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.

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 16	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 10	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 10	79.99 7	78.56 7	82.31 23	91.03 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 7	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 28	90.29 4

DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 8	63.19 12	88.63 2	86.00 4	64.52 5	78.71 11	77.63 15	82.26 24	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		77.82 5	83.46 5	71.24 8	75.26 17	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 7	66.24 3	78.21 17	78.56 7	80.34 46	89.39 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		77.58 6	82.93 6	71.35 6	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 22	86.10 7	82.98 8	64.76 4	78.29 15	76.78 22	83.40 6	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		77.32 7	82.51 7	71.26 7	75.43 15	80.19 8	82.22 7	58.26 3	84.83 7	64.36 7	78.19 15	83.46 6	63.61 8	81.00 1	80.28 1	83.66 4	89.62 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		77.13 8	81.70 8	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 9	64.79 5	83.69 10	84.46 5	62.83 13	77.13 26	75.21 32	83.35 7	87.85 16

ACMMP_NAP		76.15 9	81.17 9	70.30 11	74.09 21	79.47 10	81.59 12	57.09 14	81.38 11	63.89 10	79.02 13	80.48 19	62.24 17	80.05 6	79.12 4	82.94 11	88.64 9

HPM-MVS++		76.01 10	80.47 12	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 11	78.80 14	82.53 11	64.40 6	78.74 10	78.84 5	81.81 34	87.46 18

APD-MVS		75.80 11	80.90 11	69.86 15	75.42 16	78.48 16	81.43 13	57.44 12	80.45 14	59.32 28	85.28 8	80.82 18	63.96 7	76.89 28	76.08 28	81.58 39	88.30 12
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		75.62 12	79.91 14	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 16	63.04 13	70.69 25	81.15 16	62.99 11	80.23 5	79.54 3	83.11 8	89.16 8

SteuartSystems-ACMMP		75.23 13	79.60 15	70.13 13	76.81 6	78.92 12	81.74 8	57.99 6	75.30 29	59.83 27	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 10
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + MP.		75.22 14	80.06 13	69.56 16	74.61 19	72.74 49	80.59 14	55.70 23	80.80 13	62.65 15	86.25 6	82.92 9	62.07 19	76.89 28	75.66 31	81.77 36	85.19 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HFP-MVS		74.87 15	78.86 20	70.21 12	73.99 22	77.91 18	80.36 16	56.63 16	78.41 19	64.27 8	74.54 20	77.75 29	62.96 12	78.70 12	77.82 13	83.02 9	86.91 21

CSCG		74.68 16	79.22 16	69.40 17	75.69 12	80.01 9	79.12 24	52.83 41	79.34 17	63.99 9	70.49 26	82.02 12	60.35 32	77.48 24	77.22 19	84.38 1	87.97 15

SD-MVS		74.43 17	78.87 18	69.26 19	74.39 20	73.70 45	79.06 25	55.24 25	81.04 12	62.71 14	80.18 12	82.61 10	61.70 21	75.43 40	73.92 43	82.44 22	85.22 32
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
MP-MVS		74.31 18	78.87 18	68.99 21	73.49 24	78.56 15	79.25 23	56.51 17	75.33 27	60.69 24	75.30 19	79.12 23	61.81 20	77.78 21	77.93 12	82.18 30	88.06 14
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 23	80.51 15	57.09 14	78.25 20	62.28 18	65.54 37	78.26 25	62.18 18	79.13 8	78.51 10	83.01 10	87.68 17

DeepPCF-MVS	66.49 1	74.25 20	80.97 10	66.41 32	67.75 51	78.87 13	75.61 40	54.16 33	84.86 6	58.22 34	77.94 16	81.01 17	62.52 15	78.34 13	77.38 16	80.16 49	88.40 11

train_agg		73.89 21	78.25 22	68.80 23	75.25 18	72.27 51	79.75 18	56.05 20	74.87 32	58.97 29	81.83 11	79.76 21	61.05 25	77.39 25	76.01 29	81.71 37	85.61 30

DeepC-MVS	66.32 2	73.85 22	78.10 23	68.90 22	67.92 50	79.31 11	78.16 29	59.28 1	78.24 21	61.13 21	67.36 35	76.10 33	63.40 9	79.11 9	78.41 11	83.52 5	88.16 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMPR		73.79 23	78.41 21	68.40 24	72.35 28	77.79 20	79.32 20	56.38 18	77.67 23	58.30 33	74.16 21	76.66 30	61.40 22	78.32 14	77.80 14	82.68 15	86.51 22

MCST-MVS		73.67 24	77.39 26	69.33 18	76.26 9	78.19 17	78.77 26	54.54 30	75.33 27	59.99 26	67.96 32	79.23 22	62.43 16	78.00 18	75.71 30	84.02 2	87.30 19

PGM-MVS		72.89 25	77.13 27	67.94 25	72.47 27	77.25 24	79.27 22	54.63 29	73.71 36	57.95 35	72.38 23	75.33 35	60.75 27	78.25 16	77.36 18	82.57 20	85.62 29

DPM-MVS		72.80 26	75.90 30	69.19 20	75.51 13	77.68 21	81.62 11	54.83 26	75.96 25	62.06 19	63.96 49	76.58 31	58.55 40	76.66 33	76.77 23	82.60 19	83.68 40

CP-MVS		72.63 27	76.95 28	67.59 26	70.67 37	75.53 34	77.95 31	56.01 21	75.65 26	58.82 30	69.16 30	76.48 32	60.46 30	77.66 22	77.20 20	81.65 38	86.97 20

TSAR-MVS + ACMM		72.56 28	79.07 17	64.96 41	73.24 25	73.16 48	78.50 27	48.80 67	79.34 17	55.32 42	85.04 9	81.49 15	58.57 39	75.06 43	73.75 44	75.35 112	85.61 30

MVS_0304		72.45 29	77.44 25	66.61 30	71.08 35	77.81 19	76.74 34	49.30 61	73.12 38	61.17 20	73.70 22	78.08 26	58.78 37	76.75 32	76.52 25	82.61 18	86.14 25

DeepC-MVS_fast	65.08 3	72.00 30	76.11 29	67.21 28	68.93 46	77.46 22	76.54 36	54.35 31	74.92 31	58.64 32	65.18 39	74.04 43	62.62 14	77.92 19	77.02 21	82.16 31	86.21 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP		71.57 31	75.84 31	66.59 31	70.30 41	76.85 29	78.46 28	53.95 34	73.52 37	55.56 40	70.13 27	71.36 50	58.55 40	77.00 27	76.23 27	82.71 14	85.81 28
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
CDPH-MVS		71.47 32	75.82 32	66.41 32	72.97 26	77.15 25	78.14 30	54.71 27	69.88 49	53.07 57	70.98 24	74.83 37	56.95 52	76.22 34	76.57 24	82.62 17	85.09 34

X-MVS		71.18 33	75.66 33	65.96 36	71.71 30	76.96 26	77.26 33	55.88 22	72.75 40	54.48 50	64.39 44	74.47 38	54.19 70	77.84 20	77.37 17	82.21 27	85.85 27

HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 38	72.89 39	54.88 47	70.03 28	70.48 52	57.26 48	76.02 36	75.01 35	81.78 35	86.21 23

TSAR-MVS + GP.		69.71 35	73.92 36	64.80 43	68.27 48	70.56 57	71.90 50	50.75 51	71.38 44	57.46 37	68.68 31	75.42 34	60.10 33	73.47 51	73.99 42	80.32 47	83.97 38

