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.

TDRefinement		86.29 1	90.77 1	81.06 1	75.10 52	83.76 2	93.79 1	61.08 18	89.57 1	86.19 1	90.06 10	93.01 24	76.72 2	94.71 1	92.72 1	93.47 1	91.56 2

COLMAP_ROB	75.87 2	84.34 2	89.80 2	77.97 11	75.52 50	82.76 4	90.39 19	54.21 54	89.37 2	83.18 2	89.90 12	95.58 11	72.34 10	92.31 4	90.04 5	92.17 5	88.61 18
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CP-MVS		84.06 3	86.79 10	80.86 2	81.81 8	79.66 29	92.67 6	64.48 1	83.13 30	82.32 3	80.89 78	92.97 25	72.51 9	91.74 6	90.02 6	91.40 17	89.14 8

ACMMPR		83.94 4	87.20 4	80.14 4	81.04 13	81.92 8	92.57 8	63.14 5	84.35 19	79.45 11	83.37 48	92.04 35	72.82 8	90.66 12	88.96 11	91.80 6	89.13 9

MP-MVS		83.50 5	86.11 19	80.45 3	82.58 4	80.60 24	92.68 5	63.48 3	81.43 44	80.21 9	81.95 66	90.76 54	72.86 6	90.14 19	89.30 10	90.92 19	88.59 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP		83.17 6	86.75 11	79.01 7	80.11 25	82.01 7	92.29 10	60.35 25	82.20 38	78.32 15	80.59 79	93.14 22	70.67 15	91.30 8	89.36 9	92.30 4	88.62 17
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
PGM-MVS		83.03 7	85.67 26	79.95 5	80.69 17	81.09 15	92.40 9	63.06 6	79.38 59	80.21 9	80.31 82	91.44 40	71.75 12	90.46 15	88.53 14	91.57 9	88.50 20

LGP-MVS_train		82.91 8	86.50 13	78.72 8	78.72 34	81.03 16	89.78 23	61.16 17	80.15 54	80.44 6	84.83 37	94.19 14	70.52 17	90.70 11	87.19 22	91.71 8	87.37 29

ACMM	71.24 7	82.85 9	86.59 12	78.50 9	80.10 26	78.59 32	91.77 11	60.76 22	84.43 17	76.49 24	81.58 72	93.50 17	70.45 18	91.38 7	89.42 8	91.42 16	87.22 31
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HFP-MVS		82.37 10	86.28 15	77.81 14	79.94 27	80.96 18	91.13 14	63.30 4	84.04 21	71.81 39	82.39 59	89.59 72	69.16 23	89.08 25	88.83 13	91.49 13	89.10 10

DeepC-MVS	73.80 3	82.34 11	86.87 8	77.06 18	78.62 35	84.34 1	90.30 21	63.54 2	83.10 31	71.30 44	86.91 24	90.54 60	67.12 29	87.81 34	87.05 23	91.46 15	88.37 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CPTT-MVS		82.32 12	85.00 34	79.19 6	80.73 16	80.86 21	91.68 12	62.59 10	82.55 35	75.53 28	73.88 126	92.28 31	73.74 5	90.07 20	87.65 18	90.87 20	87.74 25

ACMP	70.35 9	82.17 13	86.45 14	77.18 17	79.33 28	81.00 17	89.27 27	58.63 31	81.35 46	75.46 29	82.97 54	95.08 12	68.90 24	90.49 14	87.43 21	91.48 14	86.84 33
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SteuartSystems-ACMMP		82.16 14	85.55 28	78.21 10	80.48 19	79.28 30	92.65 7	61.03 19	80.55 52	77.00 22	81.80 69	90.71 55	68.73 25	90.25 17	87.94 17	89.36 27	88.30 22
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		82.15 15	85.93 21	77.74 15	80.13 24	80.25 26	91.01 15	60.61 23	85.54 11	78.61 14	83.21 51	86.96 106	65.95 34	88.10 31	87.59 19	90.11 21	89.83 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
SD-MVS		82.13 16	86.80 9	76.67 19	80.36 22	80.66 22	89.48 25	56.93 34	82.50 36	67.55 67	87.05 22	91.40 42	72.84 7	88.66 27	88.32 15	92.85 2	89.04 11
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
LTVRE_ROB	75.99 1	82.04 17	87.16 5	76.07 22	63.57 127	70.27 74	86.48 42	62.99 7	89.00 5	80.32 7	86.25 27	91.04 47	74.66 4	92.58 3	90.29 4	88.42 34	90.72 3
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
DVP-MVS++		82.03 18	88.03 3	75.05 27	82.08 6	78.96 31	88.98 31	56.44 39	89.29 3	72.39 37	93.25 1	93.86 16	63.42 49	85.46 45	81.36 57	86.96 46	94.00 1

PMVS	70.37 8	81.82 19	87.08 6	75.68 24	77.06 42	77.23 40	87.77 38	56.25 42	83.33 29	67.18 72	89.48 15	87.94 90	77.70 1	93.02 2	92.57 2	88.13 36	86.00 38
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_NAP		81.79 20	85.72 24	77.21 16	79.15 32	79.68 28	91.62 13	59.66 27	83.55 26	77.74 18	83.72 46	87.34 98	65.36 35	88.61 28	87.56 20	89.73 26	89.58 6

X-MVS		81.61 21	84.73 36	77.97 11	80.31 23	81.29 12	93.53 2	62.50 11	81.41 45	77.45 19	72.04 138	90.19 65	62.50 56	90.57 13	88.87 12	91.54 10	88.73 15

OPM-MVS		81.44 22	85.68 25	76.49 20	79.27 29	78.21 35	89.84 22	58.67 30	85.25 12	76.26 25	85.28 34	92.88 26	66.03 33	87.20 37	85.40 27	88.86 31	85.58 42
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + MP.		81.23 23	86.13 17	75.52 25	80.74 15	83.22 3	90.55 16	55.12 49	80.87 49	67.62 66	88.01 17	92.38 30	70.61 16	86.64 39	83.10 42	88.51 32	88.67 16
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TSAR-MVS + ACMM		81.20 24	86.92 7	74.52 29	77.60 38	82.29 5	84.41 48	62.95 8	82.99 32	64.03 82	87.71 18	89.17 77	71.98 11	88.19 30	88.10 16	86.18 55	89.95 4

APDe-MVS		81.08 25	86.12 18	75.20 26	79.25 30	80.91 19	90.38 20	57.05 33	85.83 10	66.07 77	87.34 21	91.27 43	69.45 19	85.99 43	82.55 44	88.98 30	88.95 13
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		81.01 26	85.18 30	76.15 21	78.58 36	80.64 23	89.77 24	57.92 32	81.66 43	73.45 32	86.84 25	89.80 70	69.33 21	85.40 46	82.91 43	87.87 38	89.01 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		80.60 27	84.63 37	75.91 23	81.22 11	81.48 10	90.49 17	58.81 29	77.54 65	67.49 69	85.90 29	89.82 69	69.43 20	86.08 42	83.80 37	88.01 37	87.77 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		80.44 28	82.57 49	77.96 13	81.99 7	72.76 61	90.48 18	61.31 14	80.85 50	77.90 17	81.93 67	87.01 103	68.20 27	84.15 56	85.27 29	87.85 39	86.00 38

DVP-MVS		80.31 29	85.60 27	74.15 33	76.23 46	78.39 33	86.62 40	55.79 45	86.47 9	71.32 43	90.96 7	89.02 79	69.28 22	84.62 55	81.64 54	85.66 60	88.09 23
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
ACMH+	67.97 10	80.15 30	86.16 16	73.14 40	73.82 59	76.41 43	83.59 52	54.82 52	87.35 6	70.86 48	86.98 23	96.27 4	66.50 30	89.17 24	83.39 39	89.26 28	83.56 48

