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.

SF-MVS		77.13 9	81.70 9	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 10	64.79 5	83.69 11	84.46 6	62.83 14	77.13 27	75.21 33	83.35 7	87.85 17

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 18	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 12	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 11	79.99 7	78.56 7	82.31 25	91.03 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
APDe-MVS		77.58 7	82.93 7	71.35 7	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 24	86.10 8	82.98 9	64.76 5	78.29 15	76.78 22	83.40 6	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 9	63.19 12	88.63 2	86.00 4	64.52 6	78.71 11	77.63 15	82.26 26	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ME-MVS		77.69 6	83.11 6	71.36 6	77.52 6	80.15 9	82.75 7	57.21 13	84.71 8	62.22 20	87.31 6	85.76 5	65.28 4	78.00 18	76.77 23	83.21 8	89.06 9

SteuartSystems-ACMMP		75.23 14	79.60 16	70.13 14	76.81 7	78.92 13	81.74 10	57.99 6	75.30 30	59.83 29	75.69 19	78.45 25	60.48 30	80.58 2	79.77 2	83.94 3	88.52 11
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 8	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 30	90.29 4

HPM-MVS++		76.01 11	80.47 13	70.81 10	76.60 9	74.96 37	80.18 19	58.36 2	81.96 11	63.50 11	78.80 15	82.53 12	64.40 7	78.74 10	78.84 5	81.81 36	87.46 19

MCST-MVS		73.67 25	77.39 27	69.33 19	76.26 10	78.19 18	78.77 28	54.54 32	75.33 28	59.99 28	67.96 33	79.23 23	62.43 17	78.00 18	75.71 31	84.02 2	87.30 20

CNVR-MVS		75.62 13	79.91 15	70.61 11	75.76 11	78.82 15	81.66 11	57.12 15	79.77 17	63.04 13	70.69 26	81.15 17	62.99 12	80.23 5	79.54 3	83.11 10	89.16 8

NCCC		74.27 20	77.83 25	70.13 14	75.70 12	77.41 24	80.51 17	57.09 16	78.25 21	62.28 19	65.54 38	78.26 26	62.18 19	79.13 8	78.51 10	83.01 12	87.68 18

CSCG		74.68 17	79.22 17	69.40 18	75.69 13	80.01 10	79.12 26	52.83 43	79.34 18	63.99 9	70.49 27	82.02 13	60.35 33	77.48 25	77.22 19	84.38 1	87.97 16

DPM-MVS		72.80 27	75.90 31	69.19 21	75.51 14	77.68 22	81.62 13	54.83 28	75.96 26	62.06 21	63.96 50	76.58 32	58.55 41	76.66 34	76.77 23	82.60 21	83.68 41

TPM-MVS					75.48 15	76.70 31	79.31 23			62.34 18	64.71 43	77.88 29	56.94 55			81.88 34	83.68 41
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
SMA-MVS		77.32 8	82.51 8	71.26 8	75.43 16	80.19 8	82.22 9	58.26 3	84.83 7	64.36 7	78.19 16	83.46 7	63.61 9	81.00 1	80.28 1	83.66 4	89.62 6
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
APD-MVS		75.80 12	80.90 12	69.86 16	75.42 17	78.48 17	81.43 15	57.44 12	80.45 15	59.32 30	85.28 9	80.82 19	63.96 8	76.89 29	76.08 29	81.58 41	88.30 13
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSP-MVS		77.82 5	83.46 5	71.24 9	75.26 18	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 8	66.24 3	78.21 17	78.56 7	80.34 48	89.39 7
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
train_agg		73.89 22	78.25 23	68.80 24	75.25 19	72.27 52	79.75 20	56.05 22	74.87 33	58.97 31	81.83 12	79.76 22	61.05 26	77.39 26	76.01 30	81.71 39	85.61 31

TSAR-MVS + MP.		75.22 15	80.06 14	69.56 17	74.61 20	72.74 50	80.59 16	55.70 25	80.80 14	62.65 16	86.25 7	82.92 10	62.07 20	76.89 29	75.66 32	81.77 38	85.19 34
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		74.43 18	78.87 19	69.26 20	74.39 21	73.70 46	79.06 27	55.24 27	81.04 13	62.71 15	80.18 13	82.61 11	61.70 22	75.43 41	73.92 44	82.44 24	85.22 33
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
ACMMP_NAP		76.15 10	81.17 10	70.30 12	74.09 22	79.47 11	81.59 14	57.09 16	81.38 12	63.89 10	79.02 14	80.48 20	62.24 18	80.05 6	79.12 4	82.94 13	88.64 10

HFP-MVS		74.87 16	78.86 21	70.21 13	73.99 23	77.91 19	80.36 18	56.63 18	78.41 20	64.27 8	74.54 21	77.75 30	62.96 13	78.70 12	77.82 13	83.02 11	86.91 22

AdaColmap		67.89 46	68.85 61	66.77 30	73.73 24	74.30 44	75.28 43	53.58 38	70.24 48	57.59 38	51.19 125	59.19 114	60.74 29	75.33 43	73.72 46	79.69 56	77.96 77

MP-MVS		74.31 19	78.87 19	68.99 22	73.49 25	78.56 16	79.25 25	56.51 19	75.33 28	60.69 26	75.30 20	79.12 24	61.81 21	77.78 22	77.93 12	82.18 32	88.06 15
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		72.56 29	79.07 18	64.96 42	73.24 26	73.16 49	78.50 29	48.80 69	79.34 18	55.32 44	85.04 10	81.49 16	58.57 40	75.06 44	73.75 45	75.35 124	85.61 31

CDPH-MVS		71.47 33	75.82 33	66.41 33	72.97 27	77.15 26	78.14 32	54.71 29	69.88 50	53.07 67	70.98 25	74.83 38	56.95 54	76.22 35	76.57 25	82.62 19	85.09 35

PGM-MVS		72.89 26	77.13 28	67.94 26	72.47 28	77.25 25	79.27 24	54.63 31	73.71 37	57.95 37	72.38 24	75.33 36	60.75 28	78.25 16	77.36 18	82.57 22	85.62 30

ACMMPR		73.79 24	78.41 22	68.40 25	72.35 29	77.79 21	79.32 22	56.38 20	77.67 24	58.30 35	74.16 22	76.66 31	61.40 23	78.32 14	77.80 14	82.68 17	86.51 23

OPM-MVS		69.33 38	71.05 47	67.32 28	72.34 30	75.70 34	79.57 21	56.34 21	55.21 93	53.81 64	59.51 83	68.96 59	59.67 35	77.61 24	76.44 27	82.19 30	83.88 40
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
X-MVS		71.18 34	75.66 34	65.96 37	71.71 31	76.96 27	77.26 35	55.88 24	72.75 41	54.48 60	64.39 45	74.47 39	54.19 81	77.84 21	77.37 17	82.21 29	85.85 28

