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++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 4	91.18 1	81.17 2	89.55 2	87.93 8	91.01 7	96.21 1

SED-MVS		88.85 2	91.59 3	85.67 2	90.54 15	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 3	90.64 4	81.10 3	89.53 3	88.02 7	91.00 8	95.73 3

DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 16	92.36 2	90.69 9	76.15 4	93.08 2	82.75 4	92.19 6	90.71 3	80.45 6	89.27 6	87.91 9	90.82 12	95.84 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		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 8	82.09 6	93.85 1	90.75 2	81.25 1	88.62 8	87.59 15	90.96 9	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		88.09 5	90.84 5	84.88 7	90.00 23	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 2	89.18 6	80.89 4	87.99 16	87.91 9	89.70 45	94.51 7
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
APDe-MVS		88.00 6	90.50 6	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 14	92.27 5	88.34 11	80.80 5	88.00 15	86.99 19	91.09 5	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		87.56 7	90.17 7	84.52 9	91.71 3	90.57 9	90.77 8	75.19 13	90.67 7	80.50 13	86.59 17	88.86 8	78.09 15	89.92 1	89.41 1	90.84 11	95.19 5
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		87.47 8	89.70 8	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 7	91.12 8	88.93 7	78.82 10	87.42 20	86.23 30	91.28 3	93.90 13

HPM-MVS++		87.09 9	88.92 13	84.95 6	92.61 1	87.91 40	90.23 15	76.06 5	88.85 12	81.20 9	87.33 13	87.93 12	79.47 9	88.59 9	88.23 5	90.15 34	93.60 20

SD-MVS		86.96 10	89.45 9	84.05 14	90.13 19	89.23 23	89.77 18	74.59 14	89.17 10	80.70 10	89.93 11	89.67 5	78.47 12	87.57 19	86.79 23	90.67 18	93.76 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.		86.88 11	89.23 10	84.14 12	89.78 26	88.67 30	90.59 10	73.46 26	88.99 11	80.52 12	91.26 7	88.65 9	79.91 8	86.96 29	86.22 31	90.59 20	93.83 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APD-MVS		86.84 12	88.91 14	84.41 10	90.66 11	90.10 13	90.78 7	75.64 9	87.38 16	78.72 18	90.68 10	86.82 17	80.15 7	87.13 25	86.45 29	90.51 21	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMMP_NAP		86.52 13	89.01 11	83.62 16	90.28 18	90.09 14	90.32 13	74.05 19	88.32 13	79.74 15	87.04 15	85.59 23	76.97 28	89.35 4	88.44 4	90.35 30	94.27 11

CNVR-MVS		86.36 14	88.19 17	84.23 11	91.33 5	89.84 15	90.34 11	75.56 10	87.36 17	78.97 17	81.19 29	86.76 18	78.74 11	89.30 5	88.58 2	90.45 27	94.33 10

HFP-MVS		86.15 15	87.95 18	84.06 13	90.80 9	89.20 24	89.62 19	74.26 16	87.52 14	80.63 11	86.82 16	84.19 29	78.22 14	87.58 18	87.19 17	90.81 13	93.13 25

SteuartSystems-ACMMP		85.99 16	88.31 16	83.27 20	90.73 10	89.84 15	90.27 14	74.31 15	84.56 29	75.88 31	87.32 14	85.04 24	77.31 23	89.01 7	88.46 3	91.14 4	93.96 12
Skip Steuart: Steuart Systems R&D Blog.
ACMMPR		85.52 17	87.53 20	83.17 21	90.13 19	89.27 21	89.30 20	73.97 20	86.89 19	77.14 25	86.09 18	83.18 32	77.74 19	87.42 20	87.20 16	90.77 14	92.63 26

MP-MVS		85.50 18	87.40 21	83.28 19	90.65 12	89.51 20	89.16 23	74.11 18	83.70 34	78.06 22	85.54 20	84.89 28	77.31 23	87.40 22	87.14 18	90.41 28	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NCCC		85.34 19	86.59 25	83.88 15	91.48 4	88.88 25	89.79 17	75.54 11	86.67 20	77.94 23	76.55 35	84.99 25	78.07 16	88.04 13	87.68 13	90.46 26	93.31 21

DeepPCF-MVS	79.04 1	85.30 20	88.93 12	81.06 32	88.77 36	90.48 11	85.46 46	73.08 28	90.97 6	73.77 38	84.81 22	85.95 20	77.43 22	88.22 11	87.73 11	87.85 86	94.34 9

CSCG		85.28 21	87.68 19	82.49 24	89.95 24	91.99 5	88.82 24	71.20 37	86.41 21	79.63 16	79.26 30	88.36 10	73.94 41	86.64 31	86.67 26	91.40 2	94.41 8

MCST-MVS		85.13 22	86.62 24	83.39 17	90.55 14	89.82 17	89.29 21	73.89 22	84.38 30	76.03 30	79.01 32	85.90 21	78.47 12	87.81 17	86.11 33	92.11 1	93.29 22

TSAR-MVS + ACMM		85.10 23	88.81 15	80.77 35	89.55 29	88.53 32	88.59 27	72.55 30	87.39 15	71.90 43	90.95 9	87.55 13	74.57 36	87.08 27	86.54 27	87.47 94	93.67 17

train_agg		84.86 24	87.21 23	82.11 26	90.59 13	85.47 55	89.81 16	73.55 25	83.95 31	73.30 39	89.84 12	87.23 15	75.61 33	86.47 33	85.46 38	89.78 40	92.06 32

DeepC-MVS	78.47 2	84.81 25	86.03 29	83.37 18	89.29 32	90.38 12	88.61 26	76.50 1	86.25 22	77.22 24	75.12 41	80.28 45	77.59 21	88.39 10	88.17 6	91.02 6	93.66 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CP-MVS		84.74 26	86.43 27	82.77 23	89.48 30	88.13 39	88.64 25	73.93 21	84.92 24	76.77 27	81.94 27	83.50 31	77.29 25	86.92 30	86.49 28	90.49 22	93.14 24

MVS_0304		84.63 27	87.25 22	81.59 29	88.58 37	90.50 10	87.82 34	69.16 52	83.82 33	78.46 20	82.32 25	84.97 26	74.56 37	88.16 12	87.72 12	90.94 10	93.24 23

PGM-MVS		84.42 28	86.29 28	82.23 25	90.04 22	88.82 26	89.23 22	71.74 35	82.82 39	74.61 34	84.41 23	82.09 35	77.03 27	87.13 25	86.73 25	90.73 16	92.06 32

DeepC-MVS_fast	78.24 3	84.27 29	85.50 31	82.85 22	90.46 17	89.24 22	87.83 33	74.24 17	84.88 25	76.23 29	75.26 40	81.05 43	77.62 20	88.02 14	87.62 14	90.69 17	92.41 28
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.		83.69 30	86.58 26	80.32 36	85.14 54	86.96 44	84.91 50	70.25 41	84.71 28	73.91 37	85.16 21	85.63 22	77.92 17	85.44 42	85.71 36	89.77 41	92.45 27

ACMMP		83.42 31	85.27 32	81.26 31	88.47 38	88.49 33	88.31 31	72.09 32	83.42 35	72.77 41	82.65 24	78.22 50	75.18 34	86.24 38	85.76 35	90.74 15	92.13 31
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
DPM-MVS		83.30 32	84.33 35	82.11 26	89.56 28	88.49 33	90.33 12	73.24 27	83.85 32	76.46 28	72.43 52	82.65 33	73.02 48	86.37 35	86.91 20	90.03 36	89.62 53

