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.

MCST-MVS		85.13 22	86.62 23	83.39 17	90.55 14	89.82 16	89.29 21	73.89 22	84.38 30	76.03 29	79.01 31	85.90 21	78.47 12	87.81 16	86.11 33	92.11 1	93.29 22

CSCG		85.28 21	87.68 19	82.49 24	89.95 24	91.99 5	88.82 24	71.20 37	86.41 21	79.63 16	79.26 29	88.36 10	73.94 41	86.64 31	86.67 25	91.40 2	94.41 8

SF-MVS		87.47 8	89.70 8	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 7	91.12 8	88.93 7	78.82 10	87.42 19	86.23 30	91.28 3	93.90 13

SteuartSystems-ACMMP		85.99 16	88.31 16	83.27 20	90.73 10	89.84 14	90.27 14	74.31 15	84.56 29	75.88 30	87.32 14	85.04 24	77.31 23	89.01 7	88.46 3	91.14 4	93.96 12
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		88.00 6	90.50 6	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 14	92.27 5	88.34 11	80.80 5	88.00 14	86.99 18	91.09 5	95.16 6

DeepC-MVS	78.47 2	84.81 25	86.03 28	83.37 18	89.29 32	90.38 11	88.61 26	76.50 1	86.25 22	77.22 23	75.12 40	80.28 45	77.59 21	88.39 10	88.17 6	91.02 6	93.66 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 4	91.18 1	81.17 2	89.55 2	87.93 8	91.01 7	96.21 1

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

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 8	82.09 6	93.85 1	90.75 2	81.25 1	88.62 8	87.59 14	90.96 9	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		87.56 7	90.17 7	84.52 9	91.71 3	90.57 9	90.77 8	75.19 13	90.67 7	80.50 13	86.59 17	88.86 8	78.09 15	89.92 1	89.41 1	90.84 10	95.19 5
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 16	92.36 2	90.69 9	76.15 4	93.08 2	82.75 4	92.19 6	90.71 3	80.45 6	89.27 6	87.91 9	90.82 11	95.84 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
HFP-MVS		86.15 15	87.95 18	84.06 13	90.80 9	89.20 23	89.62 19	74.26 16	87.52 14	80.63 11	86.82 16	84.19 28	78.22 14	87.58 17	87.19 16	90.81 12	93.13 24

ACMMPR		85.52 17	87.53 20	83.17 21	90.13 19	89.27 20	89.30 20	73.97 20	86.89 19	77.14 24	86.09 18	83.18 32	77.74 19	87.42 19	87.20 15	90.77 13	92.63 25

ACMMP		83.42 30	85.27 31	81.26 30	88.47 37	88.49 33	88.31 31	72.09 32	83.42 34	72.77 40	82.65 24	78.22 50	75.18 34	86.24 38	85.76 35	90.74 14	92.13 30
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		84.42 27	86.29 27	82.23 25	90.04 22	88.82 26	89.23 22	71.74 35	82.82 36	74.61 33	84.41 23	82.09 35	77.03 27	87.13 24	86.73 24	90.73 15	92.06 31

DeepC-MVS_fast	78.24 3	84.27 28	85.50 30	82.85 22	90.46 17	89.24 21	87.83 33	74.24 17	84.88 25	76.23 28	75.26 39	81.05 43	77.62 20	88.02 13	87.62 13	90.69 16	92.41 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		86.96 10	89.45 9	84.05 14	90.13 19	89.23 22	89.77 18	74.59 14	89.17 10	80.70 10	89.93 11	89.67 5	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
EC-MVSNet		79.44 48	81.35 45	77.22 52	82.95 63	84.67 62	81.31 60	63.65 92	72.47 67	68.75 57	73.15 47	78.33 49	75.99 32	86.06 40	83.96 48	90.67 17	90.79 41

TSAR-MVS + MP.		86.88 11	89.23 10	84.14 12	89.78 26	88.67 30	90.59 10	73.46 26	88.99 11	80.52 12	91.26 7	88.65 9	79.91 8	86.96 29	86.22 31	90.59 19	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
MVS_0304		81.73 38	83.86 35	79.26 41	86.22 49	89.18 24	86.41 38	67.15 64	75.28 53	70.75 52	74.59 42	83.49 31	74.42 38	87.05 27	86.34 29	90.58 20	91.08 39

APD-MVS		86.84 12	88.91 14	84.41 10	90.66 11	90.10 12	90.78 7	75.64 9	87.38 16	78.72 18	90.68 10	86.82 17	80.15 7	87.13 24	86.45 28	90.51 21	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		84.74 26	86.43 26	82.77 23	89.48 30	88.13 39	88.64 25	73.93 21	84.92 24	76.77 26	81.94 26	83.50 30	77.29 25	86.92 30	86.49 27	90.49 22	93.14 23

XVS					86.63 45	88.68 27	85.00 47			71.81 45		81.92 37				90.47 23

X-MVStestdata					86.63 45	88.68 27	85.00 47			71.81 45		81.92 37				90.47 23

X-MVS		83.23 32	85.20 32	80.92 33	89.71 27	88.68 27	88.21 32	73.60 23	82.57 37	71.81 45	77.07 32	81.92 37	71.72 58	86.98 28	86.86 20	90.47 23	92.36 28

NCCC		85.34 19	86.59 24	83.88 15	91.48 4	88.88 25	89.79 17	75.54 11	86.67 20	77.94 22	76.55 34	84.99 25	78.07 16	88.04 12	87.68 12	90.46 26	93.31 21

CNVR-MVS		86.36 14	88.19 17	84.23 11	91.33 5	89.84 14	90.34 11	75.56 10	87.36 17	78.97 17	81.19 28	86.76 18	78.74 11	89.30 5	88.58 2	90.45 27	94.33 10

MP-MVS		85.50 18	87.40 21	83.28 19	90.65 12	89.51 19	89.16 23	74.11 18	83.70 33	78.06 21	85.54 20	84.89 27	77.31 23	87.40 21	87.14 17	90.41 28	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	75.73 4	82.40 34	82.76 39	81.97 28	88.02 38	89.67 17	86.60 37	71.48 36	81.28 41	78.18 20	64.78 85	77.96 52	77.13 26	87.32 22	86.83 21	90.41 28	91.48 35

ACMMP_NAP		86.52 13	89.01 11	83.62 16	90.28 18	90.09 13	90.32 13	74.05 19	88.32 13	79.74 15	87.04 15	85.59 23	76.97 28	89.35 4	88.44 4	90.35 30	94.27 11

CS-MVS		79.22 51	81.11 48	77.01 54	81.36 75	84.03 65	80.35 66	63.25 96	73.43 64	70.37 53	74.10 46	76.03 58	76.40 30	86.32 37	83.95 49	90.34 31	89.93 47

CDPH-MVS		82.64 33	85.03 33	79.86 38	89.41 31	88.31 36	88.32 30	71.84 34	80.11 43	67.47 64	82.09 25	81.44 41	71.85 56	85.89 41	86.15 32	90.24 32	91.25 37

LGP-MVS_train		79.83 43	81.22 47	78.22 48	86.28 48	85.36 57	86.76 36	69.59 46	77.34 48	65.14 73	75.68 36	70.79 79	71.37 62	84.60 50	84.01 46	90.18 33	90.74 42