HQP-MVS		70.88 35	75.02 35	66.05 36	71.69 32	74.47 42	77.51 34	53.17 40	72.89 40	54.88 50	70.03 29	70.48 53	57.26 49	76.02 37	75.01 36	81.78 37	86.21 24

MAR-MVS		68.04 45	70.74 49	64.90 43	71.68 33	76.33 33	74.63 46	50.48 57	63.81 58	55.52 43	54.88 105	69.90 55	57.39 48	75.42 42	74.79 38	79.71 53	80.03 58
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
mPP-MVS					71.67 34							74.36 42

SR-MVS					71.46 35			54.67 30				81.54 15

MGCNet		72.45 30	77.44 26	66.61 31	71.08 36	77.81 20	76.74 36	49.30 63	73.12 39	61.17 22	73.70 23	78.08 27	58.78 38	76.75 33	76.52 26	82.61 20	86.14 26

CLD-MVS		67.02 50	71.57 44	61.71 52	71.01 37	74.81 39	71.62 54	38.91 185	71.86 44	60.70 25	64.97 42	67.88 68	51.88 108	76.77 32	74.98 37	76.11 112	69.75 145
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		72.63 28	76.95 29	67.59 27	70.67 38	75.53 35	77.95 33	56.01 23	75.65 27	58.82 32	69.16 31	76.48 33	60.46 31	77.66 23	77.20 20	81.65 40	86.97 21

ACMM	60.30 7	67.58 48	68.82 62	66.13 35	70.59 39	72.01 54	76.54 38	54.26 34	65.64 56	54.78 54	50.35 128	61.72 103	58.74 39	75.79 39	75.03 35	81.88 34	81.17 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					70.49 40	76.96 27	74.36 47			54.48 60		74.47 39				82.24 27

X-MVStestdata					70.49 40	76.96 27	74.36 47			54.48 60		74.47 39				82.24 27

ACMMP		71.57 32	75.84 32	66.59 32	70.30 42	76.85 30	78.46 30	53.95 36	73.52 38	55.56 42	70.13 28	71.36 51	58.55 41	77.00 28	76.23 28	82.71 16	85.81 29
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
MVS_111021_HR		67.62 47	70.39 51	64.39 45	69.77 43	70.45 61	71.44 56	51.72 49	60.77 66	55.06 47	62.14 63	66.40 80	58.13 44	76.13 36	74.79 38	80.19 50	82.04 50

MSLP-MVS++		68.17 44	70.72 50	65.19 40	69.41 44	70.64 58	74.99 44	45.76 81	70.20 49	60.17 27	56.42 96	73.01 45	61.14 24	72.80 55	70.54 61	79.70 54	81.42 52

LGP-MVS_train		68.87 40	72.03 43	65.18 41	69.33 45	74.03 45	76.67 37	53.88 37	68.46 51	52.05 74	63.21 53	63.89 89	56.31 58	75.99 38	74.43 40	82.83 15	84.18 37

ACMP	61.42 5	68.72 43	71.37 45	65.64 39	69.06 46	74.45 43	75.88 41	53.30 39	68.10 52	55.74 41	61.53 69	62.29 97	56.97 53	74.70 47	74.23 42	82.88 14	84.31 36
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS_fast	65.08 3	72.00 31	76.11 30	67.21 29	68.93 47	77.46 23	76.54 38	54.35 33	74.92 32	58.64 34	65.18 40	74.04 44	62.62 15	77.92 20	77.02 21	82.16 33	86.21 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		68.77 41	73.01 38	63.83 46	68.30 48	75.19 36	73.73 50	47.90 70	63.86 57	54.84 53	67.51 35	74.36 42	57.62 45	74.22 49	73.57 48	80.56 46	82.36 47

TSAR-MVS + GP.		69.71 36	73.92 37	64.80 44	68.27 49	70.56 59	71.90 52	50.75 53	71.38 45	57.46 39	68.68 32	75.42 35	60.10 34	73.47 52	73.99 43	80.32 49	83.97 39

3Dnovator+	62.63 4	69.51 37	72.62 40	65.88 38	68.21 50	76.47 32	73.50 51	52.74 44	70.85 46	58.65 33	55.97 98	69.95 54	61.11 25	76.80 31	75.09 34	81.09 44	83.23 45

DeepC-MVS	66.32 2	73.85 23	78.10 24	68.90 23	67.92 51	79.31 12	78.16 31	59.28 1	78.24 22	61.13 23	67.36 36	76.10 34	63.40 10	79.11 9	78.41 11	83.52 5	88.16 14
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	66.49 1	74.25 21	80.97 11	66.41 33	67.75 52	78.87 14	75.61 42	54.16 35	84.86 6	58.22 36	77.94 17	81.01 18	62.52 16	78.34 13	77.38 16	80.16 51	88.40 12

EC-MVSNet		67.01 51	70.27 54	63.21 48	67.21 53	70.47 60	69.01 72	46.96 74	59.16 75	53.23 66	64.01 49	69.71 57	60.37 32	74.92 45	71.24 56	82.50 23	82.41 46

UA-Net		58.50 112	64.68 97	51.30 141	66.97 54	67.13 100	53.68 188	45.65 84	49.51 128	31.58 176	62.91 55	68.47 61	35.85 205	68.20 118	67.28 102	74.03 139	69.24 156

PHI-MVS		69.27 39	74.84 36	62.76 51	66.83 55	74.83 38	73.88 49	49.32 62	70.61 47	50.93 79	69.62 30	74.84 37	57.25 50	75.53 40	74.32 41	78.35 72	84.17 38

3Dnovator	60.86 6	66.99 52	70.32 52	63.11 49	66.63 56	74.52 40	71.56 55	45.76 81	67.37 54	55.00 49	54.31 110	68.19 64	58.49 43	73.97 50	73.63 47	81.22 43	80.23 57

EPNet		65.14 62	69.54 58	60.00 71	66.61 57	67.67 90	67.53 81	55.32 26	62.67 62	46.22 100	67.74 34	65.93 83	48.07 131	72.17 58	72.12 50	76.28 108	78.47 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	57.13 9	62.81 81	65.75 88	59.39 75	66.47 58	69.52 63	64.26 119	43.07 144	61.34 65	50.19 82	47.29 146	64.41 88	54.60 78	70.18 84	68.62 82	77.73 79	78.89 66

ACMH	52.42 13	58.24 119	59.56 139	56.70 101	66.34 59	69.59 62	66.71 91	49.12 64	46.08 162	28.90 189	42.67 199	41.20 222	52.60 100	71.39 65	70.28 63	76.51 104	75.72 112
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 114	58.97 145	57.85 92	66.27 60	66.23 109	67.72 78	42.33 148	53.43 101	43.68 112	43.39 187	45.35 199	49.75 120	68.66 107	67.77 92	77.38 90	67.96 161

QAPM		65.27 58	69.49 59	60.35 67	65.43 61	72.20 53	65.69 104	47.23 72	63.46 59	49.14 84	53.56 111	71.04 52	57.01 52	72.60 57	71.41 54	77.62 83	82.14 49

