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 23	86.62 25	83.39 18	90.55 14	89.82 18	89.29 22	73.89 23	84.38 31	76.03 31	79.01 33	85.90 22	78.47 13	87.81 18	86.11 34	92.11 1	93.29 23

CSCG		85.28 22	87.68 20	82.49 25	89.95 25	91.99 5	88.82 25	71.20 38	86.41 22	79.63 17	79.26 31	88.36 11	73.94 42	86.64 32	86.67 27	91.40 2	94.41 9

SF-MVS		87.47 9	89.70 9	84.86 8	91.26 6	91.10 9	90.90 7	75.65 8	89.21 10	81.25 7	91.12 9	88.93 8	78.82 11	87.42 21	86.23 31	91.28 3	93.90 14

SteuartSystems-ACMMP		85.99 17	88.31 17	83.27 21	90.73 10	89.84 16	90.27 15	74.31 16	84.56 30	75.88 32	87.32 15	85.04 25	77.31 24	89.01 7	88.46 3	91.14 4	93.96 13
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		88.00 7	90.50 7	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 15	92.27 6	88.34 12	80.80 6	88.00 15	86.99 19	91.09 5	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepC-MVS	78.47 2	84.81 26	86.03 30	83.37 19	89.29 33	90.38 13	88.61 27	76.50 1	86.25 23	77.22 25	75.12 42	80.28 46	77.59 22	88.39 10	88.17 6	91.02 6	93.66 19
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 5	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 4	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 9	82.09 6	93.85 2	90.75 2	81.25 1	88.62 8	87.59 15	90.96 9	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ME-MVS		88.06 6	90.84 5	84.81 9	90.52 16	91.48 8	91.13 6	75.02 14	90.82 7	80.35 14	94.25 1	90.29 5	80.86 5	87.82 17	86.80 23	90.95 10	94.45 8

MGCNet		84.63 28	87.25 23	81.59 30	88.58 38	90.50 11	87.82 35	69.16 53	83.82 34	78.46 21	82.32 26	84.97 27	74.56 38	88.16 12	87.72 12	90.94 11	93.24 24

SMA-MVS		87.56 8	90.17 8	84.52 10	91.71 3	90.57 10	90.77 9	75.19 13	90.67 8	80.50 13	86.59 18	88.86 9	78.09 16	89.92 1	89.41 1	90.84 12	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 17	92.36 2	90.69 10	76.15 4	93.08 2	82.75 4	92.19 7	90.71 3	80.45 7	89.27 6	87.91 9	90.82 13	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 16	87.95 19	84.06 14	90.80 9	89.20 25	89.62 20	74.26 17	87.52 15	80.63 11	86.82 17	84.19 30	78.22 15	87.58 19	87.19 17	90.81 14	93.13 26

ACMMPR		85.52 18	87.53 21	83.17 22	90.13 20	89.27 22	89.30 21	73.97 21	86.89 20	77.14 26	86.09 19	83.18 33	77.74 20	87.42 21	87.20 16	90.77 15	92.63 27

ACMMP		83.42 32	85.27 33	81.26 32	88.47 39	88.49 34	88.31 32	72.09 33	83.42 36	72.77 42	82.65 25	78.22 51	75.18 35	86.24 39	85.76 36	90.74 16	92.13 32
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 29	86.29 29	82.23 26	90.04 23	88.82 27	89.23 23	71.74 36	82.82 40	74.61 35	84.41 24	82.09 36	77.03 28	87.13 26	86.73 26	90.73 17	92.06 33

DeepC-MVS_fast	78.24 3	84.27 30	85.50 32	82.85 23	90.46 18	89.24 23	87.83 34	74.24 18	84.88 26	76.23 30	75.26 41	81.05 44	77.62 21	88.02 14	87.62 14	90.69 18	92.41 29
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 11	89.45 10	84.05 15	90.13 20	89.23 24	89.77 19	74.59 15	89.17 11	80.70 10	89.93 12	89.67 6	78.47 13	87.57 20	86.79 24	90.67 19	93.76 17
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 49	81.35 48	77.22 53	82.95 64	84.67 65	81.31 74	63.65 94	72.47 70	68.75 67	73.15 48	78.33 50	75.99 33	86.06 41	83.96 50	90.67 19	90.79 42

TSAR-MVS + MP.		86.88 12	89.23 11	84.14 13	89.78 27	88.67 31	90.59 11	73.46 27	88.99 12	80.52 12	91.26 8	88.65 10	79.91 9	86.96 30	86.22 32	90.59 21	93.83 15
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APD-MVS		86.84 13	88.91 15	84.41 11	90.66 11	90.10 14	90.78 8	75.64 9	87.38 17	78.72 19	90.68 11	86.82 18	80.15 8	87.13 26	86.45 30	90.51 22	93.83 15
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		84.74 27	86.43 28	82.77 24	89.48 31	88.13 40	88.64 26	73.93 22	84.92 25	76.77 28	81.94 28	83.50 32	77.29 26	86.92 31	86.49 29	90.49 23	93.14 25

XVS					86.63 47	88.68 28	85.00 48			71.81 47		81.92 38				90.47 24

X-MVStestdata					86.63 47	88.68 28	85.00 48			71.81 47		81.92 38				90.47 24

X-MVS		83.23 34	85.20 34	80.92 35	89.71 28	88.68 28	88.21 33	73.60 24	82.57 41	71.81 47	77.07 34	81.92 38	71.72 59	86.98 29	86.86 21	90.47 24	92.36 30

NCCC		85.34 20	86.59 26	83.88 16	91.48 4	88.88 26	89.79 18	75.54 11	86.67 21	77.94 24	76.55 36	84.99 26	78.07 17	88.04 13	87.68 13	90.46 27	93.31 22

CNVR-MVS		86.36 15	88.19 18	84.23 12	91.33 5	89.84 16	90.34 12	75.56 10	87.36 18	78.97 18	81.19 30	86.76 19	78.74 12	89.30 5	88.58 2	90.45 28	94.33 11

MP-MVS		85.50 19	87.40 22	83.28 20	90.65 12	89.51 21	89.16 24	74.11 19	83.70 35	78.06 23	85.54 21	84.89 29	77.31 24	87.40 23	87.14 18	90.41 29	93.65 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	75.73 4	82.40 36	82.76 40	81.97 29	88.02 40	89.67 19	86.60 39	71.48 37	81.28 45	78.18 22	64.78 106	77.96 53	77.13 27	87.32 24	86.83 22	90.41 29	91.48 37

ACMMP_NAP		86.52 14	89.01 12	83.62 17	90.28 19	90.09 15	90.32 14	74.05 20	88.32 14	79.74 16	87.04 16	85.59 24	76.97 29	89.35 4	88.44 4	90.35 31	94.27 12

CS-MVS		79.22 52	81.11 51	77.01 55	81.36 78	84.03 69	80.35 81	63.25 100	73.43 67	70.37 58	74.10 47	76.03 60	76.40 31	86.32 38	83.95 51	90.34 32	89.93 50

CDPH-MVS		82.64 35	85.03 35	79.86 40	89.41 32	88.31 37	88.32 31	71.84 35	80.11 47	67.47 77	82.09 27	81.44 42	71.85 57	85.89 42	86.15 33	90.24 33	91.25 39

LGP-MVS_train		79.83 44	81.22 50	78.22 49	86.28 50	85.36 60	86.76 38	69.59 47	77.34 52	65.14 89	75.68 38	70.79 98	71.37 64	84.60 51	84.01 48	90.18 34	90.74 43

HPM-MVS++		87.09 10	88.92 14	84.95 6	92.61 1	87.91 41	90.23 16	76.06 5	88.85 13	81.20 9	87.33 14	87.93 13	79.47 10	88.59 9	88.23 5	90.15 35	93.60 21

3Dnovator	73.76 5	79.75 46	80.52 56	78.84 44	84.94 60	87.35 42	84.43 53	65.54 76	78.29 51	73.97 37	63.00 114	75.62 63	74.07 41	85.00 48	85.34 40	90.11 36	89.04 57

DPM-MVS		83.30 33	84.33 36	82.11 27	89.56 29	88.49 34	90.33 13	73.24 28	83.85 33	76.46 29	72.43 53	82.65 34	73.02 49	86.37 36	86.91 20	90.03 37	89.62 54