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

3Dnovator	73.76 5	79.75 45	80.52 53	78.84 43	84.94 59	87.35 41	84.43 52	65.54 75	78.29 47	73.97 35	63.00 93	75.62 60	74.07 40	85.00 47	85.34 39	90.11 35	89.04 54

DPM-MVS		83.30 31	84.33 34	82.11 26	89.56 28	88.49 33	90.33 12	73.24 27	83.85 32	76.46 27	72.43 50	82.65 33	73.02 48	86.37 35	86.91 19	90.03 36	89.62 51

ETV-MVS		77.32 63	78.81 61	75.58 62	82.24 70	83.64 73	79.98 68	64.02 88	69.64 74	63.90 78	70.89 58	69.94 85	73.41 44	85.39 45	83.91 50	89.92 37	88.31 59

ACMP	73.23 7	79.79 44	80.53 52	78.94 42	85.61 52	85.68 52	85.61 43	69.59 46	77.33 49	71.00 51	74.45 43	69.16 90	71.88 54	83.15 66	83.37 54	89.92 37	90.57 44
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS-test		78.79 57	80.72 50	76.53 57	81.11 80	83.88 68	79.69 75	63.72 91	73.80 61	69.95 55	75.40 38	76.17 56	74.85 35	84.50 53	82.78 59	89.87 39	88.54 58

train_agg		84.86 24	87.21 22	82.11 26	90.59 13	85.47 54	89.81 16	73.55 25	83.95 31	73.30 38	89.84 12	87.23 15	75.61 33	86.47 33	85.46 38	89.78 40	92.06 31

TSAR-MVS + GP.		83.69 29	86.58 25	80.32 35	85.14 54	86.96 44	84.91 50	70.25 41	84.71 28	73.91 36	85.16 21	85.63 22	77.92 17	85.44 42	85.71 36	89.77 41	92.45 26

ACMM	72.26 8	78.86 56	78.13 64	79.71 39	86.89 44	83.40 75	86.02 40	70.50 39	75.28 53	71.49 49	63.01 92	69.26 89	73.57 43	84.11 56	83.98 47	89.76 42	87.84 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TPM-MVS					90.07 21	88.36 35	88.45 29			77.10 25	75.60 37	83.98 29	71.33 63			89.75 43	89.62 51

OPM-MVS		79.68 47	79.28 60	80.15 37	87.99 39	86.77 46	88.52 28	72.72 29	64.55 98	67.65 63	67.87 74	74.33 65	74.31 39	86.37 35	85.25 40	89.73 44	89.81 49
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MSP-MVS		88.09 5	90.84 5	84.88 7	90.00 23	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 2	89.18 6	80.89 4	87.99 15	87.91 9	89.70 45	94.51 7
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
CANet		81.62 39	83.41 36	79.53 40	87.06 42	88.59 31	85.47 45	67.96 57	76.59 51	74.05 34	74.69 41	81.98 36	72.98 49	86.14 39	85.47 37	89.68 46	90.42 45

MVS_111021_HR		80.13 42	81.46 44	78.58 45	85.77 51	85.17 58	83.45 55	69.28 49	74.08 60	70.31 54	74.31 44	75.26 61	73.13 46	86.46 34	85.15 41	89.53 47	89.81 49

IS_MVSNet		73.33 82	77.34 73	68.65 114	81.29 76	83.47 74	74.45 125	63.58 94	65.75 90	48.49 150	67.11 78	70.61 80	54.63 168	84.51 52	83.58 53	89.48 48	86.34 77

DELS-MVS		79.15 54	81.07 49	76.91 55	83.54 61	87.31 42	84.45 51	64.92 80	69.98 69	69.34 56	71.62 54	76.26 55	69.84 68	86.57 32	85.90 34	89.39 49	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
UniMVSNet_NR-MVSNet		70.59 104	72.19 103	68.72 112	77.72 110	80.72 101	73.81 140	69.65 45	61.99 118	43.23 177	60.54 102	57.50 137	58.57 136	79.56 113	81.07 74	89.34 50	83.97 105

casdiffmvs_mvg		77.79 61	79.55 59	75.73 61	81.56 72	84.70 61	82.12 57	64.26 87	74.27 58	67.93 61	70.83 59	74.66 63	69.19 73	83.33 65	81.94 64	89.29 51	87.14 70
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		75.64 71	76.60 78	74.53 71	82.43 68	83.84 69	78.32 90	62.28 119	65.96 88	63.28 82	68.95 66	67.54 100	71.61 60	82.55 71	81.63 68	89.24 52	85.72 81

PHI-MVS		82.36 35	85.89 29	78.24 47	86.40 47	89.52 18	85.52 44	69.52 48	82.38 39	65.67 70	81.35 27	82.36 34	73.07 47	87.31 23	86.76 23	89.24 52	91.56 34

canonicalmvs		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 63	63.18 98	82.90 35	67.34 65	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

MSLP-MVS++		82.09 36	82.66 40	81.42 29	87.03 43	87.22 43	85.82 42	70.04 42	80.30 42	78.66 19	68.67 70	81.04 44	77.81 18	85.19 46	84.88 43	89.19 55	91.31 36

HQP-MVS		81.19 40	83.27 37	78.76 44	87.40 41	85.45 55	86.95 35	70.47 40	81.31 40	66.91 67	79.24 30	76.63 54	71.67 59	84.43 54	83.78 51	89.19 55	92.05 33

EPP-MVSNet		74.00 79	77.41 71	70.02 99	80.53 86	83.91 67	74.99 119	62.68 112	65.06 93	49.77 145	68.68 69	72.09 73	63.06 106	82.49 73	80.73 79	89.12 57	88.91 55

NR-MVSNet		68.79 125	70.56 113	66.71 143	77.48 113	79.54 111	73.52 144	69.20 50	61.20 126	39.76 184	58.52 114	50.11 189	51.37 177	80.26 104	80.71 84	88.97 58	83.59 111

PVSNet_Blended_VisFu		76.57 66	77.90 65	75.02 65	80.56 85	86.58 48	79.24 79	66.18 69	64.81 95	68.18 60	65.61 79	71.45 74	67.05 82	84.16 55	81.80 66	88.90 59	90.92 40

TranMVSNet+NR-MVSNet		69.25 120	70.81 112	67.43 127	77.23 115	79.46 113	73.48 145	69.66 44	60.43 131	39.56 185	58.82 113	53.48 165	55.74 161	79.59 111	81.21 72	88.89 60	82.70 115

QAPM		78.47 58	80.22 56	76.43 58	85.03 56	86.75 47	80.62 65	66.00 72	73.77 62	65.35 72	65.54 81	78.02 51	72.69 50	83.71 59	83.36 55	88.87 61	90.41 46

casdiffmvs		76.76 65	78.46 63	74.77 68	80.32 89	83.73 72	80.65 64	63.24 97	73.58 63	66.11 69	69.39 65	74.09 66	69.49 71	82.52 72	79.35 109	88.84 62	86.52 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		81.77 37	83.10 38	80.21 36	85.93 50	86.45 49	87.72 34	70.98 38	82.54 38	71.53 48	74.23 45	81.49 40	76.31 31	82.85 69	81.87 65	88.79 63	92.26 29