X-MVS		83.23 33	85.20 33	80.92 34	89.71 27	88.68 27	88.21 32	73.60 23	82.57 40	71.81 46	77.07 33	81.92 37	71.72 58	86.98 28	86.86 21	90.47 23	92.36 29

CDPH-MVS		82.64 34	85.03 34	79.86 39	89.41 31	88.31 36	88.32 30	71.84 34	80.11 46	67.47 65	82.09 26	81.44 41	71.85 56	85.89 41	86.15 32	90.24 32	91.25 38

3Dnovator+	75.73 4	82.40 35	82.76 39	81.97 28	88.02 39	89.67 18	86.60 38	71.48 36	81.28 44	78.18 21	64.78 90	77.96 52	77.13 26	87.32 23	86.83 22	90.41 28	91.48 36

PHI-MVS		82.36 36	85.89 30	78.24 47	86.40 48	89.52 19	85.52 44	69.52 48	82.38 42	65.67 72	81.35 28	82.36 34	73.07 47	87.31 24	86.76 24	89.24 52	91.56 35

MSLP-MVS++		82.09 37	82.66 40	81.42 30	87.03 44	87.22 43	85.82 42	70.04 42	80.30 45	78.66 19	68.67 74	81.04 44	77.81 18	85.19 46	84.88 43	89.19 56	91.31 37

CPTT-MVS		81.77 38	83.10 38	80.21 37	85.93 50	86.45 49	87.72 35	70.98 38	82.54 41	71.53 49	74.23 45	81.49 40	76.31 31	82.85 71	81.87 67	88.79 65	92.26 30

CANet		81.62 39	83.41 36	79.53 41	87.06 43	88.59 31	85.47 45	67.96 58	76.59 54	74.05 35	74.69 42	81.98 36	72.98 49	86.14 39	85.47 37	89.68 46	90.42 46

HQP-MVS		81.19 40	83.27 37	78.76 44	87.40 42	85.45 56	86.95 36	70.47 40	81.31 43	66.91 69	79.24 31	76.63 54	71.67 59	84.43 54	83.78 52	89.19 56	92.05 34

OMC-MVS		80.26 41	82.59 41	77.54 50	83.04 62	85.54 54	83.25 56	65.05 79	87.32 18	72.42 42	72.04 54	78.97 47	73.30 45	83.86 57	81.60 71	88.15 75	88.83 58

MVS_111021_HR		80.13 42	81.46 46	78.58 45	85.77 51	85.17 59	83.45 55	69.28 49	74.08 62	70.31 54	74.31 44	75.26 63	73.13 46	86.46 34	85.15 41	89.53 47	89.81 51

LGP-MVS_train		79.83 43	81.22 49	78.22 48	86.28 49	85.36 58	86.76 37	69.59 46	77.34 51	65.14 75	75.68 37	70.79 84	71.37 62	84.60 50	84.01 47	90.18 33	90.74 42

ACMP	73.23 7	79.79 44	80.53 54	78.94 42	85.61 52	85.68 53	85.61 43	69.59 46	77.33 52	71.00 52	74.45 43	69.16 95	71.88 54	83.15 67	83.37 55	89.92 37	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
3Dnovator	73.76 5	79.75 45	80.52 55	78.84 43	84.94 59	87.35 41	84.43 52	65.54 75	78.29 50	73.97 36	63.00 98	75.62 62	74.07 40	85.00 47	85.34 39	90.11 35	89.04 56

AdaColmap		79.74 46	78.62 64	81.05 33	89.23 33	86.06 52	84.95 49	71.96 33	79.39 49	75.51 32	63.16 96	68.84 100	76.51 29	83.55 61	82.85 59	88.13 76	86.46 80

OPM-MVS		79.68 47	79.28 62	80.15 38	87.99 40	86.77 46	88.52 28	72.72 29	64.55 103	67.65 64	67.87 78	74.33 67	74.31 39	86.37 35	85.25 40	89.73 44	89.81 51
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EC-MVSNet		79.44 48	81.35 47	77.22 52	82.95 63	84.67 63	81.31 61	63.65 92	72.47 69	68.75 57	73.15 47	78.33 49	75.99 32	86.06 40	83.96 49	90.67 18	90.79 41

PCF-MVS	73.28 6	79.42 49	80.41 56	78.26 46	84.88 60	88.17 37	86.08 39	69.85 43	75.23 57	68.43 58	68.03 77	78.38 48	71.76 57	81.26 90	80.65 89	88.56 68	91.18 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		79.35 50	81.23 48	77.16 53	85.01 57	86.92 45	85.87 41	60.89 134	80.07 48	75.35 33	72.96 48	73.21 72	68.43 80	85.41 44	84.63 44	87.41 95	85.44 92
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		79.22 51	81.11 50	77.01 54	81.36 77	84.03 67	80.35 68	63.25 96	73.43 66	70.37 53	74.10 46	76.03 59	76.40 30	86.32 37	83.95 50	90.34 31	89.93 49

MAR-MVS		79.21 52	80.32 57	77.92 49	87.46 41	88.15 38	83.95 53	67.48 64	74.28 59	68.25 59	64.70 91	77.04 53	72.17 52	85.42 43	85.00 42	88.22 72	87.62 67
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
sasdasda		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 64	63.18 98	82.90 37	67.34 66	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

canonicalmvs		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 64	63.18 98	82.90 37	67.34 66	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

DELS-MVS		79.15 55	81.07 51	76.91 55	83.54 61	87.31 42	84.45 51	64.92 80	69.98 73	69.34 56	71.62 56	76.26 55	69.84 68	86.57 32	85.90 34	89.39 49	89.88 50
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		79.08 56	80.62 53	77.28 51	88.90 35	83.17 82	83.65 54	72.41 31	74.41 58	67.15 68	76.78 34	74.37 66	64.43 102	83.70 60	83.69 53	87.15 98	88.19 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMM	72.26 8	78.86 57	78.13 66	79.71 40	86.89 45	83.40 77	86.02 40	70.50 39	75.28 56	71.49 50	63.01 97	69.26 94	73.57 43	84.11 56	83.98 48	89.76 42	87.84 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SPE-MVS-test		78.79 58	80.72 52	76.53 57	81.11 82	83.88 70	79.69 77	63.72 91	73.80 63	69.95 55	75.40 39	76.17 56	74.85 35	84.50 53	82.78 60	89.87 39	88.54 60

QAPM		78.47 59	80.22 58	76.43 58	85.03 56	86.75 47	80.62 67	66.00 72	73.77 64	65.35 74	65.54 86	78.02 51	72.69 50	83.71 59	83.36 56	88.87 62	90.41 47

TSAR-MVS + COLMAP		78.34 60	81.64 45	74.48 74	80.13 94	85.01 60	81.73 58	65.93 74	84.75 27	61.68 88	85.79 19	66.27 110	71.39 61	82.91 70	80.78 80	86.01 135	85.98 82