ETV-MVS		77.32 66	78.81 64	75.58 69	82.24 72	83.64 78	79.98 84	64.02 90	69.64 87	63.90 96	70.89 61	69.94 104	73.41 45	85.39 46	83.91 52	89.92 38	88.31 62

ACMP	73.23 7	79.79 45	80.53 55	78.94 43	85.61 53	85.68 55	85.61 44	69.59 47	77.33 53	71.00 54	74.45 44	69.16 109	71.88 55	83.15 68	83.37 56	89.92 38	90.57 46
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SPE-MVS-test		78.79 59	80.72 53	76.53 58	81.11 83	83.88 72	79.69 91	63.72 93	73.80 64	69.95 63	75.40 40	76.17 57	74.85 36	84.50 54	82.78 61	89.87 40	88.54 61

train_agg		84.86 25	87.21 24	82.11 27	90.59 13	85.47 57	89.81 17	73.55 26	83.95 32	73.30 40	89.84 13	87.23 16	75.61 34	86.47 34	85.46 39	89.78 41	92.06 33

TSAR-MVS + GP.		83.69 31	86.58 27	80.32 37	85.14 55	86.96 45	84.91 51	70.25 42	84.71 29	73.91 38	85.16 22	85.63 23	77.92 18	85.44 43	85.71 37	89.77 42	92.45 28

ACMM	72.26 8	78.86 58	78.13 68	79.71 41	86.89 46	83.40 80	86.02 41	70.50 40	75.28 57	71.49 51	63.01 113	69.26 108	73.57 44	84.11 57	83.98 49	89.76 43	87.84 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TPM-MVS					90.07 22	88.36 36	88.45 30			77.10 27	75.60 39	83.98 31	71.33 65			89.75 44	89.62 54
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
OPM-MVS		79.68 48	79.28 63	80.15 39	87.99 41	86.77 47	88.52 29	72.72 30	64.55 119	67.65 76	67.87 86	74.33 68	74.31 40	86.37 36	85.25 41	89.73 45	89.81 52
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 24	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 3	89.18 7	80.89 4	87.99 16	87.91 9	89.70 46	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 40	83.41 37	79.53 42	87.06 44	88.59 32	85.47 46	67.96 59	76.59 55	74.05 36	74.69 43	81.98 37	72.98 50	86.14 40	85.47 38	89.68 47	90.42 47

MVS_111021_HR		80.13 43	81.46 47	78.58 46	85.77 52	85.17 61	83.45 56	69.28 50	74.08 63	70.31 59	74.31 45	75.26 64	73.13 47	86.46 35	85.15 42	89.53 48	89.81 52

IS_MVSNet		73.33 101	77.34 81	68.65 135	81.29 79	83.47 79	74.45 146	63.58 96	65.75 109	48.49 175	67.11 96	70.61 99	54.63 197	84.51 53	83.58 55	89.48 49	86.34 85

DELS-MVS		79.15 56	81.07 52	76.91 56	83.54 62	87.31 43	84.45 52	64.92 82	69.98 80	69.34 66	71.62 57	76.26 56	69.84 71	86.57 33	85.90 35	89.39 50	89.88 51
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		70.59 125	72.19 124	68.72 133	77.72 127	80.72 118	73.81 161	69.65 46	61.99 139	43.23 207	60.54 123	57.50 162	58.57 158	79.56 131	81.07 78	89.34 51	83.97 126

casdiffmvs_mvg		77.79 63	79.55 62	75.73 63	81.56 75	84.70 64	82.12 59	64.26 89	74.27 61	67.93 73	70.83 62	74.66 66	69.19 88	83.33 67	81.94 67	89.29 52	87.14 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
EIA-MVS		75.64 87	76.60 93	74.53 85	82.43 69	83.84 73	78.32 108	62.28 132	65.96 107	63.28 100	68.95 74	67.54 121	71.61 62	82.55 75	81.63 72	89.24 53	85.72 96

PHI-MVS		82.36 37	85.89 31	78.24 48	86.40 49	89.52 20	85.52 45	69.52 49	82.38 43	65.67 85	81.35 29	82.36 35	73.07 48	87.31 25	86.76 25	89.24 53	91.56 36

sasdasda		79.16 54	82.37 43	75.41 74	82.33 70	86.38 51	80.80 77	63.18 106	82.90 38	67.34 78	72.79 50	76.07 58	69.62 74	83.46 65	84.41 46	89.20 55	90.60 44

canonicalmvs		79.16 54	82.37 43	75.41 74	82.33 70	86.38 51	80.80 77	63.18 106	82.90 38	67.34 78	72.79 50	76.07 58	69.62 74	83.46 65	84.41 46	89.20 55	90.60 44

MSLP-MVS++		82.09 38	82.66 41	81.42 31	87.03 45	87.22 44	85.82 43	70.04 43	80.30 46	78.66 20	68.67 80	81.04 45	77.81 19	85.19 47	84.88 44	89.19 57	91.31 38

HQP-MVS		81.19 41	83.27 38	78.76 45	87.40 43	85.45 58	86.95 37	70.47 41	81.31 44	66.91 82	79.24 32	76.63 55	71.67 61	84.43 55	83.78 53	89.19 57	92.05 35

EPP-MVSNet		74.00 97	77.41 79	70.02 120	80.53 98	83.91 71	74.99 140	62.68 125	65.06 114	49.77 170	68.68 79	72.09 79	63.06 126	82.49 77	80.73 83	89.12 59	88.91 58

NR-MVSNet		68.79 146	70.56 134	66.71 164	77.48 130	79.54 130	73.52 165	69.20 51	61.20 148	39.76 214	58.52 135	50.11 219	51.37 207	80.26 120	80.71 88	88.97 60	83.59 132

PVSNet_Blended_VisFu		76.57 71	77.90 69	75.02 78	80.56 97	86.58 49	79.24 96	66.18 70	64.81 116	68.18 71	65.61 100	71.45 85	67.05 98	84.16 56	81.80 70	88.90 61	90.92 41

TranMVSNet+NR-MVSNet		69.25 141	70.81 133	67.43 148	77.23 132	79.46 132	73.48 166	69.66 45	60.43 153	39.56 215	58.82 134	53.48 195	55.74 186	79.59 129	81.21 76	88.89 62	82.70 136

QAPM		78.47 60	80.22 59	76.43 59	85.03 57	86.75 48	80.62 80	66.00 73	73.77 65	65.35 88	65.54 102	78.02 52	72.69 51	83.71 60	83.36 57	88.87 63	90.41 48

MGCFI-Net		76.55 72	81.71 45	70.52 112	81.71 74	84.62 66	75.02 139	62.17 133	82.91 37	53.58 148	72.78 52	75.87 62	61.75 141	82.96 70	82.61 63	88.86 64	90.26 49

casdiffmvs		76.76 68	78.46 66	74.77 81	80.32 101	83.73 77	80.65 79	63.24 102	73.58 66	66.11 84	69.39 72	74.09 69	69.49 83	82.52 76	79.35 119	88.84 65	86.52 83
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 39	83.10 39	80.21 38	85.93 51	86.45 50	87.72 36	70.98 39	82.54 42	71.53 50	74.23 46	81.49 41	76.31 32	82.85 72	81.87 68	88.79 66	92.26 31

Effi-MVS+		75.28 89	76.20 96	74.20 88	81.15 81	83.24 83	81.11 75	63.13 110	66.37 103	60.27 108	64.30 110	68.88 113	70.93 68	81.56 82	81.69 71	88.61 67	87.35 70

UniMVSNet (Re)		69.53 137	71.90 127	66.76 162	76.42 136	80.93 114	72.59 171	68.03 58	61.75 143	41.68 212	58.34 141	57.23 164	53.27 203	79.53 132	80.62 92	88.57 68	84.90 118

viewdifsd2359ckpt09		77.36 65	78.39 67	76.16 60	79.98 106	85.78 54	82.78 58	65.29 78	70.87 78	68.68 68	68.99 73	70.81 97	71.70 60	82.68 74	81.86 69	88.56 69	87.71 68