CPTT-MVS		68.76 42	73.01 38	63.81 47	65.42 62	73.66 47	76.39 40	52.08 45	72.61 42	50.33 81	60.73 75	72.65 47	59.43 36	73.32 53	72.12 50	79.19 62	85.99 27

MS-PatchMatch		58.19 121	60.20 126	55.85 108	65.17 63	64.16 130	64.82 111	41.48 159	50.95 118	42.17 121	45.38 167	56.42 126	48.08 130	68.30 113	66.70 113	73.39 158	69.46 154

casdiffseed414692147		63.90 73	66.17 85	61.24 55	64.92 64	69.27 65	70.00 69	46.18 78	58.66 78	51.43 77	55.30 102	62.51 94	56.20 61	70.93 72	68.62 82	78.73 64	77.90 78

PCF-MVS	59.98 8	67.32 49	71.04 48	62.97 50	64.77 65	74.49 41	74.78 45	49.54 59	67.44 53	54.39 63	58.35 90	72.81 46	55.79 65	71.54 64	69.24 72	78.57 66	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EG-PatchMatch MVS		56.98 128	58.24 152	55.50 110	64.66 66	68.62 69	61.48 128	43.63 127	38.44 225	41.44 125	38.05 217	46.18 194	43.95 149	71.71 63	70.61 60	77.87 73	74.08 125

Effi-MVS+-dtu		60.34 97	62.32 109	58.03 87	64.31 67	67.44 95	65.99 98	42.26 149	49.55 126	42.00 124	48.92 136	59.79 112	56.27 59	68.07 122	67.03 105	77.35 91	75.45 115

FC-MVSNet-train		58.40 115	63.15 106	52.85 131	64.29 68	61.84 146	55.98 168	46.47 76	53.06 105	34.96 158	61.95 65	56.37 128	39.49 173	68.67 106	68.36 85	75.92 118	71.81 133

Effi-MVS+		63.28 78	65.96 87	60.17 69	64.26 69	68.06 82	68.78 75	45.71 83	54.08 97	46.64 95	55.92 99	63.13 93	55.94 63	70.38 80	71.43 53	79.68 57	78.70 67

LS3D		60.20 98	61.70 110	58.45 82	64.18 70	67.77 87	67.19 84	48.84 68	61.67 64	41.27 128	45.89 161	51.81 145	54.18 82	68.78 104	66.50 123	75.03 128	69.48 152

ACMH+	53.71 12	59.26 104	60.28 123	58.06 85	64.17 71	68.46 70	67.51 82	50.93 52	52.46 113	35.83 154	40.83 205	45.12 203	52.32 103	69.88 88	69.00 77	77.59 86	76.21 109

GeoE		62.43 84	64.79 96	59.68 74	64.15 72	67.17 99	68.80 74	44.42 100	55.65 92	47.38 89	51.54 122	62.51 94	54.04 84	69.99 87	68.07 87	79.28 60	78.57 68

DELS-MVS		65.87 54	70.30 53	60.71 66	64.05 73	72.68 51	70.90 57	45.43 85	57.49 87	49.05 86	64.43 44	68.66 60	55.11 73	74.31 48	73.02 49	79.70 54	81.51 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
sasdasda		65.62 55	72.06 41	58.11 83	63.94 74	71.05 56	64.49 116	43.18 140	74.08 34	47.35 90	64.17 47	71.97 48	51.17 113	71.87 60	70.74 58	78.51 69	80.56 55

canonicalmvs		65.62 55	72.06 41	58.11 83	63.94 74	71.05 56	64.49 116	43.18 140	74.08 34	47.35 90	64.17 47	71.97 48	51.17 113	71.87 60	70.74 58	78.51 69	80.56 55

EIA-MVS		61.53 92	63.79 102	58.89 80	63.82 76	67.61 91	65.35 107	42.15 152	49.98 123	45.66 103	57.47 94	56.62 124	56.59 57	70.91 73	69.15 73	79.78 52	74.80 119

Anonymous202405211			60.60 119		63.44 77	66.71 106	61.00 133	47.23 72	50.62 121		36.85 220	60.63 109	43.03 157	69.17 100	67.72 94	75.41 121	72.54 130

ETV-MVS		63.23 79	66.08 86	59.91 72	63.13 78	68.13 76	67.62 80	44.62 96	53.39 102	46.23 99	58.74 87	58.19 117	57.45 47	73.60 51	71.38 55	80.39 47	79.13 63

viewcassd2359sk11		64.22 63	67.08 67	60.87 61	63.08 79	68.05 84	70.51 63	43.92 118	59.80 69	55.05 48	62.49 61	66.89 72	55.09 74	69.39 96	66.19 130	77.60 84	76.77 98

E3new		64.18 65	67.01 70	60.89 59	63.07 80	68.08 80	70.57 61	43.95 115	59.33 72	54.87 52	61.94 67	66.76 75	55.16 71	69.60 93	66.42 126	77.70 80	76.92 91

E2		64.19 64	67.06 68	60.84 63	63.07 80	68.02 85	70.44 64	43.88 119	59.94 68	55.15 46	62.73 57	66.97 71	55.01 75	69.18 99	65.98 134	77.53 88	76.63 100

E3		64.18 65	67.01 70	60.89 59	63.07 80	68.07 81	70.57 61	43.94 116	59.32 73	54.88 50	61.95 65	66.78 74	55.16 71	69.60 93	66.43 125	77.70 80	76.92 91

E6new		64.03 69	66.63 78	60.99 57	63.04 83	68.16 73	70.80 58	44.14 102	57.66 85	54.63 55	60.32 77	66.05 81	55.49 66	70.14 85	67.09 103	77.85 74	76.94 89

E6		64.03 69	66.63 78	60.99 57	63.04 83	68.16 73	70.80 58	44.14 102	57.66 85	54.63 55	60.32 77	66.05 81	55.49 66	70.14 85	67.09 103	77.85 74	76.94 89

E4		64.06 68	66.79 75	60.87 61	63.03 85	68.11 77	70.61 60	44.00 111	58.24 82	54.56 57	61.00 74	66.64 76	55.22 69	69.80 89	66.69 114	77.81 76	77.07 88

E5new		64.00 71	66.77 76	60.77 64	63.02 86	68.11 77	70.42 65	43.97 113	58.41 80	54.52 58	61.10 71	66.52 77	54.97 76	69.61 91	66.52 120	77.74 77	77.09 86