Effi-MVS+		75.28 73	76.20 79	74.20 73	81.15 78	83.24 78	81.11 61	63.13 100	66.37 84	60.27 88	64.30 89	68.88 94	70.93 66	81.56 78	81.69 67	88.61 64	87.35 66

UniMVSNet (Re)		69.53 116	71.90 106	66.76 141	76.42 119	80.93 97	72.59 150	68.03 56	61.75 121	41.68 182	58.34 120	57.23 139	53.27 173	79.53 114	80.62 88	88.57 65	84.90 97

PCF-MVS	73.28 6	79.42 49	80.41 54	78.26 46	84.88 60	88.17 37	86.08 39	69.85 43	75.23 55	68.43 58	68.03 73	78.38 48	71.76 57	81.26 87	80.65 87	88.56 66	91.18 38
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GeoE		74.23 77	74.84 85	73.52 75	80.42 88	81.46 91	79.77 72	61.06 129	67.23 81	63.67 79	59.56 109	68.74 96	67.90 79	80.25 105	79.37 108	88.31 67	87.26 69

test2506		71.72 93	72.95 97	70.29 94	81.49 73	83.27 76	75.74 108	67.59 61	68.19 77	49.81 144	61.15 97	49.73 191	58.82 134	84.76 48	82.94 56	88.27 68	80.63 136

ECVR-MVS		72.20 89	73.91 89	70.20 96	81.49 73	83.27 76	75.74 108	67.59 61	68.19 77	49.31 148	55.77 131	62.00 118	58.82 134	84.76 48	82.94 56	88.27 68	80.41 140

MAR-MVS		79.21 52	80.32 55	77.92 49	87.46 40	88.15 38	83.95 53	67.48 63	74.28 57	68.25 59	64.70 86	77.04 53	72.17 52	85.42 43	85.00 42	88.22 70	87.62 65
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
Fast-Effi-MVS+		73.11 84	73.66 90	72.48 79	77.72 110	80.88 100	78.55 87	58.83 157	65.19 92	60.36 87	59.98 106	62.42 117	71.22 64	81.66 75	80.61 89	88.20 71	84.88 98

ET-MVSNet_ETH3D		72.46 88	74.19 87	70.44 92	62.50 200	81.17 95	79.90 71	62.46 117	64.52 99	57.52 101	71.49 56	59.15 130	72.08 53	78.61 126	81.11 73	88.16 72	83.29 113

OMC-MVS		80.26 41	82.59 41	77.54 50	83.04 62	85.54 53	83.25 56	65.05 79	87.32 18	72.42 41	72.04 52	78.97 47	73.30 45	83.86 57	81.60 69	88.15 73	88.83 56

AdaColmap		79.74 46	78.62 62	81.05 32	89.23 33	86.06 51	84.95 49	71.96 33	79.39 46	75.51 31	63.16 91	68.84 95	76.51 29	83.55 61	82.85 58	88.13 74	86.46 76

test1111		71.56 95	73.44 92	69.38 107	81.16 77	82.95 81	74.99 119	67.68 59	66.89 82	46.33 164	55.19 137	60.91 121	57.99 142	84.59 51	82.70 60	88.12 75	80.85 133

OpenMVS	70.44 10	76.15 69	76.82 77	75.37 64	85.01 57	84.79 60	78.99 83	62.07 120	71.27 68	67.88 62	57.91 122	72.36 72	70.15 67	82.23 74	81.41 70	88.12 75	87.78 64

FA-MVS(training)		73.66 80	74.95 84	72.15 80	78.63 102	80.46 104	78.92 84	54.79 170	69.71 73	65.37 71	62.04 94	66.89 103	67.10 81	80.72 94	79.87 97	88.10 77	84.97 95

UA-Net		74.47 76	77.80 66	70.59 91	85.33 53	85.40 56	73.54 143	65.98 73	60.65 129	56.00 109	72.11 51	79.15 46	54.63 168	83.13 67	82.25 62	88.04 78	81.92 125

DU-MVS		69.63 115	70.91 111	68.13 118	75.99 121	79.54 111	73.81 140	69.20 50	61.20 126	43.23 177	58.52 114	53.50 163	58.57 136	79.22 118	80.45 90	87.97 79	83.97 105

FC-MVSNet-train		72.60 87	75.07 83	69.71 102	81.10 81	78.79 121	73.74 142	65.23 78	66.10 87	53.34 124	70.36 61	63.40 114	56.92 152	81.44 80	80.96 76	87.93 80	84.46 103

IB-MVS	66.94 12	71.21 100	71.66 108	70.68 88	79.18 97	82.83 83	72.61 149	61.77 124	59.66 134	63.44 81	53.26 154	59.65 128	59.16 133	76.78 146	82.11 63	87.90 81	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
PVSNet_BlendedMVS		76.21 67	77.52 69	74.69 69	79.46 95	83.79 70	77.50 97	64.34 85	69.88 70	71.88 43	68.54 71	70.42 81	67.05 82	83.48 62	79.63 100	87.89 82	86.87 72

PVSNet_Blended		76.21 67	77.52 69	74.69 69	79.46 95	83.79 70	77.50 97	64.34 85	69.88 70	71.88 43	68.54 71	70.42 81	67.05 82	83.48 62	79.63 100	87.89 82	86.87 72

DeepPCF-MVS	79.04 1	85.30 20	88.93 12	81.06 31	88.77 36	90.48 10	85.46 46	73.08 28	90.97 6	73.77 37	84.81 22	85.95 20	77.43 22	88.22 11	87.73 11	87.85 84	94.34 9

thisisatest0530		71.48 97	73.01 96	69.70 103	73.83 146	78.62 123	74.53 124	59.12 151	64.13 101	58.63 94	64.60 87	58.63 132	64.27 99	80.28 103	80.17 95	87.82 85	84.64 101

TAPA-MVS	71.42 9	77.69 62	80.05 57	74.94 66	80.68 84	84.52 63	81.36 59	63.14 99	84.77 26	64.82 75	68.72 68	75.91 59	71.86 55	81.62 76	79.55 104	87.80 86	85.24 90
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tttt0517		71.41 98	72.95 97	69.60 104	73.70 148	78.70 122	74.42 128	59.12 151	63.89 105	58.35 97	64.56 88	58.39 134	64.27 99	80.29 102	80.17 95	87.74 87	84.69 100

MVS_Test		75.37 72	77.13 75	73.31 77	79.07 98	81.32 93	79.98 68	60.12 142	69.72 72	64.11 77	70.53 60	73.22 68	68.90 74	80.14 107	79.48 106	87.67 88	85.50 85

DI_MVS_plusplus_trai		75.13 74	76.12 80	73.96 74	78.18 104	81.55 88	80.97 62	62.54 114	68.59 75	65.13 74	61.43 96	74.81 62	69.32 72	81.01 92	79.59 102	87.64 89	85.89 79

MVSTER		72.06 90	74.24 86	69.51 105	70.39 176	75.97 151	76.91 103	57.36 164	64.64 97	61.39 86	68.86 67	63.76 112	63.46 103	81.44 80	79.70 99	87.56 90	85.31 89