3Dnovator+	62.63 4	69.51 36	72.62 39	65.88 37	68.21 49	76.47 31	73.50 49	52.74 42	70.85 45	58.65 31	55.97 87	69.95 53	61.11 24	76.80 30	75.09 33	81.09 42	83.23 44

OPM-MVS		69.33 37	71.05 46	67.32 27	72.34 29	75.70 33	79.57 19	56.34 19	55.21 81	53.81 54	59.51 72	68.96 58	59.67 34	77.61 23	76.44 26	82.19 28	83.88 39
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PHI-MVS		69.27 38	74.84 35	62.76 50	66.83 54	74.83 37	73.88 47	49.32 60	70.61 46	50.93 67	69.62 29	74.84 36	57.25 49	75.53 39	74.32 40	78.35 68	84.17 37

LGP-MVS_train		68.87 39	72.03 42	65.18 40	69.33 44	74.03 44	76.67 35	53.88 35	68.46 50	52.05 64	63.21 52	63.89 78	56.31 56	75.99 37	74.43 39	82.83 13	84.18 36

CANet		68.77 40	73.01 37	63.83 45	68.30 47	75.19 35	73.73 48	47.90 68	63.86 56	54.84 48	67.51 34	74.36 41	57.62 44	74.22 48	73.57 47	80.56 44	82.36 46

CPTT-MVS		68.76 41	73.01 37	63.81 46	65.42 61	73.66 46	76.39 38	52.08 43	72.61 41	50.33 69	60.73 66	72.65 46	59.43 35	73.32 52	72.12 49	79.19 60	85.99 26

ACMP	61.42 5	68.72 42	71.37 44	65.64 38	69.06 45	74.45 42	75.88 39	53.30 37	68.10 51	55.74 39	61.53 64	62.29 85	56.97 51	74.70 46	74.23 41	82.88 12	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MSLP-MVS++		68.17 43	70.72 49	65.19 39	69.41 43	70.64 56	74.99 42	45.76 77	70.20 48	60.17 25	56.42 85	73.01 44	61.14 23	72.80 54	70.54 59	79.70 52	81.42 51

MAR-MVS		68.04 44	70.74 48	64.90 42	71.68 32	76.33 32	74.63 44	50.48 55	63.81 57	55.52 41	54.88 93	69.90 54	57.39 47	75.42 41	74.79 37	79.71 51	80.03 57
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
AdaColmap		67.89 45	68.85 60	66.77 29	73.73 23	74.30 43	75.28 41	53.58 36	70.24 47	57.59 36	51.19 113	59.19 102	60.74 28	75.33 42	73.72 45	79.69 54	77.96 75

MVS_111021_HR		67.62 46	70.39 50	64.39 44	69.77 42	70.45 59	71.44 53	51.72 47	60.77 65	55.06 44	62.14 61	66.40 73	58.13 43	76.13 35	74.79 37	80.19 48	82.04 49

ACMM	60.30 7	67.58 47	68.82 61	66.13 34	70.59 38	72.01 53	76.54 36	54.26 32	65.64 55	54.78 49	50.35 116	61.72 91	58.74 38	75.79 38	75.03 34	81.88 32	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PCF-MVS	59.98 8	67.32 48	71.04 47	62.97 49	64.77 63	74.49 40	74.78 43	49.54 57	67.44 52	54.39 53	58.35 79	72.81 45	55.79 62	71.54 62	69.24 70	78.57 62	83.41 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		67.02 49	71.57 43	61.71 51	71.01 36	74.81 38	71.62 51	38.91 171	71.86 43	60.70 23	64.97 41	67.88 67	51.88 96	76.77 31	74.98 36	76.11 100	69.75 133
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EC-MVSNet		67.01 50	70.27 53	63.21 47	67.21 52	70.47 58	69.01 60	46.96 71	59.16 71	53.23 56	64.01 48	69.71 56	60.37 31	74.92 44	71.24 55	82.50 21	82.41 45

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 48	66.63 55	74.52 39	71.56 52	45.76 77	67.37 53	55.00 46	54.31 98	68.19 63	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

CS-MVS		65.88 52	69.71 56	61.41 52	61.76 84	68.14 70	67.65 66	44.00 105	59.14 72	52.69 58	65.19 38	68.13 64	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

DELS-MVS		65.87 53	70.30 52	60.71 55	64.05 71	72.68 50	70.90 54	45.43 81	57.49 76	49.05 74	64.43 43	68.66 59	55.11 65	74.31 47	73.02 48	79.70 52	81.51 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
sasdasda		65.62 54	72.06 40	58.11 72	63.94 72	71.05 54	64.49 103	43.18 128	74.08 33	47.35 77	64.17 46	71.97 47	51.17 101	71.87 58	70.74 56	78.51 65	80.56 54

canonicalmvs		65.62 54	72.06 40	58.11 72	63.94 72	71.05 54	64.49 103	43.18 128	74.08 33	47.35 77	64.17 46	71.97 47	51.17 101	71.87 58	70.74 56	78.51 65	80.56 54

QAPM		65.27 56	69.49 58	60.35 56	65.43 60	72.20 52	65.69 91	47.23 69	63.46 58	49.14 72	53.56 99	71.04 51	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

casdiffmvs_mvg		65.26 57	69.48 59	60.33 57	62.99 78	69.34 62	69.80 58	45.27 83	63.38 59	51.11 66	65.12 40	69.75 55	53.51 78	71.74 60	68.86 76	79.33 56	78.19 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SPE-MVS-test		65.18 58	68.70 62	61.07 53	61.92 81	68.06 72	67.09 75	45.18 85	58.47 73	52.02 65	65.76 36	66.44 72	59.24 36	72.71 55	70.05 64	80.98 43	79.40 60

OMC-MVS		65.16 59	71.35 45	57.94 77	52.95 160	68.82 65	69.00 61	38.28 179	79.89 15	55.20 43	62.76 55	68.31 61	56.14 59	71.30 64	68.70 78	76.06 104	79.67 58

EPNet		65.14 60	69.54 57	60.00 60	66.61 56	67.67 79	67.53 68	55.32 24	62.67 61	46.22 87	67.74 33	65.93 74	48.07 119	72.17 57	72.12 49	76.28 96	78.47 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewcassd2359sk11		64.22 61	67.08 65	60.87 54	63.08 77	68.05 74	70.51 55	43.92 107	59.80 67	55.05 45	62.49 59	66.89 70	55.09 66	69.39 86	66.19 120	77.60 73	76.77 87

casdiffmvs		64.09 62	68.13 63	59.37 65	61.81 82	68.32 69	68.48 64	44.45 95	61.95 62	49.12 73	63.04 53	69.67 57	53.83 74	70.46 74	66.06 121	78.55 63	77.43 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt13		63.83 63	67.03 66	60.10 59	62.56 79	68.92 64	69.73 59	43.49 120	57.96 74	52.16 63	61.09 65	65.39 75	55.20 64	70.36 78	67.48 96	77.48 77	78.00 74

viewmanbaseed2359cas		63.67 64	67.42 64	59.30 67	61.34 87	67.42 85	70.01 57	40.50 158	59.53 68	52.60 59	62.56 58	67.34 69	54.44 69	70.33 79	66.93 104	76.91 86	77.82 77

PVSNet_Blended_VisFu		63.65 65	66.92 68	59.83 62	60.03 99	73.44 47	66.33 81	48.95 63	52.20 103	50.81 68	56.07 86	60.25 98	53.56 76	73.23 53	70.01 65	79.30 57	83.24 43

viewmacassd2359aftdt		63.43 66	66.95 67	59.32 66	61.27 90	67.48 83	70.15 56	40.54 155	57.82 75	52.27 62	60.49 67	66.81 71	54.58 68	70.67 72	67.39 98	77.08 85	78.02 73