PCF-MVS	73.28 6	79.42 50	80.41 57	78.26 47	84.88 61	88.17 38	86.08 40	69.85 44	75.23 58	68.43 69	68.03 85	78.38 49	71.76 58	81.26 94	80.65 91	88.56 69	91.18 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GeoE		74.23 95	74.84 104	73.52 90	80.42 100	81.46 107	79.77 88	61.06 144	67.23 100	63.67 97	59.56 130	68.74 115	67.90 94	80.25 121	79.37 117	88.31 71	87.26 73

test2506		71.72 114	72.95 118	70.29 115	81.49 76	83.27 81	75.74 128	67.59 63	68.19 95	49.81 169	61.15 118	49.73 221	58.82 156	84.76 49	82.94 58	88.27 72	80.63 157

ECVR-MVS		72.20 110	73.91 110	70.20 117	81.49 76	83.27 81	75.74 128	67.59 63	68.19 95	49.31 173	55.77 152	62.00 139	58.82 156	84.76 49	82.94 58	88.27 72	80.41 161

MAR-MVS		79.21 53	80.32 58	77.92 50	87.46 42	88.15 39	83.95 54	67.48 65	74.28 60	68.25 70	64.70 107	77.04 54	72.17 53	85.42 44	85.00 43	88.22 74	87.62 69
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+		73.11 103	73.66 111	72.48 95	77.72 127	80.88 117	78.55 105	58.83 177	65.19 113	60.36 107	59.98 127	62.42 138	71.22 66	81.66 79	80.61 93	88.20 75	84.88 119

ET-MVSNet_ETH3D		72.46 109	74.19 106	70.44 113	62.50 224	81.17 112	79.90 87	62.46 130	64.52 120	57.52 121	71.49 59	59.15 151	72.08 54	78.61 144	81.11 77	88.16 76	83.29 134

OMC-MVS		80.26 42	82.59 42	77.54 51	83.04 63	85.54 56	83.25 57	65.05 81	87.32 19	72.42 43	72.04 55	78.97 48	73.30 46	83.86 58	81.60 73	88.15 77	88.83 59

AdaColmap		79.74 47	78.62 65	81.05 34	89.23 34	86.06 53	84.95 50	71.96 34	79.39 50	75.51 33	63.16 112	68.84 114	76.51 30	83.55 62	82.85 60	88.13 78	86.46 84

test1111		71.56 116	73.44 113	69.38 128	81.16 80	82.95 95	74.99 140	67.68 61	66.89 101	46.33 193	55.19 158	60.91 142	57.99 164	84.59 52	82.70 62	88.12 79	80.85 154

OpenMVS	70.44 10	76.15 82	76.82 89	75.37 76	85.01 58	84.79 63	78.99 100	62.07 134	71.27 75	67.88 74	57.91 143	72.36 77	70.15 70	82.23 78	81.41 74	88.12 79	87.78 67

E6new		76.06 83	76.54 94	75.51 72	80.71 91	83.10 86	81.74 68	63.03 111	68.89 90	69.71 64	66.73 97	70.84 95	69.76 72	80.88 101	79.61 109	88.11 81	85.72 96

E6		76.06 83	76.54 94	75.51 72	80.71 91	83.10 86	81.74 68	63.03 111	68.89 90	69.71 64	66.73 97	70.84 95	69.76 72	80.88 101	79.61 109	88.11 81	85.72 96

E4		76.24 77	76.77 92	75.61 68	80.69 93	83.05 92	81.98 63	63.25 100	69.47 88	70.06 60	67.40 91	71.46 84	69.59 78	80.73 103	79.37 117	88.10 83	85.95 87

FA-MVS(training)		73.66 98	74.95 103	72.15 96	78.63 119	80.46 122	78.92 102	54.79 202	69.71 86	65.37 87	62.04 115	66.89 124	67.10 97	80.72 106	79.87 103	88.10 83	84.97 116

E5new		76.23 78	76.79 90	75.58 69	80.69 93	83.05 92	82.00 60	63.37 97	69.73 83	70.01 61	67.77 88	71.43 87	69.37 85	80.50 111	79.13 122	88.04 85	85.92 88

E5		76.23 78	76.79 90	75.58 69	80.69 93	83.05 92	82.00 60	63.37 97	69.73 83	70.01 61	67.77 88	71.43 87	69.37 85	80.50 111	79.13 122	88.04 85	85.92 88

UA-Net		74.47 94	77.80 71	70.59 111	85.33 54	85.40 59	73.54 164	65.98 74	60.65 151	56.00 129	72.11 54	79.15 47	54.63 197	83.13 69	82.25 65	88.04 85	81.92 146

E3new		76.51 73	77.22 83	75.69 66	80.74 89	83.07 88	81.99 62	63.23 103	71.18 76	70.52 57	68.77 76	71.75 82	69.61 76	80.73 103	79.18 120	88.03 88	85.85 91

E3		76.51 73	77.21 84	75.69 66	80.74 89	83.06 91	81.98 63	63.22 104	71.17 77	70.55 56	68.77 76	71.76 81	69.61 76	80.73 103	79.18 120	88.03 88	85.84 93

viewcassd2359sk11		76.64 70	77.43 78	75.72 65	80.75 88	83.07 88	81.95 65	63.20 105	72.02 74	70.88 55	69.50 70	72.02 80	69.58 79	80.68 108	78.98 126	87.97 90	85.74 94

DU-MVS		69.63 136	70.91 132	68.13 139	75.99 138	79.54 130	73.81 161	69.20 51	61.20 148	43.23 207	58.52 135	53.50 193	58.57 158	79.22 136	80.45 94	87.97 90	83.97 126

FC-MVSNet-train		72.60 106	75.07 102	69.71 123	81.10 84	78.79 140	73.74 163	65.23 80	66.10 106	53.34 149	70.36 65	63.40 135	56.92 174	81.44 87	80.96 80	87.93 92	84.46 124

E2		76.70 69	77.54 73	75.73 63	80.76 87	83.07 88	81.91 66	63.15 108	72.42 71	71.09 53	70.03 67	72.22 78	69.53 80	80.57 110	78.80 130	87.91 93	85.64 99

IB-MVS	66.94 12	71.21 121	71.66 129	70.68 106	79.18 114	82.83 99	72.61 170	61.77 138	59.66 156	63.44 99	53.26 176	59.65 149	59.16 155	76.78 168	82.11 66	87.90 94	87.33 71
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 80	77.52 75	74.69 82	79.46 112	83.79 74	77.50 115	64.34 87	69.88 81	71.88 45	68.54 81	70.42 100	67.05 98	83.48 63	79.63 107	87.89 95	86.87 77

PVSNet_Blended		76.21 80	77.52 75	74.69 82	79.46 112	83.79 74	77.50 115	64.34 87	69.88 81	71.88 45	68.54 81	70.42 100	67.05 98	83.48 63	79.63 107	87.89 95	86.87 77

DeepPCF-MVS	79.04 1	85.30 21	88.93 13	81.06 33	88.77 37	90.48 12	85.46 47	73.08 29	90.97 6	73.77 39	84.81 23	85.95 21	77.43 23	88.22 11	87.73 11	87.85 97	94.34 10

thisisatest0530		71.48 118	73.01 117	69.70 124	73.83 167	78.62 142	74.53 145	59.12 171	64.13 122	58.63 114	64.60 108	58.63 153	64.27 119	80.28 119	80.17 100	87.82 98	84.64 122

TAPA-MVS	71.42 9	77.69 64	80.05 60	74.94 79	80.68 96	84.52 67	81.36 73	63.14 109	84.77 27	64.82 91	68.72 78	75.91 61	71.86 56	81.62 80	79.55 113	87.80 99	85.24 111
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tttt0517		71.41 119	72.95 118	69.60 125	73.70 169	78.70 141	74.42 149	59.12 171	63.89 126	58.35 117	64.56 109	58.39 159	64.27 119	80.29 118	80.17 100	87.74 100	84.69 121

viewmacassd2359aftdt		75.85 85	77.01 87	74.49 86	79.69 109	82.87 98	81.77 67	61.06 144	69.37 89	67.26 80	66.73 97	71.63 83	69.48 84	81.51 84	80.20 97	87.69 101	86.77 80

MVS_Test		75.37 88	77.13 86	73.31 92	79.07 115	81.32 109	79.98 84	60.12 160	69.72 85	64.11 95	70.53 64	73.22 72	68.90 89	80.14 123	79.48 115	87.67 102	85.50 104