OMC-MVS		79.95 31	85.28 29	73.74 36	72.95 62	80.10 27	87.87 37	48.13 84	84.62 16	79.42 12	80.27 83	92.49 28	64.14 43	87.25 36	85.11 30	89.92 24	87.10 32

SED-MVS		79.70 32	85.16 31	73.34 38	75.83 49	78.11 36	88.77 33	56.45 38	84.85 14	69.45 59	90.70 9	88.38 85	63.16 51	85.12 51	81.28 58	86.40 52	87.63 26

MSP-MVS		79.65 33	84.28 40	74.25 31	78.92 33	81.86 9	89.07 28	60.49 24	83.85 24	70.05 54	85.12 35	90.92 52	62.99 53	81.15 76	81.64 54	83.99 68	85.42 44
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
DeepPCF-MVS	71.57 5	79.49 34	84.05 41	74.17 32	74.14 56	80.88 20	89.33 26	56.24 43	82.41 37	71.58 41	82.27 60	86.47 109	66.47 31	84.80 53	84.16 35	87.26 44	87.34 30

LS3D		79.33 35	84.03 42	73.84 34	75.37 51	78.09 37	83.30 53	52.94 61	84.42 18	76.01 26	84.16 41	87.44 97	65.34 36	86.30 40	82.08 51	90.09 22	85.70 40

3Dnovator+	72.94 4	78.78 36	83.05 46	73.80 35	70.70 75	81.34 11	88.33 34	56.01 44	81.33 47	72.87 36	78.06 100	81.15 140	63.83 46	87.39 35	85.82 25	91.06 18	86.28 37

UA-Net		78.65 37	83.96 43	72.46 42	84.87 1	76.15 44	89.06 29	55.70 46	77.25 66	53.14 120	79.73 88	82.09 138	59.69 72	92.21 5	90.93 3	92.32 3	89.36 7

DeepC-MVS_fast	71.40 6	78.48 38	82.92 47	73.31 39	76.44 45	82.23 6	87.59 39	56.56 37	77.79 63	68.91 63	77.00 104	87.32 99	61.90 58	85.40 46	84.37 32	88.46 33	86.33 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		78.36 39	83.47 45	72.41 43	76.04 48	75.72 47	83.86 50	51.81 65	84.00 23	70.65 51	81.27 74	92.22 32	64.64 41	83.28 66	80.28 60	87.44 43	87.49 28

WR-MVS		78.32 40	86.09 20	69.25 60	76.22 47	72.33 68	85.71 45	59.02 28	86.66 7	51.41 126	92.91 2	96.76 1	53.09 106	90.21 18	85.30 28	90.05 23	78.46 75

ACMH	66.19 11	78.12 41	84.55 38	70.63 51	69.62 81	72.40 67	80.77 68	46.43 96	89.24 4	77.99 16	87.42 20	95.83 9	62.95 54	86.27 41	78.24 70	86.00 58	82.46 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
train_agg		77.83 42	80.47 59	74.77 28	80.92 14	69.60 75	88.87 32	56.32 41	74.03 85	71.03 46	83.67 47	87.68 93	64.75 40	83.70 58	81.85 53	86.71 48	82.73 49

NCCC		77.82 43	80.72 58	74.43 30	79.24 31	75.72 47	88.06 35	56.36 40	79.61 56	73.22 34	67.75 152	87.05 102	63.09 52	85.62 44	84.00 36	86.62 49	85.30 45

CNVR-MVS		77.79 44	81.57 53	73.38 37	78.37 37	75.91 45	87.97 36	55.11 50	79.41 58	70.98 47	74.70 122	86.43 110	61.77 59	85.10 52	83.73 38	86.10 57	85.68 41

WR-MVS_H		77.56 45	85.88 22	67.86 64	80.54 18	74.32 56	83.23 54	61.78 12	83.47 27	47.46 148	91.81 6	95.84 8	50.50 122	90.44 16	84.37 32	83.63 73	80.89 62

RPSCF		77.56 45	84.51 39	69.46 59	65.17 114	74.36 55	79.74 75	47.45 87	84.01 22	72.89 35	77.89 101	90.67 56	65.14 38	88.25 29	89.74 7	86.38 53	86.64 35

PS-CasMVS		77.46 47	85.80 23	67.73 66	81.24 10	72.88 60	80.63 69	61.28 15	84.14 20	50.53 133	92.13 4	96.76 1	50.12 125	91.02 9	84.46 31	82.60 85	79.19 68

DTE-MVSNet		77.28 48	84.87 35	68.42 62	82.94 3	72.70 63	81.60 63	61.78 12	85.03 13	51.40 127	92.11 5	96.00 6	49.42 128	89.73 22	82.52 46	83.39 78	75.98 87

SixPastTwentyTwo		77.24 49	83.65 44	69.78 56	65.14 115	64.85 98	77.44 85	47.74 86	82.76 34	68.52 64	87.65 19	93.31 19	71.68 13	89.49 23	82.41 47	88.14 35	85.05 46

CDPH-MVS		77.22 50	81.05 57	72.75 41	77.29 40	77.46 39	86.36 43	54.02 56	73.00 91	69.75 57	77.78 102	88.90 81	61.31 63	84.09 57	82.54 45	87.79 40	83.57 47

PEN-MVS		77.06 51	85.05 32	67.74 65	82.29 5	72.59 64	80.86 67	61.03 19	84.66 15	50.08 136	92.19 3	96.59 3	49.12 130	89.83 21	82.35 48	83.06 79	77.14 80

CP-MVSNet		77.01 52	85.04 33	67.65 67	81.16 12	72.72 62	80.54 70	61.18 16	82.09 39	50.41 134	90.81 8	95.89 7	50.03 126	90.86 10	84.30 34	82.56 87	78.65 74

CSCG		76.95 53	82.08 51	70.97 47	73.32 61	78.35 34	81.08 66	47.19 88	83.47 27	69.82 56	80.44 80	87.19 100	64.59 42	81.01 79	77.26 77	89.83 25	86.84 33

CNLPA		76.67 54	81.72 52	70.77 50	70.75 73	76.68 42	86.14 44	46.11 98	81.82 41	74.68 30	76.37 106	86.23 113	62.92 55	85.28 49	83.29 40	84.02 67	82.40 51

MSLP-MVS++		76.66 55	82.32 50	70.06 53	70.51 76	80.27 25	79.77 74	55.58 47	77.79 63	63.09 83	67.25 158	89.50 73	71.01 14	88.10 31	85.74 26	80.39 99	87.56 27

TSAR-MVS + COLMAP		75.85 56	81.06 55	69.77 57	71.15 69	76.90 41	82.93 56	52.43 63	79.25 60	70.13 52	82.78 55	87.00 104	60.02 68	80.30 83	79.61 64	81.95 91	81.61 58

HQP-MVS		75.81 57	78.91 66	72.18 44	77.41 39	75.38 50	84.75 46	53.35 58	76.12 73	73.32 33	69.48 143	88.07 88	57.76 80	79.42 89	78.44 67	86.48 50	85.50 43

PLC	64.88 15	75.76 58	80.22 60	70.57 52	70.46 77	77.75 38	82.01 61	48.84 78	80.74 51	70.85 49	71.32 140	84.82 125	63.69 47	84.73 54	82.35 48	87.54 41	79.80 65
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	66.11 12	75.37 59	79.24 64	70.86 48	67.63 88	74.09 57	83.17 55	44.75 113	81.82 41	80.83 5	65.61 169	88.04 89	61.58 60	83.21 67	80.12 61	87.17 45	81.82 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PHI-MVS		75.17 60	78.37 67	71.43 45	71.13 70	72.46 66	82.28 60	50.55 71	73.39 88	79.05 13	73.65 128	87.50 96	61.98 57	81.10 77	78.48 66	83.60 74	81.99 52