MVS_111021_LR		78.13 61	79.85 60	76.13 59	81.12 81	81.50 93	80.28 69	65.25 77	76.09 55	71.32 51	76.49 36	72.87 74	72.21 51	82.79 72	81.29 73	86.59 120	87.91 64

casdiffmvs_mvg		77.79 62	79.55 61	75.73 61	81.56 74	84.70 62	82.12 57	64.26 87	74.27 60	67.93 62	70.83 61	74.66 65	69.19 75	83.33 66	81.94 66	89.29 51	87.14 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
TAPA-MVS	71.42 9	77.69 63	80.05 59	74.94 67	80.68 86	84.52 65	81.36 60	63.14 100	84.77 26	64.82 77	68.72 72	75.91 60	71.86 55	81.62 78	79.55 107	87.80 88	85.24 95
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETV-MVS		77.32 64	78.81 63	75.58 62	82.24 71	83.64 75	79.98 70	64.02 88	69.64 78	63.90 82	70.89 60	69.94 90	73.41 44	85.39 45	83.91 51	89.92 37	88.31 61

CNLPA		77.20 65	77.54 71	76.80 56	82.63 65	84.31 66	79.77 74	64.64 81	85.17 23	73.18 40	56.37 134	69.81 91	74.53 38	81.12 93	78.69 118	86.04 134	87.29 70

casdiffmvs		76.76 66	78.46 65	74.77 69	80.32 91	83.73 74	80.65 66	63.24 97	73.58 65	66.11 71	69.39 69	74.09 68	69.49 73	82.52 74	79.35 112	88.84 64	86.52 79
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		76.57 67	77.90 67	75.02 66	80.56 87	86.58 48	79.24 82	66.18 69	64.81 100	68.18 60	65.61 84	71.45 78	67.05 84	84.16 55	81.80 68	88.90 60	90.92 40

MGCFI-Net		76.55 68	81.71 44	70.52 96	81.71 73	84.62 64	75.02 123	62.17 121	82.91 36	53.58 128	72.78 51	75.87 61	61.75 125	82.96 69	82.61 62	88.86 63	90.26 48

viewmanbaseed2359cas		76.36 69	77.87 68	74.60 72	79.81 95	82.88 85	81.69 59	61.02 132	72.14 71	67.97 61	69.61 67	72.45 75	69.53 71	81.53 81	79.83 100	87.57 92	86.65 78

PVSNet_BlendedMVS		76.21 70	77.52 72	74.69 70	79.46 98	83.79 72	77.50 101	64.34 85	69.88 74	71.88 44	68.54 75	70.42 86	67.05 84	83.48 62	79.63 103	87.89 84	86.87 75

PVSNet_Blended		76.21 70	77.52 72	74.69 70	79.46 98	83.79 72	77.50 101	64.34 85	69.88 74	71.88 44	68.54 75	70.42 86	67.05 84	83.48 62	79.63 103	87.89 84	86.87 75

OpenMVS	70.44 10	76.15 72	76.82 81	75.37 65	85.01 57	84.79 61	78.99 86	62.07 122	71.27 72	67.88 63	57.91 127	72.36 76	70.15 67	82.23 76	81.41 72	88.12 77	87.78 66

PLC	68.99 11	75.68 73	75.31 86	76.12 60	82.94 64	81.26 97	79.94 72	66.10 70	77.15 53	66.86 70	59.13 117	68.53 102	73.73 42	80.38 103	79.04 113	87.13 102	81.68 132
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		75.64 74	76.60 82	74.53 73	82.43 68	83.84 71	78.32 94	62.28 120	65.96 93	63.28 86	68.95 70	67.54 105	71.61 60	82.55 73	81.63 70	89.24 52	85.72 86

MVS_Test		75.37 75	77.13 79	73.31 79	79.07 101	81.32 96	79.98 70	60.12 146	69.72 76	64.11 81	70.53 63	73.22 71	68.90 76	80.14 110	79.48 109	87.67 90	85.50 90

Effi-MVS+		75.28 76	76.20 83	74.20 75	81.15 80	83.24 80	81.11 62	63.13 101	66.37 89	60.27 92	64.30 94	68.88 99	70.93 66	81.56 80	81.69 69	88.61 66	87.35 68

DI_MVS_pp		75.13 77	76.12 84	73.96 76	78.18 107	81.55 91	80.97 63	62.54 115	68.59 79	65.13 76	61.43 101	74.81 64	69.32 74	81.01 95	79.59 105	87.64 91	85.89 83

diffmvs_AUTHOR		74.91 78	77.47 74	71.92 84	75.60 133	80.50 106	79.48 80	60.02 148	72.41 70	64.39 79	70.63 62	73.27 70	66.55 93	79.97 111	78.34 123	85.46 146	87.17 72

diffmvs		74.86 79	77.37 76	71.93 83	75.62 131	80.35 110	79.42 81	60.15 145	72.81 68	64.63 78	71.51 57	73.11 73	66.53 96	79.02 125	77.98 127	85.25 150	86.83 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UA-Net		74.47 80	77.80 69	70.59 95	85.33 53	85.40 57	73.54 148	65.98 73	60.65 134	56.00 113	72.11 53	79.15 46	54.63 173	83.13 68	82.25 64	88.04 80	81.92 130

GeoE		74.23 81	74.84 90	73.52 77	80.42 90	81.46 94	79.77 74	61.06 131	67.23 86	63.67 83	59.56 114	68.74 101	67.90 81	80.25 108	79.37 111	88.31 69	87.26 71

LS3D		74.08 82	73.39 98	74.88 68	85.05 55	82.62 87	79.71 76	68.66 53	72.82 67	58.80 96	57.61 128	61.31 125	71.07 65	80.32 104	78.87 117	86.00 136	80.18 147

EPP-MVSNet		74.00 83	77.41 75	70.02 104	80.53 88	83.91 69	74.99 124	62.68 113	65.06 98	49.77 150	68.68 73	72.09 77	63.06 110	82.49 75	80.73 81	89.12 58	88.91 57

FA-MVS(training)		73.66 84	74.95 89	72.15 82	78.63 105	80.46 108	78.92 88	54.79 176	69.71 77	65.37 73	62.04 99	66.89 108	67.10 83	80.72 97	79.87 99	88.10 79	84.97 100

DCV-MVSNet		73.65 85	75.78 85	71.16 89	80.19 92	79.27 120	77.45 103	61.68 128	66.73 88	58.72 97	65.31 87	69.96 89	62.19 115	81.29 89	80.97 77	86.74 113	86.91 74

viewmambaseed2359dif		73.61 86	75.14 87	71.84 85	75.87 128	79.69 115	78.99 86	60.42 141	68.19 81	64.15 80	67.85 79	71.20 82	66.55 93	77.41 142	75.78 157	85.04 153	85.85 84

IS_MVSNet		73.33 87	77.34 77	68.65 119	81.29 78	83.47 76	74.45 130	63.58 94	65.75 95	48.49 155	67.11 83	70.61 85	54.63 173	84.51 52	83.58 54	89.48 48	86.34 81

CANet_DTU		73.29 88	76.96 80	69.00 116	77.04 119	82.06 89	79.49 79	56.30 173	67.85 84	53.29 130	71.12 59	70.37 88	61.81 124	81.59 79	80.96 78	86.09 129	84.73 104

Fast-Effi-MVS+		73.11 89	73.66 95	72.48 81	77.72 113	80.88 103	78.55 91	58.83 162	65.19 97	60.36 91	59.98 111	62.42 122	71.22 64	81.66 77	80.61 91	88.20 73	84.88 103