TSAR-MVS + ACMM		85.10 23	88.81 15	80.77 34	89.55 29	88.53 32	88.59 27	72.55 30	87.39 15	71.90 42	90.95 9	87.55 13	74.57 36	87.08 26	86.54 26	87.47 91	93.67 17

CLD-MVS		79.35 50	81.23 46	77.16 53	85.01 57	86.92 45	85.87 41	60.89 131	80.07 45	75.35 32	72.96 48	73.21 69	68.43 78	85.41 44	84.63 44	87.41 92	85.44 87
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Effi-MVS+-dtu		71.82 92	71.86 107	71.78 82	78.77 99	80.47 103	78.55 87	61.67 127	60.68 128	55.49 110	58.48 116	65.48 107	68.85 75	76.92 143	75.55 155	87.35 93	85.46 86

WR-MVS		63.03 166	67.40 151	57.92 184	75.14 131	77.60 138	60.56 198	66.10 70	54.11 174	23.88 207	53.94 148	53.58 161	34.50 203	73.93 162	77.71 127	87.35 93	80.94 132

v144192		69.34 119	68.68 137	70.12 97	74.06 142	80.54 102	78.08 93	60.54 135	54.99 167	54.13 117	52.92 161	52.80 174	66.73 89	77.13 141	76.72 144	87.15 95	85.63 82

EPNet		79.08 55	80.62 51	77.28 51	88.90 35	83.17 80	83.65 54	72.41 31	74.41 56	67.15 66	76.78 33	74.37 64	64.43 98	83.70 60	83.69 52	87.15 95	88.19 60
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		67.24 146	66.94 154	67.60 125	78.73 100	81.35 92	73.28 147	59.49 147	46.89 199	51.42 136	43.65 193	53.49 164	55.50 164	81.38 82	80.66 86	87.15 95	81.17 131

v1144		69.93 113	69.36 127	70.61 90	74.89 134	80.93 97	79.11 81	60.64 133	55.97 159	55.31 112	53.85 149	54.14 156	66.54 91	78.10 131	77.44 134	87.14 98	85.09 92

anonymousdsp		65.28 156	67.98 144	62.13 165	58.73 208	73.98 165	67.10 172	50.69 191	48.41 195	47.66 158	54.27 143	52.75 175	61.45 124	76.71 147	80.20 93	87.13 99	89.53 53

PLC	68.99 11	75.68 70	75.31 82	76.12 60	82.94 64	81.26 94	79.94 70	66.10 70	77.15 50	66.86 68	59.13 112	68.53 97	73.73 42	80.38 100	79.04 110	87.13 99	81.68 127
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v10		70.22 109	69.76 122	70.74 86	74.79 135	80.30 108	79.22 80	59.81 145	57.71 145	56.58 107	54.22 147	55.31 149	66.95 85	78.28 129	77.47 133	87.12 101	85.07 93

v1192		69.50 117	68.83 133	70.29 94	74.49 138	80.92 99	78.55 87	60.54 135	55.04 165	54.21 115	52.79 163	52.33 176	66.92 86	77.88 133	77.35 137	87.04 102	85.51 84

v1921920		69.03 122	68.32 141	69.86 100	74.03 143	80.37 105	77.55 95	60.25 139	54.62 169	53.59 123	52.36 167	51.50 182	66.75 88	77.17 140	76.69 146	86.96 103	85.56 83

v2v482		70.05 112	69.46 126	70.74 86	74.62 137	80.32 107	79.00 82	60.62 134	57.41 147	56.89 104	55.43 136	55.14 151	66.39 93	77.25 139	77.14 139	86.90 104	83.57 112

Vis-MVSNet		72.77 86	77.20 74	67.59 126	74.19 141	84.01 66	76.61 107	61.69 125	60.62 130	50.61 140	70.25 62	71.31 77	55.57 163	83.85 58	82.28 61	86.90 104	88.08 61
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PEN-MVS		62.96 167	65.77 161	59.70 177	73.98 144	75.45 155	63.39 191	67.61 60	52.49 180	25.49 206	53.39 151	49.12 193	40.85 196	71.94 174	77.26 138	86.86 106	80.72 135

v8		70.23 108	69.86 120	70.67 89	74.69 136	79.82 110	78.79 85	59.18 150	58.80 138	58.20 98	55.00 138	57.33 138	66.31 94	77.51 136	76.71 145	86.82 107	83.88 108

ACMH+	66.54 13	71.36 99	70.09 117	72.85 78	82.59 66	81.13 96	78.56 86	68.04 55	61.55 122	52.52 131	51.50 171	54.14 156	68.56 77	78.85 123	79.50 105	86.82 107	83.94 107

v1240		68.64 127	67.89 147	69.51 105	73.89 145	80.26 109	76.73 105	59.97 144	53.43 177	53.08 126	51.82 170	50.84 185	66.62 90	76.79 145	76.77 143	86.78 109	85.34 88

DCV-MVSNet		73.65 81	75.78 81	71.16 85	80.19 90	79.27 115	77.45 99	61.68 126	66.73 83	58.72 93	65.31 82	69.96 84	62.19 111	81.29 86	80.97 75	86.74 110	86.91 71

GBi-Net		70.78 101	73.37 94	67.76 119	72.95 153	78.00 128	75.15 114	62.72 107	64.13 101	51.44 133	58.37 117	69.02 91	57.59 144	81.33 83	80.72 80	86.70 111	82.02 119

test1		70.78 101	73.37 94	67.76 119	72.95 153	78.00 128	75.15 114	62.72 107	64.13 101	51.44 133	58.37 117	69.02 91	57.59 144	81.33 83	80.72 80	86.70 111	82.02 119

FMVSNet2		70.39 107	72.67 101	67.72 122	72.95 153	78.00 128	75.15 114	62.69 111	63.29 109	51.25 137	55.64 132	68.49 98	57.59 144	80.91 93	80.35 92	86.70 111	82.02 119

v7n		67.05 149	66.94 154	67.17 133	72.35 158	78.97 116	73.26 148	58.88 156	51.16 188	50.90 138	48.21 184	50.11 189	60.96 125	77.70 134	77.38 135	86.68 114	85.05 94

WR-MVS_H		61.83 181	65.87 160	57.12 187	71.72 163	76.87 142	61.45 196	66.19 68	51.97 185	22.92 211	53.13 158	52.30 178	33.80 204	71.03 181	75.00 158	86.65 115	80.78 134

MSDG		71.52 96	69.87 119	73.44 76	82.21 71	79.35 114	79.52 76	64.59 82	66.15 86	61.87 83	53.21 156	56.09 146	65.85 96	78.94 122	78.50 117	86.60 116	76.85 165

FMVSNet3		70.49 105	72.90 99	67.67 124	72.88 156	77.98 131	74.96 122	62.72 107	64.13 101	51.44 133	58.37 117	69.02 91	57.43 147	79.43 116	79.57 103	86.59 117	81.81 126