MVS_0304		74.91 61	79.25 63	69.85 55	75.01 53	74.95 52	86.61 41	48.67 79	68.87 127	67.51 68	80.13 85	83.78 132	55.77 90	83.37 64	81.89 52	85.55 62	81.75 55

anonymousdsp		74.76 62	82.59 48	65.63 84	45.61 218	61.13 127	89.06 29	32.58 204	74.11 84	59.55 95	84.06 42	94.12 15	75.24 3	88.94 26	86.95 24	91.74 7	88.81 14

AdaColmap		74.73 63	77.57 72	71.40 46	76.90 43	75.76 46	84.54 47	53.08 60	76.20 71	66.64 75	66.06 167	78.16 160	61.32 62	85.37 48	82.20 50	85.95 59	79.27 67

v7n		74.47 64	81.06 55	66.77 73	66.98 94	67.10 78	76.76 89	45.88 100	81.98 40	67.43 70	88.38 16	95.67 10	61.38 61	80.76 81	73.49 98	82.21 89	80.06 63

PCF-MVS	65.25 14	73.99 65	76.74 76	70.79 49	71.61 68	75.33 51	83.76 51	50.40 72	74.88 76	74.50 31	67.60 153	85.36 122	58.30 78	78.61 95	74.25 93	86.15 56	81.13 61
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MCST-MVS		73.84 66	77.44 73	69.63 58	73.75 60	74.73 54	81.38 65	48.58 80	74.77 77	69.16 61	71.97 139	86.20 114	59.50 73	78.51 96	74.06 95	85.42 63	81.85 53

TSAR-MVS + GP.		73.42 67	76.31 77	70.05 54	77.15 41	71.13 71	81.59 64	54.11 55	69.84 120	58.65 98	66.20 166	78.77 156	65.29 37	83.65 59	83.14 41	83.54 75	81.47 59

Gipuma		73.40 68	79.27 62	66.55 78	63.64 126	59.35 138	70.28 128	45.92 99	83.79 25	71.78 40	84.04 43	93.07 23	68.69 26	87.90 33	76.76 79	78.98 112	69.96 128
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVS_111021_HR		72.37 69	76.12 80	68.00 63	68.55 85	64.30 106	82.93 56	48.98 77	74.25 82	65.39 78	73.59 129	84.11 130	59.48 74	82.61 70	78.38 68	82.66 84	75.59 89

TinyColmap		71.85 70	76.11 81	66.87 72	66.07 103	65.34 92	74.35 101	49.30 76	79.93 55	75.93 27	75.66 112	87.74 92	54.72 98	80.66 82	70.42 121	80.85 97	73.02 105

UniMVSNet_ETH3D		71.84 71	81.36 54	60.74 109	76.46 44	66.01 86	66.49 151	60.24 26	86.58 8	41.87 174	90.04 11	96.02 5	43.72 162	85.14 50	77.30 76	75.64 137	68.40 142

TranMVSNet+NR-MVSNet		71.66 72	79.23 65	62.83 100	72.54 65	65.64 88	74.77 99	55.27 48	75.91 74	45.50 161	89.55 13	94.25 13	45.96 151	82.74 69	77.03 78	82.96 81	69.48 136

MVS_111021_LR		71.60 73	75.21 84	67.38 68	67.42 89	62.44 116	81.73 62	46.24 97	70.89 105	66.80 74	73.19 132	84.98 123	60.09 67	81.94 73	77.77 74	82.00 90	75.29 90

EG-PatchMatch MVS		71.50 74	76.82 75	65.30 85	70.74 74	66.50 82	74.23 103	43.25 121	72.02 96	59.11 96	79.85 87	86.88 107	63.95 45	80.29 84	75.25 89	80.51 98	76.98 81

DPM-MVS		71.35 75	73.50 105	68.84 61	74.93 54	73.35 58	84.07 49	50.56 70	71.91 97	67.06 73	61.21 189	77.02 165	52.64 109	74.15 118	75.14 90	83.79 71	81.74 56

UniMVSNet (Re)		71.29 76	78.14 68	63.30 95	70.29 78	66.57 81	75.98 91	54.74 53	70.20 113	46.20 159	85.08 36	93.21 20	48.19 138	82.50 71	78.33 69	84.40 65	71.08 118

CLD-MVS		71.24 77	78.12 69	63.20 97	74.03 57	71.60 69	82.82 58	32.91 201	74.23 83	69.32 60	79.65 89	91.54 38	47.02 146	81.22 75	79.01 65	73.09 158	69.63 132
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		71.07 78	75.09 86	66.39 79	72.57 64	71.53 70	82.38 59	47.10 89	59.81 161	59.81 94	74.97 117	84.37 129	54.25 101	79.89 87	77.64 75	82.25 88	77.40 78

v1192		71.06 79	74.87 88	66.61 75	66.38 98	65.80 87	78.27 79	45.28 105	70.19 114	70.79 50	83.37 48	91.79 36	58.76 77	70.86 159	69.02 128	80.16 102	73.08 103

DU-MVS		71.03 80	77.92 70	62.98 99	70.81 71	65.48 90	73.93 106	56.76 35	69.95 118	46.77 155	85.70 32	93.49 18	46.91 147	83.47 60	77.82 73	82.72 83	69.54 133

v1240		70.94 81	74.52 92	66.76 74	66.54 97	64.40 102	77.76 82	45.29 104	70.05 116	71.45 42	83.36 50	90.96 49	60.37 65	70.50 162	68.68 129	79.14 110	73.68 99

v1921920		70.82 82	74.46 94	66.58 77	66.33 99	64.35 105	77.72 83	45.07 107	70.39 110	71.18 45	83.15 52	90.62 58	59.97 69	70.90 157	68.43 136	79.19 109	73.39 100

UniMVSNet_NR-MVSNet		70.82 82	77.44 73	63.11 98	71.75 67	66.02 85	73.93 106	55.00 51	70.90 104	46.77 155	86.68 26	91.54 38	46.91 147	81.07 78	76.32 83	84.28 66	69.54 133

PVSNet_Blended_VisFu		70.70 84	73.62 103	67.28 70	63.53 128	72.96 59	77.97 80	52.10 64	63.65 149	62.66 84	71.14 141	73.46 176	63.55 48	79.35 93	75.34 88	83.90 69	79.43 66

v144192		70.68 85	74.40 96	66.34 80	65.94 105	64.38 103	77.63 84	45.18 106	69.97 117	70.11 53	82.70 57	90.77 53	59.84 71	71.43 154	68.46 132	79.31 108	73.08 103

EC-MVSNet		70.50 86	73.32 108	67.20 71	72.07 66	66.21 84	70.86 125	50.10 73	57.66 174	60.49 93	74.97 117	79.42 151	63.32 50	79.65 88	75.46 87	86.35 54	79.87 64

FPMVS		70.46 87	74.89 87	65.28 86	69.09 83	61.42 122	77.07 87	46.92 92	76.73 70	53.53 116	67.33 155	75.07 171	67.23 28	83.41 62	81.54 56	77.86 121	78.73 72

v1144		70.45 88	74.50 93	65.73 83	65.74 108	64.88 97	77.33 86	44.16 115	70.59 109	69.63 58	83.15 52	91.42 41	57.79 79	71.29 155	68.53 131	79.72 106	71.63 115

v10		70.25 89	74.59 91	65.19 87	65.32 112	66.46 83	76.60 90	44.84 110	67.38 134	67.21 71	82.75 56	90.56 59	57.70 81	71.69 149	68.63 130	79.44 107	74.67 93

