 83	79.62 134	89.72 108	90.52 81	95.59 53	91.58 145

Anonymous20231211		84.42 106	83.02 114	86.05 87	88.85 119	92.70 103	88.92 103	83.40 89	79.99 111	78.31 90	55.83 202	78.92 91	83.33 89	89.06 118	89.76 101	93.50 153	94.90 62

Vis-MVSNet		84.38 107	86.68 81	81.70 137	87.65 134	94.89 64	88.14 113	80.90 119	74.48 148	68.23 140	77.53 79	80.72 74	69.98 188	92.68 53	91.90 56	95.33 70	94.58 71
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
viewdifsd2359ckpt11		84.31 108	83.65 111	85.08 96	88.07 126	91.03 120	86.86 136	80.65 121	79.92 112	79.63 82	75.08 97	73.99 121	82.74 92	86.40 156	85.98 166	92.51 168	93.16 101

viewmsd2359difaftdt		84.31 108	83.65 111	85.07 97	88.07 126	91.03 120	86.86 136	80.65 121	79.92 112	79.61 83	75.08 97	73.98 122	82.74 92	86.40 156	85.99 164	92.51 168	93.16 101

FMVSNet2		83.87 110	83.73 110	84.05 113	84.20 174	89.95 136	89.70 81	80.21 130	79.17 122	74.89 106	65.91 149	77.49 99	79.75 131	90.87 88	91.00 68	95.52 59	91.71 138

MSDG		83.87 110	81.02 132	87.19 78	92.17 72	89.80 143	89.15 95	85.72 53	80.61 108	79.24 86	66.66 146	68.75 149	82.69 94	87.95 131	87.44 137	94.19 127	85.92 190

Fast-Effi-MVS+		83.77 112	82.98 115	84.69 99	87.98 128	91.87 114	88.10 114	77.70 160	78.10 128	73.04 118	69.13 134	68.51 150	86.66 66	90.49 99	89.85 98	94.67 105	92.88 109

Vis-MVSNet (Re-imp)		83.65 113	86.81 79	79.96 157	90.46 97	92.71 102	84.84 159	82.00 109	80.93 104	62.44 174	76.29 87	82.32 68	65.54 204	92.29 58	91.66 58	94.49 116	91.47 147

RPSCF		83.46 114	83.36 113	83.59 118	87.75 130	87.35 176	84.82 160	79.46 141	83.84 74	78.12 91	82.69 50	79.87 79	82.60 97	82.47 196	81.13 200	88.78 202	86.13 188

PatchMatch-RL		83.34 115	81.36 127	85.65 89	90.33 101	89.52 151	84.36 163	81.82 110	80.87 106	79.29 85	74.04 105	62.85 172	86.05 70	88.40 127	87.04 144	92.04 173	86.77 183

IterMVS-LS		83.28 116	82.95 116	83.65 116	88.39 122	88.63 166	86.80 138	78.64 151	76.56 134	73.43 115	72.52 116	75.35 112	80.81 111	86.43 155	88.51 128	93.84 142	92.66 117
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		82.86 117	81.46 125	84.48 102	90.30 102	93.09 94	89.05 99	82.71 97	75.14 143	69.56 131	65.72 152	63.13 167	80.38 120	91.15 78	89.51 106	94.91 91	92.50 126

baseline2		82.80 118	82.86 117	82.73 127	87.68 133	90.50 127	84.92 158	78.93 147	78.07 129	73.06 117	75.08 97	69.77 143	77.31 151	88.90 121	86.94 145	94.50 114	90.74 152

thres200		82.77 119	81.25 129	84.54 101	90.38 99	93.05 95	89.13 96	82.67 99	74.40 149	69.53 133	65.69 154	63.03 170	80.63 115	91.15 78	89.42 110	94.88 92	92.04 132

thres400		82.68 120	81.15 130	84.47 103	90.52 94	92.89 99	88.95 102	82.71 97	74.33 150	69.22 136	65.31 157	62.61 173	80.63 115	90.96 87	89.50 107	94.79 96	92.45 128