DI_MVS_pp		75.13 90	76.12 97	73.96 89	78.18 121	81.55 104	80.97 76	62.54 127	68.59 93	65.13 90	61.43 117	74.81 65	69.32 87	81.01 99	79.59 111	87.64 103	85.89 90

viewdifsd2359ckpt13		76.26 76	77.31 82	75.03 77	80.14 103	83.77 76	81.58 72	62.80 117	70.34 79	67.83 75	68.06 84	70.93 94	70.20 69	81.46 85	79.88 102	87.63 104	86.71 81

viewmanbaseed2359cas		76.36 75	77.87 70	74.60 84	79.81 107	82.88 97	81.69 71	61.02 146	72.14 73	67.97 72	69.61 69	72.45 76	69.53 80	81.53 83	79.83 104	87.57 105	86.65 82

MVSTER		72.06 111	74.24 105	69.51 126	70.39 197	75.97 173	76.91 123	57.36 188	64.64 118	61.39 104	68.86 75	63.76 133	63.46 123	81.44 87	79.70 106	87.56 106	85.31 110

TSAR-MVS + ACMM		85.10 24	88.81 16	80.77 36	89.55 30	88.53 33	88.59 28	72.55 31	87.39 16	71.90 44	90.95 10	87.55 14	74.57 37	87.08 28	86.54 28	87.47 107	93.67 18

CLD-MVS		79.35 51	81.23 49	77.16 54	85.01 58	86.92 46	85.87 42	60.89 148	80.07 49	75.35 34	72.96 49	73.21 73	68.43 93	85.41 45	84.63 45	87.41 108	85.44 106
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		71.82 113	71.86 128	71.78 100	78.77 116	80.47 121	78.55 105	61.67 141	60.68 150	55.49 130	58.48 137	65.48 128	68.85 90	76.92 165	75.55 178	87.35 109	85.46 105

WR-MVS		63.03 192	67.40 173	57.92 214	75.14 152	77.60 159	60.56 229	66.10 71	54.11 198	23.88 239	53.94 170	53.58 191	34.50 235	73.93 185	77.71 145	87.35 109	80.94 153

v144192		69.34 140	68.68 158	70.12 118	74.06 163	80.54 119	78.08 111	60.54 152	54.99 191	54.13 137	52.92 183	52.80 204	66.73 105	77.13 163	76.72 163	87.15 111	85.63 100

EPNet		79.08 57	80.62 54	77.28 52	88.90 36	83.17 85	83.65 55	72.41 32	74.41 59	67.15 81	76.78 35	74.37 67	64.43 118	83.70 61	83.69 54	87.15 111	88.19 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		67.24 167	66.94 176	67.60 146	78.73 117	81.35 108	73.28 168	59.49 166	46.89 230	51.42 161	43.65 223	53.49 194	55.50 189	81.38 89	80.66 90	87.15 111	81.17 152

v1144		69.93 134	69.36 148	70.61 108	74.89 155	80.93 114	79.11 98	60.64 150	55.97 181	55.31 132	53.85 171	54.14 186	66.54 109	78.10 149	77.44 153	87.14 114	85.09 113

anonymousdsp		65.28 178	67.98 166	62.13 193	58.73 239	73.98 195	67.10 202	50.69 225	48.41 225	47.66 187	54.27 164	52.75 205	61.45 145	76.71 169	80.20 97	87.13 115	89.53 56

PLC	68.99 11	75.68 86	75.31 100	76.12 62	82.94 65	81.26 111	79.94 86	66.10 71	77.15 54	66.86 83	59.13 133	68.53 116	73.73 43	80.38 116	79.04 124	87.13 115	81.68 148
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v10		70.22 130	69.76 143	70.74 104	74.79 156	80.30 126	79.22 97	59.81 164	57.71 167	56.58 127	54.22 168	55.31 175	66.95 101	78.28 147	77.47 152	87.12 117	85.07 114

v1192		69.50 138	68.83 154	70.29 115	74.49 159	80.92 116	78.55 105	60.54 152	55.04 189	54.21 135	52.79 185	52.33 206	66.92 102	77.88 153	77.35 156	87.04 118	85.51 103

v1921920		69.03 143	68.32 162	69.86 121	74.03 164	80.37 123	77.55 113	60.25 157	54.62 193	53.59 147	52.36 192	51.50 212	66.75 104	77.17 162	76.69 165	86.96 119	85.56 101

v2v482		70.05 133	69.46 147	70.74 104	74.62 158	80.32 125	79.00 99	60.62 151	57.41 169	56.89 124	55.43 157	55.14 177	66.39 113	77.25 161	77.14 158	86.90 120	83.57 133

Vis-MVSNet		72.77 105	77.20 85	67.59 147	74.19 162	84.01 70	76.61 127	61.69 139	60.62 152	50.61 165	70.25 66	71.31 90	55.57 188	83.85 59	82.28 64	86.90 120	88.08 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PEN-MVS		62.96 195	65.77 183	59.70 207	73.98 165	75.45 177	63.39 221	67.61 62	52.49 204	25.49 238	53.39 173	49.12 223	40.85 227	71.94 197	77.26 157	86.86 122	80.72 156

v8		70.23 129	69.86 141	70.67 107	74.69 157	79.82 128	78.79 103	59.18 170	58.80 160	58.20 118	55.00 159	57.33 163	66.31 114	77.51 157	76.71 164	86.82 123	83.88 129

ACMH+	66.54 13	71.36 120	70.09 138	72.85 93	82.59 67	81.13 113	78.56 104	68.04 57	61.55 144	52.52 156	51.50 196	54.14 186	68.56 92	78.85 141	79.50 114	86.82 123	83.94 128

usedtu_dtu_shiyan1		66.26 173	68.15 164	64.06 180	67.01 209	76.52 168	70.61 181	61.10 142	61.86 141	44.86 201	49.77 205	56.69 169	53.97 200	77.58 156	77.88 142	86.80 125	76.78 194

v1240		68.64 148	67.89 169	69.51 126	73.89 166	80.26 127	76.73 125	59.97 163	53.43 201	53.08 151	51.82 195	50.84 215	66.62 106	76.79 167	76.77 162	86.78 126	85.34 109

DCV-MVSNet		73.65 99	75.78 99	71.16 103	80.19 102	79.27 134	77.45 117	61.68 140	66.73 102	58.72 113	65.31 103	69.96 103	62.19 131	81.29 93	80.97 79	86.74 127	86.91 76

GBi-Net		70.78 122	73.37 115	67.76 140	72.95 174	78.00 149	75.15 134	62.72 120	64.13 122	51.44 158	58.37 138	69.02 110	57.59 166	81.33 90	80.72 84	86.70 128	82.02 140

test1		70.78 122	73.37 115	67.76 140	72.95 174	78.00 149	75.15 134	62.72 120	64.13 122	51.44 158	58.37 138	69.02 110	57.59 166	81.33 90	80.72 84	86.70 128	82.02 140

FMVSNet2		70.39 128	72.67 122	67.72 143	72.95 174	78.00 149	75.15 134	62.69 124	63.29 130	51.25 162	55.64 153	68.49 117	57.59 166	80.91 100	80.35 96	86.70 128	82.02 140

v7n		67.05 170	66.94 176	67.17 154	72.35 179	78.97 135	73.26 169	58.88 176	51.16 216	50.90 163	48.21 210	50.11 219	60.96 146	77.70 154	77.38 154	86.68 131	85.05 115

WR-MVS_H		61.83 211	65.87 182	57.12 217	71.72 184	76.87 163	61.45 227	66.19 69	51.97 209	22.92 243	53.13 180	52.30 208	33.80 237	71.03 204	75.00 181	86.65 132	80.78 155

MSDG		71.52 117	69.87 140	73.44 91	82.21 73	79.35 133	79.52 92	64.59 84	66.15 105	61.87 101	53.21 178	56.09 172	65.85 116	78.94 140	78.50 133	86.60 133	76.85 193

FMVSNet3		70.49 126	72.90 120	67.67 145	72.88 177	77.98 152	74.96 143	62.72 120	64.13 122	51.44 158	58.37 138	69.02 110	57.43 169	79.43 134	79.57 112	86.59 134	81.81 147

MVS_111021_LR		78.13 62	79.85 61	76.13 61	81.12 82	81.50 106	80.28 83	65.25 79	76.09 56	71.32 52	76.49 37	72.87 75	72.21 52	82.79 73	81.29 75	86.59 134	87.91 65