Effi-MVS+-dtu		70.10 90	73.76 102	65.82 82	70.23 79	74.92 53	79.47 76	44.49 114	56.98 179	54.34 110	64.26 173	84.78 126	59.97 69	80.96 80	80.38 59	86.44 51	74.05 97

SPE-MVS-test		70.00 91	72.92 111	66.59 76	66.71 96	64.06 108	80.28 72	44.82 111	58.41 166	58.08 101	73.57 130	80.94 142	63.98 44	83.29 65	75.93 85	85.65 61	74.23 94

MAR-MVS		70.00 91	72.28 122	67.34 69	69.89 80	72.57 65	80.09 73	49.49 75	60.28 160	69.03 62	59.29 198	80.79 144	54.68 99	78.39 98	76.00 84	80.87 96	78.67 73
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
Vis-MVSNet		69.95 93	77.69 71	60.91 107	60.67 146	66.71 79	77.94 81	48.58 80	69.10 125	45.78 160	80.21 84	83.58 134	53.41 105	82.92 68	80.11 62	79.08 111	81.21 60
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS		69.56 94	72.49 118	66.14 81	66.85 95	64.10 107	72.55 112	42.91 123	58.90 163	60.78 89	72.93 135	83.21 136	66.32 32	78.77 94	72.84 105	87.45 42	76.72 82

EPP-MVSNet		69.51 95	76.17 78	61.74 104	68.38 87	66.60 80	71.77 116	46.98 90	73.60 87	41.79 175	82.06 63	69.65 187	52.51 110	83.41 62	79.94 63	89.02 29	77.94 76

3Dnovator	65.69 13	69.43 96	75.74 83	62.06 103	60.78 145	70.50 73	75.85 93	39.57 162	74.44 79	57.41 103	75.91 108	77.73 162	55.34 94	76.86 102	75.61 86	83.44 76	79.14 69

Effi-MVS+		69.04 97	73.01 110	64.40 90	67.20 92	64.83 99	74.87 98	43.97 117	63.33 151	60.90 88	73.06 133	85.79 119	55.61 91	73.58 126	76.41 82	83.84 70	74.09 96

v2v482		69.01 98	73.39 107	63.89 92	63.86 120	62.99 113	75.26 96	42.05 134	70.22 112	68.46 65	82.64 58	91.61 37	55.38 92	70.89 158	66.93 153	78.30 117	68.48 141

MSDG		68.98 99	73.31 109	63.92 91	67.08 93	68.27 76	75.41 95	40.77 150	67.61 132	64.89 79	75.75 111	78.96 153	53.70 103	76.72 105	73.95 96	81.71 93	71.93 113

v8		68.77 100	73.50 105	63.26 96	63.74 124	64.47 101	74.22 104	42.07 133	67.30 135	64.89 79	82.08 62	90.23 64	56.50 88	71.85 148	66.57 154	78.14 118	72.02 111

NR-MVSNet		68.66 101	76.15 79	59.93 115	65.49 109	65.48 90	74.42 100	56.76 35	69.95 118	45.38 162	85.70 32	91.13 44	34.68 196	74.52 117	76.75 80	82.83 82	69.49 135

USDC		68.53 102	71.82 130	64.68 88	63.53 128	61.87 121	70.12 130	46.98 90	77.89 62	76.58 23	68.55 148	86.88 107	50.50 122	73.73 123	65.62 156	80.39 99	68.21 145

IS_MVSNet		68.20 103	74.41 95	60.96 106	68.55 85	64.36 104	71.47 120	48.33 82	70.11 115	43.30 168	80.90 77	74.54 173	47.19 145	81.25 74	77.97 72	86.94 47	71.76 114

Baseline_NR-MVSNet		68.15 104	75.12 85	60.02 114	70.81 71	55.67 162	75.88 92	53.40 57	71.25 101	43.96 166	85.88 30	92.68 27	45.76 152	83.47 60	68.34 137	70.34 178	68.58 140

GeoE		68.11 105	72.10 126	63.47 94	67.32 90	62.42 117	78.32 78	43.22 122	64.06 148	55.72 108	73.97 125	84.58 127	55.35 93	76.09 109	70.41 122	80.89 95	73.14 102

casdiffmvs_mvg		68.01 106	74.22 99	60.78 108	63.75 123	62.08 120	70.21 129	42.58 125	72.11 95	58.53 99	84.80 39	88.98 80	49.37 129	73.25 130	67.54 149	80.24 101	70.75 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Fast-Effi-MVS+		67.71 107	72.54 117	62.07 102	63.83 121	63.68 110	75.74 94	39.94 157	60.89 159	54.29 111	73.00 134	86.19 115	56.85 85	78.46 97	73.23 101	81.74 92	72.36 109

viewmacassd2359aftdt		67.58 108	74.22 99	59.84 117	61.60 139	59.46 137	72.40 113	35.74 188	76.19 72	62.14 85	83.74 45	90.96 49	51.94 112	73.07 131	65.37 161	75.17 141	70.72 122

viewcassd2359sk11		67.13 109	71.88 129	61.59 105	64.04 119	59.95 136	73.40 111	40.24 156	72.16 94	64.55 81	80.41 81	89.49 74	51.60 113	69.66 171	63.11 177	75.72 133	68.40 142

thisisatest0515		66.95 110	72.29 121	60.72 110	56.37 174	56.05 160	71.08 121	38.81 167	67.59 133	53.26 119	78.21 97	79.79 150	60.11 66	75.69 112	73.02 103	84.69 64	75.66 88

EPNet		66.87 111	68.89 146	64.53 89	73.97 58	61.13 127	78.46 77	61.03 19	56.78 181	53.41 117	66.91 161	70.91 182	43.49 163	76.08 110	76.68 81	76.81 125	73.73 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		66.73 112	72.00 128	60.58 111	62.91 132	61.21 126	72.39 115	39.64 160	68.65 128	60.54 92	78.08 99	88.54 84	52.11 111	71.52 151	65.24 163	75.88 132	70.78 120

sasdasda		66.37 113	74.37 97	57.04 134	65.89 106	65.06 93	62.58 171	42.55 126	76.82 68	46.87 153	67.33 155	86.38 111	45.49 154	76.77 103	71.85 110	78.87 114	76.35 83

canonicalmvs		66.37 113	74.37 97	57.04 134	65.89 106	65.06 93	62.58 171	42.55 126	76.82 68	46.87 153	67.33 155	86.38 111	45.49 154	76.77 103	71.85 110	78.87 114	76.35 83

QAPM		66.36 115	72.76 114	58.90 122	59.57 153	65.01 95	64.05 165	41.17 145	73.09 90	56.82 105	69.42 144	77.78 161	55.07 96	73.00 134	72.07 108	76.71 126	78.96 70

viewmanbaseed2359cas		66.24 116	72.42 119	59.03 120	61.13 142	59.13 140	71.64 118	35.37 189	71.67 98	60.68 90	80.93 76	89.48 75	50.83 118	71.60 150	64.04 170	74.50 146	70.09 126

casdiffmvs		66.19 117	72.34 120	59.02 121	62.75 133	60.61 133	69.06 135	41.38 142	69.49 123	54.11 112	84.00 44	89.74 71	49.12 130	70.74 161	62.70 179	77.70 123	69.14 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
V42		65.79 118	72.11 125	58.42 126	51.89 196	58.69 141	73.80 108	34.50 191	65.40 143	57.10 104	79.54 91	89.09 78	57.51 82	71.98 146	67.83 145	75.70 135	72.26 110

IterMVS-LS		65.76 119	70.85 139	59.81 118	65.33 111	57.78 146	64.63 162	48.02 85	65.65 142	51.05 129	81.31 73	77.47 163	54.94 97	69.46 172	69.36 127	74.90 144	74.95 91
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PM-MVS		65.66 120	71.25 136	59.14 119	58.92 161	54.88 175	73.66 110	38.55 170	66.12 139	49.91 138	69.87 142	86.97 105	60.61 64	76.30 107	74.75 91	73.19 156	69.83 129

