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.

MTAPA										83.48 1		86.45 18

SED-MVS		88.85 1	91.59 2	85.67 1	90.54 15	92.29 2	91.71 3	76.40 2	92.41 2	83.24 2	92.50 3	90.64 3	81.10 2	89.53 2	88.02 7	91.00 8	95.73 2

zzz-MVS		85.71 16	86.88 22	84.34 11	90.54 15	87.11 44	89.77 18	74.17 18	88.54 13	83.08 3	78.60 32	86.10 19	78.11 15	87.80 16	87.46 14	90.35 29	92.56 26

DVP-MVS		88.67 2	91.62 1	85.22 3	90.47 17	92.36 1	90.69 9	76.15 3	93.08 1	82.75 4	92.19 5	90.71 2	80.45 5	89.27 5	87.91 8	90.82 11	95.84 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
MTMP										82.66 5		84.91 26

DPE-MVS		88.63 3	91.29 3	85.53 2	90.87 8	92.20 3	91.98 2	76.00 5	90.55 7	82.09 6	93.85 1	90.75 1	81.25 1	88.62 7	87.59 13	90.96 9	95.48 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
xxxxxxxxxxxxxcwj		85.35 19	85.76 30	84.86 7	91.26 5	91.10 7	90.90 5	75.65 7	89.21 8	81.25 7	91.12 7	61.35 116	78.82 9	87.42 19	86.23 30	91.28 3	93.90 12

SF-MVS		87.47 7	89.70 7	84.86 7	91.26 5	91.10 7	90.90 5	75.65 7	89.21 8	81.25 7	91.12 7	88.93 6	78.82 9	87.42 19	86.23 30	91.28 3	93.90 12

MSP-MVS		88.09 4	90.84 4	84.88 6	90.00 23	91.80 5	91.63 4	75.80 6	91.99 3	81.23 9	92.54 2	89.18 5	80.89 3	87.99 14	87.91 8	89.70 43	94.51 6
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
HPM-MVS++		87.09 8	88.92 12	84.95 5	92.61 1	87.91 40	90.23 15	76.06 4	88.85 12	81.20 10	87.33 13	87.93 11	79.47 8	88.59 8	88.23 5	90.15 34	93.60 20

SD-MVS		86.96 9	89.45 8	84.05 15	90.13 20	89.23 22	89.77 18	74.59 14	89.17 10	80.70 11	89.93 11	89.67 4	78.47 12	87.57 18	86.79 22	90.67 17	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
HFP-MVS		86.15 14	87.95 17	84.06 14	90.80 9	89.20 23	89.62 20	74.26 16	87.52 15	80.63 12	86.82 16	84.19 29	78.22 14	87.58 17	87.19 16	90.81 12	93.13 24

TSAR-MVS + MP.		86.88 10	89.23 9	84.14 13	89.78 26	88.67 31	90.59 10	73.46 27	88.99 11	80.52 13	91.26 6	88.65 8	79.91 7	86.96 30	86.22 32	90.59 18	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
SMA-MVS		87.56 6	90.17 6	84.52 9	91.71 2	90.57 9	90.77 8	75.19 13	90.67 6	80.50 14	86.59 17	88.86 7	78.09 16	89.92 1	89.41 1	90.84 10	95.19 4
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
APDe-MVS		88.00 5	90.50 5	85.08 4	90.95 7	91.58 6	92.03 1	75.53 12	91.15 4	80.10 15	92.27 4	88.34 10	80.80 4	88.00 13	86.99 18	91.09 6	95.16 5

ACMMP_NAP		86.52 12	89.01 10	83.62 17	90.28 19	90.09 13	90.32 13	74.05 20	88.32 14	79.74 16	87.04 15	85.59 23	76.97 29	89.35 3	88.44 4	90.35 29	94.27 10

CSCG		85.28 22	87.68 18	82.49 25	89.95 24	91.99 4	88.82 25	71.20 38	86.41 22	79.63 17	79.26 29	88.36 9	73.94 39	86.64 32	86.67 25	91.40 2	94.41 7

CNVR-MVS		86.36 13	88.19 16	84.23 12	91.33 4	89.84 14	90.34 11	75.56 10	87.36 18	78.97 18	81.19 28	86.76 17	78.74 11	89.30 4	88.58 2	90.45 26	94.33 9

APD-MVS		86.84 11	88.91 13	84.41 10	90.66 11	90.10 12	90.78 7	75.64 9	87.38 17	78.72 19	90.68 10	86.82 16	80.15 6	87.13 25	86.45 28	90.51 20	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSLP-MVS++		82.09 37	82.66 41	81.42 30	87.03 44	87.22 43	85.82 42	70.04 43	80.30 44	78.66 20	68.67 67	81.04 44	77.81 19	85.19 46	84.88 44	89.19 53	91.31 37

3Dnovator+	75.73 4	82.40 35	82.76 40	81.97 29	88.02 38	89.67 17	86.60 37	71.48 37	81.28 43	78.18 21	64.78 83	77.96 51	77.13 27	87.32 23	86.83 21	90.41 27	91.48 36

MP-MVS		85.50 18	87.40 20	83.28 20	90.65 12	89.51 19	89.16 24	74.11 19	83.70 34	78.06 22	85.54 20	84.89 27	77.31 24	87.40 22	87.14 17	90.41 27	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NCCC		85.34 20	86.59 24	83.88 16	91.48 3	88.88 25	89.79 17	75.54 11	86.67 21	77.94 23	76.55 35	84.99 25	78.07 17	88.04 11	87.68 11	90.46 25	93.31 21

DeepC-MVS	78.47 2	84.81 26	86.03 28	83.37 19	89.29 32	90.38 11	88.61 27	76.50 1	86.25 23	77.22 24	75.12 39	80.28 45	77.59 22	88.39 9	88.17 6	91.02 7	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
ACMMPR		85.52 17	87.53 19	83.17 22	90.13 20	89.27 20	89.30 21	73.97 21	86.89 20	77.14 25	86.09 18	83.18 32	77.74 20	87.42 19	87.20 15	90.77 13	92.63 25

CP-MVS		84.74 27	86.43 26	82.77 24	89.48 30	88.13 39	88.64 26	73.93 22	84.92 25	76.77 26	81.94 26	83.50 30	77.29 26	86.92 31	86.49 27	90.49 21	93.14 23

DPM-MVS		83.30 32	84.33 35	82.11 27	89.56 28	88.49 34	90.33 12	73.24 28	83.85 33	76.46 27	72.43 48	82.65 33	73.02 47	86.37 36	86.91 19	90.03 36	89.62 51

DeepC-MVS_fast	78.24 3	84.27 29	85.50 31	82.85 23	90.46 18	89.24 21	87.83 33	74.24 17	84.88 26	76.23 28	75.26 38	81.05 43	77.62 21	88.02 12	87.62 12	90.69 16	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
MCST-MVS		85.13 23	86.62 23	83.39 18	90.55 14	89.82 16	89.29 22	73.89 23	84.38 31	76.03 29	79.01 31	85.90 21	78.47 12	87.81 15	86.11 34	92.11 1	93.29 22