UGNet		72.78 90	77.67 70	67.07 141	71.65 170	83.24 80	75.20 117	63.62 93	64.93 99	56.72 109	71.82 55	73.30 69	49.02 186	81.02 94	80.70 87	86.22 126	88.67 59
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
Vis-MVSNet		72.77 91	77.20 78	67.59 131	74.19 146	84.01 68	76.61 111	61.69 127	60.62 135	50.61 145	70.25 65	71.31 81	55.57 168	83.85 58	82.28 63	86.90 107	88.08 63
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FC-MVSNet-train		72.60 92	75.07 88	69.71 107	81.10 83	78.79 126	73.74 147	65.23 78	66.10 92	53.34 129	70.36 64	63.40 119	56.92 157	81.44 83	80.96 78	87.93 82	84.46 108

ET-MVSNet_ETH3D		72.46 93	74.19 92	70.44 97	62.50 205	81.17 98	79.90 73	62.46 118	64.52 104	57.52 105	71.49 58	59.15 135	72.08 53	78.61 130	81.11 75	88.16 74	83.29 118

ECVR-MVS		72.20 94	73.91 94	70.20 101	81.49 75	83.27 78	75.74 112	67.59 62	68.19 81	49.31 153	55.77 136	62.00 123	58.82 139	84.76 48	82.94 57	88.27 70	80.41 145

MVSTER		72.06 95	74.24 91	69.51 110	70.39 181	75.97 156	76.91 107	57.36 170	64.64 102	61.39 90	68.86 71	63.76 117	63.46 107	81.44 83	79.70 102	87.56 93	85.31 94

Anonymous20231211		71.90 96	72.48 107	71.21 88	80.14 93	81.53 92	76.92 106	62.89 104	64.46 105	58.94 94	43.80 197	70.98 83	62.22 114	80.70 98	80.19 96	86.18 127	85.73 85

Effi-MVS+-dtu		71.82 97	71.86 112	71.78 86	78.77 102	80.47 107	78.55 91	61.67 129	60.68 133	55.49 114	58.48 121	65.48 112	68.85 77	76.92 148	75.55 160	87.35 96	85.46 91

test2506		71.72 98	72.95 102	70.29 99	81.49 75	83.27 78	75.74 112	67.59 62	68.19 81	49.81 149	61.15 102	49.73 196	58.82 139	84.76 48	82.94 57	88.27 70	80.63 141

IterMVS-LS		71.69 99	72.82 105	70.37 98	77.54 115	76.34 153	75.13 121	60.46 140	61.53 128	57.57 104	64.89 89	67.33 106	66.04 99	77.09 147	77.37 140	85.48 145	85.18 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		71.56 100	73.44 97	69.38 112	81.16 79	82.95 83	74.99 124	67.68 60	66.89 87	46.33 169	55.19 142	60.91 126	57.99 147	84.59 51	82.70 61	88.12 77	80.85 138

MSDG		71.52 101	69.87 124	73.44 78	82.21 72	79.35 119	79.52 78	64.59 82	66.15 91	61.87 87	53.21 161	56.09 151	65.85 100	78.94 126	78.50 120	86.60 119	76.85 170

thisisatest0530		71.48 102	73.01 101	69.70 108	73.83 151	78.62 128	74.53 129	59.12 156	64.13 106	58.63 98	64.60 92	58.63 137	64.27 103	80.28 106	80.17 97	87.82 87	84.64 106

tttt0517		71.41 103	72.95 102	69.60 109	73.70 153	78.70 127	74.42 133	59.12 156	63.89 110	58.35 101	64.56 93	58.39 139	64.27 103	80.29 105	80.17 97	87.74 89	84.69 105

ACMH+	66.54 13	71.36 104	70.09 122	72.85 80	82.59 66	81.13 99	78.56 90	68.04 56	61.55 127	52.52 136	51.50 176	54.14 161	68.56 79	78.85 127	79.50 108	86.82 110	83.94 112

IB-MVS	66.94 12	71.21 105	71.66 113	70.68 92	79.18 100	82.83 86	72.61 154	61.77 126	59.66 139	63.44 85	53.26 159	59.65 133	59.16 138	76.78 151	82.11 65	87.90 83	87.33 69
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
GBi-Net		70.78 106	73.37 99	67.76 124	72.95 158	78.00 133	75.15 118	62.72 108	64.13 106	51.44 138	58.37 122	69.02 96	57.59 149	81.33 86	80.72 82	86.70 114	82.02 124

test1		70.78 106	73.37 99	67.76 124	72.95 158	78.00 133	75.15 118	62.72 108	64.13 106	51.44 138	58.37 122	69.02 96	57.59 149	81.33 86	80.72 82	86.70 114	82.02 124

ACMH	65.37 14	70.71 108	70.00 123	71.54 87	82.51 67	82.47 88	77.78 98	68.13 55	56.19 162	46.06 172	54.30 146	51.20 188	68.68 78	80.66 99	80.72 82	86.07 130	84.45 109
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_NR-MVSNet		70.59 109	72.19 108	68.72 117	77.72 113	80.72 104	73.81 145	69.65 45	61.99 123	43.23 182	60.54 107	57.50 142	58.57 141	79.56 117	81.07 76	89.34 50	83.97 110

FMVSNet3		70.49 110	72.90 104	67.67 129	72.88 161	77.98 136	74.96 127	62.72 108	64.13 106	51.44 138	58.37 122	69.02 96	57.43 152	79.43 120	79.57 106	86.59 120	81.81 131

baseline		70.45 111	74.09 93	66.20 150	70.95 178	75.67 157	74.26 137	53.57 178	68.33 80	58.42 99	69.87 66	71.45 78	61.55 126	74.84 162	74.76 165	78.42 184	83.72 115

FMVSNet2		70.39 112	72.67 106	67.72 127	72.95 158	78.00 133	75.15 118	62.69 112	63.29 114	51.25 142	55.64 137	68.49 103	57.59 149	80.91 96	80.35 94	86.70 114	82.02 124

v8		70.23 113	69.86 125	70.67 93	74.69 141	79.82 114	78.79 89	59.18 155	58.80 143	58.20 102	55.00 143	57.33 143	66.31 98	77.51 140	76.71 149	86.82 110	83.88 113

v10		70.22 114	69.76 127	70.74 90	74.79 140	80.30 112	79.22 83	59.81 150	57.71 150	56.58 111	54.22 152	55.31 154	66.95 87	78.28 133	77.47 137	87.12 104	85.07 98

MS-PatchMatch		70.17 115	70.49 119	69.79 106	80.98 84	77.97 138	77.51 100	58.95 159	62.33 121	55.22 117	53.14 162	65.90 111	62.03 118	79.08 124	77.11 144	84.08 162	77.91 162

baseline1		70.10 116	72.17 109	67.69 128	79.74 96	76.80 148	73.91 141	64.38 84	62.74 119	48.30 157	64.94 88	64.08 116	54.17 175	81.46 82	78.92 115	85.66 142	76.22 172

v2v482		70.05 117	69.46 131	70.74 90	74.62 142	80.32 111	79.00 85	60.62 137	57.41 152	56.89 108	55.43 141	55.14 156	66.39 97	77.25 144	77.14 143	86.90 107	83.57 117

v1144		69.93 118	69.36 132	70.61 94	74.89 139	80.93 100	79.11 84	60.64 136	55.97 164	55.31 116	53.85 154	54.14 161	66.54 95	78.10 135	77.44 138	87.14 101	85.09 97

baseline2		69.69 119	70.27 121	69.01 115	75.72 130	77.13 146	73.82 144	58.94 160	61.35 129	57.09 107	61.68 100	57.17 145	61.99 119	78.10 135	76.58 151	86.48 123	79.85 149