E5		64.00 71	66.77 76	60.77 64	63.02 86	68.11 77	70.42 65	43.97 113	58.41 80	54.52 58	61.10 71	66.52 77	54.97 76	69.61 91	66.52 120	77.74 77	77.09 86

casdiffmvs_mvg		65.26 59	69.48 60	60.33 68	62.99 88	69.34 64	69.80 70	45.27 87	63.38 60	51.11 78	65.12 41	69.75 56	53.51 89	71.74 62	68.86 78	79.33 58	78.19 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
viewdifsd2359ckpt13		63.83 74	67.03 69	60.10 70	62.56 89	68.92 67	69.73 71	43.49 132	57.96 83	52.16 73	61.09 73	65.39 86	55.20 70	70.36 81	67.48 99	77.48 89	78.00 76

viewdifsd2359ckpt09		65.38 57	68.69 64	61.53 53	62.15 90	71.64 55	71.84 53	47.45 71	58.95 77	51.79 76	61.73 68	65.71 85	57.08 51	72.17 58	70.82 57	78.87 63	79.79 59

viewdifsd2359ckpt07		61.71 88	65.49 90	57.31 95	62.12 91	65.52 115	68.53 76	38.21 196	56.37 89	48.07 88	61.11 70	65.85 84	52.82 98	68.34 112	64.46 157	74.08 136	76.80 95

gg-mvs-nofinetune		49.07 198	52.56 199	45.00 200	61.99 92	59.78 165	53.55 190	41.63 157	31.62 243	12.08 241	29.56 238	53.28 139	29.57 220	66.27 155	64.49 155	71.19 190	62.92 206

SPE-MVS-test		65.18 60	68.70 63	61.07 56	61.92 93	68.06 82	67.09 88	45.18 89	58.47 79	52.02 75	65.76 37	66.44 79	59.24 37	72.71 56	70.05 66	80.98 45	79.40 62

DCV-MVSNet		59.49 100	64.00 101	54.23 117	61.81 94	64.33 128	61.42 129	43.77 121	52.85 110	38.94 142	55.62 101	62.15 101	43.24 156	69.39 96	67.66 96	76.22 110	75.97 110

casdiffmvs		64.09 67	68.13 65	59.37 76	61.81 94	68.32 72	68.48 77	44.45 99	61.95 63	49.12 85	63.04 54	69.67 58	53.83 85	70.46 77	66.06 131	78.55 67	77.43 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		65.88 53	69.71 57	61.41 54	61.76 96	68.14 75	67.65 79	44.00 111	59.14 76	52.69 68	65.19 39	68.13 65	60.90 27	74.74 46	71.58 52	81.46 42	81.04 54

Anonymous20231211		57.71 124	60.79 116	54.13 119	61.68 97	65.81 113	60.81 134	43.70 125	51.97 116	39.67 137	34.82 225	63.59 90	43.31 154	68.55 110	66.63 117	75.59 119	74.13 124

IS_MVSNet		57.95 122	64.26 99	50.60 143	61.62 98	65.25 120	57.18 154	45.42 86	50.79 119	26.49 207	57.81 92	60.05 111	34.51 209	71.24 68	70.20 65	78.36 71	74.44 121

viewmanbaseed2359cas		63.67 75	67.42 66	59.30 78	61.34 99	67.42 96	70.01 68	40.50 172	59.53 70	52.60 69	62.56 60	67.34 70	54.44 80	70.33 82	66.93 109	76.91 98	77.82 80

NR-MVSNet		55.35 145	59.46 140	50.56 144	61.33 100	62.97 138	57.91 150	51.80 47	48.62 143	20.59 223	51.99 120	44.73 209	34.10 212	68.58 108	68.64 81	77.66 82	70.67 142

MVS_111021_LR		63.05 80	66.43 82	59.10 79	61.33 100	63.77 134	65.87 101	43.58 128	60.20 67	53.70 65	62.09 64	62.38 96	55.84 64	70.24 83	68.08 86	74.30 133	78.28 73

viewmacassd2359aftdt		63.43 77	66.95 72	59.32 77	61.27 102	67.48 94	70.15 67	40.54 169	57.82 84	52.27 72	60.49 76	66.81 73	54.58 79	70.67 75	67.39 101	77.08 97	78.02 75

MGCFI-Net		61.46 93	69.72 56	51.83 138	61.00 103	66.16 110	56.50 161	40.73 167	73.98 36	35.18 155	64.23 46	71.42 50	42.45 159	69.22 98	64.01 161	75.09 127	79.03 65

EPP-MVSNet		59.39 103	65.45 91	52.32 135	60.96 104	67.70 89	58.42 147	44.75 94	49.71 125	27.23 201	59.03 84	62.20 100	43.34 153	70.71 74	69.13 74	79.25 61	79.63 61

TransMVSNet (Re)		51.92 171	55.38 170	47.88 175	60.95 105	59.90 164	53.95 183	45.14 90	39.47 213	24.85 213	43.87 181	46.51 190	29.15 221	67.55 132	65.23 146	73.26 163	65.16 193

gm-plane-assit		44.74 222	45.95 230	43.33 209	60.88 106	46.79 238	36.97 248	32.24 238	24.15 251	11.79 242	29.26 239	32.97 245	46.64 136	65.09 170	62.95 174	71.45 186	60.42 218

baseline1		54.48 154	58.69 146	49.57 150	60.63 107	58.29 191	55.70 170	44.95 92	49.20 131	29.62 185	54.77 106	54.75 133	35.29 206	67.15 142	64.08 159	71.21 189	62.58 211

test2506		55.82 140	59.57 138	51.46 139	60.39 108	64.55 126	58.69 145	48.87 66	53.91 98	26.99 202	48.97 134	41.72 221	37.71 186	70.96 70	69.49 69	76.08 113	67.37 166

ECVR-MVS		56.44 135	60.74 117	51.42 140	60.39 108	64.55 126	58.69 145	48.87 66	53.91 98	26.76 204	45.55 166	53.43 138	37.71 186	70.96 70	69.49 69	76.08 113	67.32 168

DI_MVS_pp		61.88 86	65.17 93	58.06 85	60.05 110	65.26 118	66.03 97	44.22 101	55.75 91	46.73 93	54.64 108	68.12 66	54.13 83	69.13 101	66.66 115	77.18 93	76.61 101

PVSNet_Blended_VisFu		63.65 76	66.92 73	59.83 73	60.03 111	73.44 48	66.33 94	48.95 65	52.20 115	50.81 80	56.07 97	60.25 110	53.56 87	73.23 54	70.01 67	79.30 59	83.24 44

UniMVSNet_NR-MVSNet		56.94 130	61.14 113	52.05 137	60.02 112	65.21 121	57.44 152	52.93 42	49.37 129	24.31 216	54.62 109	50.54 151	39.04 175	68.69 105	68.84 79	78.53 68	70.72 138

IterMVS-LS		58.30 118	61.39 112	54.71 113	59.92 113	58.40 183	59.42 139	43.64 126	48.71 140	40.25 135	57.53 93	58.55 116	52.15 105	65.42 168	65.34 143	72.85 166	75.77 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 146	59.98 131	49.71 149	59.80 114	64.10 131	56.48 162	49.34 61	52.27 114	21.56 221	44.49 175	51.96 144	35.93 204	70.59 76	69.07 75	75.13 126	67.40 164