MVS_111021_LR		78.13 60	79.85 58	76.13 59	81.12 79	81.50 90	80.28 67	65.25 77	76.09 52	71.32 50	76.49 35	72.87 71	72.21 51	82.79 70	81.29 71	86.59 117	87.91 62

DTE-MVSNet		61.85 179	64.96 170	58.22 183	74.32 140	74.39 164	61.01 197	67.85 58	51.76 187	21.91 214	53.28 153	48.17 194	37.74 200	72.22 171	76.44 148	86.52 119	78.49 154

baseline2		69.69 114	70.27 116	69.01 110	75.72 126	77.13 141	73.82 139	58.94 155	61.35 124	57.09 103	61.68 95	57.17 140	61.99 115	78.10 131	76.58 147	86.48 120	79.85 144

thisisatest0515		67.40 144	68.78 134	65.80 147	70.02 178	75.24 158	69.36 162	57.37 163	54.94 168	53.67 122	55.53 135	54.85 152	58.00 141	78.19 130	78.91 113	86.39 121	83.78 109

FMVSNet1		68.84 124	70.47 115	66.94 138	71.35 170	77.68 136	74.71 123	62.35 118	56.93 150	49.94 143	50.01 177	64.59 109	57.07 149	81.33 83	80.72 80	86.25 122	82.00 122

UGNet		72.78 85	77.67 67	67.07 136	71.65 165	83.24 78	75.20 113	63.62 93	64.93 94	56.72 105	71.82 53	73.30 67	49.02 181	81.02 91	80.70 85	86.22 123	88.67 57
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
Anonymous20231211		71.90 91	72.48 102	71.21 84	80.14 91	81.53 89	76.92 102	62.89 103	64.46 100	58.94 90	43.80 192	70.98 78	62.22 110	80.70 95	80.19 94	86.18 124	85.73 80

tfpn200view9		68.11 130	68.72 136	67.40 128	77.83 108	78.93 117	74.28 130	62.81 104	56.64 152	46.82 160	52.65 164	53.47 166	56.59 153	80.41 97	78.43 118	86.11 125	80.52 138

CANet_DTU		73.29 83	76.96 76	69.00 111	77.04 116	82.06 86	79.49 77	56.30 167	67.85 79	53.29 125	71.12 57	70.37 83	61.81 120	81.59 77	80.96 76	86.09 126	84.73 99

CP-MVSNet		62.68 169	65.49 164	59.40 180	71.84 161	75.34 156	62.87 193	67.04 65	52.64 179	27.19 204	53.38 152	48.15 195	41.40 194	71.26 177	75.68 153	86.07 127	82.00 122

ACMH	65.37 14	70.71 103	70.00 118	71.54 83	82.51 67	82.47 85	77.78 94	68.13 54	56.19 157	46.06 167	54.30 141	51.20 183	68.68 76	80.66 96	80.72 80	86.07 127	84.45 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres600view7		67.68 138	68.43 140	66.80 140	77.90 105	78.86 119	73.84 138	62.75 105	56.07 158	44.70 175	52.85 162	52.81 173	55.58 162	80.41 97	77.77 126	86.05 129	80.28 141

thres200		67.98 132	68.55 139	67.30 131	77.89 107	78.86 119	74.18 134	62.75 105	56.35 155	46.48 163	52.98 160	53.54 162	56.46 154	80.41 97	77.97 124	86.05 129	79.78 146

CNLPA		77.20 64	77.54 68	76.80 56	82.63 65	84.31 64	79.77 72	64.64 81	85.17 23	73.18 39	56.37 129	69.81 86	74.53 37	81.12 90	78.69 115	86.04 131	87.29 68

TSAR-MVS + COLMAP		78.34 59	81.64 43	74.48 72	80.13 92	85.01 59	81.73 58	65.93 74	84.75 27	61.68 84	85.79 19	66.27 105	71.39 61	82.91 68	80.78 78	86.01 132	85.98 78

LS3D		74.08 78	73.39 93	74.88 67	85.05 55	82.62 84	79.71 74	68.66 52	72.82 65	58.80 92	57.61 123	61.31 120	71.07 65	80.32 101	78.87 114	86.00 133	80.18 142

Anonymous202405211			72.16 105		80.85 83	81.85 87	76.88 104	65.40 76	62.89 113		46.35 188	67.99 99	62.05 113	81.15 89	80.38 91	85.97 134	84.50 102

PS-CasMVS		62.38 175	65.06 167	59.25 181	71.73 162	75.21 160	62.77 194	66.99 66	51.94 186	26.96 205	52.00 169	47.52 198	41.06 195	71.16 180	75.60 154	85.97 134	81.97 124

thres400		67.95 133	68.62 138	67.17 133	77.90 105	78.59 124	74.27 131	62.72 107	56.34 156	45.77 169	53.00 159	53.35 169	56.46 154	80.21 106	78.43 118	85.91 136	80.43 139

thres100view900		67.60 142	68.02 143	67.12 135	77.83 108	77.75 135	73.90 137	62.52 115	56.64 152	46.82 160	52.65 164	53.47 166	55.92 158	78.77 124	77.62 129	85.72 137	79.23 150

Vis-MVSNet (Re-imp)		67.83 136	73.52 91	61.19 169	78.37 103	76.72 145	66.80 175	62.96 101	65.50 91	34.17 196	67.19 77	69.68 87	39.20 199	79.39 117	79.44 107	85.68 138	76.73 166

baseline1		70.10 111	72.17 104	67.69 123	79.74 93	76.80 143	73.91 136	64.38 84	62.74 114	48.30 152	64.94 83	64.08 111	54.17 170	81.46 79	78.92 112	85.66 139	76.22 167

V42		68.76 126	69.63 123	67.74 121	64.93 196	78.01 127	78.30 91	56.48 166	58.65 139	56.30 108	54.26 145	57.03 141	64.85 97	77.47 137	77.01 141	85.60 140	84.96 96

TransMVSNet (Re)		64.74 159	65.66 162	63.66 160	77.40 114	75.33 157	69.86 158	62.67 113	47.63 197	41.21 183	50.01 177	52.33 176	45.31 187	79.57 112	77.69 128	85.49 141	77.07 164

IterMVS-LS		71.69 94	72.82 100	70.37 93	77.54 112	76.34 148	75.13 117	60.46 137	61.53 123	57.57 100	64.89 84	67.33 101	66.04 95	77.09 142	77.37 136	85.48 142	85.18 91
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_ETH3D		67.18 148	67.03 153	67.36 129	74.44 139	78.12 126	74.07 135	66.38 67	52.22 182	46.87 159	48.64 182	51.84 180	56.96 150	77.29 138	78.53 116	85.42 143	82.59 116

Baseline_NR-MVSNet		67.53 143	68.77 135	66.09 146	75.99 121	74.75 162	72.43 151	68.41 53	61.33 125	38.33 189	51.31 172	54.13 158	56.03 157	79.22 118	78.19 121	85.37 144	82.45 117