IB-MVS	79.09 12	82.60 121	82.19 120	83.07 123	91.08 84	93.55 87	80.90 190	81.35 116	76.56 134	80.87 70	64.81 163	69.97 142	68.87 191	85.64 165	90.06 91	95.36 65	94.74 67
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
thres100view900		82.55 122	81.01 134	84.34 104	90.30 102	92.27 109	89.04 100	82.77 96	75.14 143	69.56 131	65.72 152	63.13 167	79.62 134	89.97 105	89.26 114	94.73 101	91.61 144

thres600view7		82.53 123	81.02 132	84.28 107	90.61 91	93.05 95	88.57 109	82.67 99	74.12 153	68.56 139	65.09 160	62.13 178	80.40 119	91.15 78	89.02 121	94.88 92	92.59 120

CHOSEN 1792x2688		82.16 124	80.91 135	83.61 117	91.14 83	92.01 112	89.55 87	79.15 145	79.87 114	70.29 127	52.51 211	72.56 132	81.39 104	88.87 122	88.17 130	90.15 195	92.37 129

Effi-MVS+-dtu		82.05 125	81.76 122	82.38 131	87.72 131	90.56 126	86.90 135	78.05 156	73.85 156	66.85 145	71.29 120	71.90 135	82.00 101	86.64 150	85.48 171	92.76 165	92.58 121

EPNet_dtu		81.98 126	83.82 109	79.83 159	94.10 51	85.97 185	87.29 125	84.08 71	80.61 108	59.96 192	81.62 59	77.19 104	62.91 208	87.21 136	86.38 156	90.66 191	87.77 178
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet_NR-MVSNet		81.87 127	81.33 128	82.50 128	85.31 160	91.30 117	85.70 148	84.25 66	75.89 138	64.21 161	66.95 145	64.65 162	80.22 121	87.07 138	89.18 117	95.27 75	94.29 76

ACMH	78.52 14	81.86 128	80.45 139	83.51 121	90.51 96	91.22 118	85.62 151	84.23 67	70.29 179	62.21 175	69.04 136	64.05 164	84.48 82	87.57 134	88.45 129	94.01 134	92.54 124
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	79.08 13	81.84 129	80.06 144	83.91 114	89.92 108	90.62 125	86.21 143	83.48 85	73.88 155	65.75 151	66.38 147	65.30 160	84.63 81	85.90 162	87.25 140	93.45 154	91.13 151

MS-PatchMatch		81.79 130	81.44 126	82.19 134	90.35 100	89.29 155	88.08 115	75.36 179	77.60 130	69.00 137	64.37 166	78.87 92	77.14 154	88.03 130	85.70 169	93.19 160	86.24 187

PMMVS		81.65 131	84.05 107	78.86 164	78.56 213	82.63 207	83.10 171	67.22 210	81.39 96	70.11 130	84.91 42	79.74 82	82.12 99	87.31 135	85.70 169	92.03 174	86.67 186

FMVSNet1		81.64 132	80.61 137	82.84 125	82.36 199	89.20 157	88.67 104	79.58 139	70.79 174	72.63 121	58.95 193	72.26 134	79.34 137	90.73 92	90.72 73	94.47 117	91.62 143

CDS-MVSNet		81.63 133	82.09 121	81.09 146	87.21 139	90.28 130	87.46 123	80.33 128	69.06 183	70.66 125	71.30 119	73.87 123	67.99 194	89.58 111	89.87 97	92.87 164	90.69 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HyFIR lowres test		81.62 134	79.45 155	84.14 111	91.00 86	93.38 91	88.27 112	78.19 154	76.28 136	70.18 129	48.78 215	73.69 126	83.52 87	87.05 139	87.83 134	93.68 149	89.15 164

UniMVSNet (Re)		81.22 135	81.08 131	81.39 141	85.35 159	91.76 115	84.93 157	82.88 94	76.13 137	65.02 158	64.94 161	63.09 169	75.17 164	87.71 133	89.04 120	94.97 88	94.88 63

DU-MVS		81.20 136	80.30 140	82.25 132	84.98 167	90.94 123	85.70 148	83.58 81	75.74 139	64.21 161	65.30 158	59.60 191	80.22 121	86.89 142	89.31 111	94.77 98	94.29 76

dmvs_re		81.08 137	79.92 147	82.44 130	86.66 144	87.70 172	87.91 116	83.30 91	72.86 165	65.29 157	65.76 151	63.43 166	76.69 155	88.93 120	89.50 107	94.80 95	91.23 150

CostFormer		80.94 138	80.21 141	81.79 136	87.69 132	88.58 167	87.47 122	70.66 196	80.02 110	77.88 95	73.03 112	71.40 136	78.24 144	79.96 206	79.63 202	88.82 201	88.84 165