DTE-MVSNet		61.85 209	64.96 194	58.22 213	74.32 161	74.39 187	61.01 228	67.85 60	51.76 211	21.91 246	53.28 175	48.17 224	37.74 232	72.22 194	76.44 168	86.52 136	78.49 175

baseline2		69.69 135	70.27 137	69.01 131	75.72 146	77.13 162	73.82 160	58.94 175	61.35 146	57.09 123	61.68 116	57.17 165	61.99 135	78.10 149	76.58 166	86.48 137	79.85 165

thisisatest0515		67.40 165	68.78 155	65.80 168	70.02 199	75.24 180	69.36 187	57.37 187	54.94 192	53.67 146	55.53 156	54.85 182	58.00 163	78.19 148	78.91 128	86.39 138	83.78 130

FMVSNet1		68.84 145	70.47 136	66.94 159	71.35 191	77.68 157	74.71 144	62.35 131	56.93 172	49.94 168	50.01 202	64.59 130	57.07 171	81.33 90	80.72 84	86.25 139	82.00 143

UGNet		72.78 104	77.67 72	67.07 157	71.65 186	83.24 83	75.20 133	63.62 95	64.93 115	56.72 125	71.82 56	73.30 70	49.02 211	81.02 98	80.70 89	86.22 140	88.67 60
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		71.90 112	72.48 123	71.21 102	80.14 103	81.53 105	76.92 120	62.89 115	64.46 121	58.94 110	43.80 222	70.98 93	62.22 130	80.70 107	80.19 99	86.18 141	85.73 95

FE-MVSNET2		58.78 221	60.53 225	56.73 219	57.08 241	72.23 200	62.74 225	59.35 169	47.17 228	30.52 229	34.62 239	43.62 237	44.57 218	75.24 176	76.57 167	86.11 142	74.30 212

tfpn200view9		68.11 151	68.72 157	67.40 149	77.83 125	78.93 136	74.28 151	62.81 116	56.64 174	46.82 189	52.65 189	53.47 196	56.59 175	80.41 113	78.43 134	86.11 142	80.52 159

CANet_DTU		73.29 102	76.96 88	69.00 132	77.04 133	82.06 102	79.49 93	56.30 198	67.85 98	53.29 150	71.12 60	70.37 102	61.81 140	81.59 81	80.96 80	86.09 144	84.73 120

CP-MVSNet		62.68 199	65.49 186	59.40 210	71.84 182	75.34 178	62.87 223	67.04 66	52.64 203	27.19 236	53.38 174	48.15 225	41.40 225	71.26 200	75.68 174	86.07 145	82.00 143

ACMH	65.37 14	70.71 124	70.00 139	71.54 101	82.51 68	82.47 101	77.78 112	68.13 56	56.19 179	46.06 196	54.30 162	51.20 213	68.68 91	80.66 109	80.72 84	86.07 145	84.45 125
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres600view7		67.68 159	68.43 161	66.80 161	77.90 122	78.86 138	73.84 159	62.75 118	56.07 180	44.70 205	52.85 184	52.81 203	55.58 187	80.41 113	77.77 144	86.05 147	80.28 162

thres200		67.98 153	68.55 160	67.30 152	77.89 124	78.86 138	74.18 155	62.75 118	56.35 177	46.48 192	52.98 182	53.54 192	56.46 176	80.41 113	77.97 141	86.05 147	79.78 167

CNLPA		77.20 67	77.54 73	76.80 57	82.63 66	84.31 68	79.77 88	64.64 83	85.17 24	73.18 41	56.37 150	69.81 105	74.53 39	81.12 97	78.69 131	86.04 149	87.29 72

TSAR-MVS + COLMAP		78.34 61	81.64 46	74.48 87	80.13 105	85.01 62	81.73 70	65.93 75	84.75 28	61.68 102	85.79 20	66.27 126	71.39 63	82.91 71	80.78 82	86.01 150	85.98 86

LS3D		74.08 96	73.39 114	74.88 80	85.05 56	82.62 100	79.71 90	68.66 54	72.82 68	58.80 112	57.61 144	61.31 141	71.07 67	80.32 117	78.87 129	86.00 151	80.18 163

Anonymous202405211			72.16 126		80.85 86	81.85 103	76.88 124	65.40 77	62.89 134		46.35 218	67.99 120	62.05 133	81.15 96	80.38 95	85.97 152	84.50 123

PS-CasMVS		62.38 205	65.06 190	59.25 211	71.73 183	75.21 182	62.77 224	66.99 67	51.94 210	26.96 237	52.00 194	47.52 228	41.06 226	71.16 203	75.60 175	85.97 152	81.97 145

thres400		67.95 154	68.62 159	67.17 154	77.90 122	78.59 143	74.27 152	62.72 120	56.34 178	45.77 198	53.00 181	53.35 199	56.46 176	80.21 122	78.43 134	85.91 154	80.43 160

thres100view900		67.60 163	68.02 165	67.12 156	77.83 125	77.75 156	73.90 158	62.52 128	56.64 174	46.82 189	52.65 189	53.47 196	55.92 183	78.77 142	77.62 147	85.72 155	79.23 171

Vis-MVSNet (Re-imp)		67.83 157	73.52 112	61.19 199	78.37 120	76.72 166	66.80 205	62.96 113	65.50 112	34.17 226	67.19 95	69.68 106	39.20 230	79.39 135	79.44 116	85.68 156	76.73 195

baseline1		70.10 132	72.17 125	67.69 144	79.74 108	76.80 164	73.91 157	64.38 86	62.74 135	48.30 177	64.94 104	64.08 132	54.17 199	81.46 85	78.92 127	85.66 157	76.22 196

V42		68.76 147	69.63 144	67.74 142	64.93 220	78.01 148	78.30 109	56.48 193	58.65 161	56.30 128	54.26 166	57.03 166	64.85 117	77.47 158	77.01 160	85.60 158	84.96 117

blended_shiyan8		62.98 193	63.65 205	62.21 191	59.20 230	74.17 188	69.03 190	56.52 191	51.08 218	47.96 182	48.07 214	55.02 178	55.00 194	70.43 212	68.60 212	85.52 159	78.15 179

blended_shiyan6		62.98 193	63.66 204	62.19 192	59.20 230	74.17 188	69.04 189	56.52 191	51.09 217	47.91 183	48.11 213	55.02 178	54.98 195	70.43 212	68.59 213	85.51 160	78.20 177

TransMVSNet (Re)		64.74 183	65.66 184	63.66 185	77.40 131	75.33 179	69.86 183	62.67 126	47.63 227	41.21 213	50.01 202	52.33 206	45.31 217	79.57 130	77.69 146	85.49 161	77.07 192

IterMVS-LS		71.69 115	72.82 121	70.37 114	77.54 129	76.34 170	75.13 137	60.46 154	61.53 145	57.57 120	64.89 105	67.33 122	66.04 115	77.09 164	77.37 155	85.48 162	85.18 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.91 91	77.47 77	71.92 98	75.60 149	80.50 120	79.48 94	60.02 162	72.41 72	64.39 93	70.63 63	73.27 71	66.55 107	79.97 125	78.34 136	85.46 163	87.17 74

UniMVSNet_ETH3D		67.18 169	67.03 175	67.36 150	74.44 160	78.12 147	74.07 156	66.38 68	52.22 206	46.87 188	48.64 208	51.84 210	56.96 172	77.29 160	78.53 132	85.42 164	82.59 137

Baseline_NR-MVSNet		67.53 164	68.77 156	66.09 167	75.99 138	74.75 185	72.43 172	68.41 55	61.33 147	38.33 219	51.31 197	54.13 188	56.03 182	79.22 136	78.19 138	85.37 165	82.45 138

Fast-Effi-MVS+-dtu		68.34 149	69.47 146	67.01 158	75.15 151	77.97 154	77.12 119	55.40 200	57.87 162	46.68 191	56.17 151	60.39 143	62.36 129	76.32 172	76.25 171	85.35 166	81.34 150

blend_shiyan4		64.82 182	65.21 188	64.37 177	65.04 217	74.06 190	70.30 182	55.30 201	55.39 185	53.88 141	52.71 186	58.58 155	56.43 178	69.45 223	68.13 223	85.30 167	78.14 180

wanda-best-256-512		62.84 196	63.46 207	62.12 194	59.06 232	74.03 191	68.92 192	56.37 194	51.17 212	48.02 180	48.12 211	54.93 180	55.08 192	70.13 215	68.14 218	85.26 168	77.73 185