DU-MVS		69.63 120	70.91 116	68.13 123	75.99 124	79.54 116	73.81 145	69.20 50	61.20 131	43.23 182	58.52 119	53.50 168	58.57 141	79.22 122	80.45 92	87.97 81	83.97 110

UniMVSNet (Re)		69.53 121	71.90 111	66.76 146	76.42 122	80.93 100	72.59 155	68.03 57	61.75 126	41.68 187	58.34 125	57.23 144	53.27 178	79.53 118	80.62 90	88.57 67	84.90 102

v1192		69.50 122	68.83 138	70.29 99	74.49 143	80.92 102	78.55 91	60.54 138	55.04 170	54.21 119	52.79 168	52.33 181	66.92 88	77.88 137	77.35 141	87.04 105	85.51 89

HyFIR lowres test		69.47 123	68.94 137	70.09 103	76.77 121	82.93 84	76.63 110	60.17 144	59.00 142	54.03 122	40.54 207	65.23 113	67.89 82	76.54 154	78.30 124	85.03 154	80.07 148

v144192		69.34 124	68.68 142	70.12 102	74.06 147	80.54 105	78.08 97	60.54 138	54.99 172	54.13 121	52.92 166	52.80 179	66.73 91	77.13 146	76.72 148	87.15 98	85.63 87

TranMVSNet+NR-MVSNet		69.25 125	70.81 117	67.43 132	77.23 118	79.46 118	73.48 150	69.66 44	60.43 136	39.56 190	58.82 118	53.48 170	55.74 166	79.59 115	81.21 74	88.89 61	82.70 120

CHOSEN 1792x2688		69.20 126	69.26 133	69.13 113	76.86 120	78.93 122	77.27 104	60.12 146	61.86 125	54.42 118	42.54 201	61.61 124	66.91 89	78.55 131	78.14 126	79.23 182	83.23 119

v1921920		69.03 127	68.32 146	69.86 105	74.03 148	80.37 109	77.55 99	60.25 143	54.62 174	53.59 127	52.36 172	51.50 187	66.75 90	77.17 145	76.69 150	86.96 106	85.56 88

CostFormer		68.92 128	69.58 129	68.15 122	75.98 126	76.17 155	78.22 96	51.86 190	65.80 94	61.56 89	63.57 95	62.83 120	61.85 122	70.40 194	68.67 191	79.42 180	79.62 153

FMVSNet1		68.84 129	70.47 120	66.94 143	71.35 175	77.68 141	74.71 128	62.35 119	56.93 155	49.94 148	50.01 182	64.59 114	57.07 154	81.33 86	80.72 82	86.25 125	82.00 127

NR-MVSNet		68.79 130	70.56 118	66.71 148	77.48 116	79.54 116	73.52 149	69.20 50	61.20 131	39.76 189	58.52 119	50.11 194	51.37 182	80.26 107	80.71 86	88.97 59	83.59 116

V42		68.76 131	69.63 128	67.74 126	64.93 201	78.01 132	78.30 95	56.48 172	58.65 144	56.30 112	54.26 150	57.03 146	64.85 101	77.47 141	77.01 145	85.60 143	84.96 101

v1240		68.64 132	67.89 152	69.51 110	73.89 150	80.26 113	76.73 109	59.97 149	53.43 182	53.08 131	51.82 175	50.84 190	66.62 92	76.79 150	76.77 147	86.78 112	85.34 93

Fast-Effi-MVS+-dtu		68.34 133	69.47 130	67.01 142	75.15 135	77.97 138	77.12 105	55.40 175	57.87 145	46.68 167	56.17 135	60.39 127	62.36 113	76.32 155	76.25 155	85.35 149	81.34 134

GA-MVS		68.14 134	69.17 135	66.93 144	73.77 152	78.50 130	74.45 130	58.28 164	55.11 169	48.44 156	60.08 109	53.99 164	61.50 127	78.43 132	77.57 134	85.13 151	80.54 142

tfpn200view9		68.11 135	68.72 141	67.40 133	77.83 111	78.93 122	74.28 135	62.81 105	56.64 157	46.82 165	52.65 169	53.47 171	56.59 158	80.41 100	78.43 121	86.11 128	80.52 143

EPNet_dtu		68.08 136	71.00 115	64.67 158	79.64 97	68.62 190	75.05 122	63.30 95	66.36 90	45.27 176	67.40 81	66.84 109	43.64 195	75.37 158	74.98 164	81.15 174	77.44 165
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres200		67.98 137	68.55 144	67.30 136	77.89 110	78.86 124	74.18 139	62.75 106	56.35 160	46.48 168	52.98 165	53.54 167	56.46 159	80.41 100	77.97 128	86.05 132	79.78 151

thres400		67.95 138	68.62 143	67.17 138	77.90 108	78.59 129	74.27 136	62.72 108	56.34 161	45.77 174	53.00 164	53.35 174	56.46 159	80.21 109	78.43 121	85.91 139	80.43 144

pmmvs4		67.89 139	67.39 157	68.48 120	71.60 172	73.57 171	74.45 130	60.98 133	64.65 101	57.97 103	54.95 144	51.73 186	61.88 121	73.78 168	75.11 162	83.99 164	77.91 162

v148		67.85 140	67.53 153	68.23 121	73.25 156	77.57 144	74.26 137	57.36 170	55.70 165	57.45 106	53.53 155	55.42 153	61.96 120	75.23 159	73.92 168	85.08 152	81.32 135

Vis-MVSNet (Re-imp)		67.83 141	73.52 96	61.19 174	78.37 106	76.72 150	66.80 180	62.96 102	65.50 96	34.17 201	67.19 82	69.68 92	39.20 204	79.39 121	79.44 110	85.68 141	76.73 171

PatchMatch-RL		67.78 142	66.65 162	69.10 114	73.01 157	72.69 174	68.49 170	61.85 125	62.93 117	60.20 93	56.83 133	50.42 192	69.52 72	75.62 157	74.46 167	81.51 172	73.62 189

thres600view7		67.68 143	68.43 145	66.80 145	77.90 108	78.86 124	73.84 143	62.75 106	56.07 163	44.70 180	52.85 167	52.81 178	55.58 167	80.41 100	77.77 130	86.05 132	80.28 146

COLMAP_ROB	62.73 15	67.66 144	66.76 161	68.70 118	80.49 89	77.98 136	75.29 116	62.95 103	63.62 112	49.96 147	47.32 192	50.72 191	58.57 141	76.87 149	75.50 161	84.94 156	75.33 181
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CDS-MVSNet		67.65 145	69.83 126	65.09 154	75.39 134	76.55 151	74.42 133	63.75 90	53.55 180	49.37 152	59.41 115	62.45 121	44.44 193	79.71 114	79.82 101	83.17 168	77.36 166
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		67.64 146	71.25 114	63.43 167	61.86 207	70.73 181	67.26 175	50.86 195	74.20 61	58.91 95	67.49 80	69.33 93	64.10 105	71.41 181	68.45 195	77.61 186	77.17 167

thres100view900		67.60 147	68.02 148	67.12 140	77.83 111	77.75 140	73.90 142	62.52 116	56.64 157	46.82 165	52.65 169	53.47 171	55.92 163	78.77 128	77.62 133	85.72 140	79.23 155