UGNet		65.61 121	74.79 89	54.91 148	54.54 190	68.20 77	70.97 124	48.21 83	67.14 137	41.67 176	74.15 124	80.65 146	36.10 190	79.39 90	77.99 71	77.95 120	76.01 86
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
DELS-MVS		65.54 122	71.79 131	58.24 129	59.68 152	65.55 89	70.99 122	38.69 169	62.29 154	49.27 142	75.03 116	81.42 139	50.93 117	73.71 125	71.35 113	79.90 104	73.20 101
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
pmmvs-eth3d		65.36 123	70.09 142	59.85 116	63.05 131	53.61 178	74.29 102	46.45 95	68.14 130	51.45 125	78.83 95	85.78 120	49.87 127	70.44 163	70.45 120	74.00 149	63.38 166

FA-MVS(training)		65.22 124	69.19 145	60.58 111	60.91 143	57.60 150	71.57 119	38.82 166	65.84 141	61.18 87	75.95 107	74.52 174	51.18 116	73.32 128	67.41 150	79.80 105	69.70 131

v148		64.92 125	70.58 141	58.32 127	59.89 150	57.09 153	66.04 154	35.27 190	69.11 124	60.66 91	79.57 90	90.93 51	53.91 102	69.81 170	62.22 180	74.14 147	65.31 158

FC-MVSNet-train		64.87 126	74.76 90	53.33 156	65.24 113	58.05 143	69.69 132	41.92 137	70.99 103	32.62 202	85.75 31	88.23 86	32.10 207	77.61 101	74.41 92	78.43 116	68.25 144

pmmvs6		64.78 127	75.82 82	51.89 162	62.41 134	57.13 152	60.24 179	45.59 102	82.90 33	34.69 193	84.83 37	93.18 21	36.22 189	76.43 106	71.13 116	72.21 162	65.12 159

OpenMVS	60.79 16	64.42 128	69.72 143	58.23 130	61.63 138	62.17 118	64.11 164	37.54 180	67.17 136	55.71 109	65.89 168	74.89 172	52.67 108	72.20 144	68.29 139	77.73 122	77.39 79

MGCFI-Net		64.40 129	73.52 104	53.76 155	65.41 110	63.86 109	58.32 189	42.38 129	77.23 67	37.76 182	68.03 150	86.11 117	39.76 174	75.70 111	67.69 148	78.96 113	76.03 85

test1111		64.34 130	71.57 132	55.90 142	67.25 91	60.24 135	66.66 149	51.63 68	73.36 89	34.69 193	75.63 113	80.67 145	39.43 175	78.17 99	71.69 112	75.71 134	61.23 172

DCV-MVSNet		64.34 130	72.84 113	54.42 151	63.79 122	62.09 119	62.50 173	42.72 124	74.32 81	41.34 177	66.96 159	88.57 83	39.18 176	75.20 114	70.35 123	77.01 124	72.37 108

ETV-MVS		64.30 132	64.76 163	63.77 93	68.59 84	62.49 115	77.02 88	45.31 103	49.27 207	50.88 130	56.23 210	59.91 210	57.12 84	80.19 86	74.23 94	83.68 72	71.03 119

viewdifsd2359ckpt11		64.18 133	72.66 115	54.28 154	59.33 158	55.48 166	68.20 139	34.30 193	69.68 121	42.09 172	82.03 64	90.43 63	48.52 133	73.95 120	65.57 157	73.27 154	71.49 116

viewmsd2359difaftdt		64.18 133	72.66 115	54.29 153	59.33 158	55.49 165	68.20 139	34.31 192	69.68 121	42.10 171	82.03 64	90.45 62	48.51 134	73.94 121	65.57 157	73.27 154	71.48 117

ECVR-MVS		63.93 135	71.52 133	55.08 146	66.19 100	61.34 123	63.84 166	51.79 66	70.75 107	34.77 191	74.70 122	81.10 141	38.92 177	79.39 90	73.43 99	75.00 142	59.92 180

Anonymous20231211		63.69 136	72.86 112	53.00 159	63.72 125	60.25 134	60.33 178	40.96 146	72.49 92	38.91 180	81.77 70	88.17 87	37.60 184	73.30 129	68.01 142	76.47 130	66.06 155

diffmvs_AUTHOR		63.60 137	71.07 137	54.90 149	56.75 172	55.35 168	67.91 144	37.08 183	66.87 138	50.84 131	81.64 71	88.73 82	45.49 154	70.02 169	64.15 168	71.31 167	70.70 123

TransMVSNet (Re)		63.49 138	73.86 101	51.39 168	64.26 118	56.07 159	61.17 176	42.23 131	78.81 61	34.80 190	85.94 28	90.63 57	34.35 200	72.73 139	67.98 143	71.50 166	64.84 160

DI_MVS_pp		63.43 139	67.54 151	58.63 123	62.34 135	58.06 142	65.75 158	42.15 132	63.05 152	53.28 118	75.88 110	75.92 168	50.18 124	68.04 175	64.20 167	78.07 119	67.65 147

EIA-MVS		63.24 140	64.16 167	62.16 101	69.30 82	63.20 112	72.40 113	40.82 149	48.31 213	51.50 124	59.63 196	62.23 202	57.33 83	78.00 100	71.94 109	81.59 94	65.82 156

Fast-Effi-MVS+-dtu		63.22 141	65.55 157	60.49 113	61.24 141	64.70 100	74.15 105	53.24 59	51.46 192	49.67 140	58.03 205	78.42 157	48.05 140	72.03 145	71.14 115	76.60 129	63.09 167

IterMVS-SCA-FT		62.67 142	68.00 148	56.45 141	56.92 171	64.92 96	57.51 193	38.12 172	59.44 162	53.62 115	74.74 121	71.60 179	64.84 39	70.24 165	65.27 162	67.70 186	69.83 129

diffmvs		62.64 143	69.66 144	54.46 150	56.19 177	55.06 171	67.36 147	36.74 186	64.18 146	50.58 132	79.54 91	87.55 95	45.13 158	68.04 175	63.20 174	70.78 173	70.02 127
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		62.58 144	67.46 152	56.89 137	59.52 154	55.90 161	64.94 160	38.83 165	57.08 178	56.55 106	76.53 105	84.49 128	47.45 142	66.95 179	62.01 181	74.04 148	69.27 137

MDA-MVSNet-bldmvs		62.46 145	72.13 124	51.19 170	34.32 228	56.10 158	68.65 137	38.85 164	69.05 126	49.50 141	78.17 98	85.43 121	51.32 114	86.67 38	67.40 151	64.46 191	62.08 169

pm-mvs1		61.97 146	72.01 127	50.25 176	60.64 147	55.23 169	58.67 187	42.44 128	74.40 80	33.63 199	81.03 75	89.86 68	34.87 195	72.93 137	67.95 144	71.28 168	62.65 168

FMVSNet1		61.92 147	71.36 134	50.90 172	57.67 170	59.29 139	59.48 185	44.14 116	70.24 111	34.72 192	75.45 115	84.94 124	36.75 186	72.33 141	68.45 133	72.66 159	68.83 139

viewmambaseed2359dif		61.91 148	67.70 150	55.15 145	58.68 164	54.97 172	66.48 152	38.16 171	61.22 158	49.79 139	75.90 109	85.95 118	46.19 150	67.70 177	60.19 187	71.60 163	67.93 146

PVSNet_BlendedMVS		61.75 149	65.07 161	57.87 132	56.27 175	60.99 130	65.81 156	43.75 118	51.27 196	54.08 113	62.12 184	78.84 154	50.67 119	71.49 152	63.91 171	76.64 127	66.86 149