Effi-MVS+		63.28 67	65.96 76	60.17 58	64.26 67	68.06 72	68.78 63	45.71 79	54.08 85	46.64 82	55.92 88	63.13 82	55.94 60	70.38 77	71.43 52	79.68 55	78.70 65

ETV-MVS		63.23 68	66.08 75	59.91 61	63.13 76	68.13 71	67.62 67	44.62 92	53.39 90	46.23 86	58.74 76	58.19 105	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

MVS_111021_LR		63.05 69	66.43 72	59.10 68	61.33 88	63.77 122	65.87 88	43.58 116	60.20 66	53.70 55	62.09 62	62.38 84	55.84 61	70.24 80	68.08 83	74.30 121	78.28 71

OpenMVS	57.13 9	62.81 70	65.75 77	59.39 64	66.47 57	69.52 61	64.26 106	43.07 132	61.34 64	50.19 70	47.29 134	64.41 77	54.60 67	70.18 81	68.62 80	77.73 70	78.89 64

CNLPA		62.78 71	66.31 73	58.65 70	58.47 109	68.41 68	65.98 86	41.22 149	78.02 22	56.04 38	46.65 137	59.50 101	57.50 45	69.67 84	65.27 134	72.70 149	76.67 88

TSAR-MVS + COLMAP		62.65 72	69.90 54	54.19 106	46.31 197	66.73 92	65.49 93	41.36 146	76.57 24	46.31 85	76.80 17	56.68 111	53.27 85	69.50 85	66.65 110	72.40 154	76.36 96

GeoE		62.43 73	64.79 84	59.68 63	64.15 70	67.17 88	68.80 62	44.42 96	55.65 80	47.38 76	51.54 110	62.51 83	54.04 73	69.99 82	68.07 84	79.28 58	78.57 66

MVS_Test		62.40 74	66.23 74	57.94 77	59.77 103	64.77 112	66.50 80	41.76 141	57.26 77	49.33 71	62.68 56	67.47 68	53.50 80	68.57 98	66.25 117	76.77 88	76.58 90

DI_MVS_pp		61.88 75	65.17 81	58.06 74	60.05 98	65.26 106	66.03 84	44.22 97	55.75 79	46.73 80	54.64 96	68.12 65	54.13 72	69.13 90	66.66 109	77.18 81	76.61 89

diffmvs_AUTHOR		61.79 76	66.80 69	55.95 94	56.69 135	63.92 120	67.27 70	41.28 147	59.32 70	46.43 84	63.31 51	68.30 62	50.56 104	68.30 101	66.06 121	73.48 135	78.36 69

diffmvs		61.64 77	66.55 71	55.90 95	56.63 136	63.71 123	67.13 74	41.27 148	59.49 69	46.70 81	63.93 50	68.01 66	50.46 105	67.30 126	65.51 130	73.24 142	77.87 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
PVSNet_BlendedMVS		61.63 78	64.82 82	57.91 79	57.21 129	67.55 81	63.47 110	46.08 75	54.72 83	52.46 60	58.59 77	60.73 94	51.82 97	70.46 74	65.20 136	76.44 93	76.50 94

PVSNet_Blended		61.63 78	64.82 82	57.91 79	57.21 129	67.55 81	63.47 110	46.08 75	54.72 83	52.46 60	58.59 77	60.73 94	51.82 97	70.46 74	65.20 136	76.44 93	76.50 94

EIA-MVS		61.53 80	63.79 90	58.89 69	63.82 74	67.61 80	65.35 94	42.15 140	49.98 111	45.66 90	57.47 83	56.62 112	56.59 55	70.91 70	69.15 71	79.78 50	74.80 107

MGCFI-Net		61.46 81	69.72 55	51.83 126	61.00 91	66.16 99	56.50 148	40.73 153	73.98 35	35.18 142	64.23 45	71.42 49	42.45 147	69.22 88	64.01 148	75.09 115	79.03 63

TAPA-MVS	54.74 10	60.85 82	66.61 70	54.12 108	47.38 193	65.33 104	65.35 94	36.51 188	75.16 30	48.82 75	54.70 95	63.51 80	53.31 84	68.36 100	64.97 140	73.37 137	74.27 110
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
viewmambaseed2359dif		60.40 83	64.15 88	56.03 93	57.79 114	63.53 124	65.91 87	41.64 142	54.98 82	46.47 83	60.16 69	64.71 76	50.76 103	66.25 144	62.83 162	73.61 134	76.57 92

Fast-Effi-MVS+		60.36 84	63.35 93	56.87 87	58.70 106	65.86 101	65.08 97	37.11 185	53.00 95	45.36 92	52.12 107	56.07 118	56.27 57	71.28 65	69.42 69	78.71 61	75.69 101

Effi-MVS+-dtu		60.34 85	62.32 97	58.03 76	64.31 65	67.44 84	65.99 85	42.26 137	49.55 114	42.00 111	48.92 124	59.79 100	56.27 57	68.07 110	67.03 100	77.35 79	75.45 103

LS3D		60.20 86	61.70 98	58.45 71	64.18 68	67.77 76	67.19 71	48.84 66	61.67 63	41.27 115	45.89 149	51.81 133	54.18 71	68.78 93	66.50 115	75.03 116	69.48 139

FA-MVS(training)		60.00 87	63.14 95	56.33 91	59.50 104	64.30 117	65.15 96	38.75 176	56.20 78	45.77 88	53.08 100	56.45 113	52.10 94	69.04 92	67.67 92	76.69 89	75.27 106

DCV-MVSNet		59.49 88	64.00 89	54.23 105	61.81 82	64.33 116	61.42 116	43.77 109	52.85 98	38.94 129	55.62 90	62.15 89	43.24 144	69.39 86	67.66 93	76.22 98	75.97 98

viewdifsd2359ckpt11		59.45 89	63.57 91	54.65 103	57.17 131	62.71 130	64.67 101	38.99 168	52.96 96	42.12 109	58.97 74	62.23 86	51.18 99	67.35 124	63.98 149	73.75 127	76.80 85

viewmsd2359difaftdt		59.45 89	63.57 91	54.65 103	57.17 131	62.71 130	64.67 101	38.99 168	52.96 96	42.12 109	58.97 74	62.22 87	51.18 99	67.35 124	63.98 149	73.75 127	76.80 85

EPP-MVSNet		59.39 91	65.45 79	52.32 123	60.96 92	67.70 78	58.42 134	44.75 90	49.71 113	27.23 178	59.03 73	62.20 88	43.34 141	70.71 71	69.13 72	79.25 59	79.63 59

ACMH+	53.71 12	59.26 92	60.28 111	58.06 74	64.17 69	68.46 67	67.51 69	50.93 50	52.46 101	35.83 141	40.83 186	45.12 179	52.32 91	69.88 83	69.00 75	77.59 75	76.21 97

PLC	52.09 14	59.21 93	62.47 96	55.41 99	53.24 158	64.84 111	64.47 105	40.41 161	65.92 54	44.53 96	46.19 145	55.69 119	55.33 63	68.24 105	65.30 133	74.50 119	71.09 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v10		59.17 94	60.60 107	57.50 82	57.95 112	66.73 92	67.09 75	44.11 98	46.85 142	45.42 91	48.18 130	51.07 135	53.63 75	67.84 114	66.59 113	76.79 87	76.92 83