Baseline_NR-MVSNet		67.53 148	68.77 140	66.09 151	75.99 124	74.75 167	72.43 156	68.41 54	61.33 130	38.33 194	51.31 177	54.13 163	56.03 162	79.22 122	78.19 125	85.37 148	82.45 122

thisisatest0515		67.40 149	68.78 139	65.80 152	70.02 183	75.24 163	69.36 167	57.37 169	54.94 173	53.67 126	55.53 140	54.85 157	58.00 146	78.19 134	78.91 116	86.39 124	83.78 114

USDC		67.36 150	67.90 151	66.74 147	71.72 168	75.23 164	71.58 158	60.28 142	67.45 85	50.54 146	60.93 103	45.20 209	62.08 116	76.56 153	74.50 166	84.25 160	75.38 180

EG-PatchMatch MVS		67.24 151	66.94 159	67.60 130	78.73 103	81.35 95	73.28 152	59.49 152	46.89 204	51.42 141	43.65 198	53.49 169	55.50 169	81.38 85	80.66 88	87.15 98	81.17 136

dmvs_re		67.22 152	67.92 150	66.40 149	75.94 127	70.55 183	74.97 126	63.87 89	57.07 154	44.75 178	54.29 147	56.72 148	54.65 172	79.53 118	77.51 136	84.20 161	79.78 151

UniMVSNet_ETH3D		67.18 153	67.03 158	67.36 134	74.44 144	78.12 131	74.07 140	66.38 67	52.22 187	46.87 164	48.64 187	51.84 185	56.96 155	77.29 143	78.53 119	85.42 147	82.59 121

v7n		67.05 154	66.94 159	67.17 138	72.35 163	78.97 121	73.26 153	58.88 161	51.16 193	50.90 143	48.21 189	50.11 194	60.96 130	77.70 138	77.38 139	86.68 117	85.05 99

IterMVS-SCA-FT		66.89 155	69.22 134	64.17 160	71.30 176	75.64 158	71.33 159	53.17 182	57.63 151	49.08 154	60.72 105	60.05 131	63.09 109	74.99 161	73.92 168	77.07 190	81.57 133

IterMVS		66.36 156	68.30 147	64.10 161	69.48 188	74.61 168	73.41 151	50.79 196	57.30 153	48.28 158	60.64 106	59.92 132	60.85 134	74.14 166	72.66 175	81.80 171	78.82 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TDRefinement		66.09 157	65.03 174	67.31 135	69.73 185	76.75 149	75.33 114	64.55 83	60.28 137	49.72 151	45.63 195	42.83 212	60.46 135	75.75 156	75.95 156	84.08 162	78.04 161

pm-mvs1		65.62 158	67.42 155	63.53 166	73.66 154	76.39 152	69.66 164	60.87 135	49.73 197	43.97 181	51.24 178	57.00 147	48.16 187	79.89 112	77.84 129	84.85 158	79.82 150

tpm cat1		65.41 159	63.81 182	67.28 137	75.61 132	72.88 173	75.32 115	52.85 184	62.97 116	63.66 84	53.24 160	53.29 176	61.83 123	65.54 205	64.14 207	74.43 202	74.60 183

SCA		65.40 160	66.58 163	64.02 162	70.65 179	73.37 172	67.35 174	53.46 180	63.66 111	54.14 120	60.84 104	60.20 130	61.50 127	69.96 195	68.14 196	77.01 191	69.91 195

anonymousdsp		65.28 161	67.98 149	62.13 170	58.73 214	73.98 170	67.10 177	50.69 197	48.41 200	47.66 163	54.27 148	52.75 180	61.45 129	76.71 152	80.20 95	87.13 102	89.53 55

PMMVS		65.06 162	69.17 135	60.26 179	55.25 220	63.43 206	66.71 181	43.01 215	62.41 120	50.64 144	69.44 68	67.04 107	63.29 108	74.36 165	73.54 171	82.68 169	73.99 188

CR-MVSNet		64.83 163	65.54 168	64.01 163	70.64 180	69.41 185	65.97 185	52.74 185	57.81 147	52.65 133	54.27 148	56.31 150	60.92 131	72.20 177	73.09 173	81.12 175	75.69 177

TransMVSNet (Re)		64.74 164	65.66 167	63.66 165	77.40 117	75.33 162	69.86 163	62.67 114	47.63 202	41.21 188	50.01 182	52.33 181	45.31 192	79.57 116	77.69 132	85.49 144	77.07 169

test-LLR		64.42 165	64.36 178	64.49 159	75.02 137	63.93 203	66.61 182	61.96 123	54.41 175	47.77 160	57.46 129	60.25 128	55.20 170	70.80 188	69.33 186	80.40 178	74.38 185

MDTV_nov1_ep13		64.37 166	65.24 170	63.37 168	68.94 190	70.81 180	72.40 157	50.29 199	60.10 138	53.91 124	60.07 110	59.15 135	57.21 153	69.43 198	67.30 198	77.47 187	69.78 197

tfpnnormal		64.27 167	63.64 183	65.02 155	75.84 129	75.61 159	71.24 161	62.52 116	47.79 201	42.97 184	42.65 200	44.49 210	52.66 180	78.77 128	76.86 146	84.88 157	79.29 154

PatchmatchNet		64.21 168	64.65 176	63.69 164	71.29 177	68.66 189	69.63 165	51.70 192	63.04 115	53.77 125	59.83 113	58.34 140	60.23 136	68.54 201	66.06 203	75.56 197	68.08 201
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
dps		64.00 169	62.99 185	65.18 153	73.29 155	72.07 176	68.98 169	53.07 183	57.74 149	58.41 100	55.55 139	47.74 202	60.89 133	69.53 197	67.14 200	76.44 194	71.19 193

pmmvs-eth3d		63.52 170	62.44 192	64.77 157	66.82 196	70.12 184	69.41 166	59.48 153	54.34 178	52.71 132	46.24 194	44.35 211	56.93 156	72.37 172	73.77 170	83.30 166	75.91 174

WR-MVS		63.03 171	67.40 156	57.92 189	75.14 136	77.60 143	60.56 203	66.10 70	54.11 179	23.88 212	53.94 153	53.58 166	34.50 208	73.93 167	77.71 131	87.35 96	80.94 137

PEN-MVS		62.96 172	65.77 166	59.70 182	73.98 149	75.45 160	63.39 196	67.61 61	52.49 185	25.49 211	53.39 156	49.12 198	40.85 201	71.94 179	77.26 142	86.86 109	80.72 140

TinyColmap		62.84 173	61.03 198	64.96 156	69.61 186	71.69 177	68.48 171	59.76 151	55.41 166	47.69 162	47.33 191	34.20 221	62.76 112	74.52 163	72.59 176	81.44 173	71.47 192

CP-MVSNet		62.68 174	65.49 169	59.40 185	71.84 166	75.34 161	62.87 198	67.04 65	52.64 184	27.19 209	53.38 157	48.15 200	41.40 199	71.26 182	75.68 158	86.07 130	82.00 127

gg-mvs-nofinetune		62.55 175	65.05 173	59.62 183	78.72 104	77.61 142	70.83 162	53.63 177	39.71 216	22.04 218	36.36 211	64.32 115	47.53 188	81.16 91	79.03 114	85.00 155	77.17 167

CVMVSNet		62.55 175	65.89 164	58.64 187	66.95 194	69.15 187	66.49 184	56.29 174	52.46 186	32.70 202	59.27 116	58.21 141	50.09 184	71.77 180	71.39 180	79.31 181	78.99 157