PVSNet_Blended		61.75 149	65.07 161	57.87 132	56.27 175	60.99 130	65.81 156	43.75 118	51.27 196	54.08 113	62.12 184	78.84 154	50.67 119	71.49 152	63.91 171	76.64 127	66.86 149

tttt0517		61.44 151	63.85 169	58.62 124	55.20 186	55.61 163	68.80 136	38.02 175	55.70 183	50.01 137	66.93 160	48.90 221	56.69 86	73.84 122	71.10 117	82.99 80	74.89 92

tfpnnormal		61.41 152	71.33 135	49.83 177	61.73 137	54.90 174	58.52 188	41.24 143	75.20 75	32.00 207	82.13 61	87.87 91	35.63 193	72.75 138	66.30 155	69.87 179	60.14 176

IB-MVS	57.02 17	61.37 153	65.39 158	56.69 138	56.65 173	60.85 132	70.70 126	37.90 177	49.37 206	45.37 163	48.75 222	79.14 152	53.55 104	76.26 108	70.85 119	75.97 131	72.50 107
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
CANet_DTU		61.22 154	67.07 154	54.40 152	59.89 150	63.62 111	70.98 123	36.77 185	50.49 199	47.15 149	62.45 182	80.81 143	37.90 183	71.87 147	70.09 125	73.69 150	70.19 125

pmmvs4		61.12 155	64.61 164	57.04 134	60.88 144	52.15 184	70.59 127	44.82 111	61.35 157	46.91 152	72.08 137	73.27 177	46.79 149	65.06 183	67.76 146	72.28 160	60.58 174

thisisatest0530		61.02 156	63.44 174	58.19 131	54.75 188	55.09 170	68.03 143	38.02 175	55.45 184	49.06 143	66.58 164	48.69 222	56.69 86	73.07 131	71.10 117	82.60 85	74.14 95

Vis-MVSNet (Re-imp)		60.99 157	67.78 149	53.06 158	64.66 117	53.49 179	67.40 145	49.52 74	68.55 129	28.00 216	79.53 93	71.41 181	33.08 204	75.30 113	71.28 114	75.69 136	54.91 192

PatchMatch-RL		60.96 158	63.00 177	58.57 125	59.16 160	52.18 183	67.38 146	41.99 135	57.85 172	48.16 144	53.55 218	69.77 186	59.47 75	73.73 123	72.49 107	75.27 140	61.44 171

GA-MVS		60.73 159	64.24 166	56.64 139	59.38 157	57.45 151	65.07 159	36.65 187	57.39 176	58.17 100	73.43 131	69.10 190	47.38 143	64.47 188	63.63 173	73.19 156	64.22 163

CVMVSNet		60.45 160	63.72 171	56.63 140	54.82 187	53.75 176	68.41 138	41.95 136	55.07 185	48.03 145	58.08 204	68.67 191	55.09 95	69.14 173	68.34 137	71.51 165	72.97 106

ET-MVSNet_ETH3D		60.33 161	62.10 180	58.27 128	58.61 165	58.05 143	68.06 141	41.20 144	51.40 193	51.10 128	64.06 174	49.42 220	50.61 121	74.72 115	70.29 124	80.05 103	66.74 151

FC-MVSNet-test		60.28 162	70.83 140	47.96 188	54.69 189	47.12 199	68.06 141	41.68 141	71.42 99	23.73 224	84.70 40	77.41 164	28.92 212	82.33 72	73.08 102	70.68 174	59.77 181

test2506		59.86 163	64.01 168	55.02 147	66.19 100	61.34 123	63.84 166	51.79 66	70.75 107	34.39 197	62.65 181	39.92 236	38.92 177	79.39 90	73.43 99	75.00 142	60.56 175

EU-MVSNet		59.77 164	66.07 155	52.42 160	47.81 207	51.86 186	62.98 170	32.28 206	62.08 155	47.10 150	59.94 194	83.42 135	53.08 107	70.06 168	63.19 175	71.26 170	71.96 112

IterMVS		59.24 165	64.45 165	53.16 157	50.98 198	61.29 125	66.51 150	32.85 202	58.17 168	46.31 158	72.58 136	70.23 184	54.26 100	64.81 186	60.24 186	68.04 185	63.81 165
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		59.15 166	62.28 179	55.49 144	52.42 194	62.59 114	71.76 117	39.74 158	50.25 201	41.92 173	62.88 179	69.16 189	55.85 89	62.77 193	67.18 152	71.27 169	61.11 173

thres600view7		58.87 167	65.91 156	50.66 174	61.27 140	56.32 156	59.88 183	40.63 152	64.88 144	32.10 206	64.82 170	69.83 185	36.72 187	72.99 135	72.55 106	73.34 152	59.97 179

FE-MVSNET		58.15 168	67.14 153	47.65 191	49.53 203	50.47 188	57.09 198	37.15 182	67.85 131	35.64 189	67.57 154	87.16 101	35.36 194	71.23 156	65.57 157	71.17 172	60.12 177

CMPMVS	45.32 18	58.10 169	65.24 160	49.76 178	47.88 206	46.86 202	48.16 220	32.82 203	58.06 169	61.35 86	59.64 195	80.00 147	47.27 144	70.15 166	64.10 169	61.08 195	77.85 77
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		58.09 170	63.54 173	51.74 164	50.13 200	46.56 203	66.95 148	33.41 199	63.52 150	58.77 97	74.84 119	84.10 131	43.12 164	65.95 182	54.69 202	58.04 201	55.13 191

CDS-MVSNet		57.90 171	63.57 172	51.28 169	62.30 136	53.17 180	64.70 161	51.61 69	57.41 175	32.75 201	63.73 175	70.53 183	27.12 214	72.49 140	73.02 103	69.22 182	54.68 193
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FMVSNet2		57.80 172	65.39 158	48.94 184	55.88 178	57.61 147	57.26 194	42.37 130	58.21 167	33.19 200	68.36 149	75.55 170	34.58 197	66.91 180	64.55 165	70.38 175	66.56 152

thres400		57.25 173	63.73 170	49.70 179	60.19 149	54.95 173	58.16 190	39.60 161	62.42 153	31.98 209	62.33 183	69.20 188	35.96 191	70.07 167	68.03 141	72.28 160	59.12 183

WB-MVS		57.14 174	71.03 138	40.93 207	47.97 205	53.10 181	52.35 210	39.66 159	79.59 57	23.31 225	89.49 14	89.23 76	32.94 205	74.68 116	61.41 183	49.32 217	49.74 202

gm-plane-assit		56.76 175	57.64 194	55.73 143	66.01 104	55.45 167	74.96 97	30.54 211	73.71 86	56.04 107	81.81 68	30.91 239	43.83 160	58.77 203	54.71 201	63.02 193	48.13 209

MIMVSNet1		56.72 176	68.69 147	42.76 203	46.70 213	42.81 210	69.13 133	30.52 212	81.01 48	32.00 207	74.82 120	91.10 46	26.83 216	73.98 119	64.72 164	51.40 213	52.38 197