MVS_Test		62.40 85	66.23 84	57.94 88	59.77 115	64.77 124	66.50 93	41.76 155	57.26 88	49.33 83	62.68 58	67.47 69	53.50 91	68.57 109	66.25 127	76.77 100	76.58 102

FA-MVS(training)		60.00 99	63.14 107	56.33 103	59.50 116	64.30 129	65.15 109	38.75 191	56.20 90	45.77 101	53.08 112	56.45 125	52.10 106	69.04 103	67.67 95	76.69 101	75.27 118

TranMVSNet+NR-MVSNet		55.87 138	60.14 128	50.88 142	59.46 117	63.82 133	57.93 149	52.98 41	48.94 135	20.52 224	52.87 114	47.33 177	36.81 196	69.12 102	69.03 76	77.56 87	69.89 144

Fast-Effi-MVS+		60.36 96	63.35 105	56.87 99	58.70 118	65.86 112	65.08 110	37.11 207	53.00 107	45.36 105	52.12 119	56.07 130	56.27 59	71.28 67	69.42 71	78.71 65	75.69 113

IB-MVS	54.11 11	58.36 117	60.70 118	55.62 109	58.67 119	68.02 85	61.56 126	43.15 142	46.09 161	44.06 111	44.24 177	50.99 150	48.71 125	66.70 148	70.33 62	77.60 84	78.50 69
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
Fast-Effi-MVS+-dtu		56.30 136	59.29 142	52.82 132	58.64 120	64.89 122	65.56 105	32.89 235	45.80 164	35.04 157	45.89 161	54.14 135	49.41 121	67.16 141	66.45 124	75.37 123	70.69 140

CNLPA		62.78 82	66.31 83	58.65 81	58.47 121	68.41 71	65.98 99	41.22 163	78.02 23	56.04 40	46.65 149	59.50 113	57.50 46	69.67 90	65.27 145	72.70 172	76.67 99

tpm cat1		53.30 159	53.41 185	53.17 128	58.16 122	59.15 173	63.73 122	38.27 195	50.73 120	46.98 92	45.57 165	44.00 215	49.20 122	55.90 230	54.02 229	62.65 222	64.50 198

v1144		58.88 107	60.16 127	57.39 94	58.03 123	67.26 97	67.14 86	44.46 98	45.17 167	44.33 110	47.81 143	49.92 156	53.20 97	67.77 128	66.62 118	77.15 94	76.58 102

v10		59.17 106	60.60 119	57.50 93	57.95 124	66.73 103	67.09 88	44.11 104	46.85 155	45.42 104	48.18 142	51.07 147	53.63 86	67.84 126	66.59 119	76.79 99	76.92 91

v1192		58.51 111	59.66 134	57.17 96	57.82 125	67.72 88	66.21 96	44.83 93	44.15 175	43.49 113	46.68 148	47.94 167	53.55 88	67.39 135	66.51 122	77.13 95	77.20 84

viewmambaseed2359dif		60.40 95	64.15 100	56.03 105	57.79 126	63.53 136	65.91 100	41.64 156	54.98 94	46.47 96	60.16 80	64.71 87	50.76 115	66.25 156	62.83 176	73.61 155	76.57 104

v144192		58.23 120	59.40 141	56.87 99	57.56 127	66.89 101	65.70 102	45.01 91	44.06 176	42.88 115	46.61 150	48.09 166	53.49 92	66.94 146	65.90 137	76.61 102	77.29 82

v1921920		57.89 123	59.02 144	56.58 102	57.55 128	66.66 107	64.72 113	44.70 95	43.55 180	42.73 116	46.17 158	46.93 185	53.51 89	66.78 147	65.75 139	76.29 107	77.28 83

Vis-MVSNet (Re-imp)		50.37 182	57.73 158	41.80 216	57.53 129	54.35 207	45.70 227	45.24 88	49.80 124	13.43 238	58.23 91	56.42 126	20.11 240	62.96 178	63.36 170	68.76 200	58.96 223

CostFormer		56.57 133	59.13 143	53.60 122	57.52 130	61.12 153	66.94 90	35.95 215	53.44 100	44.68 108	55.87 100	54.44 134	48.21 128	60.37 191	58.33 199	68.27 202	70.33 143

thres400		52.38 165	55.51 168	48.74 161	57.49 131	60.10 163	55.45 173	43.54 129	42.90 188	26.72 205	43.34 189	45.03 207	36.61 199	66.20 158	64.53 154	72.66 173	66.43 179

thres600view7		51.91 172	55.14 172	48.14 171	57.43 132	60.18 161	54.60 179	43.73 123	42.61 192	25.20 211	43.10 192	44.47 212	35.19 207	66.36 152	63.28 171	72.66 173	66.01 186

thres200		52.39 164	55.37 171	48.90 159	57.39 133	60.18 161	55.60 171	43.73 123	42.93 187	27.41 199	43.35 188	45.09 204	36.61 199	66.36 152	63.92 166	72.66 173	65.78 188

baseline2		55.89 137	57.82 155	53.64 121	57.36 134	61.09 154	59.75 138	40.45 173	47.38 153	41.26 129	51.23 124	46.90 186	48.11 129	65.63 165	64.38 158	74.90 129	68.16 160

v8		58.88 107	60.57 121	56.92 98	57.35 135	65.69 114	66.69 92	42.64 146	47.89 150	45.77 101	49.04 133	52.98 140	52.77 99	67.51 133	65.57 140	76.26 109	75.30 117

thres100view900		52.04 169	54.81 176	48.80 160	57.31 136	59.33 169	55.30 175	42.92 145	42.85 189	27.81 197	43.00 193	45.06 205	36.99 192	64.74 171	63.51 168	72.47 176	65.21 192

tfpn200view9		52.53 162	55.51 168	49.06 157	57.31 136	60.24 160	55.42 174	43.77 121	42.85 189	27.81 197	43.00 193	45.06 205	37.32 190	66.38 151	64.54 153	72.71 171	66.54 176

v1240		57.55 125	58.63 148	56.29 104	57.30 138	66.48 108	63.77 121	44.56 97	42.77 191	42.48 118	45.64 164	46.28 192	53.46 93	66.32 154	65.80 138	76.16 111	77.13 85

dmvs_re		52.07 167	55.11 173	48.54 166	57.27 139	51.93 216	57.73 151	43.13 143	43.65 178	26.57 206	44.52 174	50.00 155	36.53 201	66.58 150	62.15 182	69.97 196	66.91 173

CHOSEN 1792x2688		55.85 139	58.01 153	53.33 124	57.26 140	62.82 140	63.29 125	41.55 158	46.65 157	38.34 143	34.55 226	53.50 136	52.43 102	67.10 143	67.56 98	67.13 206	73.92 127

PVSNet_BlendedMVS		61.63 90	64.82 94	57.91 90	57.21 141	67.55 92	63.47 123	46.08 79	54.72 95	52.46 70	58.59 88	60.73 106	51.82 109	70.46 77	65.20 147	76.44 105	76.50 106