USDC		80.69 139	79.89 148	81.62 139	86.48 146	89.11 160	86.53 140	78.86 148	81.15 101	63.48 167	72.98 113	59.12 196	81.16 107	87.10 137	85.01 175	93.23 158	84.77 195

TranMVSNet+NR-MVSNet		80.52 140	79.84 149	81.33 143	84.92 169	90.39 128	85.53 153	84.22 68	74.27 151	60.68 190	64.93 162	59.96 186	77.48 150	86.75 147	89.28 112	95.12 85	93.29 99

COLMAP_ROB	76.78 15	80.50 141	78.49 160	82.85 124	90.96 87	89.65 149	86.20 144	83.40 89	77.15 132	66.54 146	62.27 171	65.62 159	77.89 147	85.23 172	84.70 179	92.11 172	84.83 194
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CHOSEN 280x420		80.28 142	81.66 123	78.67 168	82.92 192	79.24 220	85.36 154	66.79 212	78.11 127	70.32 126	75.03 100	79.87 79	81.09 108	89.07 117	83.16 189	85.54 217	87.17 180

NR-MVSNet		80.25 143	79.98 146	80.56 152	85.20 162	90.94 123	85.65 150	83.58 81	75.74 139	61.36 185	65.30 158	56.75 205	72.38 180	88.46 126	88.80 124	95.16 81	93.87 88

pmmvs4		79.99 144	78.08 166	82.22 133	83.04 189	87.16 179	84.95 156	78.80 150	78.64 125	74.53 107	64.61 164	59.41 192	79.45 136	84.13 185	84.54 182	92.53 167	88.08 173

Fast-Effi-MVS+-dtu		79.95 145	80.69 136	79.08 162	86.36 147	89.14 159	85.85 146	72.28 190	72.85 166	59.32 195	70.43 126	68.42 152	77.57 149	86.14 159	86.44 155	93.11 161	91.39 148

v8		79.90 146	78.39 163	81.66 138	83.97 178	89.81 142	87.16 130	77.40 162	71.49 169	67.71 141	61.24 176	62.49 174	79.83 130	85.48 169	86.17 159	93.89 139	92.02 134

v2v482		79.84 147	78.07 167	81.90 135	83.75 179	90.21 133	87.17 129	79.85 137	70.65 175	65.93 150	61.93 173	60.07 185	80.82 110	85.25 171	86.71 148	93.88 140	91.70 142

Baseline_NR-MVSNet		79.84 147	78.37 164	81.55 140	84.98 167	86.66 181	85.06 155	83.49 83	75.57 141	63.31 168	58.22 197	60.97 181	78.00 146	86.89 142	87.13 141	94.47 117	93.15 103

thisisatest0515		79.76 149	80.59 138	78.80 165	84.40 172	88.91 164	79.48 196	76.94 166	72.29 167	67.33 143	67.82 142	65.99 157	70.80 186	88.50 125	87.84 132	93.86 141	92.75 115

v10		79.62 150	78.19 165	81.28 144	83.73 180	89.69 147	87.27 126	76.86 167	70.50 177	65.46 152	60.58 183	60.47 183	80.44 118	86.91 141	86.63 151	93.93 136	92.55 123

V42		79.59 151	78.43 162	80.94 147	82.79 195	89.71 146	86.66 139	76.73 169	71.38 170	67.42 142	61.01 178	62.30 176	78.39 143	85.56 167	86.48 153	93.65 150	92.60 119

GA-MVS		79.52 152	79.71 152	79.30 161	85.68 154	90.36 129	84.55 161	78.44 152	70.47 178	57.87 200	68.52 138	61.38 179	76.21 158	89.40 115	87.89 131	93.04 162	89.96 160

SCA		79.51 153	80.15 143	78.75 166	86.58 145	87.70 172	83.07 172	68.53 205	81.31 97	66.40 147	73.83 106	75.38 111	79.30 138	80.49 204	79.39 205	88.63 204	82.96 202

test-LLR		79.47 154	79.84 149	79.03 163	87.47 135	82.40 210	81.24 187	78.05 156	73.72 157	62.69 171	73.76 107	74.42 117	73.49 175	84.61 181	82.99 192	91.25 185	87.01 181