SteuartSystems-ACMMP		85.99 15	88.31 15	83.27 21	90.73 10	89.84 14	90.27 14	74.31 15	84.56 30	75.88 30	87.32 14	85.04 24	77.31 24	89.01 6	88.46 3	91.14 5	93.96 11
Skip Steuart: Steuart Systems R&D Blog.
AdaColmap		79.74 47	78.62 59	81.05 33	89.23 33	86.06 52	84.95 49	71.96 34	79.39 48	75.51 31	63.16 89	68.84 93	76.51 30	83.55 57	82.85 55	88.13 71	86.46 75

CLD-MVS		79.35 50	81.23 46	77.16 54	85.01 58	86.92 46	85.87 41	60.89 127	80.07 47	75.35 32	72.96 46	73.21 65	68.43 76	85.41 43	84.63 45	87.41 87	85.44 86
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PGM-MVS		84.42 28	86.29 27	82.23 26	90.04 22	88.82 27	89.23 23	71.74 36	82.82 37	74.61 33	84.41 23	82.09 35	77.03 28	87.13 25	86.73 24	90.73 15	92.06 32

CANet		81.62 40	83.41 37	79.53 41	87.06 43	88.59 32	85.47 45	67.96 59	76.59 53	74.05 34	74.69 40	81.98 36	72.98 48	86.14 39	85.47 38	89.68 44	90.42 46

3Dnovator	73.76 5	79.75 46	80.52 51	78.84 45	84.94 60	87.35 41	84.43 52	65.54 74	78.29 49	73.97 35	63.00 91	75.62 57	74.07 38	85.00 47	85.34 40	90.11 35	89.04 53

TSAR-MVS + GP.		83.69 30	86.58 25	80.32 36	85.14 55	86.96 45	84.91 50	70.25 42	84.71 29	73.91 36	85.16 21	85.63 22	77.92 18	85.44 41	85.71 37	89.77 40	92.45 27

DeepPCF-MVS	79.04 1	85.30 21	88.93 11	81.06 32	88.77 36	90.48 10	85.46 46	73.08 29	90.97 5	73.77 37	84.81 22	85.95 20	77.43 23	88.22 10	87.73 10	87.85 79	94.34 8

train_agg		84.86 25	87.21 21	82.11 27	90.59 13	85.47 55	89.81 16	73.55 26	83.95 32	73.30 38	89.84 12	87.23 14	75.61 32	86.47 34	85.46 39	89.78 39	92.06 32

CNLPA		77.20 61	77.54 66	76.80 56	82.63 65	84.31 63	79.77 72	64.64 80	85.17 24	73.18 39	56.37 125	69.81 83	74.53 35	81.12 86	78.69 110	86.04 126	87.29 68

abl_6				79.05 43	87.27 42	88.85 26	83.62 56	68.25 55	81.68 41	72.94 40	73.79 45	84.45 28	72.55 50			89.66 45	90.64 43

ACMMP		83.42 31	85.27 32	81.26 31	88.47 37	88.49 34	88.31 31	72.09 33	83.42 35	72.77 41	82.65 24	78.22 49	75.18 33	86.24 38	85.76 36	90.74 14	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
OMC-MVS		80.26 42	82.59 42	77.54 52	83.04 63	85.54 54	83.25 58	65.05 78	87.32 19	72.42 42	72.04 50	78.97 47	73.30 43	83.86 53	81.60 65	88.15 70	88.83 55

TSAR-MVS + ACMM		85.10 24	88.81 14	80.77 35	89.55 29	88.53 33	88.59 28	72.55 31	87.39 16	71.90 43	90.95 9	87.55 12	74.57 34	87.08 27	86.54 26	87.47 86	93.67 17

PVSNet_BlendedMVS		76.21 65	77.52 67	74.69 69	79.46 91	83.79 67	77.50 95	64.34 84	69.88 68	71.88 44	68.54 68	70.42 78	67.05 79	83.48 58	79.63 95	87.89 77	86.87 71

PVSNet_Blended		76.21 65	77.52 67	74.69 69	79.46 91	83.79 67	77.50 95	64.34 84	69.88 68	71.88 44	68.54 68	70.42 78	67.05 79	83.48 58	79.63 95	87.89 77	86.87 71

XVS					86.63 46	88.68 28	85.00 47			71.81 46		81.92 37				90.47 22

X-MVStestdata					86.63 46	88.68 28	85.00 47			71.81 46		81.92 37				90.47 22

X-MVS		83.23 33	85.20 33	80.92 34	89.71 27	88.68 28	88.21 32	73.60 24	82.57 38	71.81 46	77.07 33	81.92 37	71.72 58	86.98 29	86.86 20	90.47 22	92.36 29

CPTT-MVS		81.77 38	83.10 39	80.21 37	85.93 51	86.45 50	87.72 34	70.98 39	82.54 39	71.53 49	74.23 44	81.49 40	76.31 31	82.85 64	81.87 61	88.79 61	92.26 30

ACMM	72.26 8	78.86 55	78.13 61	79.71 40	86.89 45	83.40 73	86.02 40	70.50 40	75.28 55	71.49 50	63.01 90	69.26 87	73.57 41	84.11 52	83.98 48	89.76 41	87.84 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS_111021_LR		78.13 58	79.85 56	76.13 58	81.12 76	81.50 86	80.28 67	65.25 76	76.09 54	71.32 51	76.49 36	72.87 67	72.21 51	82.79 65	81.29 67	86.59 112	87.91 61

ACMP	73.23 7	79.79 45	80.53 50	78.94 44	85.61 53	85.68 53	85.61 43	69.59 47	77.33 51	71.00 52	74.45 42	69.16 88	71.88 54	83.15 61	83.37 53	89.92 37	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS_0304		81.73 39	83.86 36	79.26 42	86.22 50	89.18 24	86.41 38	67.15 63	75.28 55	70.75 53	74.59 41	83.49 31	74.42 36	87.05 28	86.34 29	90.58 19	91.08 40

MVS_111021_HR		80.13 43	81.46 45	78.58 47	85.77 52	85.17 59	83.45 57	69.28 50	74.08 61	70.31 54	74.31 43	75.26 58	73.13 44	86.46 35	85.15 42	89.53 46	89.81 49

DELS-MVS		79.15 53	81.07 48	76.91 55	83.54 62	87.31 42	84.45 51	64.92 79	69.98 67	69.34 55	71.62 52	76.26 54	69.84 67	86.57 33	85.90 35	89.39 48	89.88 48
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
test_part1		74.24 75	73.44 88	75.18 64	82.02 72	82.34 81	83.88 54	62.40 113	60.93 123	68.68 56	49.25 175	69.71 84	65.73 94	81.26 82	81.98 60	88.35 65	88.60 57

PCF-MVS	73.28 6	79.42 49	80.41 52	78.26 48	84.88 61	88.17 37	86.08 39	69.85 44	75.23 57	68.43 57	68.03 70	78.38 48	71.76 57	81.26 82	80.65 83	88.56 64	91.18 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MAR-MVS		79.21 51	80.32 53	77.92 51	87.46 40	88.15 38	83.95 53	67.48 62	74.28 59	68.25 58	64.70 84	77.04 52	72.17 52	85.42 42	85.00 43	88.22 67	87.62 64
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
PVSNet_Blended_VisFu		76.57 64	77.90 63	75.02 65	80.56 81	86.58 49	79.24 78	66.18 68	64.81 90	68.18 59	65.61 77	71.45 70	67.05 79	84.16 51	81.80 62	88.90 57	90.92 41