CANet_DTU		58.88 95	64.68 85	52.12 124	55.77 140	66.75 91	63.92 107	37.04 186	53.32 91	37.45 137	59.81 70	61.81 90	44.43 136	68.25 103	67.47 97	74.12 123	75.33 104

v1144		58.88 95	60.16 115	57.39 83	58.03 111	67.26 86	67.14 73	44.46 94	45.17 154	44.33 97	47.81 131	49.92 144	53.20 86	67.77 116	66.62 112	77.15 82	76.58 90

v8		58.88 95	60.57 109	56.92 86	57.35 123	65.69 103	66.69 79	42.64 134	47.89 137	45.77 88	49.04 121	52.98 128	52.77 87	67.51 121	65.57 129	76.26 97	75.30 105

v2v482		58.69 98	60.12 118	57.03 85	57.16 133	66.05 100	67.17 72	43.52 118	46.33 146	45.19 93	49.46 120	51.02 136	52.51 89	67.30 126	66.03 123	76.61 90	74.62 108

v1192		58.51 99	59.66 122	57.17 84	57.82 113	67.72 77	66.21 83	44.83 89	44.15 162	43.49 100	46.68 136	47.94 148	53.55 77	67.39 123	66.51 114	77.13 83	77.20 81

UA-Net		58.50 100	64.68 85	51.30 129	66.97 53	67.13 89	53.68 171	45.65 80	49.51 116	31.58 157	62.91 54	68.47 60	35.85 181	68.20 106	67.28 99	74.03 124	69.24 143

Vis-MVSNet		58.48 101	65.70 78	50.06 136	53.40 157	67.20 87	60.24 124	43.32 125	48.83 125	30.23 163	62.38 60	61.61 92	40.35 156	71.03 67	69.77 66	72.82 145	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MSDG		58.46 102	58.97 133	57.85 81	66.27 59	66.23 98	67.72 65	42.33 136	53.43 89	43.68 99	43.39 172	45.35 175	49.75 108	68.66 96	67.77 89	77.38 78	67.96 148

FC-MVSNet-train		58.40 103	63.15 94	52.85 119	64.29 66	61.84 134	55.98 155	46.47 73	53.06 93	34.96 145	61.95 63	56.37 116	39.49 158	68.67 95	68.36 82	75.92 106	71.81 121

ET-MVSNet_ETH3D		58.38 104	61.57 99	54.67 102	42.15 210	65.26 106	65.70 89	43.82 108	48.84 124	42.34 106	59.76 71	47.76 151	56.68 54	67.02 133	68.60 81	77.33 80	73.73 116

IB-MVS	54.11 11	58.36 105	60.70 106	55.62 97	58.67 107	68.02 75	61.56 113	43.15 130	46.09 148	44.06 98	44.24 164	50.99 138	48.71 113	66.70 136	70.33 60	77.60 73	78.50 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
IterMVS-LS		58.30 106	61.39 100	54.71 101	59.92 101	58.40 165	59.42 126	43.64 114	48.71 128	40.25 122	57.53 82	58.55 104	52.15 93	65.42 156	65.34 132	72.85 143	75.77 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	52.42 13	58.24 107	59.56 127	56.70 89	66.34 58	69.59 60	66.71 78	49.12 62	46.08 149	28.90 170	42.67 181	41.20 198	52.60 88	71.39 63	70.28 61	76.51 92	75.72 100
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v144192		58.23 108	59.40 129	56.87 87	57.56 115	66.89 90	65.70 89	45.01 87	44.06 163	42.88 102	46.61 138	48.09 147	53.49 81	66.94 134	65.90 126	76.61 90	77.29 79

MS-PatchMatch		58.19 109	60.20 114	55.85 96	65.17 62	64.16 118	64.82 98	41.48 145	50.95 106	42.17 108	45.38 155	56.42 114	48.08 118	68.30 101	66.70 108	73.39 136	69.46 141

IS_MVSNet		57.95 110	64.26 87	50.60 131	61.62 86	65.25 108	57.18 141	45.42 82	50.79 107	26.49 184	57.81 81	60.05 99	34.51 185	71.24 66	70.20 63	78.36 67	74.44 109

v1921920		57.89 111	59.02 132	56.58 90	57.55 116	66.66 96	64.72 100	44.70 91	43.55 167	42.73 103	46.17 146	46.93 161	53.51 78	66.78 135	65.75 128	76.29 95	77.28 80

Anonymous20231211		57.71 112	60.79 104	54.13 107	61.68 85	65.81 102	60.81 121	43.70 113	51.97 104	39.67 124	34.82 201	63.59 79	43.31 142	68.55 99	66.63 111	75.59 107	74.13 112

v1240		57.55 113	58.63 136	56.29 92	57.30 126	66.48 97	63.77 108	44.56 93	42.77 177	42.48 105	45.64 152	46.28 168	53.46 82	66.32 142	65.80 127	76.16 99	77.13 82

MVSTER		57.19 114	61.11 102	52.62 121	50.82 180	58.79 161	61.55 114	37.86 182	48.81 126	41.31 114	57.43 84	52.10 131	48.60 114	68.19 107	66.75 107	75.56 108	75.68 102

UGNet		57.03 115	65.25 80	47.44 166	46.54 196	66.73 92	56.30 150	43.28 126	50.06 110	32.99 149	62.57 57	63.26 81	33.31 190	68.25 103	67.58 94	72.20 157	78.29 70
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
EG-PatchMatch MVS		56.98 116	58.24 140	55.50 98	64.66 64	68.62 66	61.48 115	43.63 115	38.44 202	41.44 112	38.05 193	46.18 170	43.95 137	71.71 61	70.61 58	77.87 69	74.08 113

V42		56.97 117	60.14 116	53.28 113	48.16 189	62.78 129	66.30 82	37.93 181	47.44 139	42.68 104	48.19 129	52.59 130	51.90 95	67.46 122	65.94 125	72.72 147	76.55 93

UniMVSNet_NR-MVSNet		56.94 118	61.14 101	52.05 125	60.02 100	65.21 109	57.44 139	52.93 40	49.37 117	24.31 191	54.62 97	50.54 139	39.04 160	68.69 94	68.84 77	78.53 64	70.72 126

HyFIR lowres test		56.87 119	58.60 137	54.84 100	56.62 137	69.27 63	64.77 99	42.21 138	45.66 152	37.50 136	33.08 205	57.47 110	53.33 83	65.46 155	67.94 85	74.60 118	71.35 123

thisisatest0530		56.68 120	59.68 121	53.19 115	52.97 159	60.96 144	59.41 127	40.51 156	48.26 134	41.06 117	52.67 103	46.30 167	49.78 106	67.66 119	67.83 87	75.39 110	74.07 114

CostFormer		56.57 121	59.13 131	53.60 110	57.52 118	61.12 141	66.94 77	35.95 190	53.44 88	44.68 95	55.87 89	54.44 122	48.21 116	60.37 177	58.33 185	68.27 176	70.33 131

tttt0517		56.53 122	59.59 123	52.95 118	52.66 162	60.99 143	59.21 129	40.51 156	47.89 137	40.40 120	52.50 106	46.04 171	49.78 106	67.75 117	67.83 87	75.15 113	74.17 111

ECVR-MVS		56.44 123	60.74 105	51.42 128	60.39 96	64.55 114	58.69 132	48.87 64	53.91 86	26.76 181	45.55 154	53.43 126	37.71 168	70.96 68	69.49 67	76.08 101	67.32 155