EPNet_dtu		56.63 177	60.77 186	51.80 163	55.47 183	44.63 204	69.83 131	38.74 168	50.27 200	47.64 146	58.01 206	72.27 178	33.71 202	68.60 174	67.72 147	65.39 189	63.86 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GBi-Net		56.54 178	63.26 175	48.70 185	55.88 178	57.61 147	57.26 194	41.75 138	49.06 208	32.37 203	61.81 186	67.02 193	34.58 197	72.33 141	68.45 133	70.38 175	66.56 152

test1		56.54 178	63.26 175	48.70 185	55.88 178	57.61 147	57.26 194	41.75 138	49.06 208	32.37 203	61.81 186	67.02 193	34.58 197	72.33 141	68.45 133	70.38 175	66.56 152

gg-mvs-nofinetune		56.45 180	61.04 184	51.10 171	63.42 130	49.40 195	53.71 206	52.52 62	74.77 77	46.93 151	77.31 103	53.88 214	26.42 218	62.51 194	57.81 194	63.60 192	51.57 200

thres200		56.35 181	62.36 178	49.34 181	58.87 162	56.32 156	55.91 199	40.63 152	58.51 165	31.34 210	58.81 202	67.31 192	35.96 191	72.99 135	65.51 160	73.34 152	57.07 186

MS-PatchMatch		56.31 182	60.22 189	51.73 165	60.53 148	55.53 164	63.41 168	37.18 181	51.34 195	37.44 183	60.53 192	62.19 203	45.52 153	64.25 189	63.17 176	66.33 187	64.56 161

tfpn200view9		56.07 183	61.85 181	49.34 181	58.57 166	56.48 155	58.01 192	40.72 151	53.23 186	31.01 211	56.41 208	66.40 198	34.18 201	73.02 133	68.06 140	73.53 151	59.35 182

FMVSNet3		54.77 184	60.73 187	47.81 189	54.29 191	56.88 154	55.89 200	41.75 138	49.06 208	32.37 203	61.81 186	67.02 193	33.67 203	62.88 192	61.96 182	68.88 183	65.53 157

thres100view900		53.88 185	59.19 190	47.68 190	58.57 166	52.74 182	54.45 203	38.07 174	53.23 186	31.01 211	56.41 208	66.40 198	32.80 206	65.03 185	64.43 166	71.18 171	56.10 189

CR-MVSNet		53.82 186	55.40 198	51.98 161	51.57 197	50.23 190	45.00 222	44.97 108	46.90 215	52.60 121	67.91 151	46.99 229	48.37 135	59.15 201	59.53 190	69.38 181	57.07 186

baseline2		53.55 187	55.19 199	51.62 166	55.27 185	51.95 185	60.89 177	34.23 194	46.69 217	42.47 169	53.56 217	50.01 217	45.33 157	64.63 187	61.22 184	71.56 164	58.28 185

test20.03		53.49 188	60.95 185	44.78 199	64.73 116	47.25 198	61.58 175	43.30 120	65.86 140	22.85 226	66.87 163	79.85 148	22.99 220	62.38 195	56.95 196	53.25 210	47.46 211

baseline		53.46 189	61.55 182	44.01 200	45.83 216	48.77 196	57.26 194	28.75 215	49.99 202	38.85 181	68.78 146	75.65 169	38.30 180	60.80 196	59.78 189	55.10 208	67.07 148

MVSTER		53.08 190	56.39 196	49.21 183	47.19 209	51.08 187	60.14 181	31.74 208	40.63 226	38.97 179	55.78 211	46.74 230	42.47 167	67.29 178	62.99 178	74.73 145	70.23 124

CHOSEN 1792x2688		52.99 191	56.91 195	48.42 187	47.32 208	50.10 192	64.18 163	33.85 196	45.46 220	36.95 185	55.20 214	66.49 197	51.20 115	59.28 199	59.81 188	57.01 203	61.99 170

baseline1		52.90 192	58.38 191	46.51 197	58.87 162	50.01 193	54.17 204	40.45 155	56.81 180	29.25 214	62.72 180	58.99 211	30.25 210	65.05 184	60.57 185	66.07 188	54.54 194

CostFormer		52.59 193	55.14 200	49.61 180	52.72 192	50.40 189	66.28 153	33.78 197	52.85 188	43.43 167	66.30 165	51.37 216	41.78 170	54.92 213	51.18 209	59.68 197	58.98 184

SCA		52.47 194	53.97 203	50.71 173	46.95 212	57.79 145	60.18 180	46.89 93	51.92 191	46.71 157	60.73 190	49.97 218	47.69 141	56.39 210	52.98 206	55.82 205	48.03 210

testgi		51.94 195	61.37 183	40.94 206	58.38 168	47.03 200	65.88 155	30.49 213	70.87 106	22.64 227	57.53 207	87.59 94	18.30 227	63.01 191	54.32 203	49.93 216	49.27 204

dmvs_re		51.01 196	54.88 201	46.49 198	58.06 169	44.35 207	60.08 182	37.67 178	42.11 224	28.68 215	45.12 227	66.70 196	31.90 209	66.62 181	59.18 192	62.59 194	60.11 178

tpm cat1		50.98 197	51.28 209	50.62 175	55.74 181	49.92 194	63.13 169	38.12 172	52.38 190	47.61 147	60.11 193	44.51 233	44.86 159	51.31 221	47.49 216	54.25 209	53.24 196

RPMNet		50.92 198	50.32 211	51.62 166	50.25 199	50.23 190	59.16 186	46.70 94	46.90 215	42.39 170	48.97 221	37.23 237	41.78 170	57.30 208	56.18 198	69.44 180	55.43 190

pmmvs5		50.64 199	58.01 192	42.05 204	47.01 211	43.67 208	49.27 218	29.43 214	50.77 198	33.83 198	68.69 147	76.16 167	27.82 213	57.53 207	57.07 195	64.95 190	52.18 198

PatchT		50.55 200	53.55 205	47.05 195	37.59 227	42.26 211	50.55 215	37.56 179	46.37 218	52.60 121	66.91 161	43.54 235	48.37 135	59.15 201	59.53 190	55.62 206	57.07 186

Anonymous20231206		50.28 201	57.94 193	41.35 205	55.45 184	43.65 209	58.06 191	34.12 195	62.02 156	24.25 223	59.33 197	79.80 149	24.49 219	59.55 197	54.28 204	51.74 212	46.94 213

dps		49.71 202	51.97 207	47.07 194	52.37 195	47.00 201	53.02 209	40.52 154	44.91 221	41.23 178	64.55 171	44.27 234	40.12 173	57.71 206	51.97 208	55.14 207	53.41 195

MDTV_nov1_ep13		49.60 203	51.57 208	47.31 192	46.28 214	44.61 205	59.82 184	30.96 209	48.80 212	50.20 135	59.26 199	52.38 215	38.56 179	56.20 211	49.70 212	58.04 201	50.01 201

PatchmatchNet		48.67 204	50.10 212	46.99 196	48.29 204	41.00 212	55.54 201	38.94 163	51.38 194	45.15 164	63.22 177	48.45 224	42.83 165	53.80 218	48.50 215	51.19 215	44.37 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
new-patchmatchnet		47.33 205	60.49 188	31.99 223	55.69 182	33.86 224	36.84 232	33.31 200	72.36 93	14.33 232	80.09 86	92.14 33	13.27 229	63.54 190	40.09 224	38.51 226	41.32 223

tpm		46.67 206	49.20 217	43.72 201	49.60 201	36.60 221	53.93 205	26.84 217	52.70 189	58.05 102	69.04 145	47.96 225	30.06 211	48.33 224	42.76 219	43.88 220	47.01 212

pmmvs3		46.64 207	54.13 202	37.90 214	31.23 232	40.68 213	49.83 217	15.34 228	46.31 219	36.34 187	53.15 219	74.40 175	36.36 188	58.43 204	56.64 197	58.32 200	49.29 203

TAMVS		46.64 207	53.62 204	38.49 212	49.56 202	36.87 218	53.16 208	25.76 219	56.33 182	22.55 228	60.72 191	61.80 205	27.12 214	59.50 198	58.33 193	52.79 211	41.82 222

test-LLR		46.01 209	45.06 226	47.11 193	59.39 155	36.72 219	51.28 212	40.95 147	36.41 230	34.45 195	46.14 224	47.02 227	38.00 181	51.78 219	48.53 213	58.60 198	48.84 206