OpenMVS	70.44 10	76.15 67	76.82 75	75.37 63	85.01 58	84.79 61	78.99 82	62.07 116	71.27 66	67.88 60	57.91 118	72.36 68	70.15 66	82.23 69	81.41 66	88.12 72	87.78 63

OPM-MVS		79.68 48	79.28 57	80.15 38	87.99 39	86.77 47	88.52 29	72.72 30	64.55 93	67.65 61	67.87 71	74.33 61	74.31 37	86.37 36	85.25 41	89.73 42	89.81 49

CDPH-MVS		82.64 34	85.03 34	79.86 39	89.41 31	88.31 36	88.32 30	71.84 35	80.11 45	67.47 62	82.09 25	81.44 41	71.85 56	85.89 40	86.15 33	90.24 32	91.25 38

canonicalmvs		79.16 52	82.37 43	75.41 62	82.33 69	86.38 51	80.80 63	63.18 92	82.90 36	67.34 63	72.79 47	76.07 55	69.62 68	83.46 60	84.41 46	89.20 52	90.60 44

EPNet		79.08 54	80.62 49	77.28 53	88.90 35	83.17 76	83.65 55	72.41 32	74.41 58	67.15 64	76.78 34	74.37 60	64.43 96	83.70 56	83.69 51	87.15 90	88.19 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HQP-MVS		81.19 41	83.27 38	78.76 46	87.40 41	85.45 56	86.95 35	70.47 41	81.31 42	66.91 65	79.24 30	76.63 53	71.67 59	84.43 50	83.78 50	89.19 53	92.05 34

PLC	68.99 11	75.68 68	75.31 80	76.12 59	82.94 64	81.26 90	79.94 70	66.10 69	77.15 52	66.86 66	59.13 108	68.53 95	73.73 40	80.38 95	79.04 105	87.13 94	81.68 125
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
casdiffmvs		76.76 63	78.46 60	74.77 68	80.32 85	83.73 69	80.65 65	63.24 91	73.58 63	66.11 67	69.39 62	74.09 62	69.49 70	82.52 67	79.35 104	88.84 60	86.52 74

CS-MVS		76.92 62	78.01 62	75.64 60	81.47 73	83.59 71	80.68 64	62.47 111	68.39 73	65.83 68	67.84 72	70.74 76	73.07 45	85.31 45	82.79 56	90.33 31	87.42 65

PHI-MVS		82.36 36	85.89 29	78.24 49	86.40 48	89.52 18	85.52 44	69.52 49	82.38 40	65.67 69	81.35 27	82.36 34	73.07 45	87.31 24	86.76 23	89.24 50	91.56 35

QAPM		78.47 56	80.22 54	76.43 57	85.03 57	86.75 48	80.62 66	66.00 71	73.77 62	65.35 70	65.54 79	78.02 50	72.69 49	83.71 55	83.36 54	88.87 59	90.41 47

LGP-MVS_train		79.83 44	81.22 47	78.22 50	86.28 49	85.36 58	86.76 36	69.59 47	77.34 50	65.14 71	75.68 37	70.79 75	71.37 62	84.60 48	84.01 47	90.18 33	90.74 42

DI_MVS_plusplus_trai		75.13 72	76.12 78	73.96 74	78.18 99	81.55 84	80.97 62	62.54 108	68.59 72	65.13 72	61.43 93	74.81 59	69.32 71	81.01 88	79.59 97	87.64 84	85.89 78

TAPA-MVS	71.42 9	77.69 59	80.05 55	74.94 66	80.68 80	84.52 62	81.36 60	63.14 93	84.77 27	64.82 73	68.72 65	75.91 56	71.86 55	81.62 71	79.55 99	87.80 81	85.24 89
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
diffmvs		74.86 73	77.37 70	71.93 80	75.62 121	80.35 101	79.42 77	60.15 137	72.81 65	64.63 74	71.51 53	73.11 66	66.53 89	79.02 115	77.98 118	85.25 141	86.83 73

MVS_Test		75.37 70	77.13 73	73.31 77	79.07 94	81.32 89	79.98 68	60.12 138	69.72 70	64.11 75	70.53 57	73.22 64	68.90 72	80.14 102	79.48 101	87.67 83	85.50 84

ETV-MVS		77.32 60	78.81 58	75.58 61	82.24 70	83.64 70	79.98 68	64.02 86	69.64 71	63.90 76	70.89 56	69.94 82	73.41 42	85.39 44	83.91 49	89.92 37	88.31 58

GeoE		74.23 76	74.84 82	73.52 75	80.42 84	81.46 87	79.77 72	61.06 125	67.23 77	63.67 77	59.56 105	68.74 94	67.90 77	80.25 100	79.37 103	88.31 66	87.26 69

tpm cat1		65.41 148	63.81 171	67.28 128	75.61 122	72.88 163	75.32 107	52.85 173	62.97 106	63.66 78	53.24 148	53.29 166	61.83 117	65.54 194	64.14 196	74.43 191	74.60 172

IB-MVS	66.94 12	71.21 95	71.66 103	70.68 87	79.18 93	82.83 78	72.61 143	61.77 120	59.66 130	63.44 79	53.26 147	59.65 124	59.16 131	76.78 140	82.11 59	87.90 76	87.33 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
EIA-MVS		75.64 69	76.60 76	74.53 71	82.43 68	83.84 66	78.32 88	62.28 115	65.96 83	63.28 80	68.95 63	67.54 98	71.61 60	82.55 66	81.63 64	89.24 50	85.72 80

MSDG		71.52 91	69.87 114	73.44 76	82.21 71	79.35 109	79.52 75	64.59 81	66.15 81	61.87 81	53.21 149	56.09 141	65.85 93	78.94 116	78.50 112	86.60 111	76.85 159

TSAR-MVS + COLMAP		78.34 57	81.64 44	74.48 72	80.13 88	85.01 60	81.73 59	65.93 73	84.75 28	61.68 82	85.79 19	66.27 102	71.39 61	82.91 63	80.78 74	86.01 127	85.98 77

CostFormer		68.92 118	69.58 119	68.15 113	75.98 118	76.17 145	78.22 90	51.86 179	65.80 84	61.56 83	63.57 88	62.83 112	61.85 116	70.40 183	68.67 180	79.42 169	79.62 142

MVSTER		72.06 87	74.24 83	69.51 102	70.39 170	75.97 146	76.91 101	57.36 160	64.64 92	61.39 84	68.86 64	63.76 109	63.46 101	81.44 75	79.70 94	87.56 85	85.31 88

Fast-Effi-MVS+		73.11 82	73.66 86	72.48 79	77.72 105	80.88 96	78.55 85	58.83 153	65.19 87	60.36 85	59.98 102	62.42 114	71.22 63	81.66 70	80.61 85	88.20 68	84.88 96

Effi-MVS+		75.28 71	76.20 77	74.20 73	81.15 75	83.24 74	81.11 61	63.13 94	66.37 79	60.27 86	64.30 87	68.88 92	70.93 65	81.56 73	81.69 63	88.61 62	87.35 66