Fast-Effi-MVS+-dtu		56.30 124	59.29 130	52.82 120	58.64 108	64.89 110	65.56 92	32.89 208	45.80 151	35.04 144	45.89 149	54.14 123	49.41 109	67.16 129	66.45 116	75.37 111	70.69 128

baseline2		55.89 125	57.82 143	53.64 109	57.36 122	61.09 142	59.75 125	40.45 159	47.38 140	41.26 116	51.23 112	46.90 162	48.11 117	65.63 153	64.38 145	74.90 117	68.16 147

TranMVSNet+NR-MVSNet		55.87 126	60.14 116	50.88 130	59.46 105	63.82 121	57.93 136	52.98 39	48.94 123	20.52 199	52.87 102	47.33 157	36.81 176	69.12 91	69.03 74	77.56 76	69.89 132

CHOSEN 1792x2688		55.85 127	58.01 141	53.33 112	57.26 128	62.82 128	63.29 112	41.55 144	46.65 144	38.34 130	34.55 202	53.50 124	52.43 90	67.10 131	67.56 95	67.13 180	73.92 115

test2506		55.82 128	59.57 126	51.46 127	60.39 96	64.55 114	58.69 132	48.87 64	53.91 86	26.99 179	48.97 122	41.72 197	37.71 168	70.96 68	69.49 67	76.08 101	67.37 153

v7n		55.67 129	57.46 148	53.59 111	56.06 138	65.29 105	61.06 119	43.26 127	40.17 193	37.99 133	40.79 187	45.27 178	47.09 123	67.67 118	66.21 118	76.08 101	76.82 84

GA-MVS		55.67 129	58.33 138	52.58 122	55.23 145	63.09 125	61.08 118	40.15 164	42.95 172	37.02 139	52.61 104	47.68 152	47.51 121	65.92 149	65.35 131	74.49 120	70.68 129

v148		55.58 131	57.61 147	53.20 114	54.59 150	61.86 133	61.18 117	38.70 177	44.30 161	42.25 107	47.53 132	50.24 142	48.73 112	65.15 157	62.61 166	73.79 126	71.61 122

DU-MVS		55.41 132	59.59 123	50.54 133	54.60 148	62.97 126	57.44 139	51.80 45	48.62 131	24.31 191	51.99 108	47.00 160	39.04 160	68.11 108	67.75 90	76.03 105	70.72 126

NR-MVSNet		55.35 133	59.46 128	50.56 132	61.33 88	62.97 126	57.91 137	51.80 45	48.62 131	20.59 198	51.99 108	44.73 185	34.10 188	68.58 97	68.64 79	77.66 71	70.67 130

test1111		55.24 134	59.98 119	49.71 137	59.80 102	64.10 119	56.48 149	49.34 59	52.27 102	21.56 196	44.49 162	51.96 132	35.93 180	70.59 73	69.07 73	75.13 114	67.40 151

GBi-Net		55.20 135	60.25 112	49.31 140	52.42 163	61.44 136	57.03 142	44.04 101	49.18 120	30.47 159	48.28 126	58.19 105	38.22 163	68.05 111	66.96 101	73.69 130	69.65 134

test1		55.20 135	60.25 112	49.31 140	52.42 163	61.44 136	57.03 142	44.04 101	49.18 120	30.47 159	48.28 126	58.19 105	38.22 163	68.05 111	66.96 101	73.69 130	69.65 134

baseline		55.19 137	60.88 103	48.55 153	49.87 184	58.10 170	58.70 131	34.75 194	52.82 99	39.48 128	60.18 68	60.86 93	45.41 131	61.05 173	60.74 176	63.10 194	72.41 119

UniMVSNet (Re)		55.15 138	60.39 110	49.03 146	55.31 142	64.59 113	55.77 156	50.63 52	48.66 130	20.95 197	51.47 111	50.40 140	34.41 187	67.81 115	67.89 86	77.11 84	71.88 120

FMVSNet2		55.04 139	59.95 120	49.31 140	52.42 163	61.44 136	57.03 142	44.08 100	49.55 114	30.40 162	46.89 135	58.84 103	38.22 163	67.07 132	66.21 118	73.69 130	69.65 134

FMVSNet3		54.78 140	59.58 125	49.17 143	52.37 166	61.31 140	56.72 147	44.04 101	49.18 120	30.47 159	48.28 126	58.19 105	38.09 166	65.48 154	65.20 136	73.31 139	69.45 142

pmmvs4		54.66 141	56.07 152	53.00 117	54.63 147	57.08 176	60.43 123	44.10 99	51.69 105	40.55 119	46.55 141	44.79 184	45.95 129	62.54 166	63.66 153	72.36 155	66.20 163

baseline1		54.48 142	58.69 134	49.57 138	60.63 95	58.29 168	55.70 157	44.95 88	49.20 119	29.62 166	54.77 94	54.75 121	35.29 182	67.15 130	64.08 146	71.21 164	62.58 186

FMVSNet1		54.08 143	58.68 135	48.71 150	50.90 179	61.35 139	56.73 146	43.94 106	45.91 150	29.32 169	42.72 180	56.26 117	37.70 170	68.05 111	66.96 101	73.69 130	69.50 138

thisisatest0515		53.85 144	56.84 151	50.37 134	50.25 183	58.17 169	55.99 154	39.90 165	41.88 182	38.16 132	45.91 148	45.30 176	44.58 135	66.15 147	66.89 105	73.36 138	73.57 117

Baseline_NR-MVSNet		53.50 145	57.89 142	48.37 157	54.60 148	59.25 158	56.10 151	51.84 44	49.32 118	17.92 206	45.38 155	47.68 152	36.93 175	68.11 108	65.95 124	72.84 144	69.57 137

IterMVS		53.45 146	57.12 149	49.17 143	49.23 186	60.93 145	59.05 130	34.63 196	44.53 157	33.22 147	51.09 115	51.01 137	48.38 115	62.43 168	60.79 175	70.54 168	69.05 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm cat1		53.30 147	53.41 170	53.17 116	58.16 110	59.15 159	63.73 109	38.27 180	50.73 108	46.98 79	45.57 153	44.00 191	49.20 110	55.90 205	54.02 204	62.65 196	64.50 177

anonymousdsp		52.84 148	57.78 144	47.06 167	40.24 214	58.95 160	53.70 170	33.54 204	36.51 209	32.69 152	43.88 166	45.40 174	47.97 120	67.17 128	70.28 61	74.22 122	82.29 47

UniMVSNet_ETH3D		52.62 149	55.98 153	48.70 151	51.04 177	60.71 146	56.87 145	46.74 72	42.52 179	26.96 180	42.50 182	45.95 172	37.87 167	66.22 145	65.15 139	72.74 146	68.78 146

tfpn200view9		52.53 150	55.51 155	49.06 145	57.31 124	60.24 148	55.42 161	43.77 109	42.85 175	27.81 174	43.00 178	45.06 181	37.32 172	66.38 139	64.54 142	72.71 148	66.54 158

CDS-MVSNet		52.42 151	57.06 150	47.02 168	53.92 155	58.30 167	55.50 159	46.47 73	42.52 179	29.38 168	49.50 119	52.85 129	28.49 200	66.70 136	66.89 105	68.34 175	62.63 185
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
thres200		52.39 152	55.37 158	48.90 147	57.39 121	60.18 149	55.60 158	43.73 111	42.93 173	27.41 176	43.35 173	45.09 180	36.61 177	66.36 140	63.92 152	72.66 150	65.78 168

thres400		52.38 153	55.51 155	48.74 149	57.49 119	60.10 151	55.45 160	43.54 117	42.90 174	26.72 182	43.34 174	45.03 183	36.61 177	66.20 146	64.53 143	72.66 150	66.43 159