IterMVS-SCA-FT		79.41 155	80.20 142	78.49 170	85.88 150	86.26 183	83.95 166	71.94 191	73.55 160	61.94 178	70.48 125	70.50 139	75.23 162	85.81 164	84.61 181	91.99 175	90.18 159

v1144		79.38 156	77.83 170	81.18 145	83.62 181	90.23 131	87.15 131	78.35 153	69.13 182	64.02 164	60.20 185	59.41 192	80.14 125	86.78 145	86.57 152	93.81 144	92.53 125

UniMVSNet_ETH3D		79.24 157	76.47 183	82.48 129	85.66 155	90.97 122	86.08 145	81.63 112	64.48 203	68.94 138	54.47 204	57.65 200	78.83 141	85.20 175	88.91 123	93.72 147	93.60 96

MDTV_nov1_ep13		79.14 158	79.49 154	78.74 167	85.40 158	86.89 180	84.32 165	70.29 198	78.85 123	69.42 134	75.37 95	73.29 130	75.64 161	80.61 202	79.48 204	87.36 208	81.91 204

TDRefinement		79.05 159	77.05 178	81.39 141	88.45 121	89.00 162	86.92 133	82.65 101	74.21 152	64.41 160	59.17 190	59.16 194	74.52 170	85.23 172	85.09 174	91.37 183	87.51 179

v1192		78.94 160	77.33 174	80.82 148	83.25 185	89.90 140	86.91 134	77.72 159	68.63 186	62.61 173	59.17 190	57.53 201	80.62 117	86.89 142	86.47 154	93.79 145	92.75 115

v144192		78.81 161	77.22 176	80.67 150	82.95 190	89.79 144	86.40 141	77.42 161	68.26 188	63.13 169	59.50 188	58.13 197	80.08 126	85.93 161	86.08 161	94.06 131	92.83 111

IterMVS		78.79 162	79.71 152	77.71 174	85.26 161	85.91 186	84.54 162	69.84 202	73.38 161	61.25 186	70.53 124	70.35 140	74.43 171	85.21 174	83.80 186	90.95 189	88.77 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		78.71 163	78.86 157	78.55 169	85.85 153	85.15 194	82.30 179	68.23 206	74.71 146	65.37 154	64.39 165	69.59 145	77.18 152	85.10 177	84.87 176	92.34 171	88.21 171

PatchmatchNet		78.67 164	78.85 158	78.46 171	86.85 143	86.03 184	83.77 168	68.11 208	80.88 105	66.19 148	72.90 114	73.40 129	78.06 145	79.25 210	77.71 210	87.75 207	81.75 205
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		78.59 165	76.84 181	80.62 151	83.61 182	89.16 158	83.65 169	79.24 144	69.38 181	69.34 135	59.88 187	60.41 184	75.19 163	83.81 187	84.63 180	92.70 166	90.63 155

v1921920		78.57 166	76.99 179	80.41 155	82.93 191	89.63 150	86.38 142	77.14 164	68.31 187	61.80 181	58.89 194	56.79 204	80.19 124	86.50 154	86.05 163	94.02 133	92.76 114

pm-mvs1		78.51 167	77.75 172	79.40 160	84.83 170	89.30 154	83.55 170	79.38 142	62.64 207	63.68 166	58.73 195	64.68 161	70.78 187	89.79 107	87.84 132	94.17 128	91.28 149

v1240		78.15 168	76.53 182	80.04 156	82.85 194	89.48 153	85.61 152	76.77 168	67.05 190	61.18 188	58.37 196	56.16 208	79.89 129	86.11 160	86.08 161	93.92 137	92.47 127

dps		78.02 169	75.94 191	80.44 154	86.06 149	86.62 182	82.58 174	69.98 200	75.14 143	77.76 97	69.08 135	59.93 187	78.47 142	79.47 208	77.96 209	87.78 206	83.40 199

anonymousdsp		77.94 170	79.00 156	76.71 182	79.03 211	87.83 171	79.58 195	72.87 188	65.80 198	58.86 199	65.82 150	62.48 175	75.99 159	86.77 146	88.66 125	93.92 137	95.68 53

test-mter		77.79 171	80.02 145	75.18 193	81.18 207	82.85 205	80.52 193	62.03 224	73.62 159	62.16 176	73.55 109	73.83 124	73.81 173	84.67 180	83.34 188	91.37 183	88.31 170