PatchMatch-RL		67.78 132	66.65 151	69.10 105	73.01 146	72.69 164	68.49 159	61.85 119	62.93 107	60.20 87	56.83 124	50.42 182	69.52 69	75.62 146	74.46 156	81.51 161	73.62 178

Anonymous20231211		71.90 88	72.48 97	71.21 83	80.14 87	81.53 85	76.92 100	62.89 97	64.46 95	58.94 88	43.80 186	70.98 74	62.22 108	80.70 90	80.19 90	86.18 119	85.73 79

RPSCF		67.64 136	71.25 104	63.43 157	61.86 196	70.73 171	67.26 164	50.86 184	74.20 60	58.91 89	67.49 73	69.33 86	64.10 99	71.41 170	68.45 184	77.61 175	77.17 156

LS3D		74.08 77	73.39 89	74.88 67	85.05 56	82.62 79	79.71 74	68.66 53	72.82 64	58.80 90	57.61 119	61.31 117	71.07 64	80.32 96	78.87 109	86.00 128	80.18 137

DCV-MVSNet		73.65 79	75.78 79	71.16 84	80.19 86	79.27 110	77.45 97	61.68 122	66.73 78	58.72 91	65.31 80	69.96 81	62.19 109	81.29 81	80.97 71	86.74 105	86.91 70

thisisatest0530		71.48 92	73.01 92	69.70 100	73.83 140	78.62 118	74.53 118	59.12 147	64.13 96	58.63 92	64.60 85	58.63 128	64.27 97	80.28 98	80.17 91	87.82 80	84.64 99

baseline		70.45 101	74.09 85	66.20 140	70.95 167	75.67 147	74.26 126	53.57 167	68.33 74	58.42 93	69.87 60	71.45 70	61.55 119	74.84 151	74.76 154	78.42 173	83.72 108

dps		64.00 158	62.99 174	65.18 143	73.29 144	72.07 166	68.98 158	53.07 172	57.74 140	58.41 94	55.55 129	47.74 191	60.89 126	69.53 186	67.14 189	76.44 183	71.19 182

tttt0517		71.41 93	72.95 93	69.60 101	73.70 142	78.70 117	74.42 122	59.12 147	63.89 100	58.35 95	64.56 86	58.39 130	64.27 97	80.29 97	80.17 91	87.74 82	84.69 98

v8		70.23 103	69.86 115	70.67 88	74.69 130	79.82 105	78.79 83	59.18 146	58.80 134	58.20 96	55.00 132	57.33 134	66.31 91	77.51 130	76.71 139	86.82 102	83.88 106

pmmvs4		67.89 129	67.39 146	68.48 111	71.60 161	73.57 161	74.45 119	60.98 126	64.65 91	57.97 97	54.95 133	51.73 176	61.88 115	73.78 157	75.11 151	83.99 153	77.91 151

IterMVS-LS		71.69 90	72.82 95	70.37 92	77.54 107	76.34 143	75.13 113	60.46 133	61.53 118	57.57 98	64.89 82	67.33 99	66.04 92	77.09 136	77.37 130	85.48 137	85.18 90
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ET-MVSNet_ETH3D		72.46 86	74.19 84	70.44 91	62.50 194	81.17 91	79.90 71	62.46 112	64.52 94	57.52 99	71.49 54	59.15 126	72.08 53	78.61 120	81.11 69	88.16 69	83.29 111

v148		67.85 130	67.53 142	68.23 112	73.25 145	77.57 134	74.26 126	57.36 160	55.70 155	57.45 100	53.53 143	55.42 143	61.96 114	75.23 148	73.92 157	85.08 143	81.32 128

baseline2		69.69 109	70.27 111	69.01 106	75.72 120	77.13 136	73.82 133	58.94 151	61.35 119	57.09 101	61.68 92	57.17 136	61.99 113	78.10 125	76.58 141	86.48 115	79.85 139

v2v482		70.05 107	69.46 121	70.74 85	74.62 131	80.32 102	79.00 81	60.62 130	57.41 143	56.89 102	55.43 131	55.14 146	66.39 90	77.25 133	77.14 133	86.90 99	83.57 110

UGNet		72.78 83	77.67 65	67.07 132	71.65 159	83.24 74	75.20 109	63.62 88	64.93 89	56.72 103	71.82 51	73.30 63	49.02 175	81.02 87	80.70 81	86.22 118	88.67 56
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
CMPMVS	47.78 17	62.49 166	62.52 179	62.46 159	70.01 173	70.66 172	62.97 186	51.84 180	51.98 179	56.71 104	42.87 188	53.62 155	57.80 138	72.23 164	70.37 172	75.45 188	75.91 163
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v10		70.22 104	69.76 117	70.74 85	74.79 129	80.30 103	79.22 79	59.81 141	57.71 141	56.58 105	54.22 140	55.31 144	66.95 82	78.28 123	77.47 127	87.12 96	85.07 92

V42		68.76 121	69.63 118	67.74 117	64.93 190	78.01 122	78.30 89	56.48 162	58.65 135	56.30 106	54.26 138	57.03 137	64.85 95	77.47 131	77.01 135	85.60 135	84.96 94

UA-Net		74.47 74	77.80 64	70.59 90	85.33 54	85.40 57	73.54 137	65.98 72	60.65 125	56.00 107	72.11 49	79.15 46	54.63 162	83.13 62	82.25 58	88.04 73	81.92 123

Effi-MVS+-dtu		71.82 89	71.86 102	71.78 81	78.77 95	80.47 99	78.55 85	61.67 123	60.68 124	55.49 108	58.48 112	65.48 104	68.85 73	76.92 137	75.55 149	87.35 88	85.46 85

tpm		62.41 167	63.15 173	61.55 163	72.24 153	63.79 194	71.31 149	46.12 202	57.82 137	55.33 109	59.90 103	54.74 148	53.63 165	67.24 193	64.29 195	70.65 201	74.25 176

v1144		69.93 108	69.36 122	70.61 89	74.89 128	80.93 93	79.11 80	60.64 129	55.97 154	55.31 110	53.85 142	54.14 151	66.54 88	78.10 125	77.44 128	87.14 93	85.09 91

MS-PatchMatch		70.17 105	70.49 109	69.79 98	80.98 78	77.97 128	77.51 94	58.95 150	62.33 111	55.22 111	53.14 150	65.90 103	62.03 112	79.08 114	77.11 134	84.08 151	77.91 151

CHOSEN 1792x2688		69.20 116	69.26 123	69.13 104	76.86 112	78.93 112	77.27 98	60.12 138	61.86 115	54.42 112	42.54 190	61.61 115	66.91 84	78.55 121	78.14 117	79.23 171	83.23 112

v1192		69.50 112	68.83 128	70.29 93	74.49 132	80.92 95	78.55 85	60.54 131	55.04 160	54.21 113	52.79 156	52.33 171	66.92 83	77.88 127	77.35 131	87.04 97	85.51 83