FE-blended-shiyan7		62.84 196	63.46 207	62.12 194	59.06 232	74.03 191	68.92 192	56.37 194	51.17 212	48.02 180	48.12 211	54.93 180	55.08 192	70.13 215	68.14 218	85.26 168	77.73 185

usedtu_blend_shiyan5		64.27 186	64.70 196	63.77 183	59.06 232	74.03 191	71.65 175	56.37 194	51.17 212	53.88 141	52.71 186	58.58 155	56.43 178	70.13 215	68.14 218	85.26 168	78.14 180

FE-MVSNET3		64.07 189	64.71 195	63.32 189	59.06 232	74.03 191	68.92 192	56.37 194	51.17 212	53.88 141	52.71 186	58.58 155	56.43 178	70.13 215	68.14 218	85.26 168	78.20 177

diffmvs		74.86 92	77.37 80	71.93 97	75.62 147	80.35 124	79.42 95	60.15 159	72.81 69	64.63 92	71.51 58	73.11 74	66.53 110	79.02 139	77.98 140	85.25 172	86.83 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GA-MVS		68.14 150	69.17 151	66.93 160	73.77 168	78.50 146	74.45 146	58.28 180	55.11 188	48.44 176	60.08 125	53.99 189	61.50 143	78.43 146	77.57 149	85.13 173	80.54 158

v148		67.85 156	67.53 170	68.23 137	73.25 172	77.57 160	74.26 153	57.36 188	55.70 183	57.45 122	53.53 172	55.42 174	61.96 136	75.23 177	73.92 186	85.08 174	81.32 151

viewmambaseed2359dif		73.61 100	75.14 101	71.84 99	75.87 142	79.69 129	78.99 100	60.42 155	68.19 95	64.15 94	67.85 87	71.20 92	66.55 107	77.41 159	75.78 173	85.04 175	85.85 91

HyFIR lowres test		69.47 139	68.94 153	70.09 119	76.77 135	82.93 96	76.63 126	60.17 158	59.00 159	54.03 138	40.54 232	65.23 129	67.89 95	76.54 171	78.30 137	85.03 176	80.07 164

gg-mvs-nofinetune		62.55 200	65.05 191	59.62 208	78.72 118	77.61 158	70.83 180	53.63 204	39.71 243	22.04 245	36.36 236	64.32 131	47.53 213	81.16 95	79.03 125	85.00 177	77.17 190

viewdifsd2359ckpt07		74.55 93	76.09 98	72.75 94	79.51 111	81.32 109	80.29 82	58.44 179	68.61 92	65.63 86	68.17 83	71.24 91	67.64 96	80.13 124	77.62 147	84.96 178	85.56 101

COLMAP_ROB	62.73 15	67.66 160	66.76 178	68.70 134	80.49 99	77.98 152	75.29 132	62.95 114	63.62 128	49.96 167	47.32 217	50.72 216	58.57 158	76.87 166	75.50 179	84.94 179	75.33 206
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpnnormal		64.27 186	63.64 206	65.02 171	75.84 145	75.61 176	71.24 179	62.52 128	47.79 226	42.97 209	42.65 225	44.49 235	52.66 205	78.77 142	76.86 161	84.88 180	79.29 170

viewdifsd2359ckpt11		72.49 107	74.10 107	70.61 108	75.87 142	78.53 144	76.92 120	58.16 181	65.69 110	61.34 105	67.21 93	68.35 118	66.51 111	77.91 151	75.60 175	84.86 181	85.43 107

viewmsd2359difaftdt		72.49 107	74.10 107	70.61 108	75.87 142	78.53 144	76.92 120	58.16 181	65.69 110	61.33 106	67.21 93	68.34 119	66.51 111	77.91 151	75.60 175	84.86 181	85.42 108

pm-mvs1		65.62 175	67.42 172	63.53 186	73.66 170	76.39 169	69.66 184	60.87 149	49.73 222	43.97 206	51.24 198	57.00 167	48.16 212	79.89 126	77.84 143	84.85 183	79.82 166

gm-plane-assit		57.00 225	57.62 232	56.28 221	76.10 137	62.43 240	47.62 248	46.57 239	33.84 247	23.24 241	37.52 233	40.19 243	59.61 153	79.81 127	77.55 150	84.55 184	72.03 217

USDC		67.36 166	67.90 168	66.74 163	71.72 184	75.23 181	71.58 176	60.28 156	67.45 99	50.54 166	60.93 119	45.20 234	62.08 132	76.56 170	74.50 184	84.25 185	75.38 205

dmvs_re		67.22 168	67.92 167	66.40 165	75.94 141	70.55 209	74.97 142	63.87 91	57.07 171	44.75 203	54.29 163	56.72 168	54.65 196	79.53 132	77.51 151	84.20 186	79.78 167

MS-PatchMatch		70.17 131	70.49 135	69.79 122	80.98 85	77.97 154	77.51 114	58.95 174	62.33 137	55.22 133	53.14 179	65.90 127	62.03 134	79.08 138	77.11 159	84.08 187	77.91 183

TDRefinement		66.09 174	65.03 192	67.31 151	69.73 201	76.75 165	75.33 130	64.55 85	60.28 154	49.72 171	45.63 220	42.83 238	60.46 151	75.75 173	75.95 172	84.08 187	78.04 182

pmmvs4		67.89 155	67.39 174	68.48 136	71.60 188	73.57 196	74.45 146	60.98 147	64.65 117	57.97 119	54.95 160	51.73 211	61.88 137	73.78 186	75.11 180	83.99 189	77.91 183

pmmvs5		62.37 206	64.04 201	60.42 202	65.03 218	71.67 204	67.17 201	52.70 215	50.30 219	44.80 202	54.23 167	51.19 214	49.37 210	72.88 189	73.48 190	83.45 190	74.55 209

0.4-1-1-0.2		64.94 180	65.02 193	64.85 173	66.45 214	74.76 184	71.66 174	54.40 203	55.85 182	53.84 144	53.97 169	58.62 154	59.33 154	68.27 229	68.20 217	83.40 191	75.47 204

pmmvs-eth3d		63.52 191	62.44 217	64.77 174	66.82 213	70.12 210	69.41 186	59.48 167	54.34 197	52.71 152	46.24 219	44.35 236	56.93 173	72.37 190	73.77 188	83.30 192	75.91 198

pmmvs6		62.41 203	62.88 211	61.87 196	71.38 190	75.18 183	67.76 198	59.45 168	41.64 238	42.52 211	37.33 234	52.91 202	46.87 214	77.67 155	76.26 170	83.23 193	79.18 172

CDS-MVSNet		67.65 161	69.83 142	65.09 170	75.39 150	76.55 167	74.42 149	63.75 92	53.55 199	49.37 172	59.41 131	62.45 137	44.44 219	79.71 128	79.82 105	83.17 194	77.36 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PMMVS		65.06 179	69.17 151	60.26 204	55.25 246	63.43 234	66.71 206	43.01 243	62.41 136	50.64 164	69.44 71	67.04 123	63.29 124	74.36 183	73.54 189	82.68 195	73.99 214

SixPastTwentyTwo		61.84 210	62.45 216	61.12 200	69.20 205	72.20 201	62.03 226	57.40 186	46.54 231	38.03 221	57.14 148	41.72 240	58.12 162	69.67 221	71.58 198	81.94 196	78.30 176

IterMVS		66.36 172	68.30 163	64.10 179	69.48 204	74.61 186	73.41 167	50.79 224	57.30 170	48.28 178	60.64 122	59.92 148	60.85 150	74.14 184	72.66 194	81.80 197	78.82 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchMatch-RL		67.78 158	66.65 179	69.10 130	73.01 173	72.69 199	68.49 195	61.85 137	62.93 133	60.20 109	56.83 149	50.42 217	69.52 82	75.62 174	74.46 185	81.51 198	73.62 215

TinyColmap		62.84 196	61.03 223	64.96 172	69.61 202	71.69 203	68.48 196	59.76 165	55.41 184	47.69 186	47.33 216	34.20 249	62.76 128	74.52 181	72.59 195	81.44 199	71.47 218