IterMVS-SCA-FT		52.18 154	57.75 145	45.68 173	51.01 178	62.06 132	55.10 164	34.75 194	44.85 155	32.86 151	51.13 114	51.22 134	48.74 111	62.47 167	61.51 171	51.61 220	71.02 125

dmvs_re		52.07 155	55.11 160	48.54 154	57.27 127	51.93 191	57.73 138	43.13 131	43.65 165	26.57 183	44.52 161	50.00 143	36.53 179	66.58 138	62.15 168	69.97 170	66.91 156

EPNet_dtu		52.05 156	58.26 139	44.81 178	54.10 153	50.09 198	52.01 176	40.82 152	53.03 94	27.41 176	54.90 92	57.96 109	26.72 202	62.97 163	62.70 165	67.78 178	66.19 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres100view900		52.04 157	54.81 163	48.80 148	57.31 124	59.33 156	55.30 162	42.92 133	42.85 175	27.81 174	43.00 178	45.06 181	36.99 174	64.74 159	63.51 154	72.47 153	65.21 172

COLMAP_ROB	46.52 15	51.99 158	54.86 162	48.63 152	49.13 187	61.73 135	60.53 122	36.57 187	53.14 92	32.95 150	37.10 194	38.68 209	40.49 155	65.72 151	63.08 158	72.11 158	64.60 176
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TransMVSNet (Re)		51.92 159	55.38 157	47.88 163	60.95 93	59.90 152	53.95 168	45.14 86	39.47 196	24.85 188	43.87 167	46.51 166	29.15 197	67.55 120	65.23 135	73.26 141	65.16 173

thres600view7		51.91 160	55.14 159	48.14 159	57.43 120	60.18 149	54.60 166	43.73 111	42.61 178	25.20 187	43.10 177	44.47 188	35.19 183	66.36 140	63.28 157	72.66 150	66.01 166

pmmvs-eth3d		51.33 161	52.25 180	50.26 135	50.82 180	54.65 181	56.03 153	43.45 124	43.51 168	37.20 138	39.20 190	39.04 208	42.28 148	61.85 171	62.78 163	71.78 160	64.72 175

USDC		51.11 162	53.71 167	48.08 161	44.76 202	55.99 179	53.01 175	40.90 150	52.49 100	36.14 140	44.67 160	33.66 219	43.27 143	63.23 162	61.10 173	70.39 169	64.82 174

pm-mvs1		51.02 163	55.55 154	45.73 172	54.16 152	58.52 163	50.92 178	42.56 135	40.32 191	25.67 186	43.66 169	50.34 141	30.06 195	65.85 150	63.97 151	70.99 166	66.21 162

SCA		50.99 164	53.22 174	48.40 156	51.07 176	56.78 177	50.25 180	39.05 167	48.31 133	41.38 113	49.54 118	46.70 165	46.00 128	58.31 187	56.28 188	62.65 196	56.60 204

CR-MVSNet		50.47 165	52.61 176	47.98 162	49.03 188	52.94 186	48.27 187	38.86 173	44.41 158	39.59 125	44.34 163	44.65 187	46.63 125	58.97 182	60.31 177	65.48 186	62.66 183

dps		50.42 166	51.20 187	49.51 139	55.88 139	56.07 178	53.73 169	38.89 172	43.66 164	40.36 121	45.66 151	37.63 213	45.23 132	59.05 180	56.18 189	62.94 195	60.16 194

Vis-MVSNet (Re-imp)		50.37 167	57.73 146	41.80 192	57.53 117	54.35 182	45.70 201	45.24 84	49.80 112	13.43 212	58.23 80	56.42 114	20.11 214	62.96 164	63.36 156	68.76 174	58.96 198

MDTV_nov1_ep13		50.32 168	52.43 179	47.86 164	49.87 184	54.70 180	58.10 135	34.29 198	45.59 153	37.71 134	47.44 133	47.42 156	41.86 150	58.07 190	55.21 197	65.34 188	58.56 199

tfpnnormal		50.16 169	52.19 181	47.78 165	56.86 134	58.37 166	54.15 167	44.01 104	38.35 204	25.94 185	36.10 197	37.89 211	34.50 186	65.93 148	63.42 155	71.26 163	65.28 171

PatchMatch-RL		50.11 170	51.56 184	48.43 155	46.23 198	51.94 190	50.21 181	38.62 178	46.62 145	37.51 135	42.43 183	39.38 206	52.24 92	60.98 174	59.56 180	65.76 185	60.01 196

PatchmatchNet		49.92 171	51.29 185	48.32 158	51.83 170	51.86 192	53.38 174	37.63 184	47.90 136	40.83 118	48.54 125	45.30 176	45.19 133	56.86 195	53.99 206	61.08 201	54.57 207
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TDRefinement		49.31 172	52.44 178	45.67 174	30.44 225	59.42 155	59.24 128	39.78 166	48.76 127	31.20 158	35.73 198	29.90 224	42.81 146	64.24 161	62.59 167	70.55 167	66.43 159

test-LLR		49.28 173	50.29 191	48.10 160	55.26 143	47.16 207	49.52 182	43.48 122	39.22 197	31.98 153	43.65 170	47.93 149	41.29 153	56.80 196	55.36 195	67.08 181	61.94 187

CMPMVS	37.70 17	49.24 174	52.71 175	45.19 175	45.97 199	51.23 194	47.44 193	29.31 213	43.04 171	44.69 94	34.45 203	48.35 146	43.64 138	62.59 165	59.82 179	60.08 202	69.48 139
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PEN-MVS		49.21 175	54.32 165	43.24 187	54.33 151	59.26 157	47.04 195	51.37 49	41.67 183	9.97 220	46.22 144	41.80 196	22.97 211	60.52 175	64.03 147	73.73 129	66.75 157

PMMVS		49.20 176	54.28 166	43.28 186	34.13 219	45.70 214	48.98 185	26.09 221	46.31 147	34.92 146	55.22 91	53.47 125	47.48 122	59.43 179	59.04 183	68.05 177	60.77 191

gg-mvs-nofinetune		49.07 177	52.56 177	45.00 177	61.99 80	59.78 153	53.55 173	41.63 143	31.62 218	12.08 214	29.56 214	53.28 127	29.57 196	66.27 143	64.49 144	71.19 165	62.92 182

tpm		48.82 178	51.27 186	45.96 171	54.10 153	47.35 206	56.05 152	30.23 212	46.70 143	43.21 101	52.54 105	47.55 155	37.28 173	54.11 210	50.50 213	54.90 213	60.12 195

WR-MVS		48.78 179	55.06 161	41.45 193	55.50 141	60.40 147	43.77 209	49.99 56	41.92 181	8.10 225	45.24 158	45.56 173	17.47 215	61.57 172	64.60 141	73.85 125	66.14 165

CP-MVSNet		48.37 180	53.53 169	42.34 189	51.35 173	58.01 171	46.56 196	50.54 53	41.62 184	10.61 216	46.53 142	40.68 202	23.18 209	58.71 185	61.83 169	71.81 159	67.36 154

pmmvs6		48.35 181	51.64 183	44.51 180	51.92 169	57.94 172	49.44 184	42.17 139	34.45 211	24.62 190	28.87 216	46.90 162	29.07 199	64.60 160	63.08 158	69.83 171	65.68 169

PS-CasMVS		48.18 182	53.25 173	42.27 190	51.26 174	57.94 172	46.51 197	50.52 54	41.30 185	10.56 217	45.35 157	40.34 204	23.04 210	58.66 186	61.79 170	71.74 161	67.38 152