PVSNet_Blended		61.63 90	64.82 94	57.91 90	57.21 141	67.55 92	63.47 123	46.08 79	54.72 95	52.46 70	58.59 88	60.73 106	51.82 109	70.46 77	65.20 147	76.44 105	76.50 106

viewdifsd2359ckpt11		59.45 101	63.57 103	54.65 115	57.17 143	62.71 142	64.67 114	38.99 182	52.96 108	42.12 122	58.97 85	62.23 98	51.18 111	67.35 136	63.98 162	73.75 148	76.80 95

viewmsd2359difaftdt		59.45 101	63.57 103	54.65 115	57.17 143	62.71 142	64.67 114	38.99 182	52.96 108	42.12 122	58.97 85	62.22 99	51.18 111	67.35 136	63.98 162	73.75 148	76.80 95

v2v482		58.69 110	60.12 130	57.03 97	57.16 145	66.05 111	67.17 85	43.52 130	46.33 159	45.19 106	49.46 132	51.02 148	52.51 101	67.30 138	66.03 133	76.61 102	74.62 120

tfpnnormal		50.16 184	52.19 205	47.78 177	56.86 146	58.37 185	54.15 181	44.01 110	38.35 227	25.94 209	36.10 221	37.89 235	34.50 210	65.93 160	63.42 169	71.26 188	65.28 191

diffmvs_AUTHOR		61.79 87	66.80 74	55.95 106	56.69 147	63.92 132	67.27 83	41.28 161	59.32 73	46.43 97	63.31 52	68.30 63	50.56 116	68.30 113	66.06 131	73.48 156	78.36 71

diffmvs		61.64 89	66.55 81	55.90 107	56.63 148	63.71 135	67.13 87	41.27 162	59.49 71	46.70 94	63.93 51	68.01 67	50.46 117	67.30 138	65.51 141	73.24 164	77.87 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
HyFIR lowres test		56.87 131	58.60 149	54.84 112	56.62 149	69.27 65	64.77 112	42.21 150	45.66 165	37.50 149	33.08 229	57.47 122	53.33 94	65.46 167	67.94 88	74.60 130	71.35 135

v7n		55.67 141	57.46 160	53.59 123	56.06 150	65.29 117	61.06 132	43.26 139	40.17 210	37.99 146	40.79 206	45.27 202	47.09 135	67.67 130	66.21 128	76.08 113	76.82 94

dps		50.42 180	51.20 211	49.51 151	55.88 151	56.07 203	53.73 184	38.89 186	43.66 177	40.36 134	45.66 163	37.63 237	45.23 144	59.05 201	56.18 211	62.94 221	60.16 219

CANet_DTU		58.88 107	64.68 97	52.12 136	55.77 152	66.75 102	63.92 120	37.04 208	53.32 103	37.45 150	59.81 81	61.81 102	44.43 148	68.25 115	67.47 100	74.12 135	75.33 116

WR-MVS		48.78 203	55.06 174	41.45 217	55.50 153	60.40 159	43.77 235	49.99 58	41.92 197	8.10 252	45.24 170	45.56 197	17.47 241	61.57 186	64.60 152	73.85 142	66.14 185

UniMVSNet (Re)		55.15 150	60.39 122	49.03 158	55.31 154	64.59 125	55.77 169	50.63 54	48.66 142	20.95 222	51.47 123	50.40 152	34.41 211	67.81 127	67.89 89	77.11 96	71.88 132

test-LLR		49.28 192	50.29 215	48.10 172	55.26 155	47.16 233	49.52 207	43.48 134	39.22 214	31.98 172	43.65 185	47.93 168	41.29 165	56.80 219	55.36 219	67.08 207	61.94 212

test0.0.03 1		43.15 227	46.95 229	38.72 226	55.26 155	50.56 220	42.48 238	43.48 134	38.16 229	15.11 233	35.07 224	44.69 210	16.47 243	55.95 229	54.34 228	59.54 230	49.87 243

GA-MVS		55.67 141	58.33 150	52.58 134	55.23 157	63.09 137	61.08 131	40.15 178	42.95 186	37.02 152	52.61 116	47.68 171	47.51 133	65.92 161	65.35 142	74.49 132	70.68 141

DTE-MVSNet		48.03 209	53.28 187	41.91 215	54.64 158	57.50 198	44.63 234	51.66 50	41.02 204	7.97 253	46.26 155	40.90 223	20.24 239	60.45 190	62.89 175	72.33 179	63.97 200

pmmvs4		54.66 153	56.07 164	53.00 129	54.63 159	57.08 200	60.43 136	44.10 105	51.69 117	40.55 132	46.55 153	44.79 208	45.95 141	62.54 180	63.66 167	72.36 178	66.20 183

DU-MVS		55.41 144	59.59 135	50.54 145	54.60 160	62.97 138	57.44 152	51.80 47	48.62 143	24.31 216	51.99 120	47.00 182	39.04 175	68.11 120	67.75 93	76.03 117	70.72 138

Baseline_NR-MVSNet		53.50 157	57.89 154	48.37 169	54.60 160	59.25 172	56.10 164	51.84 46	49.32 130	17.92 231	45.38 167	47.68 171	36.93 193	68.11 120	65.95 135	72.84 167	69.57 150

v148		55.58 143	57.61 159	53.20 126	54.59 162	61.86 145	61.18 130	38.70 192	44.30 174	42.25 120	47.53 144	50.24 154	48.73 124	65.15 169	62.61 180	73.79 143	71.61 134

PEN-MVS		49.21 195	54.32 178	43.24 211	54.33 163	59.26 171	47.04 220	51.37 51	41.67 200	9.97 247	46.22 156	41.80 220	22.97 236	60.52 189	64.03 160	73.73 150	66.75 175

pm-mvs1		51.02 176	55.55 167	45.73 191	54.16 164	58.52 178	50.92 203	42.56 147	40.32 208	25.67 210	43.66 184	50.34 153	30.06 219	65.85 162	63.97 164	70.99 192	66.21 182

EPNet_dtu		52.05 168	58.26 151	44.81 201	54.10 165	50.09 223	52.01 201	40.82 166	53.03 106	27.41 199	54.90 104	57.96 121	26.72 227	62.97 177	62.70 179	67.78 204	66.19 184
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 202	51.27 210	45.96 190	54.10 165	47.35 232	56.05 165	30.23 239	46.70 156	43.21 114	52.54 117	47.55 174	37.28 191	54.11 235	50.50 239	54.90 240	60.12 220

CDS-MVSNet		52.42 163	57.06 162	47.02 181	53.92 167	58.30 190	55.50 172	46.47 76	42.52 193	29.38 187	49.50 131	52.85 141	28.49 225	66.70 148	66.89 110	68.34 201	62.63 210
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 236	44.20 237	35.92 234	53.73 168	49.05 224	38.54 245	43.49 132	32.55 240	9.54 248	27.88 242	39.12 231	12.24 248	56.28 226	54.69 225	57.96 235	49.83 244