CMPMVS	47.78 17	62.49 177	62.52 190	62.46 169	70.01 184	70.66 182	62.97 197	51.84 191	51.98 189	56.71 110	42.87 199	53.62 165	57.80 148	72.23 175	70.37 183	75.45 199	75.91 174
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		62.41 178	62.88 186	61.87 171	71.38 174	75.18 166	67.76 173	59.45 154	41.64 212	42.52 186	37.33 209	52.91 177	46.87 189	77.67 139	76.26 154	83.23 167	79.18 156

tpm		62.41 178	63.15 184	61.55 173	72.24 164	63.79 205	71.31 160	46.12 213	57.82 146	55.33 115	59.90 112	54.74 158	53.63 176	67.24 204	64.29 206	70.65 212	74.25 187

PS-CasMVS		62.38 180	65.06 172	59.25 186	71.73 167	75.21 165	62.77 199	66.99 66	51.94 191	26.96 210	52.00 174	47.52 203	41.06 200	71.16 185	75.60 159	85.97 137	81.97 129

pmmvs5		62.37 181	64.04 180	60.42 177	65.03 199	71.67 178	67.17 176	52.70 187	50.30 194	44.80 177	54.23 151	51.19 189	49.37 185	72.88 171	73.48 172	83.45 165	74.55 184

tpmrst		62.00 182	62.35 193	61.58 172	71.62 171	64.14 202	69.07 168	48.22 209	62.21 122	53.93 123	58.26 126	55.30 155	55.81 165	63.22 210	62.62 209	70.85 211	70.70 194

PatchT		61.97 183	64.04 180	59.55 184	60.49 209	67.40 193	56.54 210	48.65 205	56.69 156	52.65 133	51.10 179	52.14 184	60.92 131	72.20 177	73.09 173	78.03 185	75.69 177

DTE-MVSNet		61.85 184	64.96 175	58.22 188	74.32 145	74.39 169	61.01 202	67.85 59	51.76 192	21.91 219	53.28 158	48.17 199	37.74 205	72.22 176	76.44 152	86.52 122	78.49 159

SixPastTwentyTwo		61.84 185	62.45 191	61.12 175	69.20 189	72.20 175	62.03 200	57.40 168	46.54 205	38.03 196	57.14 132	41.72 214	58.12 145	69.67 196	71.58 179	81.94 170	78.30 160

WR-MVS_H		61.83 186	65.87 165	57.12 192	71.72 168	76.87 147	61.45 201	66.19 68	51.97 190	22.92 216	53.13 163	52.30 183	33.80 209	71.03 186	75.00 163	86.65 118	80.78 139

LTVRE_ROB	59.44 16	61.82 187	62.64 189	60.87 176	72.83 162	77.19 145	64.37 192	58.97 158	33.56 221	28.00 208	52.59 171	42.21 213	63.93 106	74.52 163	76.28 153	77.15 189	82.13 123
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
RPMNet		61.71 188	62.88 186	60.34 178	69.51 187	69.41 185	63.48 195	49.23 201	57.81 147	45.64 175	50.51 180	50.12 193	53.13 179	68.17 203	68.49 194	81.07 176	75.62 179

TESTMET0.1,1		61.10 189	64.36 178	57.29 191	57.53 215	63.93 203	66.61 182	36.22 219	54.41 175	47.77 160	57.46 129	60.25 128	55.20 170	70.80 188	69.33 186	80.40 178	74.38 185

test-mter		60.84 190	64.62 177	56.42 194	55.99 218	64.18 201	65.39 187	34.23 220	54.39 177	46.21 171	57.40 131	59.49 134	55.86 164	71.02 187	69.65 185	80.87 177	76.20 173

PM-MVS		60.48 191	60.94 199	59.94 180	58.85 212	66.83 196	64.27 193	51.39 193	55.03 171	48.03 159	50.00 184	40.79 216	58.26 144	69.20 199	67.13 201	78.84 183	77.60 164

MDTV_nov1_ep13_2view		60.16 192	60.51 200	59.75 181	65.39 198	69.05 188	68.00 172	48.29 207	51.99 188	45.95 173	48.01 190	49.64 197	53.39 177	68.83 200	66.52 202	77.47 187	69.55 198

EPMVS		60.00 193	61.97 194	57.71 190	68.46 191	63.17 209	64.54 191	48.23 208	63.30 113	44.72 179	60.19 108	56.05 152	50.85 183	65.27 208	62.02 210	69.44 214	63.81 208

TAMVS		59.58 194	62.81 188	55.81 196	66.03 197	65.64 200	63.86 194	48.74 204	49.95 196	37.07 198	54.77 145	58.54 138	44.44 193	72.29 174	71.79 177	74.70 201	66.66 203

test0.0.03 1		58.80 195	61.58 196	55.56 197	75.02 137	68.45 191	59.58 207	61.96 123	52.74 183	29.57 205	49.75 185	54.56 159	31.46 211	71.19 183	69.77 184	75.75 195	64.57 206

CHOSEN 280x420		58.70 196	61.88 195	54.98 199	55.45 219	50.55 222	64.92 189	40.36 216	55.21 167	38.13 195	48.31 188	63.76 117	63.03 111	73.73 169	68.58 193	68.00 217	73.04 190

MIMVSNet		58.52 197	61.34 197	55.22 198	60.76 208	67.01 195	66.81 179	49.02 203	56.43 159	38.90 192	40.59 206	54.54 160	40.57 202	73.16 170	71.65 178	75.30 200	66.00 204

FMVSNet5		57.24 198	60.02 201	53.99 202	56.45 217	62.74 210	65.27 188	47.03 210	55.14 168	39.55 191	40.88 204	53.42 173	41.83 196	72.35 173	71.10 182	73.79 204	64.50 207

gm-plane-assit		57.00 199	57.62 206	56.28 195	76.10 123	62.43 212	47.62 220	46.57 211	33.84 220	23.24 214	37.52 208	40.19 217	59.61 137	79.81 113	77.55 135	84.55 159	72.03 191

FC-MVSNet-test		56.90 200	65.20 171	47.21 210	66.98 193	63.20 208	49.11 219	58.60 163	59.38 141	11.50 226	65.60 85	56.68 149	24.66 218	71.17 184	71.36 181	72.38 208	69.02 199

Anonymous20231206		56.36 201	57.80 205	54.67 200	70.08 182	66.39 197	60.46 204	57.54 167	49.50 199	29.30 206	33.86 214	46.64 204	35.18 207	70.44 192	68.88 190	75.47 198	68.88 200

ADS-MVSNet		55.94 202	58.01 203	53.54 204	62.48 206	58.48 215	59.12 208	46.20 212	59.65 140	42.88 185	52.34 173	53.31 175	46.31 190	62.00 212	60.02 213	64.23 219	60.24 215

pmnet_mix02		55.30 203	57.01 207	53.30 205	64.14 202	59.09 214	58.39 209	50.24 200	53.47 181	38.68 193	49.75 185	45.86 207	40.14 203	65.38 207	60.22 212	68.19 216	65.33 205

EU-MVSNet		54.63 204	58.69 202	49.90 208	56.99 216	62.70 211	56.41 211	50.64 198	45.95 207	23.14 215	50.42 181	46.51 205	36.63 206	65.51 206	64.85 205	75.57 196	74.91 182