Fast-Effi-MVS+-dtu		68.34 128	69.47 125	67.01 137	75.15 130	77.97 133	77.12 101	55.40 169	57.87 140	46.68 162	56.17 130	60.39 122	62.36 109	76.32 150	76.25 151	85.35 145	81.34 129

diffmvs		74.86 75	77.37 72	71.93 81	75.62 127	80.35 106	79.42 78	60.15 141	72.81 66	64.63 76	71.51 55	73.11 70	66.53 92	79.02 121	77.98 123	85.25 146	86.83 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GA-MVS		68.14 129	69.17 130	66.93 139	73.77 147	78.50 125	74.45 125	58.28 159	55.11 164	48.44 151	60.08 104	53.99 159	61.50 122	78.43 128	77.57 130	85.13 147	80.54 137

v148		67.85 135	67.53 148	68.23 116	73.25 151	77.57 139	74.26 132	57.36 164	55.70 160	57.45 102	53.53 150	55.42 148	61.96 116	75.23 154	73.92 163	85.08 148	81.32 130

HyFIR lowres test		69.47 118	68.94 132	70.09 98	76.77 118	82.93 82	76.63 106	60.17 140	59.00 137	54.03 118	40.54 201	65.23 108	67.89 80	76.54 149	78.30 120	85.03 149	80.07 143

gg-mvs-nofinetune		62.55 170	65.05 168	59.62 178	78.72 101	77.61 137	70.83 157	53.63 171	39.71 211	22.04 213	36.36 205	64.32 110	47.53 183	81.16 88	79.03 111	85.00 150	77.17 162

COLMAP_ROB	62.73 15	67.66 139	66.76 156	68.70 113	80.49 87	77.98 131	75.29 112	62.95 102	63.62 107	49.96 142	47.32 187	50.72 186	58.57 136	76.87 144	75.50 156	84.94 151	75.33 176
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpnnormal		64.27 162	63.64 178	65.02 150	75.84 125	75.61 154	71.24 156	62.52 115	47.79 196	42.97 179	42.65 195	44.49 205	52.66 175	78.77 124	76.86 142	84.88 152	79.29 149

pm-mvs1		65.62 153	67.42 150	63.53 161	73.66 149	76.39 147	69.66 159	60.87 132	49.73 192	43.97 176	51.24 173	57.00 142	48.16 182	79.89 108	77.84 125	84.85 153	79.82 145

gm-plane-assit		57.00 194	57.62 201	56.28 190	76.10 120	62.43 207	47.62 215	46.57 205	33.84 215	23.24 209	37.52 202	40.19 212	59.61 132	79.81 109	77.55 131	84.55 154	72.03 186

USDC		67.36 145	67.90 146	66.74 142	71.72 163	75.23 159	71.58 153	60.28 138	67.45 80	50.54 141	60.93 98	45.20 204	62.08 112	76.56 148	74.50 161	84.25 155	75.38 175

dmvs_re		67.22 147	67.92 145	66.40 144	75.94 124	70.55 178	74.97 121	63.87 89	57.07 149	44.75 173	54.29 142	56.72 143	54.65 167	79.53 114	77.51 132	84.20 156	79.78 146

MS-PatchMatch		70.17 110	70.49 114	69.79 101	80.98 82	77.97 133	77.51 96	58.95 154	62.33 116	55.22 113	53.14 157	65.90 106	62.03 114	79.08 120	77.11 140	84.08 157	77.91 157

TDRefinement		66.09 152	65.03 169	67.31 130	69.73 180	76.75 144	75.33 110	64.55 83	60.28 132	49.72 146	45.63 190	42.83 207	60.46 130	75.75 151	75.95 152	84.08 157	78.04 156

pmmvs4		67.89 134	67.39 152	68.48 115	71.60 167	73.57 166	74.45 125	60.98 130	64.65 96	57.97 99	54.95 139	51.73 181	61.88 117	73.78 163	75.11 157	83.99 159	77.91 157

pmmvs5		62.37 176	64.04 175	60.42 172	65.03 194	71.67 173	67.17 171	52.70 181	50.30 189	44.80 172	54.23 146	51.19 184	49.37 180	72.88 166	73.48 167	83.45 160	74.55 179

pmmvs-eth3d		63.52 165	62.44 187	64.77 152	66.82 191	70.12 179	69.41 161	59.48 148	54.34 173	52.71 127	46.24 189	44.35 206	56.93 151	72.37 167	73.77 165	83.30 161	75.91 169

pmmvs6		62.41 173	62.88 181	61.87 166	71.38 169	75.18 161	67.76 168	59.45 149	41.64 207	42.52 181	37.33 203	52.91 172	46.87 184	77.67 135	76.26 150	83.23 162	79.18 151

CDS-MVSNet		67.65 140	69.83 121	65.09 149	75.39 129	76.55 146	74.42 128	63.75 90	53.55 175	49.37 147	59.41 110	62.45 116	44.44 188	79.71 110	79.82 98	83.17 163	77.36 161
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PMMVS		65.06 157	69.17 130	60.26 174	55.25 214	63.43 201	66.71 176	43.01 209	62.41 115	50.64 139	69.44 64	67.04 102	63.29 104	74.36 160	73.54 166	82.68 164	73.99 183

SixPastTwentyTwo		61.84 180	62.45 186	61.12 170	69.20 184	72.20 170	62.03 195	57.40 162	46.54 200	38.03 191	57.14 127	41.72 209	58.12 140	69.67 191	71.58 174	81.94 165	78.30 155

IterMVS		66.36 151	68.30 142	64.10 156	69.48 183	74.61 163	73.41 146	50.79 190	57.30 148	48.28 153	60.64 101	59.92 127	60.85 129	74.14 161	72.66 170	81.80 166	78.82 153
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchMatch-RL		67.78 137	66.65 157	69.10 109	73.01 152	72.69 169	68.49 165	61.85 123	62.93 112	60.20 89	56.83 128	50.42 187	69.52 70	75.62 152	74.46 162	81.51 167	73.62 184

TinyColmap		62.84 168	61.03 193	64.96 151	69.61 181	71.69 172	68.48 166	59.76 146	55.41 161	47.69 157	47.33 186	34.20 216	62.76 108	74.52 158	72.59 171	81.44 168	71.47 187

EPNet_dtu		68.08 131	71.00 110	64.67 153	79.64 94	68.62 185	75.05 118	63.30 95	66.36 85	45.27 171	67.40 76	66.84 104	43.64 190	75.37 153	74.98 159	81.15 169	77.44 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		64.83 158	65.54 163	64.01 158	70.64 175	69.41 180	65.97 180	52.74 179	57.81 142	52.65 128	54.27 143	56.31 145	60.92 126	72.20 172	73.09 168	81.12 170	75.69 172

RPMNet		61.71 183	62.88 181	60.34 173	69.51 182	69.41 180	63.48 190	49.23 195	57.81 142	45.64 170	50.51 175	50.12 188	53.13 174	68.17 198	68.49 189	81.07 171	75.62 174

test-mter		60.84 185	64.62 172	56.42 189	55.99 212	64.18 196	65.39 182	34.23 214	54.39 172	46.21 166	57.40 126	59.49 129	55.86 159	71.02 182	69.65 180	80.87 172	76.20 168

test-LLR		64.42 160	64.36 173	64.49 154	75.02 132	63.93 198	66.61 177	61.96 121	54.41 170	47.77 155	57.46 124	60.25 123	55.20 165	70.80 183	69.33 181	80.40 173	74.38 180