Vis-MVSNet		58.48 113	65.70 89	50.06 148	53.40 169	67.20 98	60.24 137	43.32 137	48.83 137	30.23 182	62.38 62	61.61 104	40.35 168	71.03 69	69.77 68	72.82 168	79.11 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PLC	52.09 14	59.21 105	62.47 108	55.41 111	53.24 170	64.84 123	64.47 118	40.41 175	65.92 55	44.53 109	46.19 157	55.69 131	55.33 68	68.24 117	65.30 144	74.50 131	71.09 136
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 132	59.68 133	53.19 127	52.97 171	60.96 156	59.41 140	40.51 170	48.26 146	41.06 130	52.67 115	46.30 191	49.78 118	67.66 131	67.83 90	75.39 122	74.07 126

OMC-MVS		65.16 61	71.35 46	57.94 88	52.95 172	68.82 68	69.00 73	38.28 194	79.89 16	55.20 45	62.76 56	68.31 62	56.14 62	71.30 66	68.70 80	76.06 116	79.67 60

tpmrst		48.08 207	49.88 220	45.98 189	52.71 173	48.11 229	53.62 189	33.70 230	48.70 141	39.74 136	48.96 135	46.23 193	40.29 170	50.14 245	49.28 241	55.80 237	57.71 226

tttt0517		56.53 134	59.59 135	52.95 130	52.66 174	60.99 155	59.21 142	40.51 170	47.89 150	40.40 133	52.50 118	46.04 195	49.78 118	67.75 129	67.83 90	75.15 125	74.17 123

GBi-Net		55.20 147	60.25 124	49.31 152	52.42 175	61.44 148	57.03 155	44.04 107	49.18 132	30.47 178	48.28 138	58.19 117	38.22 181	68.05 123	66.96 106	73.69 151	69.65 146

test1		55.20 147	60.25 124	49.31 152	52.42 175	61.44 148	57.03 155	44.04 107	49.18 132	30.47 178	48.28 138	58.19 117	38.22 181	68.05 123	66.96 106	73.69 151	69.65 146

FMVSNet2		55.04 151	59.95 132	49.31 152	52.42 175	61.44 148	57.03 155	44.08 106	49.55 126	30.40 181	46.89 147	58.84 115	38.22 181	67.07 144	66.21 128	73.69 151	69.65 146

FMVSNet3		54.78 152	59.58 137	49.17 155	52.37 178	61.31 152	56.72 160	44.04 107	49.18 132	30.47 178	48.28 138	58.19 117	38.09 184	65.48 166	65.20 147	73.31 161	69.45 155

testgi		38.71 239	43.64 239	32.95 239	52.30 179	48.63 228	35.59 251	35.05 220	31.58 244	9.03 251	30.29 234	40.75 225	11.19 254	55.30 231	53.47 234	54.53 242	45.48 247

Anonymous20231206		42.28 228	45.89 231	38.07 228	51.96 180	48.98 225	43.66 236	38.81 189	38.74 218	14.32 236	26.74 243	40.90 223	20.94 237	56.64 222	54.67 226	58.71 231	54.59 231

pmmvs6		48.35 205	51.64 207	44.51 203	51.92 181	57.94 196	49.44 209	42.17 151	34.45 236	24.62 215	28.87 241	46.90 186	29.07 223	64.60 172	63.08 172	69.83 197	65.68 189

PatchmatchNet		49.92 190	51.29 209	48.32 170	51.83 182	51.86 217	53.38 191	37.63 206	47.90 149	40.83 131	48.54 137	45.30 200	45.19 145	56.86 218	53.99 231	61.08 228	54.57 232
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 210	53.67 181	40.63 221	51.45 183	59.74 166	44.71 233	49.37 60	40.69 206	7.61 254	46.04 159	44.34 214	17.32 242	57.79 213	61.18 186	73.30 162	65.86 187

LTVRE_ROB	44.17 16	47.06 215	50.15 218	43.44 208	51.39 184	58.42 182	42.90 237	43.51 131	22.27 254	14.85 235	41.94 203	34.57 242	45.43 142	62.28 183	62.77 178	62.56 224	68.83 158
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
CP-MVSNet		48.37 204	53.53 182	42.34 213	51.35 185	58.01 195	46.56 222	50.54 55	41.62 201	10.61 243	46.53 154	40.68 226	23.18 234	58.71 206	61.83 183	71.81 182	67.36 167

PS-CasMVS		48.18 206	53.25 188	42.27 214	51.26 186	57.94 196	46.51 223	50.52 56	41.30 202	10.56 244	45.35 169	40.34 228	23.04 235	58.66 207	61.79 184	71.74 185	67.38 165

our_test_3					51.15 187	57.31 199	55.12 176

SCA		50.99 177	53.22 189	48.40 168	51.07 188	56.78 201	50.25 205	39.05 181	48.31 145	41.38 126	49.54 130	46.70 189	46.00 140	58.31 209	56.28 210	62.65 222	56.60 229

UniMVSNet_ETH3D		52.62 161	55.98 165	48.70 163	51.04 189	60.71 158	56.87 158	46.74 75	42.52 193	26.96 203	42.50 200	45.95 196	37.87 185	66.22 157	65.15 150	72.74 169	68.78 159

IterMVS-SCA-FT		52.18 166	57.75 157	45.68 192	51.01 190	62.06 144	55.10 177	34.75 221	44.85 168	32.86 170	51.13 126	51.22 146	48.74 123	62.47 181	61.51 185	51.61 247	71.02 137

FMVSNet1		54.08 155	58.68 147	48.71 162	50.90 191	61.35 151	56.73 159	43.94 116	45.91 163	29.32 188	42.72 195	56.26 129	37.70 188	68.05 123	66.96 106	73.69 151	69.50 151

pmmvs-eth3d		51.33 174	52.25 204	50.26 147	50.82 192	54.65 206	56.03 166	43.45 136	43.51 181	37.20 151	39.20 213	39.04 232	42.28 160	61.85 185	62.78 177	71.78 184	64.72 196

MVSTER		57.19 126	61.11 114	52.62 133	50.82 192	58.79 176	61.55 127	37.86 204	48.81 138	41.31 127	57.43 95	52.10 143	48.60 126	68.19 119	66.75 112	75.56 120	75.68 114

ambc			45.54 234		50.66 194	52.63 214	40.99 242		38.36 226	24.67 214	22.62 249	13.94 260	29.14 222	65.71 164	58.06 200	58.60 233	67.43 163

thisisatest0515		53.85 156	56.84 163	50.37 146	50.25 195	58.17 192	55.99 167	39.90 179	41.88 198	38.16 145	45.91 160	45.30 200	44.58 147	66.15 159	66.89 110	73.36 160	73.57 129

baseline		55.19 149	60.88 115	48.55 165	49.87 196	58.10 194	58.70 144	34.75 221	52.82 111	39.48 141	60.18 79	60.86 105	45.41 143	61.05 187	60.74 190	63.10 220	72.41 131