MIMVSNet		45.83 210	53.46 206	36.94 215	45.38 220	39.50 215	52.20 211	30.68 210	57.09 177	24.53 222	55.22 213	71.54 180	21.74 223	55.81 212	51.08 210	47.11 218	43.96 216

pmnet_mix02		45.67 211	55.99 197	33.63 222	45.77 217	31.22 228	42.04 227	27.60 216	64.14 147	24.89 219	75.50 114	82.30 137	21.88 222	54.53 216	41.22 221	39.62 224	43.05 218

test0.0.03 1		45.40 212	49.55 215	40.57 209	59.39 155	44.36 206	53.37 207	40.95 147	47.14 214	19.23 229	45.49 226	60.24 208	19.24 225	54.82 214	51.98 207	51.21 214	42.82 219

PMMVS		45.37 213	49.29 216	40.79 208	27.75 233	35.07 223	50.88 214	19.88 225	39.27 228	35.78 188	50.11 220	61.29 206	42.04 168	54.13 217	55.95 199	68.43 184	49.19 205

MVS-HIRNet		44.56 214	45.52 224	43.44 202	40.98 223	31.03 229	39.52 231	36.96 184	42.80 223	44.37 165	53.80 216	60.04 209	41.85 169	47.97 226	41.08 222	56.99 204	41.95 221

test-mter		44.18 215	47.60 219	40.18 210	33.20 229	39.03 216	55.28 202	13.91 230	39.07 229	36.63 186	48.09 223	49.52 219	41.12 172	54.55 215	50.91 211	60.97 196	52.03 199

EMVS		43.85 216	49.91 213	36.77 217	45.46 219	32.70 225	44.09 224	25.33 220	57.88 171	26.62 217	58.99 201	61.14 207	42.77 166	70.26 164	38.52 228	36.38 228	29.87 229

E-PMN		43.83 217	49.81 214	36.84 216	46.09 215	31.86 227	42.77 226	25.85 218	57.76 173	25.53 218	55.50 212	62.47 201	43.77 161	70.78 160	39.51 225	37.04 227	30.79 228

tpmrst		43.31 218	46.14 222	40.02 211	47.05 210	36.48 222	48.01 221	32.17 207	49.50 205	37.26 184	63.66 176	47.04 226	31.98 208	42.00 230	40.55 223	43.64 221	43.75 217

TESTMET0.1,1		41.79 219	45.06 226	37.97 213	31.32 231	36.72 219	51.28 212	14.17 229	36.41 230	34.45 195	46.14 224	47.02 227	38.00 181	51.78 219	48.53 213	58.60 198	48.84 206

ADS-MVSNet		40.61 220	46.31 220	33.96 220	40.70 224	30.42 230	40.42 229	33.44 198	58.01 170	30.87 213	63.05 178	54.48 213	22.67 221	44.35 229	39.23 227	35.64 229	34.64 226

CHOSEN 280x420		40.24 221	44.14 229	35.69 218	32.36 230	23.58 233	50.30 216	21.21 224	40.94 225	18.84 230	32.75 231	48.65 223	48.13 139	59.16 200	55.31 200	43.28 222	48.62 208

EPMVS		40.11 222	44.96 228	34.44 219	41.55 222	32.65 226	41.74 228	32.39 205	49.89 204	24.83 220	64.44 172	46.38 231	26.57 217	44.75 228	39.47 226	39.59 225	37.16 225

FMVSNet5		39.83 223	45.08 225	33.71 221	39.24 225	39.56 214	48.77 219	23.55 222	39.45 227	24.55 221	33.73 230	44.57 232	20.97 224	58.27 205	54.23 205	45.16 219	45.77 214

N_pmnet		39.50 224	51.01 210	26.09 225	44.48 221	25.59 232	40.20 230	21.49 223	64.20 145	7.98 236	73.86 127	76.67 166	13.66 228	50.17 222	36.69 230	28.71 231	29.86 230

MVE	28.01 19	35.86 225	43.56 230	26.88 224	22.33 235	19.75 235	30.85 235	23.88 221	49.90 203	10.48 234	43.64 228	61.87 204	48.99 132	47.26 227	42.15 220	24.76 232	40.37 224
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		35.76 226	45.64 223	24.22 226	38.59 226	25.83 231	31.87 234	19.24 226	49.06 208	9.01 235	54.34 215	64.73 200	12.46 230	49.21 223	44.91 217	34.17 230	31.41 227

PMMVS2		34.11 227	48.55 218	17.26 227	25.45 234	20.72 234	35.08 233	16.26 227	58.71 164	4.16 238	59.22 200	78.40 158	3.65 232	57.24 209	38.31 229	18.94 234	27.28 231

GG-mvs-BLEND		31.54 228	46.27 221	14.37 228	0.07 240	48.65 197	42.97 225	0.08 236	44.04 222	1.21 240	39.77 229	57.94 212	0.15 236	48.19 225	42.82 218	41.70 223	42.46 220

test_method		13.28 229	15.83 231	10.30 229	1.05 237	2.18 238	15.40 236	2.23 232	22.43 232	13.84 233	22.00 233	33.14 238	9.78 231	17.80 232	9.93 232	19.50 233	3.31 233

test123		0.53 230	0.60 233	0.46 231	0.22 238	0.25 239	0.33 241	0.13 235	0.66 235	1.37 239	1.10 235	0.00 243	0.43 234	0.68 234	0.61 233	0.26 237	0.88 234

testmvs		0.47 231	0.69 232	0.21 232	0.17 239	0.17 240	0.35 240	0.16 234	0.66 235	0.18 241	1.05 236	0.99 242	0.27 235	0.62 235	0.54 234	0.15 238	0.77 235

uanet_test		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 243	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet-low-res		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 243	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

sosnet		0.00 232	0.00 234	0.00 233	0.00 241	0.00 241	0.00 242	0.00 237	0.00 237	0.00 242	0.00 237	0.00 243	0.00 237	0.00 236	0.00 235	0.00 239	0.00 236

TPM-MVS					72.72 63	70.92 72	80.38 71			66.22 76	58.35 203	78.23 159	48.26 137			83.40 77	81.74 56
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										70.04 55

9.14												83.64 133

SR-MVS					81.31 9			62.63 9				91.11 45

Anonymous202405211			72.22 123		66.19 100	61.09 129	62.23 174	45.87 101	71.25 101		79.33 94	86.16 116	37.36 185	73.54 127	69.84 126	75.45 138	64.32 162

our_test_3					52.72 192	53.66 177	69.11 134

ambc			79.96 61		74.57 55	75.48 49	73.75 109		80.32 53	72.34 38	78.46 96	92.41 29	59.05 76	80.24 85	73.95 96	75.41 139	78.85 71

MTAPA										80.26 8		90.53 61

MTMP										82.07 4		91.00 48

Patchmatch-RL test							2.05 239

tmp_tt				7.47 230	8.89 236	3.32 237	4.35 238	1.14 233	15.58 234	15.76 231	8.50 234	5.90 241	2.00 233	20.02 231	21.51 231	12.70 235

XVS					80.47 20	81.29 12	93.33 3			77.45 19		90.19 65				91.52 11

X-MVStestdata					80.47 20	81.29 12	93.33 3			77.45 19		90.19 65				91.52 11

mPP-MVS					82.97 2							92.12 34

NP-MVS									71.39 100

Patchmtry						37.73 217	45.00 222	44.97 108		52.60 121

DeepMVS_CX						8.52 236	9.75 237	3.19 231	16.70 233	5.02 237	23.06 232	19.33 240	18.69 226	13.75 233		11.34 236	25.07 232

High-resolution multi-view benchmark