MVS-HIRNet		54.41 205	52.10 212	57.11 193	58.99 211	56.10 218	49.68 218	49.10 202	46.18 206	52.15 137	33.18 215	46.11 206	56.10 161	63.19 211	59.70 214	76.64 193	60.25 214

testgi		54.39 206	57.86 204	50.35 207	71.59 173	67.24 194	54.95 212	53.25 181	43.36 209	23.78 213	44.64 196	47.87 201	24.96 216	70.45 191	68.66 192	73.60 205	62.78 211

test20.03		53.93 207	56.28 208	51.19 206	72.19 165	65.83 198	53.20 214	61.08 130	42.74 210	22.08 217	37.07 210	45.76 208	24.29 219	70.44 192	69.04 188	74.31 203	63.05 210

MDA-MVSNet-bldmvs		53.37 208	53.01 211	53.79 203	43.67 224	67.95 192	59.69 206	57.92 166	43.69 208	32.41 203	41.47 202	27.89 227	52.38 181	56.97 219	65.99 204	76.68 192	67.13 202

FPMVS		51.87 209	50.00 214	54.07 201	66.83 195	57.25 216	60.25 205	50.91 194	50.25 195	34.36 200	36.04 212	32.02 223	41.49 198	58.98 216	56.07 216	70.56 213	59.36 216

MIMVSNet1		49.27 210	53.25 210	44.62 212	44.61 222	61.52 213	53.61 213	52.18 188	41.62 213	18.68 222	28.14 220	41.58 215	25.50 214	68.46 202	69.04 188	73.15 206	62.37 212

pmmvs3		47.65 211	49.08 216	45.99 211	44.61 222	54.79 219	50.04 216	31.95 223	33.91 219	29.90 204	30.37 216	33.53 222	46.31 190	63.50 209	63.67 208	73.14 207	63.77 209

N_pmnet		47.35 212	50.13 213	44.11 213	59.98 210	51.64 221	51.86 215	44.80 214	49.58 198	20.76 220	40.65 205	40.05 218	29.64 212	59.84 214	55.15 217	57.63 220	54.00 218

new-patchmatchnet		46.97 213	49.47 215	44.05 214	62.82 204	56.55 217	45.35 221	52.01 189	42.47 211	17.04 224	35.73 213	35.21 220	21.84 222	61.27 213	54.83 218	65.26 218	60.26 213

GG-mvs-BLEND		46.86 214	67.51 154	22.75 220	0.05 232	76.21 154	64.69 190	0.04 228	61.90 124	0.09 233	55.57 138	71.32 80	0.08 228	70.54 190	67.19 199	71.58 209	69.86 196

PMVS	39.38 18	46.06 215	43.30 218	49.28 209	62.93 203	38.75 224	41.88 222	53.50 179	33.33 222	35.46 199	28.90 219	31.01 224	33.04 210	58.61 218	54.63 219	68.86 215	57.88 217
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		40.01 216	45.06 217	34.13 216	58.84 213	53.28 220	28.60 225	58.10 165	32.93 223	4.65 231	40.92 203	28.33 226	7.26 225	58.86 217	56.09 215	47.36 223	44.98 220

new_pmnet		38.40 217	42.64 219	33.44 217	37.54 227	45.00 223	36.60 223	32.72 222	40.27 214	12.72 225	29.89 217	28.90 225	24.78 217	53.17 220	52.90 220	56.31 221	48.34 219

Gipuma		36.38 218	35.80 220	37.07 215	45.76 221	33.90 225	29.81 224	48.47 206	39.91 215	18.02 223	8.00 228	8.14 232	25.14 215	59.29 215	61.02 211	55.19 222	40.31 221
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		25.60 219	29.75 221	20.76 221	28.00 228	30.93 226	23.10 227	29.18 224	23.14 225	1.46 232	18.23 224	16.54 229	5.08 226	40.22 221	41.40 222	37.76 224	37.79 223

test_method		22.26 220	25.94 222	17.95 222	3.24 231	7.17 231	23.83 226	7.27 226	37.35 218	20.44 221	21.87 223	39.16 219	18.67 223	34.56 222	20.84 226	34.28 225	20.64 227

E-PMN		21.77 221	18.24 224	25.89 218	40.22 225	19.58 228	12.46 230	39.87 217	18.68 227	6.71 228	9.57 225	4.31 235	22.36 221	19.89 226	27.28 224	33.73 226	28.34 225

EMVS		20.98 222	17.15 225	25.44 219	39.51 226	19.37 229	12.66 229	39.59 218	19.10 226	6.62 229	9.27 226	4.40 234	22.43 220	17.99 227	24.40 225	31.81 227	25.53 226

MVE	19.12 19	20.47 223	23.27 223	17.20 223	12.66 230	25.41 227	10.52 231	34.14 221	14.79 228	6.53 230	8.79 227	4.68 233	16.64 224	29.49 224	41.63 221	22.73 229	38.11 222
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		0.09 224	0.15 226	0.02 225	0.01 233	0.02 233	0.05 234	0.01 229	0.11 229	0.01 234	0.26 230	0.01 236	0.06 230	0.10 228	0.10 227	0.01 231	0.43 229

test123		0.09 224	0.14 227	0.02 225	0.00 234	0.02 233	0.02 235	0.01 229	0.09 230	0.00 235	0.30 229	0.00 237	0.08 228	0.03 229	0.09 228	0.01 231	0.45 228

uanet_test		0.00 226	0.00 228	0.00 227	0.00 234	0.00 235	0.00 236	0.00 231	0.00 231	0.00 235	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

sosnet-low-res		0.00 226	0.00 228	0.00 227	0.00 234	0.00 235	0.00 236	0.00 231	0.00 231	0.00 235	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

sosnet		0.00 226	0.00 228	0.00 227	0.00 234	0.00 235	0.00 236	0.00 231	0.00 231	0.00 235	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

TPM-MVS					90.07 21	88.36 35	88.45 29			77.10 26	75.60 38	83.98 30	71.33 63			89.75 43	89.62 53
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										46.24 170

9.14												86.88 16

SR-MVS					88.99 34			73.57 24				87.54 14

Anonymous202405211			72.16 110		80.85 85	81.85 90	76.88 108	65.40 76	62.89 118		46.35 193	67.99 104	62.05 117	81.15 92	80.38 93	85.97 137	84.50 107

our_test_3					67.93 192	70.99 179	66.89 178

ambc			53.42 209		64.99 200	63.36 207	49.96 217		47.07 203	37.12 197	28.97 218	16.36 230	41.82 197	75.10 160	67.34 197	71.55 210	75.72 176

MTAPA										83.48 1		86.45 19

MTMP										82.66 5		84.91 27

Patchmatch-RL test							2.85 233

tmp_tt				14.50 224	14.68 229	7.17 231	10.46 232	2.21 227	37.73 217	28.71 207	25.26 221	16.98 228	4.37 227	31.49 223	29.77 223	26.56 228

XVS					86.63 46	88.68 27	85.00 47			71.81 46		81.92 37				90.47 23

X-MVStestdata					86.63 46	88.68 27	85.00 47			71.81 46		81.92 37				90.47 23

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 47

Patchmtry						65.80 199	65.97 185	52.74 185		52.65 133

DeepMVS_CX						18.74 230	18.55 228	8.02 225	26.96 224	7.33 227	23.81 222	13.05 231	25.99 213	25.17 225		22.45 230	36.25 224

High-resolution multi-view benchmark