PatchT		48.08 183	51.03 188	44.64 179	42.96 207	50.12 197	40.36 216	35.09 192	43.17 170	39.59 125	42.00 184	39.96 205	46.63 125	58.97 182	60.31 177	63.21 193	62.66 183

tpmrst		48.08 183	49.88 195	45.98 170	52.71 161	48.11 204	53.62 172	33.70 203	48.70 129	39.74 123	48.96 123	46.23 169	40.29 157	50.14 219	49.28 215	55.80 210	57.71 201

DTE-MVSNet		48.03 185	53.28 172	41.91 191	54.64 146	57.50 174	44.63 208	51.66 48	41.02 187	7.97 226	46.26 143	40.90 199	20.24 213	60.45 176	62.89 161	72.33 156	63.97 178

WR-MVS_H		47.65 186	53.67 168	40.63 196	51.45 171	59.74 154	44.71 207	49.37 58	40.69 189	7.61 227	46.04 147	44.34 190	17.32 216	57.79 191	61.18 172	73.30 140	65.86 167

MDTV_nov1_ep13_2view		47.62 187	49.72 196	45.18 176	48.05 190	53.70 184	54.90 165	33.80 202	39.90 195	29.79 165	38.85 191	41.89 195	39.17 159	58.99 181	55.55 194	65.34 188	59.17 197

SixPastTwentyTwo		47.55 188	50.25 193	44.41 181	47.30 194	54.31 183	47.81 190	40.36 162	33.76 212	19.93 201	43.75 168	32.77 221	42.07 149	59.82 178	60.94 174	68.98 172	66.37 161

TinyColmap		47.08 189	47.56 203	46.52 169	42.35 209	53.44 185	51.77 177	40.70 154	43.44 169	31.92 155	29.78 213	23.72 230	45.04 134	61.99 170	59.54 181	67.35 179	61.03 190

pmmvs5		47.07 190	51.02 189	42.46 188	45.18 201	51.47 193	48.23 189	33.09 207	38.17 205	28.62 172	46.60 139	43.48 192	30.74 193	58.28 188	58.63 184	68.92 173	60.48 192

LTVRE_ROB	44.17 16	47.06 191	50.15 194	43.44 184	51.39 172	58.42 164	42.90 211	43.51 119	22.27 228	14.85 210	41.94 185	34.57 217	45.43 130	62.28 169	62.77 164	62.56 198	68.83 145
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		46.41 192	48.72 198	43.72 182	47.77 192	52.94 186	46.02 200	33.92 200	44.41 158	31.82 156	36.89 195	37.42 214	37.41 171	53.88 211	54.02 204	65.37 187	61.47 189

RPSCF		46.41 192	54.42 164	37.06 206	25.70 232	45.14 215	45.39 203	20.81 225	62.79 60	35.10 143	44.92 159	55.60 120	43.56 139	56.12 202	52.45 210	51.80 219	63.91 179

CVMVSNet		46.38 194	52.01 182	39.81 198	42.40 208	50.26 196	46.15 198	37.68 183	40.03 194	15.09 209	46.56 140	47.56 154	33.72 189	56.50 200	55.65 193	63.80 192	67.53 149

TESTMET0.1,1		46.09 195	50.29 191	41.18 194	36.91 217	47.16 207	49.52 182	20.32 226	39.22 197	31.98 153	43.65 170	47.93 149	41.29 153	56.80 196	55.36 195	67.08 181	61.94 187

test-mter		45.30 196	50.37 190	39.38 199	33.65 221	46.99 209	47.59 191	18.59 227	38.75 200	28.00 173	43.28 175	46.82 164	41.50 152	57.28 193	55.78 192	66.93 183	63.70 180

gm-plane-assit		44.74 197	45.95 205	43.33 185	60.88 94	46.79 212	36.97 221	32.24 211	24.15 226	11.79 215	29.26 215	32.97 220	46.64 124	65.09 158	62.95 160	71.45 162	60.42 193

EPMVS		44.66 198	47.86 202	40.92 195	47.97 191	44.70 216	47.58 192	33.27 205	48.11 135	29.58 167	49.65 117	44.38 189	34.65 184	51.71 214	47.90 217	52.49 218	48.57 219

PM-MVS		44.55 199	48.13 201	40.37 197	32.85 223	46.82 211	46.11 199	29.28 214	40.48 190	29.99 164	39.98 189	34.39 218	41.80 151	56.08 203	53.88 208	62.19 199	65.31 170

TAMVS		44.02 200	49.18 197	37.99 204	47.03 195	45.97 213	45.04 204	28.47 216	39.11 199	20.23 200	43.22 176	48.52 145	28.49 200	58.15 189	57.95 187	58.71 204	51.36 210

MIMVSNet		43.79 201	48.53 199	38.27 202	41.46 211	48.97 201	50.81 179	32.88 209	44.55 156	22.07 194	32.05 206	47.15 158	24.76 205	58.73 184	56.09 191	57.63 209	52.14 208

test0.0.03 1		43.15 202	46.95 204	38.72 201	55.26 143	50.56 195	42.48 212	43.48 122	38.16 206	15.11 208	35.07 200	44.69 186	16.47 217	55.95 204	54.34 203	59.54 203	49.87 217

Anonymous20231206		42.28 203	45.89 206	38.07 203	51.96 168	48.98 200	43.66 210	38.81 175	38.74 201	14.32 211	26.74 218	40.90 199	20.94 212	56.64 199	54.67 201	58.71 204	54.59 206

MVS-HIRNet		42.24 204	41.15 218	43.51 183	44.06 206	40.74 219	35.77 223	35.35 191	35.38 210	38.34 130	25.63 221	38.55 210	43.48 140	50.77 216	47.03 219	64.07 190	49.98 215

MDA-MVSNet-bldmvs		41.36 205	43.15 216	39.27 200	28.74 227	52.68 188	44.95 206	40.84 151	32.89 214	18.13 205	31.61 208	22.09 231	38.97 162	50.45 218	56.11 190	64.01 191	56.23 205

FMVSNet5		40.96 206	45.81 207	35.29 211	34.30 218	44.55 217	47.28 194	28.84 215	40.76 188	21.62 195	29.85 212	42.44 193	24.77 204	57.53 192	55.00 198	54.93 212	50.56 213

CHOSEN 280x420		40.80 207	45.05 210	35.84 210	32.95 222	29.57 228	44.98 205	23.71 224	37.54 207	18.42 204	31.36 209	47.07 159	46.41 127	56.71 198	54.65 202	48.55 223	58.47 200

ADS-MVSNet		40.67 208	43.38 215	37.50 205	44.36 204	39.79 223	42.09 214	32.67 210	44.34 160	28.87 171	40.76 188	40.37 203	30.22 194	48.34 224	45.87 222	46.81 224	44.21 223

EU-MVSNet		40.63 209	45.65 208	34.78 212	39.11 215	46.94 210	40.02 217	34.03 199	33.50 213	10.37 218	35.57 199	37.80 212	23.65 208	51.90 213	50.21 214	61.49 200	63.62 181

pmnet_mix02		40.48 210	43.80 213	36.61 207	45.79 200	40.45 221	42.12 213	33.18 206	40.30 192	24.11 193	38.76 192	37.11 215	24.30 206	52.97 212	46.66 221	50.17 221	50.33 214

test20.03		40.38 211	44.20 212	35.92 209	53.73 156	49.05 199	38.54 218	43.49 120	32.55 215	9.54 221	27.88 217	39.12 207	12.24 222	56.28 201	54.69 200	57.96 208	49.83 218