FE-MVSNET		52.98 235	55.99 235	49.47 235	49.71 247	65.83 224	54.09 240	56.91 190	40.70 240	16.86 252	32.90 242	40.15 244	37.83 231	69.80 220	73.04 193	81.41 200	69.49 225

EPNet_dtu		68.08 152	71.00 131	64.67 175	79.64 110	68.62 216	75.05 138	63.30 99	66.36 104	45.27 200	67.40 91	66.84 125	43.64 221	75.37 175	74.98 182	81.15 201	77.44 188
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		64.83 181	65.54 185	64.01 182	70.64 196	69.41 211	65.97 210	52.74 213	57.81 164	52.65 153	54.27 164	56.31 171	60.92 147	72.20 195	73.09 191	81.12 202	75.69 201

RPMNet		61.71 213	62.88 211	60.34 203	69.51 203	69.41 211	63.48 220	49.23 229	57.81 164	45.64 199	50.51 200	50.12 218	53.13 204	68.17 230	68.49 215	81.07 203	75.62 203

test-mter		60.84 215	64.62 198	56.42 220	55.99 244	64.18 228	65.39 212	34.23 248	54.39 196	46.21 195	57.40 147	59.49 150	55.86 184	71.02 205	69.65 204	80.87 204	76.20 197

test-LLR		64.42 184	64.36 199	64.49 176	75.02 153	63.93 231	66.61 207	61.96 135	54.41 194	47.77 184	57.46 145	60.25 144	55.20 190	70.80 206	69.33 205	80.40 205	74.38 210

TESTMET0.1,1		61.10 214	64.36 199	57.29 216	57.53 240	63.93 231	66.61 207	36.22 247	54.41 194	47.77 184	57.46 145	60.25 144	55.20 190	70.80 206	69.33 205	80.40 205	74.38 210

CostFormer		68.92 144	69.58 145	68.15 138	75.98 140	76.17 172	78.22 110	51.86 218	65.80 108	61.56 103	63.57 111	62.83 136	61.85 138	70.40 214	68.67 210	79.42 207	79.62 169

CVMVSNet		62.55 200	65.89 181	58.64 212	66.95 211	69.15 213	66.49 209	56.29 199	52.46 205	32.70 227	59.27 132	58.21 161	50.09 209	71.77 198	71.39 199	79.31 208	78.99 173

CHOSEN 1792x2688		69.20 142	69.26 149	69.13 129	76.86 134	78.93 136	77.27 118	60.12 160	61.86 141	54.42 134	42.54 226	61.61 140	66.91 103	78.55 145	78.14 139	79.23 209	83.23 135

PM-MVS		60.48 216	60.94 224	59.94 205	58.85 237	66.83 222	64.27 218	51.39 221	55.03 190	48.03 179	50.00 204	40.79 242	58.26 161	69.20 225	67.13 228	78.84 210	77.60 187

baseline		70.45 127	74.09 109	66.20 166	70.95 194	75.67 174	74.26 153	53.57 205	68.33 94	58.42 115	69.87 68	71.45 85	61.55 142	74.84 180	74.76 183	78.42 211	83.72 131

PatchT		61.97 208	64.04 201	59.55 209	60.49 228	67.40 219	56.54 237	48.65 233	56.69 173	52.65 153	51.10 199	52.14 209	60.92 147	72.20 195	73.09 191	78.03 212	75.69 201

RPSCF		67.64 162	71.25 130	63.43 187	61.86 226	70.73 207	67.26 200	50.86 223	74.20 62	58.91 111	67.49 90	69.33 107	64.10 121	71.41 199	68.45 216	77.61 213	77.17 190

MDTV_nov1_ep13_2view		60.16 217	60.51 226	59.75 206	65.39 216	69.05 214	68.00 197	48.29 235	51.99 207	45.95 197	48.01 215	49.64 222	53.39 202	68.83 226	66.52 229	77.47 214	69.55 224

MDTV_nov1_ep13		64.37 185	65.24 187	63.37 188	68.94 206	70.81 206	72.40 173	50.29 227	60.10 155	53.91 140	60.07 126	59.15 151	57.21 170	69.43 224	67.30 225	77.47 214	69.78 223

LTVRE_ROB	59.44 16	61.82 212	62.64 214	60.87 201	72.83 178	77.19 161	64.37 217	58.97 173	33.56 248	28.00 235	52.59 191	42.21 239	63.93 122	74.52 181	76.28 169	77.15 216	82.13 139
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		66.89 171	69.22 150	64.17 178	71.30 192	75.64 175	71.33 177	53.17 209	57.63 168	49.08 174	60.72 121	60.05 147	63.09 125	74.99 179	73.92 186	77.07 217	81.57 149

SCA		65.40 177	66.58 180	64.02 181	70.65 195	73.37 197	67.35 199	53.46 207	63.66 127	54.14 136	60.84 120	60.20 146	61.50 143	69.96 219	68.14 218	77.01 218	69.91 221

MDA-MVSNet-bldmvs		53.37 234	53.01 238	53.79 229	43.67 251	67.95 218	59.69 232	57.92 184	43.69 234	32.41 228	41.47 227	27.89 255	52.38 206	56.97 247	65.99 231	76.68 219	67.13 229

MVS-HIRNet		54.41 231	52.10 239	57.11 218	58.99 236	56.10 246	49.68 246	49.10 230	46.18 232	52.15 157	33.18 241	46.11 231	56.10 181	63.19 239	59.70 242	76.64 220	60.25 242

dps		64.00 190	62.99 210	65.18 169	73.29 171	72.07 202	68.98 191	53.07 211	57.74 166	58.41 116	55.55 155	47.74 227	60.89 149	69.53 222	67.14 227	76.44 221	71.19 219

usedtu_dtu_shiyan2		49.27 237	50.47 240	47.86 237	35.37 255	64.10 230	58.53 235	53.10 210	31.42 251	29.57 231	27.09 248	38.06 247	34.31 236	63.35 237	63.36 236	76.27 222	65.93 232

test0.0.03 1		58.80 220	61.58 221	55.56 223	75.02 153	68.45 217	59.58 233	61.96 135	52.74 202	29.57 231	49.75 206	54.56 184	31.46 239	71.19 201	69.77 203	75.75 223	64.57 234

EU-MVSNet		54.63 230	58.69 228	49.90 234	56.99 242	62.70 239	56.41 238	50.64 226	45.95 233	23.14 242	50.42 201	46.51 230	36.63 233	65.51 233	64.85 232	75.57 224	74.91 207

PatchmatchNet		64.21 188	64.65 197	63.69 184	71.29 193	68.66 215	69.63 185	51.70 220	63.04 131	53.77 145	59.83 129	58.34 160	60.23 152	68.54 227	66.06 230	75.56 225	68.08 228
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous20231206		56.36 227	57.80 231	54.67 226	70.08 198	66.39 223	60.46 230	57.54 185	49.50 224	29.30 233	33.86 240	46.64 229	35.18 234	70.44 210	68.88 209	75.47 226	68.88 227

CMPMVS	47.78 17	62.49 202	62.52 215	62.46 190	70.01 200	70.66 208	62.97 222	51.84 219	51.98 208	56.71 126	42.87 224	53.62 190	57.80 165	72.23 193	70.37 202	75.45 227	75.91 198
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet		58.52 223	61.34 222	55.22 224	60.76 227	67.01 221	66.81 204	49.02 231	56.43 176	38.90 217	40.59 231	54.54 185	40.57 228	73.16 188	71.65 197	75.30 228	66.00 231

TAMVS		59.58 219	62.81 213	55.81 222	66.03 215	65.64 227	63.86 219	48.74 232	49.95 221	37.07 223	54.77 161	58.54 158	44.44 219	72.29 192	71.79 196	74.70 229	66.66 230

tpm cat1		65.41 176	63.81 203	67.28 153	75.61 148	72.88 198	75.32 131	52.85 212	62.97 132	63.66 98	53.24 177	53.29 201	61.83 139	65.54 232	64.14 234	74.43 230	74.60 208

test20.03		53.93 233	56.28 234	51.19 232	72.19 181	65.83 224	53.20 242	61.08 143	42.74 236	22.08 244	37.07 235	45.76 233	24.29 247	70.44 210	69.04 207	74.31 231	63.05 238