TESTMET0.1,1		77.78 172	79.84 149	75.38 192	80.86 208	82.40 210	81.24 187	62.72 223	73.72 157	62.69 171	73.76 107	74.42 117	73.49 175	84.61 181	82.99 192	91.25 185	87.01 181

tpm cat1		77.78 172	75.28 198	80.70 149	87.14 140	85.84 187	85.81 147	70.40 197	77.44 131	78.80 88	63.72 167	64.01 165	76.55 157	75.60 218	75.21 216	85.51 218	85.12 192

EPMVS		77.53 174	78.07 167	76.90 181	86.89 142	84.91 197	82.18 182	66.64 213	81.00 103	64.11 163	72.75 115	69.68 144	74.42 172	79.36 209	78.13 208	87.14 210	80.68 212

tfpnnormal		77.46 175	74.86 200	80.49 153	86.34 148	88.92 163	84.33 164	81.26 117	61.39 211	61.70 182	51.99 212	53.66 217	74.84 167	88.63 123	87.38 139	94.50 114	92.08 130

v7n		77.22 176	76.23 186	78.38 172	81.89 202	89.10 161	82.24 181	76.36 170	65.96 197	61.21 187	56.56 200	55.79 209	75.07 166	86.55 151	86.68 149	93.52 152	92.95 108

RPMNet		77.07 177	77.63 173	76.42 184	85.56 157	85.15 194	81.37 184	65.27 217	74.71 146	60.29 191	63.71 168	66.59 156	73.64 174	82.71 194	82.12 197	92.38 170	88.39 169

pmmvs5		76.93 178	76.33 185	77.62 175	81.97 201	88.40 169	81.32 186	74.35 183	65.42 201	61.42 184	63.07 169	57.95 199	73.23 178	85.60 166	85.35 173	93.41 155	88.55 168

TinyColmap		76.73 179	73.95 203	79.96 157	85.16 164	85.64 190	82.34 178	78.19 154	70.63 176	62.06 177	60.69 182	49.61 222	80.81 111	85.12 176	83.69 187	91.22 187	82.27 203

CVMVSNet		76.70 180	78.46 161	74.64 198	83.34 184	84.48 198	81.83 183	74.58 180	68.88 184	51.23 213	69.77 127	70.05 141	67.49 197	84.27 184	83.81 185	89.38 199	87.96 175

WR-MVS		76.63 181	78.02 169	75.02 194	84.14 177	89.76 145	78.34 203	80.64 123	69.56 180	52.32 209	61.26 175	61.24 180	60.66 209	84.45 183	87.07 142	93.99 135	92.77 113

TransMVSNet (Re)		76.57 182	75.16 199	78.22 173	85.60 156	87.24 177	82.46 175	81.23 118	59.80 215	59.05 198	57.07 199	59.14 195	66.60 202	88.09 129	86.82 146	94.37 123	87.95 176

tpmrst		76.55 183	75.99 190	77.20 177	87.32 137	83.05 203	82.86 173	65.62 215	78.61 126	67.22 144	69.19 133	65.71 158	75.87 160	76.75 216	75.33 215	84.31 220	83.28 200

FC-MVSNet-test		76.53 184	81.62 124	70.58 208	84.99 166	85.73 188	74.81 211	78.85 149	77.00 133	39.13 227	75.90 89	73.50 128	54.08 217	86.54 152	85.99 164	91.65 179	86.68 184

PatchT		76.42 185	77.81 171	74.80 196	78.46 214	84.30 199	71.82 217	65.03 219	73.89 154	65.37 154	61.58 174	66.70 155	77.18 152	85.10 177	84.87 176	90.94 190	88.21 171

TAMVS		76.42 185	77.16 177	75.56 190	83.05 188	85.55 191	80.58 192	71.43 193	65.40 202	61.04 189	67.27 144	69.22 148	67.99 194	84.88 179	84.78 178	89.28 200	83.01 201

EG-PatchMatch MVS		76.40 187	75.47 196	77.48 176	85.86 152	90.22 132	82.45 176	73.96 185	59.64 216	59.60 194	52.75 210	62.20 177	68.44 193	88.23 128	87.50 136	94.55 112	87.78 177