SCA		65.40 149	66.58 152	64.02 152	70.65 168	73.37 162	67.35 163	53.46 169	63.66 101	54.14 114	60.84 95	60.20 121	61.50 120	69.96 184	68.14 185	77.01 180	69.91 184

v144192		69.34 114	68.68 132	70.12 94	74.06 136	80.54 98	78.08 91	60.54 131	54.99 162	54.13 115	52.92 154	52.80 169	66.73 86	77.13 135	76.72 138	87.15 90	85.63 81

HyFIR lowres test		69.47 113	68.94 127	70.09 95	76.77 113	82.93 77	76.63 104	60.17 136	59.00 133	54.03 116	40.54 195	65.23 105	67.89 78	76.54 143	78.30 115	85.03 144	80.07 138

tpmrst		62.00 171	62.35 182	61.58 162	71.62 160	64.14 191	69.07 157	48.22 198	62.21 112	53.93 117	58.26 117	55.30 145	55.81 155	63.22 199	62.62 198	70.85 200	70.70 183

MDTV_nov1_ep13		64.37 155	65.24 159	63.37 158	68.94 179	70.81 170	72.40 146	50.29 188	60.10 129	53.91 118	60.07 101	59.15 126	57.21 143	69.43 187	67.30 187	77.47 176	69.78 186

PatchmatchNet		64.21 157	64.65 165	63.69 154	71.29 166	68.66 178	69.63 154	51.70 181	63.04 105	53.77 119	59.83 104	58.34 131	60.23 129	68.54 190	66.06 192	75.56 186	68.08 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0515		67.40 139	68.78 129	65.80 142	70.02 172	75.24 153	69.36 156	57.37 159	54.94 163	53.67 120	55.53 130	54.85 147	58.00 137	78.19 124	78.91 108	86.39 116	83.78 107

v1921920		69.03 117	68.32 136	69.86 97	74.03 137	80.37 100	77.55 93	60.25 135	54.62 164	53.59 121	52.36 160	51.50 177	66.75 85	77.17 134	76.69 140	86.96 98	85.56 82

FC-MVSNet-train		72.60 85	75.07 81	69.71 99	81.10 77	78.79 116	73.74 136	65.23 77	66.10 82	53.34 122	70.36 58	63.40 111	56.92 147	81.44 75	80.96 72	87.93 75	84.46 101

CANet_DTU		73.29 81	76.96 74	69.00 107	77.04 111	82.06 82	79.49 76	56.30 163	67.85 75	53.29 123	71.12 55	70.37 80	61.81 118	81.59 72	80.96 72	86.09 121	84.73 97

v1240		68.64 122	67.89 141	69.51 102	73.89 139	80.26 104	76.73 103	59.97 140	53.43 172	53.08 124	51.82 163	50.84 180	66.62 87	76.79 139	76.77 137	86.78 104	85.34 87

pmmvs-eth3d		63.52 159	62.44 181	64.77 147	66.82 185	70.12 173	69.41 155	59.48 144	54.34 168	52.71 125	46.24 183	44.35 200	56.93 146	72.37 161	73.77 159	83.30 155	75.91 163

CR-MVSNet		64.83 152	65.54 157	64.01 153	70.64 169	69.41 174	65.97 174	52.74 174	57.81 138	52.65 126	54.27 136	56.31 140	60.92 124	72.20 166	73.09 162	81.12 164	75.69 166

Patchmtry						65.80 188	65.97 174	52.74 174		52.65 126

PatchT		61.97 172	64.04 169	59.55 174	60.49 198	67.40 182	56.54 199	48.65 194	56.69 146	52.65 126	51.10 167	52.14 174	60.92 124	72.20 166	73.09 162	78.03 174	75.69 166

ACMH+	66.54 13	71.36 94	70.09 112	72.85 78	82.59 66	81.13 92	78.56 84	68.04 57	61.55 117	52.52 129	51.50 164	54.14 151	68.56 75	78.85 117	79.50 100	86.82 102	83.94 105

MVS-HIRNet		54.41 194	52.10 201	57.11 183	58.99 200	56.10 207	49.68 207	49.10 191	46.18 196	52.15 130	33.18 203	46.11 195	56.10 151	63.19 200	59.70 203	76.64 182	60.25 203

GBi-Net		70.78 96	73.37 90	67.76 115	72.95 147	78.00 123	75.15 110	62.72 101	64.13 96	51.44 131	58.37 113	69.02 89	57.59 139	81.33 78	80.72 76	86.70 106	82.02 117

test1		70.78 96	73.37 90	67.76 115	72.95 147	78.00 123	75.15 110	62.72 101	64.13 96	51.44 131	58.37 113	69.02 89	57.59 139	81.33 78	80.72 76	86.70 106	82.02 117

FMVSNet3		70.49 100	72.90 94	67.67 120	72.88 150	77.98 126	74.96 116	62.72 101	64.13 96	51.44 131	58.37 113	69.02 89	57.43 142	79.43 110	79.57 98	86.59 112	81.81 124

EG-PatchMatch MVS		67.24 141	66.94 148	67.60 121	78.73 96	81.35 88	73.28 141	59.49 143	46.89 194	51.42 134	43.65 187	53.49 159	55.50 159	81.38 77	80.66 82	87.15 90	81.17 129

FMVSNet2		70.39 102	72.67 96	67.72 118	72.95 147	78.00 123	75.15 110	62.69 105	63.29 104	51.25 135	55.64 127	68.49 96	57.59 139	80.91 89	80.35 88	86.70 106	82.02 117

v7n		67.05 143	66.94 148	67.17 129	72.35 152	78.97 111	73.26 142	58.88 152	51.16 183	50.90 136	48.21 178	50.11 184	60.96 123	77.70 128	77.38 129	86.68 109	85.05 93

PMMVS		65.06 151	69.17 125	60.26 169	55.25 208	63.43 195	66.71 170	43.01 204	62.41 110	50.64 137	69.44 61	67.04 100	63.29 102	74.36 154	73.54 160	82.68 158	73.99 177

Vis-MVSNet		72.77 84	77.20 72	67.59 122	74.19 135	84.01 64	76.61 105	61.69 121	60.62 126	50.61 138	70.25 59	71.31 73	55.57 158	83.85 54	82.28 57	86.90 99	88.08 60
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
USDC		67.36 140	67.90 140	66.74 138	71.72 157	75.23 154	71.58 147	60.28 134	67.45 76	50.54 139	60.93 94	45.20 198	62.08 110	76.56 142	74.50 155	84.25 150	75.38 169

COLMAP_ROB	62.73 15	67.66 134	66.76 150	68.70 109	80.49 83	77.98 126	75.29 108	62.95 96	63.62 102	49.96 140	47.32 181	50.72 181	58.57 132	76.87 138	75.50 150	84.94 146	75.33 170
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FMVSNet1		68.84 119	70.47 110	66.94 134	71.35 164	77.68 131	74.71 117	62.35 114	56.93 145	49.94 141	50.01 170	64.59 106	57.07 144	81.33 78	80.72 76	86.25 117	82.00 120

EPP-MVSNet		74.00 78	77.41 69	70.02 96	80.53 82	83.91 65	74.99 115	62.68 106	65.06 88	49.77 142	68.68 66	72.09 69	63.06 104	82.49 68	80.73 75	89.12 55	88.91 54