TESTMET0.1,1		61.10 184	64.36 173	57.29 186	57.53 209	63.93 198	66.61 177	36.22 213	54.41 170	47.77 155	57.46 124	60.25 123	55.20 165	70.80 183	69.33 181	80.40 173	74.38 180

CostFormer		68.92 123	69.58 124	68.15 117	75.98 123	76.17 150	78.22 92	51.86 184	65.80 89	61.56 85	63.57 90	62.83 115	61.85 118	70.40 189	68.67 186	79.42 175	79.62 148

CVMVSNet		62.55 170	65.89 159	58.64 182	66.95 189	69.15 182	66.49 179	56.29 168	52.46 181	32.70 197	59.27 111	58.21 136	50.09 179	71.77 175	71.39 175	79.31 176	78.99 152

CHOSEN 1792x2688		69.20 121	69.26 128	69.13 108	76.86 117	78.93 117	77.27 100	60.12 142	61.86 120	54.42 114	42.54 196	61.61 119	66.91 87	78.55 127	78.14 122	79.23 177	83.23 114

PM-MVS		60.48 186	60.94 194	59.94 175	58.85 207	66.83 191	64.27 188	51.39 187	55.03 166	48.03 154	50.00 179	40.79 211	58.26 139	69.20 194	67.13 196	78.84 178	77.60 159

baseline		70.45 106	74.09 88	66.20 145	70.95 173	75.67 152	74.26 132	53.57 172	68.33 76	58.42 95	69.87 63	71.45 74	61.55 121	74.84 157	74.76 160	78.42 179	83.72 110

PatchT		61.97 178	64.04 175	59.55 179	60.49 204	67.40 188	56.54 205	48.65 199	56.69 151	52.65 128	51.10 174	52.14 179	60.92 126	72.20 172	73.09 168	78.03 180	75.69 172

RPSCF		67.64 141	71.25 109	63.43 162	61.86 202	70.73 176	67.26 170	50.86 189	74.20 59	58.91 91	67.49 75	69.33 88	64.10 101	71.41 176	68.45 190	77.61 181	77.17 162

MDTV_nov1_ep13_2view		60.16 187	60.51 195	59.75 176	65.39 193	69.05 183	68.00 167	48.29 201	51.99 183	45.95 168	48.01 185	49.64 192	53.39 172	68.83 195	66.52 197	77.47 182	69.55 193

MDTV_nov1_ep13		64.37 161	65.24 165	63.37 163	68.94 185	70.81 175	72.40 152	50.29 193	60.10 133	53.91 120	60.07 105	59.15 130	57.21 148	69.43 193	67.30 193	77.47 182	69.78 192

LTVRE_ROB	59.44 16	61.82 182	62.64 184	60.87 171	72.83 157	77.19 140	64.37 187	58.97 153	33.56 216	28.00 203	52.59 166	42.21 208	63.93 102	74.52 158	76.28 149	77.15 184	82.13 118
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
IterMVS-SCA-FT		66.89 150	69.22 129	64.17 155	71.30 171	75.64 153	71.33 154	53.17 176	57.63 146	49.08 149	60.72 100	60.05 126	63.09 105	74.99 156	73.92 163	77.07 185	81.57 128

SCA		65.40 155	66.58 158	64.02 157	70.65 174	73.37 167	67.35 169	53.46 174	63.66 106	54.14 116	60.84 99	60.20 125	61.50 122	69.96 190	68.14 191	77.01 186	69.91 190

MDA-MVSNet-bldmvs		53.37 203	53.01 206	53.79 198	43.67 218	67.95 187	59.69 201	57.92 160	43.69 203	32.41 198	41.47 197	27.89 221	52.38 176	56.97 213	65.99 199	76.68 187	67.13 197

MVS-HIRNet		54.41 200	52.10 207	57.11 188	58.99 206	56.10 213	49.68 213	49.10 196	46.18 201	52.15 132	33.18 209	46.11 201	56.10 156	63.19 206	59.70 209	76.64 188	60.25 209

dps		64.00 164	62.99 180	65.18 148	73.29 150	72.07 171	68.98 164	53.07 177	57.74 144	58.41 96	55.55 134	47.74 197	60.89 128	69.53 192	67.14 195	76.44 189	71.19 188

test0.0.03 1		58.80 190	61.58 191	55.56 192	75.02 132	68.45 186	59.58 202	61.96 121	52.74 178	29.57 200	49.75 180	54.56 154	31.46 206	71.19 178	69.77 179	75.75 190	64.57 201

EU-MVSNet		54.63 199	58.69 197	49.90 203	56.99 210	62.70 206	56.41 206	50.64 192	45.95 202	23.14 210	50.42 176	46.51 200	36.63 201	65.51 201	64.85 200	75.57 191	74.91 177

PatchmatchNet		64.21 163	64.65 171	63.69 159	71.29 172	68.66 184	69.63 160	51.70 186	63.04 110	53.77 121	59.83 108	58.34 135	60.23 131	68.54 196	66.06 198	75.56 192	68.08 196
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous20231206		56.36 196	57.80 200	54.67 195	70.08 177	66.39 192	60.46 199	57.54 161	49.50 194	29.30 201	33.86 208	46.64 199	35.18 202	70.44 187	68.88 185	75.47 193	68.88 195

CMPMVS	47.78 17	62.49 172	62.52 185	62.46 164	70.01 179	70.66 177	62.97 192	51.84 185	51.98 184	56.71 106	42.87 194	53.62 160	57.80 143	72.23 170	70.37 178	75.45 194	75.91 169
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet		58.52 192	61.34 192	55.22 193	60.76 203	67.01 190	66.81 174	49.02 197	56.43 154	38.90 187	40.59 200	54.54 155	40.57 197	73.16 165	71.65 173	75.30 195	66.00 199

TAMVS		59.58 189	62.81 183	55.81 191	66.03 192	65.64 195	63.86 189	48.74 198	49.95 191	37.07 193	54.77 140	58.54 133	44.44 188	72.29 169	71.79 172	74.70 196	66.66 198

tpm cat1		65.41 154	63.81 177	67.28 132	75.61 128	72.88 168	75.32 111	52.85 178	62.97 111	63.66 80	53.24 155	53.29 171	61.83 119	65.54 200	64.14 202	74.43 197	74.60 178

test20.03		53.93 202	56.28 203	51.19 201	72.19 160	65.83 193	53.20 209	61.08 128	42.74 205	22.08 212	37.07 204	45.76 203	24.29 214	70.44 187	69.04 183	74.31 198	63.05 205

FMVSNet5		57.24 193	60.02 196	53.99 197	56.45 211	62.74 205	65.27 183	47.03 204	55.14 163	39.55 186	40.88 198	53.42 168	41.83 191	72.35 168	71.10 177	73.79 199	64.50 202

testgi		54.39 201	57.86 199	50.35 202	71.59 168	67.24 189	54.95 207	53.25 175	43.36 204	23.78 208	44.64 191	47.87 196	24.96 211	70.45 186	68.66 187	73.60 200	62.78 206