CP-MVSNet		76.36 188	76.41 184	76.32 186	82.73 196	88.64 165	79.39 197	79.62 138	67.21 189	53.70 205	60.72 181	55.22 211	67.91 196	83.52 189	86.34 157	94.55 112	93.19 100

tpm		76.30 189	76.05 189	76.59 183	86.97 141	83.01 204	83.83 167	67.06 211	71.83 168	63.87 165	69.56 131	62.88 171	73.41 177	79.79 207	78.59 206	84.41 219	86.68 184

test0.0.03 1		76.03 190	78.51 159	73.12 204	87.47 135	85.13 196	76.32 208	78.05 156	73.19 164	50.98 214	70.64 122	69.28 146	55.53 213	85.33 170	84.38 183	90.39 193	81.63 207

PEN-MVS		76.02 191	76.07 187	75.95 189	83.17 187	87.97 170	79.65 194	80.07 135	66.57 193	51.45 211	60.94 179	55.47 210	66.81 200	82.72 193	86.80 147	94.59 109	92.03 133

SixPastTwentyTwo		76.02 191	75.72 193	76.36 185	83.38 183	87.54 174	75.50 210	76.22 171	65.50 200	57.05 201	70.64 122	53.97 216	74.54 169	80.96 201	82.12 197	91.44 181	89.35 163

PS-CasMVS		75.90 193	75.86 192	75.96 188	82.59 197	88.46 168	79.23 200	79.56 140	66.00 196	52.77 207	59.48 189	54.35 215	67.14 199	83.37 190	86.23 158	94.47 117	93.10 104

WR-MVS_H		75.84 194	76.93 180	74.57 199	82.86 193	89.50 152	78.34 203	79.36 143	66.90 191	52.51 208	60.20 185	59.71 188	59.73 210	83.61 188	85.77 168	94.65 106	92.84 110

LTVRE_ROB	74.41 16	75.78 195	74.72 201	77.02 180	85.88 150	89.22 156	82.44 177	77.17 163	50.57 226	45.45 220	65.44 156	52.29 219	81.25 105	85.50 168	87.42 138	89.94 197	92.62 118
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
gg-mvs-nofinetune		75.64 196	77.26 175	73.76 200	87.92 129	92.20 110	87.32 124	64.67 220	51.92 225	35.35 230	46.44 218	77.05 105	71.97 181	92.64 54	91.02 67	95.34 68	89.53 162

FMVSNet5		75.50 197	76.07 187	74.83 195	76.16 218	81.19 213	81.34 185	70.21 199	73.20 163	61.59 183	58.97 192	68.33 153	68.50 192	85.87 163	85.85 167	91.18 188	79.11 215

DTE-MVSNet		75.14 198	75.44 197	74.80 196	83.18 186	87.19 178	78.25 205	80.11 132	66.05 195	48.31 216	60.88 180	54.67 212	64.54 205	82.57 195	86.17 159	94.43 120	90.53 157

pmmvs6		74.83 199	72.89 206	77.09 178	82.11 200	87.50 175	80.88 191	76.97 165	52.79 224	61.91 180	46.66 217	60.49 182	69.28 190	86.74 148	85.46 172	91.39 182	90.56 156

MIMVSNet		74.69 200	75.60 195	73.62 201	76.02 220	85.31 193	81.21 189	67.43 209	71.02 172	59.07 197	54.48 203	64.07 163	66.14 203	86.52 153	86.64 150	91.83 177	81.17 209

ADS-MVSNet		74.53 201	75.69 194	73.17 203	81.57 205	80.71 215	79.27 199	63.03 222	79.27 121	59.94 193	67.86 141	68.32 154	71.08 185	77.33 214	76.83 212	84.12 222	79.53 213

pmmvs-eth3d		74.32 202	71.96 208	77.08 179	77.33 216	82.71 206	78.41 202	76.02 174	66.65 192	65.98 149	54.23 206	49.02 224	73.14 179	82.37 197	82.69 194	91.61 180	86.05 189

PM-MVS		74.17 203	73.10 204	75.41 191	76.07 219	82.53 208	77.56 206	71.69 192	71.04 171	61.92 179	61.23 177	47.30 226	74.82 168	81.78 199	79.80 201	90.42 192	88.05 174