TDRefinement		66.09 146	65.03 163	67.31 126	69.73 174	76.75 139	75.33 106	64.55 82	60.28 128	49.72 143	45.63 184	42.83 201	60.46 128	75.75 145	75.95 146	84.08 151	78.04 150

CDS-MVSNet		67.65 135	69.83 116	65.09 144	75.39 123	76.55 141	74.42 122	63.75 87	53.55 170	49.37 144	59.41 106	62.45 113	44.44 182	79.71 105	79.82 93	83.17 157	77.36 155
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		66.89 144	69.22 124	64.17 150	71.30 165	75.64 148	71.33 148	53.17 171	57.63 142	49.08 145	60.72 96	60.05 122	63.09 103	74.99 150	73.92 157	77.07 179	81.57 126

IS_MVSNet		73.33 80	77.34 71	68.65 110	81.29 74	83.47 72	74.45 119	63.58 89	65.75 85	48.49 146	67.11 76	70.61 77	54.63 162	84.51 49	83.58 52	89.48 47	86.34 76

GA-MVS		68.14 124	69.17 125	66.93 135	73.77 141	78.50 120	74.45 119	58.28 155	55.11 159	48.44 147	60.08 100	53.99 154	61.50 120	78.43 122	77.57 125	85.13 142	80.54 133

baseline1		70.10 106	72.17 99	67.69 119	79.74 89	76.80 138	73.91 130	64.38 83	62.74 109	48.30 148	64.94 81	64.08 108	54.17 164	81.46 74	78.92 107	85.66 134	76.22 161

IterMVS		66.36 145	68.30 137	64.10 151	69.48 177	74.61 158	73.41 140	50.79 185	57.30 144	48.28 149	60.64 97	59.92 123	60.85 127	74.14 155	72.66 164	81.80 160	78.82 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PM-MVS		60.48 180	60.94 188	59.94 170	58.85 201	66.83 185	64.27 182	51.39 182	55.03 161	48.03 150	50.00 172	40.79 205	58.26 135	69.20 188	67.13 190	78.84 172	77.60 153

test-LLR		64.42 154	64.36 167	64.49 149	75.02 126	63.93 192	66.61 171	61.96 117	54.41 165	47.77 151	57.46 120	60.25 119	55.20 160	70.80 177	69.33 175	80.40 167	74.38 174

TESTMET0.1,1		61.10 178	64.36 167	57.29 181	57.53 203	63.93 192	66.61 171	36.22 208	54.41 165	47.77 151	57.46 120	60.25 119	55.20 160	70.80 177	69.33 175	80.40 167	74.38 174

TinyColmap		62.84 162	61.03 187	64.96 146	69.61 175	71.69 167	68.48 160	59.76 142	55.41 156	47.69 153	47.33 180	34.20 210	62.76 106	74.52 152	72.59 165	81.44 162	71.47 181

anonymousdsp		65.28 150	67.98 139	62.13 160	58.73 202	73.98 160	67.10 166	50.69 186	48.41 190	47.66 154	54.27 136	52.75 170	61.45 122	76.71 141	80.20 89	87.13 94	89.53 52

UniMVSNet_ETH3D		67.18 142	67.03 147	67.36 125	74.44 133	78.12 121	74.07 129	66.38 66	52.22 177	46.87 155	48.64 176	51.84 175	56.96 145	77.29 132	78.53 111	85.42 138	82.59 114

thres100view900		67.60 137	68.02 138	67.12 131	77.83 103	77.75 130	73.90 131	62.52 109	56.64 147	46.82 156	52.65 157	53.47 161	55.92 153	78.77 118	77.62 124	85.72 132	79.23 144

tfpn200view9		68.11 125	68.72 131	67.40 124	77.83 103	78.93 112	74.28 124	62.81 98	56.64 147	46.82 156	52.65 157	53.47 161	56.59 148	80.41 92	78.43 113	86.11 120	80.52 134

Fast-Effi-MVS+-dtu		68.34 123	69.47 120	67.01 133	75.15 124	77.97 128	77.12 99	55.40 165	57.87 136	46.68 158	56.17 126	60.39 118	62.36 107	76.32 144	76.25 145	85.35 140	81.34 127

thres200		67.98 127	68.55 134	67.30 127	77.89 102	78.86 114	74.18 128	62.75 99	56.35 150	46.48 159	52.98 153	53.54 157	56.46 149	80.41 92	77.97 119	86.05 124	79.78 141

RE-MVS-def										46.24 160

test-mter		60.84 179	64.62 166	56.42 184	55.99 206	64.18 190	65.39 176	34.23 209	54.39 167	46.21 161	57.40 122	59.49 125	55.86 154	71.02 176	69.65 174	80.87 166	76.20 162

ACMH	65.37 14	70.71 98	70.00 113	71.54 82	82.51 67	82.47 80	77.78 92	68.13 56	56.19 152	46.06 162	54.30 135	51.20 178	68.68 74	80.66 91	80.72 76	86.07 122	84.45 102
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MDTV_nov1_ep13_2view		60.16 181	60.51 189	59.75 171	65.39 187	69.05 177	68.00 161	48.29 196	51.99 178	45.95 163	48.01 179	49.64 186	53.39 166	68.83 189	66.52 191	77.47 176	69.55 187

thres400		67.95 128	68.62 133	67.17 129	77.90 100	78.59 119	74.27 125	62.72 101	56.34 151	45.77 164	53.00 152	53.35 164	56.46 149	80.21 101	78.43 113	85.91 131	80.43 135

RPMNet		61.71 177	62.88 175	60.34 168	69.51 176	69.41 174	63.48 184	49.23 190	57.81 138	45.64 165	50.51 168	50.12 183	53.13 168	68.17 192	68.49 183	81.07 165	75.62 168

EPNet_dtu		68.08 126	71.00 105	64.67 148	79.64 90	68.62 179	75.05 114	63.30 90	66.36 80	45.27 166	67.40 74	66.84 101	43.64 184	75.37 147	74.98 153	81.15 163	77.44 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs5		62.37 170	64.04 169	60.42 167	65.03 188	71.67 168	67.17 165	52.70 176	50.30 184	44.80 167	54.23 139	51.19 179	49.37 174	72.88 160	73.48 161	83.45 154	74.55 173

EPMVS		60.00 182	61.97 183	57.71 180	68.46 180	63.17 198	64.54 180	48.23 197	63.30 103	44.72 168	60.19 99	56.05 142	50.85 172	65.27 197	62.02 199	69.44 203	63.81 197

thres600view7		67.68 133	68.43 135	66.80 136	77.90 100	78.86 114	73.84 132	62.75 99	56.07 153	44.70 169	52.85 155	52.81 168	55.58 157	80.41 92	77.77 121	86.05 124	80.28 136

pm-mvs1		65.62 147	67.42 144	63.53 156	73.66 143	76.39 142	69.66 153	60.87 128	49.73 187	43.97 170	51.24 166	57.00 138	48.16 176	79.89 103	77.84 120	84.85 148	79.82 140

UniMVSNet_NR-MVSNet		70.59 99	72.19 98	68.72 108	77.72 105	80.72 97	73.81 134	69.65 46	61.99 113	43.23 171	60.54 98	57.50 133	58.57 132	79.56 108	81.07 70	89.34 49	83.97 103