FE-MVSNET		39.75 212	44.50 211	34.21 213	32.01 224	48.77 202	37.71 220	38.94 170	30.91 220	6.25 230	26.24 220	32.10 222	23.68 207	57.28 193	59.53 182	66.68 184	56.64 203

FC-MVSNet-test		39.65 213	48.35 200	29.49 217	44.43 203	39.28 225	30.23 227	40.44 160	43.59 166	3.12 234	53.00 101	42.03 194	10.02 230	55.09 207	54.77 199	48.66 222	50.71 212

testgi		38.71 214	43.64 214	32.95 214	52.30 167	48.63 203	35.59 224	35.05 193	31.58 219	9.03 224	30.29 210	40.75 201	11.19 228	55.30 206	53.47 209	54.53 215	45.48 221

FPMVS		38.36 215	40.41 219	35.97 208	38.92 216	39.85 222	45.50 202	25.79 222	41.13 186	18.70 203	30.10 211	24.56 228	31.86 192	49.42 221	46.80 220	55.04 211	51.03 211

GG-mvs-BLEND		36.62 216	53.39 171	17.06 225	0.01 238	58.61 162	48.63 186	0.01 234	47.13 141	0.02 239	43.98 165	60.64 96	0.03 234	54.92 209	51.47 212	53.64 216	56.99 202

MIMVSNet1		35.51 217	41.41 217	28.63 218	27.53 229	43.36 218	38.09 219	33.82 201	32.01 216	6.77 228	21.63 225	35.43 216	11.97 224	55.05 208	53.99 206	53.59 217	48.36 220

pmmvs3		35.10 218	38.47 220	31.17 216	26.37 231	40.47 220	34.51 225	18.09 228	24.75 225	16.88 207	23.05 223	26.69 226	32.69 191	50.73 217	51.60 211	58.46 207	51.98 209

PMVS	27.84 18	33.81 219	35.28 224	32.09 215	34.13 219	24.81 230	32.51 226	26.48 220	26.41 223	19.37 202	23.76 222	24.02 229	25.18 203	50.78 215	47.24 218	54.89 214	49.95 216
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new-patchmatchnet		33.24 220	37.20 221	28.62 219	44.32 205	38.26 226	29.68 228	36.05 189	31.97 217	6.33 229	26.59 219	27.33 225	11.12 229	50.08 220	41.05 225	44.23 225	45.15 222

N_pmnet		32.67 221	36.85 222	27.79 220	40.55 213	32.13 227	35.80 222	26.79 219	37.24 208	9.10 222	32.02 207	30.94 223	16.30 218	47.22 225	41.21 224	38.21 227	37.21 224

WB-MVS		29.70 222	35.40 223	23.05 222	40.96 212	39.59 224	18.79 231	40.20 163	25.26 224	1.88 237	33.33 204	21.97 232	3.36 231	48.69 223	44.60 223	33.11 229	34.39 225

Gipuma		25.87 223	26.91 226	24.66 221	28.98 226	20.17 231	20.46 229	34.62 197	29.55 221	9.10 222	4.91 234	5.31 238	15.76 219	49.37 222	49.10 216	39.03 226	29.95 227
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new_pmnet		23.19 224	28.17 225	17.37 223	17.03 233	24.92 229	19.66 230	16.16 230	27.05 222	4.42 231	20.77 226	19.20 233	12.19 223	37.71 226	36.38 226	34.77 228	31.17 226

PMMVS2		15.84 225	19.68 227	11.35 227	15.74 234	16.95 232	13.31 232	17.64 229	16.08 230	0.36 238	13.12 228	11.47 235	1.69 233	28.82 227	27.24 228	19.38 233	24.09 229

E-PMN		15.09 226	13.19 230	17.30 224	27.80 228	12.62 234	7.81 235	27.54 217	14.62 232	3.19 232	6.89 231	2.52 241	15.09 220	15.93 230	20.22 229	22.38 230	19.53 230

EMVS		14.49 227	12.45 231	16.87 226	27.02 230	12.56 235	8.13 234	27.19 218	15.05 231	3.14 233	6.69 232	2.67 240	15.08 221	14.60 232	18.05 230	20.67 231	17.56 232

MVE	12.28 19	13.53 228	15.72 228	10.96 228	7.39 235	15.71 233	6.05 236	23.73 223	10.29 234	3.01 235	5.77 233	3.41 239	11.91 225	20.11 228	29.79 227	13.67 234	24.98 228
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		12.44 229	14.66 229	9.85 229	1.30 237	3.32 237	13.00 233	3.21 231	22.42 227	10.22 219	14.13 227	25.64 227	11.43 227	19.75 229	11.61 232	19.96 232	5.79 233

testmvs		0.01 230	0.02 232	0.00 231	0.00 239	0.00 239	0.01 240	0.00 235	0.01 235	0.00 240	0.03 236	0.00 242	0.01 235	0.01 234	0.01 233	0.00 237	0.06 235

test123		0.01 230	0.02 232	0.00 231	0.00 239	0.00 239	0.00 241	0.00 235	0.01 235	0.00 240	0.04 235	0.00 242	0.01 235	0.00 235	0.01 233	0.00 237	0.07 234

uanet_test		0.00 232	0.00 234	0.00 231	0.00 239	0.00 239	0.00 241	0.00 235	0.00 237	0.00 240	0.00 237	0.00 242	0.00 237	0.00 235	0.00 235	0.00 237	0.00 236

sosnet-low-res		0.00 232	0.00 234	0.00 231	0.00 239	0.00 239	0.00 241	0.00 235	0.00 237	0.00 240	0.00 237	0.00 242	0.00 237	0.00 235	0.00 235	0.00 237	0.00 236

sosnet		0.00 232	0.00 234	0.00 231	0.00 239	0.00 239	0.00 241	0.00 235	0.00 237	0.00 240	0.00 237	0.00 242	0.00 237	0.00 235	0.00 235	0.00 237	0.00 236

TPM-MVS					75.48 14	76.70 30	79.31 21			62.34 17	64.71 42	77.88 28	56.94 53			81.88 32	83.68 40
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										33.01 148

9.14												81.81 13

SR-MVS					71.46 34			54.67 28				81.54 14

Anonymous202405211			60.60 107		63.44 75	66.71 95	61.00 120	47.23 69	50.62 109		36.85 196	60.63 97	43.03 145	69.17 89	67.72 91	75.41 109	72.54 118

our_test_3					51.15 175	57.31 175	55.12 163

ambc			45.54 209		50.66 182	52.63 189	40.99 215		38.36 203	24.67 189	22.62 224	13.94 234	29.14 198	65.71 152	58.06 186	58.60 206	67.43 150

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 27

Patchmatch-RL test							1.04 239

tmp_tt				5.40 230	3.97 236	2.35 238	3.26 238	0.44 233	17.56 229	12.09 213	11.48 230	7.14 236	1.98 232	15.68 231	15.49 231	10.69 235

XVS					70.49 39	76.96 26	74.36 45			54.48 50		74.47 38				82.24 25

X-MVStestdata					70.49 39	76.96 26	74.36 45			54.48 50		74.47 38				82.24 25

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 42

Patchmtry						47.61 205	48.27 187	38.86 173		39.59 125

DeepMVS_CX						6.95 236	5.98 237	2.25 232	11.73 233	2.07 236	11.85 229	5.43 237	11.75 226	11.40 233		8.10 236	18.38 231

High-resolution multi-view benchmark