MIMVSNet1		49.27 205	53.25 205	44.62 207	44.61 216	61.52 208	53.61 208	52.18 182	41.62 208	18.68 217	28.14 214	41.58 210	25.50 209	68.46 197	69.04 183	73.15 201	62.37 207

pmmvs3		47.65 206	49.08 211	45.99 206	44.61 216	54.79 214	50.04 211	31.95 217	33.91 214	29.90 199	30.37 210	33.53 217	46.31 185	63.50 204	63.67 203	73.14 202	63.77 204

FC-MVSNet-test		56.90 195	65.20 166	47.21 205	66.98 188	63.20 203	49.11 214	58.60 158	59.38 136	11.50 221	65.60 80	56.68 144	24.66 213	71.17 179	71.36 176	72.38 203	69.02 194

GG-mvs-BLEND		46.86 209	67.51 149	22.75 214	0.05 226	76.21 149	64.69 185	0.04 222	61.90 119	0.09 227	55.57 133	71.32 76	0.08 222	70.54 185	67.19 194	71.58 204	69.86 191

ambc			53.42 204		64.99 195	63.36 202	49.96 212		47.07 198	37.12 192	28.97 212	16.36 224	41.82 192	75.10 155	67.34 192	71.55 205	75.72 171

tpmrst		62.00 177	62.35 188	61.58 167	71.62 166	64.14 197	69.07 163	48.22 203	62.21 117	53.93 119	58.26 121	55.30 150	55.81 160	63.22 205	62.62 204	70.85 206	70.70 189

tpm		62.41 173	63.15 179	61.55 168	72.24 159	63.79 200	71.31 155	46.12 207	57.82 141	55.33 111	59.90 107	54.74 153	53.63 171	67.24 199	64.29 201	70.65 207	74.25 182

FPMVS		51.87 204	50.00 209	54.07 196	66.83 190	57.25 211	60.25 200	50.91 188	50.25 190	34.36 195	36.04 206	32.02 218	41.49 193	58.98 211	56.07 210	70.56 208	59.36 211

EPMVS		60.00 188	61.97 189	57.71 185	68.46 186	63.17 204	64.54 186	48.23 202	63.30 108	44.72 174	60.19 103	56.05 147	50.85 178	65.27 203	62.02 205	69.44 209	63.81 203

PMVS	39.38 18	46.06 210	43.30 212	49.28 204	62.93 198	38.75 218	41.88 217	53.50 173	33.33 217	35.46 194	28.90 213	31.01 219	33.04 205	58.61 212	54.63 213	68.86 210	57.88 212
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmnet_mix02		55.30 198	57.01 202	53.30 200	64.14 197	59.09 209	58.39 204	50.24 194	53.47 176	38.68 188	49.75 180	45.86 202	40.14 198	65.38 202	60.22 207	68.19 211	65.33 200

CHOSEN 280x420		58.70 191	61.88 190	54.98 194	55.45 213	50.55 216	64.92 184	40.36 210	55.21 162	38.13 190	48.31 183	63.76 112	63.03 107	73.73 164	68.58 188	68.00 212	73.04 185

new-patchmatchnet		46.97 208	49.47 210	44.05 209	62.82 199	56.55 212	45.35 216	52.01 183	42.47 206	17.04 219	35.73 207	35.21 215	21.84 217	61.27 208	54.83 212	65.26 213	60.26 208

ADS-MVSNet		55.94 197	58.01 198	53.54 199	62.48 201	58.48 210	59.12 203	46.20 206	59.65 135	42.88 180	52.34 168	53.31 170	46.31 185	62.00 207	60.02 208	64.23 214	60.24 210

N_pmnet		47.35 207	50.13 208	44.11 208	59.98 205	51.64 215	51.86 210	44.80 208	49.58 193	20.76 215	40.65 199	40.05 213	29.64 207	59.84 209	55.15 211	57.63 215	54.00 213

new_pmnet		38.40 211	42.64 213	33.44 211	37.54 221	45.00 217	36.60 218	32.72 216	40.27 209	12.72 220	29.89 211	28.90 220	24.78 212	53.17 214	52.90 214	56.31 216	48.34 214

Gipuma		36.38 212	35.80 214	37.07 210	45.76 215	33.90 219	29.81 219	48.47 200	39.91 210	18.02 218	8.00 222	8.14 226	25.14 210	59.29 210	61.02 206	55.19 217	40.31 215
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		25.60 213	29.75 215	20.76 215	28.00 222	30.93 220	23.10 221	29.18 218	23.14 219	1.46 226	18.23 218	16.54 223	5.08 220	40.22 215	41.40 216	37.76 218	37.79 217

test_method		22.26 214	25.94 216	17.95 216	3.24 225	7.17 225	23.83 220	7.27 220	37.35 213	20.44 216	21.87 217	39.16 214	18.67 218	34.56 216	20.84 220	34.28 219	20.64 221

E-PMN		21.77 215	18.24 218	25.89 212	40.22 219	19.58 222	12.46 224	39.87 211	18.68 221	6.71 223	9.57 219	4.31 229	22.36 216	19.89 220	27.28 218	33.73 220	28.34 219

EMVS		20.98 216	17.15 219	25.44 213	39.51 220	19.37 223	12.66 223	39.59 212	19.10 220	6.62 224	9.27 220	4.40 228	22.43 215	17.99 221	24.40 219	31.81 221	25.53 220

tmp_tt				14.50 218	14.68 223	7.17 225	10.46 226	2.21 221	37.73 212	28.71 202	25.26 215	16.98 222	4.37 221	31.49 217	29.77 217	26.56 222

MVE	19.12 19	20.47 217	23.27 217	17.20 217	12.66 224	25.41 221	10.52 225	34.14 215	14.79 222	6.53 225	8.79 221	4.68 227	16.64 219	29.49 218	41.63 215	22.73 223	38.11 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						18.74 224	18.55 222	8.02 219	26.96 218	7.33 222	23.81 216	13.05 225	25.99 208	25.17 219		22.45 224	36.25 218

testmvs		0.09 218	0.15 220	0.02 219	0.01 227	0.02 227	0.05 228	0.01 223	0.11 223	0.01 228	0.26 224	0.01 230	0.06 224	0.10 222	0.10 221	0.01 225	0.43 223

test123		0.09 218	0.14 221	0.02 219	0.00 228	0.02 227	0.02 229	0.01 223	0.09 224	0.00 229	0.30 223	0.00 231	0.08 222	0.03 223	0.09 222	0.01 225	0.45 222

uanet_test		0.00 220	0.00 222	0.00 221	0.00 228	0.00 229	0.00 230	0.00 225	0.00 225	0.00 229	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 221	0.00 228	0.00 229	0.00 230	0.00 225	0.00 225	0.00 229	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 221	0.00 228	0.00 229	0.00 230	0.00 225	0.00 225	0.00 229	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

RE-MVS-def										46.24 165

9.14												86.88 16

SR-MVS					88.99 34			73.57 24				87.54 14

our_test_3					67.93 187	70.99 174	66.89 173

MTAPA										83.48 1		86.45 19

MTMP										82.66 5		84.91 26

Patchmatch-RL test							2.85 227

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 44

Patchmtry						65.80 194	65.97 180	52.74 179		52.65 128

High-resolution multi-view benchmark