DU-MVS		69.63 110	70.91 106	68.13 114	75.99 116	79.54 106	73.81 134	69.20 51	61.20 121	43.23 171	58.52 110	53.50 158	58.57 132	79.22 112	80.45 86	87.97 74	83.97 103

tfpnnormal		64.27 156	63.64 172	65.02 145	75.84 119	75.61 149	71.24 150	62.52 109	47.79 191	42.97 173	42.65 189	44.49 199	52.66 169	78.77 118	76.86 136	84.88 147	79.29 143

ADS-MVSNet		55.94 191	58.01 192	53.54 194	62.48 195	58.48 204	59.12 197	46.20 201	59.65 131	42.88 174	52.34 161	53.31 165	46.31 179	62.00 201	60.02 202	64.23 208	60.24 204

pmmvs6		62.41 167	62.88 175	61.87 161	71.38 163	75.18 156	67.76 162	59.45 145	41.64 202	42.52 175	37.33 197	52.91 167	46.87 178	77.67 129	76.26 144	83.23 156	79.18 145

UniMVSNet (Re)		69.53 111	71.90 101	66.76 137	76.42 114	80.93 93	72.59 144	68.03 58	61.75 116	41.68 176	58.34 116	57.23 135	53.27 167	79.53 109	80.62 84	88.57 63	84.90 95

TransMVSNet (Re)		64.74 153	65.66 156	63.66 155	77.40 109	75.33 152	69.86 152	62.67 107	47.63 192	41.21 177	50.01 170	52.33 171	45.31 181	79.57 107	77.69 123	85.49 136	77.07 158

NR-MVSNet		68.79 120	70.56 108	66.71 139	77.48 108	79.54 106	73.52 138	69.20 51	61.20 121	39.76 178	58.52 110	50.11 184	51.37 171	80.26 99	80.71 80	88.97 56	83.59 109

TranMVSNet+NR-MVSNet		69.25 115	70.81 107	67.43 123	77.23 110	79.46 108	73.48 139	69.66 45	60.43 127	39.56 179	58.82 109	53.48 160	55.74 156	79.59 106	81.21 68	88.89 58	82.70 113

FMVSNet5		57.24 187	60.02 190	53.99 192	56.45 205	62.74 199	65.27 177	47.03 199	55.14 158	39.55 180	40.88 192	53.42 163	41.83 185	72.35 162	71.10 171	73.79 193	64.50 196

MIMVSNet		58.52 186	61.34 186	55.22 188	60.76 197	67.01 184	66.81 168	49.02 192	56.43 149	38.90 181	40.59 194	54.54 150	40.57 191	73.16 159	71.65 167	75.30 189	66.00 193

pmnet_mix02		55.30 192	57.01 196	53.30 195	64.14 191	59.09 203	58.39 198	50.24 189	53.47 171	38.68 182	49.75 173	45.86 196	40.14 192	65.38 196	60.22 201	68.19 205	65.33 194

Baseline_NR-MVSNet		67.53 138	68.77 130	66.09 141	75.99 116	74.75 157	72.43 145	68.41 54	61.33 120	38.33 183	51.31 165	54.13 153	56.03 152	79.22 112	78.19 116	85.37 139	82.45 115

CHOSEN 280x420		58.70 185	61.88 184	54.98 189	55.45 207	50.55 210	64.92 178	40.36 205	55.21 157	38.13 184	48.31 177	63.76 109	63.03 105	73.73 158	68.58 182	68.00 206	73.04 179

SixPastTwentyTwo		61.84 174	62.45 180	61.12 165	69.20 178	72.20 165	62.03 189	57.40 158	46.54 195	38.03 185	57.14 123	41.72 203	58.12 136	69.67 185	71.58 168	81.94 159	78.30 149

ambc			53.42 198		64.99 189	63.36 196	49.96 206		47.07 193	37.12 186	28.97 206	16.36 218	41.82 186	75.10 149	67.34 186	71.55 199	75.72 165

TAMVS		59.58 183	62.81 177	55.81 186	66.03 186	65.64 189	63.86 183	48.74 193	49.95 186	37.07 187	54.77 134	58.54 129	44.44 182	72.29 163	71.79 166	74.70 190	66.66 192

PMVS	39.38 18	46.06 204	43.30 206	49.28 199	62.93 192	38.75 212	41.88 211	53.50 168	33.33 212	35.46 188	28.90 207	31.01 213	33.04 199	58.61 206	54.63 207	68.86 204	57.88 206
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		51.87 198	50.00 203	54.07 191	66.83 184	57.25 205	60.25 194	50.91 183	50.25 185	34.36 189	36.04 200	32.02 212	41.49 187	58.98 205	56.07 204	70.56 202	59.36 205

Vis-MVSNet (Re-imp)		67.83 131	73.52 87	61.19 164	78.37 98	76.72 140	66.80 169	62.96 95	65.50 86	34.17 190	67.19 75	69.68 85	39.20 193	79.39 111	79.44 102	85.68 133	76.73 160

CVMVSNet		62.55 164	65.89 153	58.64 177	66.95 183	69.15 176	66.49 173	56.29 164	52.46 176	32.70 191	59.27 107	58.21 132	50.09 173	71.77 169	71.39 169	79.31 170	78.99 146

MDA-MVSNet-bldmvs		53.37 197	53.01 200	53.79 193	43.67 212	67.95 181	59.69 195	57.92 156	43.69 198	32.41 192	41.47 191	27.89 215	52.38 170	56.97 207	65.99 193	76.68 181	67.13 191

pmmvs3		47.65 200	49.08 205	45.99 201	44.61 210	54.79 208	50.04 205	31.95 212	33.91 209	29.90 193	30.37 204	33.53 211	46.31 179	63.50 198	63.67 197	73.14 196	63.77 198

test0.0.03 1		58.80 184	61.58 185	55.56 187	75.02 126	68.45 180	59.58 196	61.96 117	52.74 173	29.57 194	49.75 173	54.56 149	31.46 200	71.19 172	69.77 173	75.75 184	64.57 195

Anonymous20231206		56.36 190	57.80 194	54.67 190	70.08 171	66.39 186	60.46 193	57.54 157	49.50 189	29.30 195	33.86 202	46.64 193	35.18 196	70.44 181	68.88 179	75.47 187	68.88 189

tmp_tt				14.50 213	14.68 217	7.17 219	10.46 220	2.21 216	37.73 207	28.71 196	25.26 209	16.98 216	4.37 215	31.49 211	29.77 211	26.56 216

LTVRE_ROB	59.44 16	61.82 176	62.64 178	60.87 166	72.83 151	77.19 135	64.37 181	58.97 149	33.56 211	28.00 197	52.59 159	42.21 202	63.93 100	74.52 152	76.28 143	77.15 178	82.13 116
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
CP-MVSNet		62.68 163	65.49 158	59.40 175	71.84 155	75.34 151	62.87 187	67.04 64	52.64 174	27.19 198	53.38 145	48.15 189	41.40 188	71.26 171	75.68 147	86.07 122	82.00 120

PS-CasMVS		62.38 169	65.06 161	59.25 176	71.73 156	75.21 155	62.77 188	66.99 65	51.94 181	26.96 199	52.00 162	47.52 192	41.06 189	71.16 174	75.60 148	85.97 129	81.97 122