FMVSNet5		57.24 224	60.02 227	53.99 228	56.45 243	62.74 238	65.27 213	47.03 238	55.14 187	39.55 216	40.88 229	53.42 198	41.83 222	72.35 191	71.10 201	73.79 232	64.50 235

testgi		54.39 232	57.86 230	50.35 233	71.59 189	67.24 220	54.95 239	53.25 208	43.36 235	23.78 240	44.64 221	47.87 226	24.96 244	70.45 209	68.66 211	73.60 233	62.78 239

MIMVSNet1		49.27 237	53.25 237	44.62 240	44.61 249	61.52 241	53.61 241	52.18 216	41.62 239	18.68 249	28.14 247	41.58 241	25.50 242	68.46 228	69.04 207	73.15 234	62.37 240

pmmvs3		47.65 239	49.08 244	45.99 239	44.61 249	54.79 247	50.04 244	31.95 251	33.91 246	29.90 230	30.37 243	33.53 250	46.31 215	63.50 236	63.67 235	73.14 235	63.77 237

FC-MVSNet-test		56.90 226	65.20 189	47.21 238	66.98 210	63.20 236	49.11 247	58.60 178	59.38 158	11.50 254	65.60 101	56.68 170	24.66 246	71.17 202	71.36 200	72.38 236	69.02 226

GG-mvs-BLEND		46.86 242	67.51 171	22.75 248	0.05 260	76.21 171	64.69 215	0.04 256	61.90 140	0.09 261	55.57 154	71.32 89	0.08 256	70.54 208	67.19 226	71.58 237	69.86 222

ambc			53.42 236		64.99 219	63.36 235	49.96 245		47.07 229	37.12 222	28.97 245	16.36 258	41.82 223	75.10 178	67.34 224	71.55 238	75.72 200

tpmrst		62.00 207	62.35 218	61.58 197	71.62 187	64.14 229	69.07 188	48.22 237	62.21 138	53.93 139	58.26 142	55.30 176	55.81 185	63.22 238	62.62 237	70.85 239	70.70 220

tpm		62.41 203	63.15 209	61.55 198	72.24 180	63.79 233	71.31 178	46.12 241	57.82 163	55.33 131	59.90 128	54.74 183	53.63 201	67.24 231	64.29 233	70.65 240	74.25 213

FPMVS		51.87 236	50.00 242	54.07 227	66.83 212	57.25 244	60.25 231	50.91 222	50.25 220	34.36 225	36.04 237	32.02 251	41.49 224	58.98 244	56.07 244	70.56 241	59.36 244

EPMVS		60.00 218	61.97 219	57.71 215	68.46 207	63.17 237	64.54 216	48.23 236	63.30 129	44.72 204	60.19 124	56.05 173	50.85 208	65.27 235	62.02 238	69.44 242	63.81 236

PMVS	39.38 18	46.06 243	43.30 246	49.28 236	62.93 222	38.75 252	41.88 250	53.50 206	33.33 249	35.46 224	28.90 246	31.01 252	33.04 238	58.61 246	54.63 247	68.86 243	57.88 245
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmnet_mix02		55.30 229	57.01 233	53.30 231	64.14 221	59.09 242	58.39 236	50.24 228	53.47 200	38.68 218	49.75 206	45.86 232	40.14 229	65.38 234	60.22 240	68.19 244	65.33 233

CHOSEN 280x420		58.70 222	61.88 220	54.98 225	55.45 245	50.55 250	64.92 214	40.36 244	55.21 186	38.13 220	48.31 209	63.76 133	63.03 127	73.73 187	68.58 214	68.00 245	73.04 216

new-patchmatchnet		46.97 241	49.47 243	44.05 242	62.82 223	56.55 245	45.35 249	52.01 217	42.47 237	17.04 251	35.73 238	35.21 248	21.84 250	61.27 241	54.83 246	65.26 246	60.26 241

ADS-MVSNet		55.94 228	58.01 229	53.54 230	62.48 225	58.48 243	59.12 234	46.20 240	59.65 157	42.88 210	52.34 193	53.31 200	46.31 215	62.00 240	60.02 241	64.23 247	60.24 243

N_pmnet		47.35 240	50.13 241	44.11 241	59.98 229	51.64 249	51.86 243	44.80 242	49.58 223	20.76 247	40.65 230	40.05 245	29.64 240	59.84 242	55.15 245	57.63 248	54.00 246

new_pmnet		38.40 245	42.64 247	33.44 245	37.54 254	45.00 251	36.60 251	32.72 250	40.27 241	12.72 253	29.89 244	28.90 253	24.78 245	53.17 248	52.90 248	56.31 249	48.34 247

Gipuma		36.38 246	35.80 248	37.07 243	45.76 248	33.90 253	29.81 252	48.47 234	39.91 242	18.02 250	8.00 256	8.14 260	25.14 243	59.29 243	61.02 239	55.19 250	40.31 249
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WB-MVS		40.01 244	45.06 245	34.13 244	58.84 238	53.28 248	28.60 253	58.10 183	32.93 250	4.65 259	40.92 228	28.33 254	7.26 253	58.86 245	56.09 243	47.36 251	44.98 248

PMMVS2		25.60 247	29.75 249	20.76 249	28.00 256	30.93 254	23.10 255	29.18 252	23.14 253	1.46 260	18.23 252	16.54 257	5.08 254	40.22 249	41.40 250	37.76 252	37.79 251

test_method		22.26 248	25.94 250	17.95 250	3.24 259	7.17 259	23.83 254	7.27 254	37.35 245	20.44 248	21.87 251	39.16 246	18.67 251	34.56 250	20.84 254	34.28 253	20.64 255

E-PMN		21.77 249	18.24 252	25.89 246	40.22 252	19.58 256	12.46 258	39.87 245	18.68 255	6.71 256	9.57 253	4.31 263	22.36 249	19.89 254	27.28 252	33.73 254	28.34 253

EMVS		20.98 250	17.15 253	25.44 247	39.51 253	19.37 257	12.66 257	39.59 246	19.10 254	6.62 257	9.27 254	4.40 262	22.43 248	17.99 255	24.40 253	31.81 255	25.53 254

tmp_tt				14.50 252	14.68 257	7.17 259	10.46 260	2.21 255	37.73 244	28.71 234	25.26 249	16.98 256	4.37 255	31.49 251	29.77 251	26.56 256

MVE	19.12 19	20.47 251	23.27 251	17.20 251	12.66 258	25.41 255	10.52 259	34.14 249	14.79 256	6.53 258	8.79 255	4.68 261	16.64 252	29.49 252	41.63 249	22.73 257	38.11 250
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						18.74 258	18.55 256	8.02 253	26.96 252	7.33 255	23.81 250	13.05 259	25.99 241	25.17 253		22.45 258	36.25 252

testmvs		0.09 252	0.15 254	0.02 253	0.01 261	0.02 261	0.05 262	0.01 257	0.11 257	0.01 262	0.26 258	0.01 264	0.06 258	0.10 256	0.10 255	0.01 259	0.43 257

test123		0.09 252	0.14 255	0.02 253	0.00 262	0.02 261	0.02 263	0.01 257	0.09 258	0.00 263	0.30 257	0.00 265	0.08 256	0.03 257	0.09 256	0.01 259	0.45 256

uanet_test		0.00 254	0.00 256	0.00 255	0.00 262	0.00 263	0.00 264	0.00 259	0.00 259	0.00 263	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 261	0.00 258

sosnet-low-res		0.00 254	0.00 256	0.00 255	0.00 262	0.00 263	0.00 264	0.00 259	0.00 259	0.00 263	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 261	0.00 258

sosnet		0.00 254	0.00 256	0.00 255	0.00 262	0.00 263	0.00 264	0.00 259	0.00 259	0.00 263	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 261	0.00 258

RE-MVS-def										46.24 194

9.14												86.88 17

SR-MVS					88.99 35			73.57 25				87.54 15

our_test_3					67.93 208	70.99 205	66.89 203

MTAPA										83.48 1		86.45 20

MTMP										82.66 5		84.91 28

Patchmatch-RL test							2.85 261

mPP-MVS					89.90 26							81.29 43

NP-MVS									80.10 48

Patchmtry						65.80 226	65.97 210	52.74 213		52.65 153

High-resolution multi-view benchmark