CMPMVS	56.49 17	73.84 204	71.73 210	76.31 187	85.20 162	85.67 189	75.80 209	73.23 186	62.26 208	65.40 153	53.40 209	59.70 189	71.77 183	80.25 205	79.56 203	86.45 214	81.28 208
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		73.21 205	72.91 205	73.56 202	80.01 209	84.28 200	78.62 201	66.43 214	68.64 185	59.12 196	60.39 184	59.69 190	69.81 189	78.82 212	77.43 211	87.36 208	81.11 210

pmnet_mix02		71.95 206	71.83 209	72.10 205	81.40 206	80.63 216	73.78 213	72.85 189	70.90 173	54.89 203	62.17 172	57.42 202	62.92 207	76.80 215	73.98 219	86.74 213	80.87 211

testgi		71.92 207	74.20 202	69.27 210	84.58 171	83.06 202	73.40 214	74.39 182	64.04 205	46.17 219	68.90 137	57.15 203	48.89 221	84.07 186	83.08 191	88.18 205	79.09 216

Anonymous20231206		70.80 208	70.59 212	71.04 207	81.60 204	82.49 209	74.64 212	75.87 175	64.17 204	49.27 215	44.85 221	53.59 218	54.68 216	83.07 191	82.34 196	90.17 194	83.65 198

gm-plane-assit		70.29 209	70.65 211	69.88 209	85.03 165	78.50 221	58.41 228	65.47 216	50.39 227	40.88 225	49.60 214	50.11 221	75.14 165	91.43 70	89.78 99	94.32 124	84.73 196

EU-MVSNet		69.98 210	72.30 207	67.28 213	75.67 221	79.39 219	73.12 215	69.94 201	63.59 206	42.80 223	62.93 170	56.71 206	55.07 215	79.13 211	78.55 207	87.06 211	85.82 191

MVS-HIRNet		68.83 211	66.39 216	71.68 206	77.58 215	75.52 223	66.45 223	65.05 218	62.16 209	62.84 170	44.76 222	56.60 207	71.96 182	78.04 213	75.06 217	86.18 216	72.56 222

test20.03		68.31 212	70.05 213	66.28 215	82.41 198	80.84 214	67.35 222	76.11 173	58.44 218	40.80 226	53.77 208	54.54 213	42.28 224	83.07 191	81.96 199	88.73 203	77.76 218

N_pmnet		66.85 213	66.63 215	67.11 214	78.73 212	74.66 224	70.53 218	71.07 194	66.46 194	46.54 218	51.68 213	51.91 220	55.48 214	74.68 219	72.38 220	80.29 225	74.65 221

MDA-MVSNet-bldmvs		66.22 214	64.49 218	68.24 211	61.67 227	82.11 212	70.07 219	76.16 172	59.14 217	47.94 217	54.35 205	35.82 234	67.33 198	64.94 226	75.68 214	86.30 215	79.36 214

FE-MVSNET		66.05 215	67.24 214	64.66 216	59.88 229	79.66 218	69.18 220	74.46 181	55.47 223	37.02 229	41.66 225	48.62 225	55.72 212	80.54 203	83.09 190	91.68 178	81.66 206

MIMVSNet1		65.00 216	66.24 217	63.55 218	58.41 231	80.01 217	69.00 221	74.03 184	55.81 221	41.88 224	36.81 227	49.48 223	47.89 222	81.32 200	82.40 195	90.08 196	77.88 217

new-patchmatchnet		63.80 217	63.31 219	64.37 217	76.49 217	75.99 222	63.73 225	70.99 195	57.27 219	43.08 222	45.86 219	43.80 227	45.13 223	73.20 220	70.68 223	86.80 212	76.34 220

FPMVS		63.63 218	60.08 223	67.78 212	80.01 209	71.50 226	72.88 216	69.41 204	61.82 210	53.11 206	45.12 220	42.11 230	50.86 219	66.69 224	63.84 225	80.41 224	69.46 224

pmmvs3		61.89 219	61.74 221	62.06 219	64.30 226	70.83 227	64.22 224	52.14 228	48.78 228	44.47 221	41.67 224	41.70 231	63.03 206	76.06 217	76.02 213	84.18 221	77.14 219

new_pmnet		59.28 220	61.47 222	56.73 221	61.66 228	68.29 228	59.57 227	54.91 225	60.83 212	34.38 231	44.66 223	43.65 228	49.90 220	71.66 221	71.56 222	79.94 226	69.67 223

GG-mvs-BLEND		57.56 221	82.61 119	28.34 229	0.22 238	90.10 135	79.37 198	0.14 235	79.56 117	0.40 239	71.25 121	83.40 62	0.30 236	86.27 158	83.87 184	89.59 198	83.83 197