PEN-MVS		62.96 161	65.77 155	59.70 172	73.98 138	75.45 150	63.39 185	67.61 61	52.49 175	25.49 200	53.39 144	49.12 187	40.85 190	71.94 168	77.26 132	86.86 101	80.72 132

WR-MVS		63.03 160	67.40 145	57.92 179	75.14 125	77.60 133	60.56 192	66.10 69	54.11 169	23.88 201	53.94 141	53.58 156	34.50 197	73.93 156	77.71 122	87.35 88	80.94 130

testgi		54.39 195	57.86 193	50.35 197	71.59 162	67.24 183	54.95 201	53.25 170	43.36 199	23.78 202	44.64 185	47.87 190	24.96 205	70.45 180	68.66 181	73.60 194	62.78 200

gm-plane-assit		57.00 188	57.62 195	56.28 185	76.10 115	62.43 201	47.62 209	46.57 200	33.84 210	23.24 203	37.52 196	40.19 206	59.61 130	79.81 104	77.55 126	84.55 149	72.03 180

EU-MVSNet		54.63 193	58.69 191	49.90 198	56.99 204	62.70 200	56.41 200	50.64 187	45.95 197	23.14 204	50.42 169	46.51 194	36.63 195	65.51 195	64.85 194	75.57 185	74.91 171

WR-MVS_H		61.83 175	65.87 154	57.12 182	71.72 157	76.87 137	61.45 190	66.19 67	51.97 180	22.92 205	53.13 151	52.30 173	33.80 198	71.03 175	75.00 152	86.65 110	80.78 131

test20.03		53.93 196	56.28 197	51.19 196	72.19 154	65.83 187	53.20 203	61.08 124	42.74 200	22.08 206	37.07 198	45.76 197	24.29 208	70.44 181	69.04 177	74.31 192	63.05 199

gg-mvs-nofinetune		62.55 164	65.05 162	59.62 173	78.72 97	77.61 132	70.83 151	53.63 166	39.71 206	22.04 207	36.36 199	64.32 107	47.53 177	81.16 84	79.03 106	85.00 145	77.17 156

DTE-MVSNet		61.85 173	64.96 164	58.22 178	74.32 134	74.39 159	61.01 191	67.85 60	51.76 182	21.91 208	53.28 146	48.17 188	37.74 194	72.22 165	76.44 142	86.52 114	78.49 148

N_pmnet		47.35 201	50.13 202	44.11 203	59.98 199	51.64 209	51.86 204	44.80 203	49.58 188	20.76 209	40.65 193	40.05 207	29.64 201	59.84 203	55.15 205	57.63 209	54.00 207

test_method		22.26 208	25.94 210	17.95 211	3.24 219	7.17 219	23.83 214	7.27 215	37.35 208	20.44 210	21.87 211	39.16 208	18.67 212	34.56 210	20.84 214	34.28 213	20.64 215

MIMVSNet1		49.27 199	53.25 199	44.62 202	44.61 210	61.52 202	53.61 202	52.18 177	41.62 203	18.68 211	28.14 208	41.58 204	25.50 203	68.46 191	69.04 177	73.15 195	62.37 201

Gipuma		36.38 206	35.80 208	37.07 205	45.76 209	33.90 213	29.81 213	48.47 195	39.91 205	18.02 212	8.00 216	8.14 220	25.14 204	59.29 204	61.02 200	55.19 211	40.31 209
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new-patchmatchnet		46.97 202	49.47 204	44.05 204	62.82 193	56.55 206	45.35 210	52.01 178	42.47 201	17.04 213	35.73 201	35.21 209	21.84 211	61.27 202	54.83 206	65.26 207	60.26 202

new_pmnet		38.40 205	42.64 207	33.44 206	37.54 215	45.00 211	36.60 212	32.72 211	40.27 204	12.72 214	29.89 205	28.90 214	24.78 206	53.17 208	52.90 208	56.31 210	48.34 208

FC-MVSNet-test		56.90 189	65.20 160	47.21 200	66.98 182	63.20 197	49.11 208	58.60 154	59.38 132	11.50 215	65.60 78	56.68 139	24.66 207	71.17 173	71.36 170	72.38 197	69.02 188

DeepMVS_CX						18.74 218	18.55 216	8.02 214	26.96 213	7.33 216	23.81 210	13.05 219	25.99 202	25.17 213		22.45 218	36.25 212

E-PMN		21.77 209	18.24 212	25.89 207	40.22 213	19.58 216	12.46 218	39.87 206	18.68 216	6.71 217	9.57 213	4.31 223	22.36 210	19.89 214	27.28 212	33.73 214	28.34 213

EMVS		20.98 210	17.15 213	25.44 208	39.51 214	19.37 217	12.66 217	39.59 207	19.10 215	6.62 218	9.27 214	4.40 222	22.43 209	17.99 215	24.40 213	31.81 215	25.53 214

MVE	19.12 19	20.47 211	23.27 211	17.20 212	12.66 218	25.41 215	10.52 219	34.14 210	14.79 217	6.53 219	8.79 215	4.68 221	16.64 213	29.49 212	41.63 209	22.73 217	38.11 210
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		25.60 207	29.75 209	20.76 210	28.00 216	30.93 214	23.10 215	29.18 213	23.14 214	1.46 220	18.23 212	16.54 217	5.08 214	40.22 209	41.40 210	37.76 212	37.79 211

GG-mvs-BLEND		46.86 203	67.51 143	22.75 209	0.05 220	76.21 144	64.69 179	0.04 217	61.90 114	0.09 221	55.57 128	71.32 72	0.08 216	70.54 179	67.19 188	71.58 198	69.86 185

testmvs		0.09 212	0.15 214	0.02 214	0.01 221	0.02 221	0.05 222	0.01 218	0.11 218	0.01 222	0.26 218	0.01 224	0.06 218	0.10 216	0.10 215	0.01 219	0.43 217

uanet_test		0.00 214	0.00 216	0.00 216	0.00 222	0.00 223	0.00 224	0.00 220	0.00 220	0.00 223	0.00 219	0.00 225	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet-low-res		0.00 214	0.00 216	0.00 216	0.00 222	0.00 223	0.00 224	0.00 220	0.00 220	0.00 223	0.00 219	0.00 225	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

sosnet		0.00 214	0.00 216	0.00 216	0.00 222	0.00 223	0.00 224	0.00 220	0.00 220	0.00 223	0.00 219	0.00 225	0.00 219	0.00 218	0.00 217	0.00 221	0.00 218

test123		0.09 212	0.14 215	0.02 214	0.00 222	0.02 221	0.02 223	0.01 218	0.09 219	0.00 223	0.30 217	0.00 225	0.08 216	0.03 217	0.09 216	0.01 219	0.45 216

9.14												86.88 15

SR-MVS					88.99 34			73.57 25				87.54 13

Anonymous202405211			72.16 100		80.85 79	81.85 83	76.88 102	65.40 75	62.89 108		46.35 182	67.99 97	62.05 111	81.15 85	80.38 87	85.97 129	84.50 100

our_test_3					67.93 181	70.99 169	66.89 167

Patchmatch-RL test							2.85 221

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 46

High-resolution multi-view benchmark