PMVS	50.48 18	55.81 222	51.93 225	60.33 220	72.90 224	49.34 231	48.78 229	69.51 203	43.49 230	54.25 204	36.26 228	41.04 232	39.71 226	65.07 225	60.70 226	76.85 227	67.58 225
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		52.27 223	57.26 224	46.45 223	75.64 222	65.62 229	40.45 234	75.80 176	47.10 229	9.11 237	53.83 207	38.98 233	14.47 232	69.44 222	68.29 224	63.24 230	57.56 229

Gipuma		49.17 224	47.05 227	51.65 222	59.67 230	48.39 232	41.98 232	63.47 221	55.64 222	33.33 232	14.90 231	13.78 238	41.34 225	69.31 223	72.30 221	70.11 228	55.00 230
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		41.78 225	48.10 226	34.42 227	10.74 237	19.78 238	44.64 231	17.73 232	59.83 214	38.67 228	35.82 229	54.41 214	34.94 227	62.87 227	43.13 230	59.81 231	60.82 227

PMMVS2		41.68 226	44.74 228	38.10 224	46.97 234	52.32 230	40.63 233	48.08 229	35.51 231	7.36 238	26.86 230	24.64 236	16.72 231	55.24 229	59.03 227	68.85 229	59.59 228

E-PMN		31.40 227	26.80 230	36.78 225	51.39 233	29.96 235	20.20 236	54.17 226	25.93 233	12.75 235	14.73 232	8.58 240	34.10 229	27.36 232	37.83 231	48.07 234	43.18 232

MVE	30.17 19	30.88 228	33.52 229	27.80 230	23.78 236	39.16 234	18.69 238	46.90 230	21.88 234	15.39 234	14.37 233	7.31 241	24.41 230	41.63 231	56.22 228	37.64 236	54.07 231
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		30.49 229	25.44 231	36.39 226	51.47 232	29.89 236	20.17 237	54.00 227	26.49 232	12.02 236	13.94 234	8.84 239	34.37 228	25.04 233	34.37 232	46.29 235	39.53 233

testmvs		1.03 230	1.63 232	0.34 231	0.09 239	0.35 239	0.61 240	0.16 234	1.49 235	0.10 240	3.15 235	0.15 242	0.86 235	1.32 234	1.18 233	0.20 237	3.76 235

test123		0.87 231	1.40 233	0.25 232	0.03 240	0.25 240	0.35 241	0.08 236	1.21 236	0.05 241	2.84 236	0.03 243	0.89 234	0.43 235	1.16 234	0.13 238	3.87 234

uanet_test		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet-low-res		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 244	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

TPM-MVS					96.31 27	96.02 38	94.89 31			86.52 37	87.18 37	92.17 16	86.76 65			95.56 55	93.85 89
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										56.08 202

9.14												92.16 17

SR-MVS					96.58 25			90.99 21				92.40 13

Anonymous202405211			82.75 118		89.58 112	92.97 98	89.04 100	84.13 69	78.72 124		57.18 198	76.64 107	83.13 91	89.55 112	89.92 96	93.38 156	94.28 79

our_test_3					81.81 203	83.96 201	76.61 207

ambc			61.92 220		70.98 225	73.54 225	63.64 226		60.06 213	52.23 210	38.44 226	19.17 237	57.12 211	82.33 198	75.03 218	83.21 223	84.89 193

MTAPA										92.97 2		91.03 24

MTMP										93.14 1		90.21 31

Patchmatch-RL test							8.55 239

tmp_tt				32.73 228	43.96 235	21.15 237	26.71 235	8.99 233	65.67 199	51.39 212	56.01 201	42.64 229	11.76 233	56.60 228	50.81 229	53.55 233

XVS					93.11 60	96.70 25	91.91 53			83.95 50		88.82 40				95.79 40

X-MVStestdata					93.11 60	96.70 25	91.91 53			83.95 50		88.82 40				95.79 40

mPP-MVS					97.06 12							88.08 45

NP-MVS									87.47 55

Patchmtry						85.54 192	82.30 179	68.23 206		65.37 154

DeepMVS_CX						48.31 233	48.03 230	26.08 231	56.42 220	25.77 233	47.51 216	31.31 235	51.30 218	48.49 230		53.61 232	61.52 226

High-resolution multi-view benchmark