MDTV_nov1_ep13		50.32 183	52.43 201	47.86 176	49.87 196	54.70 205	58.10 148	34.29 225	45.59 166	37.71 147	47.44 145	47.42 175	41.86 162	58.07 212	55.21 222	65.34 214	58.56 224

IterMVS		53.45 158	57.12 161	49.17 155	49.23 198	60.93 157	59.05 143	34.63 223	44.53 170	33.22 166	51.09 127	51.01 149	48.38 127	62.43 182	60.79 189	70.54 194	69.05 157
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 170	54.86 175	48.63 164	49.13 199	61.73 147	60.53 135	36.57 211	53.14 104	32.95 169	37.10 218	38.68 233	40.49 167	65.72 163	63.08 172	72.11 181	64.60 197
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 179	52.61 196	47.98 174	49.03 200	52.94 211	48.27 212	38.86 187	44.41 171	39.59 138	44.34 176	44.65 211	46.63 137	58.97 203	60.31 191	65.48 212	62.66 208

V42		56.97 129	60.14 128	53.28 125	48.16 201	62.78 141	66.30 95	37.93 203	47.44 152	42.68 117	48.19 141	52.59 142	51.90 107	67.46 134	65.94 136	72.72 170	76.55 105

MDTV_nov1_ep13_2view		47.62 211	49.72 221	45.18 197	48.05 202	53.70 209	54.90 178	33.80 229	39.90 212	29.79 184	38.85 215	41.89 219	39.17 174	58.99 202	55.55 217	65.34 214	59.17 222

EPMVS		44.66 223	47.86 227	40.92 219	47.97 203	44.70 242	47.58 217	33.27 232	48.11 148	29.58 186	49.65 129	44.38 213	34.65 208	51.71 239	47.90 243	52.49 245	48.57 245

usedtu_dtu_shiyan1		51.41 173	55.78 166	46.30 188	47.91 204	59.47 167	52.99 193	42.13 153	48.17 147	24.88 212	40.95 204	48.18 165	35.95 203	64.48 173	64.49 155	73.94 141	64.75 195

RPMNet		46.41 216	48.72 223	43.72 206	47.77 205	52.94 211	46.02 226	33.92 227	44.41 171	31.82 175	36.89 219	37.42 239	37.41 189	53.88 236	54.02 229	65.37 213	61.47 214

TAPA-MVS	54.74 10	60.85 94	66.61 80	54.12 120	47.38 206	65.33 116	65.35 107	36.51 212	75.16 31	48.82 87	54.70 107	63.51 91	53.31 95	68.36 111	64.97 151	73.37 159	74.27 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 212	50.25 217	44.41 205	47.30 207	54.31 208	47.81 215	40.36 176	33.76 237	19.93 226	43.75 182	32.77 246	42.07 161	59.82 193	60.94 188	68.98 198	66.37 181

TAMVS		44.02 225	49.18 222	37.99 229	47.03 208	45.97 239	45.04 230	28.47 243	39.11 216	20.23 225	43.22 191	48.52 163	28.49 225	58.15 211	57.95 201	58.71 231	51.36 235

0.4-1-1-0.1		50.59 178	53.51 183	47.17 179	46.63 209	58.96 174	54.24 180	36.39 213	43.20 183	33.94 165	44.77 172	49.55 157	40.04 172	57.50 215	56.17 212	71.80 183	64.43 199

UGNet		57.03 127	65.25 92	47.44 178	46.54 210	66.73 103	56.30 163	43.28 138	50.06 122	32.99 168	62.57 59	63.26 92	33.31 214	68.25 115	67.58 97	72.20 180	78.29 72
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
TSAR-MVS + COLMAP		62.65 83	69.90 55	54.19 118	46.31 211	66.73 103	65.49 106	41.36 160	76.57 25	46.31 98	76.80 18	56.68 123	53.27 96	69.50 95	66.65 116	72.40 177	76.36 108

PatchMatch-RL		50.11 186	51.56 208	48.43 167	46.23 212	51.94 215	50.21 206	38.62 193	46.62 158	37.51 148	42.43 201	39.38 230	52.24 104	60.98 188	59.56 194	65.76 211	60.01 221

0.3-1-1-0.015		50.11 186	52.80 192	46.98 182	46.15 213	58.39 184	53.96 182	35.90 216	42.52 193	34.13 161	43.69 183	49.24 159	40.30 169	56.60 223	55.53 218	71.41 187	63.65 203

0.4-1-1-0.2		49.99 188	52.69 194	46.83 183	45.99 214	58.16 193	53.71 185	35.75 217	42.13 196	34.14 160	44.08 178	49.28 158	40.24 171	56.44 225	55.24 221	71.18 191	63.49 205

CMPMVS	37.70 17	49.24 193	52.71 193	45.19 196	45.97 215	51.23 219	47.44 218	29.31 240	43.04 185	44.69 107	34.45 227	48.35 164	43.64 150	62.59 179	59.82 193	60.08 229	69.48 152
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 235	43.80 238	36.61 232	45.79 216	40.45 247	42.12 239	33.18 233	40.30 209	24.11 218	38.76 216	37.11 240	24.30 231	52.97 237	46.66 247	50.17 248	50.33 240

pmmvs5		47.07 214	51.02 213	42.46 212	45.18 217	51.47 218	48.23 214	33.09 234	38.17 228	28.62 191	46.60 151	43.48 216	30.74 217	58.28 210	58.63 198	68.92 199	60.48 217

blend_shiyan4		50.41 181	53.51 183	46.79 184	44.79 218	58.47 179	52.51 194	36.99 209	41.74 199	34.13 161	42.68 196	49.24 159	38.37 178	58.53 208	56.69 209	73.96 140	67.20 169

USDC		51.11 175	53.71 180	48.08 173	44.76 219	55.99 204	53.01 192	40.90 164	52.49 112	36.14 153	44.67 173	33.66 244	43.27 155	63.23 176	61.10 187	70.39 195	64.82 194

FC-MVSNet-test		39.65 238	48.35 225	29.49 243	44.43 220	39.28 251	30.23 254	40.44 174	43.59 179	3.12 261	53.00 113	42.03 218	10.02 256	55.09 232	54.77 224	48.66 249	50.71 238

ADS-MVSNet		40.67 233	43.38 240	37.50 230	44.36 221	39.79 249	42.09 240	32.67 237	44.34 173	28.87 190	40.76 207	40.37 227	30.22 218	48.34 250	45.87 248	46.81 251	44.21 249

new-patchmatchnet		33.24 246	37.20 247	28.62 245	44.32 222	38.26 252	29.68 255	36.05 214	31.97 242	6.33 256	26.59 244	27.33 251	11.12 255	50.08 246	41.05 251	44.23 252	45.15 248

MVS-HIRNet		42.24 229	41.15 243	43.51 207	44.06 223	40.74 245	35.77 250	35.35 218	35.38 235	38.34 143	25.63 246	38.55 234	43.48 152	50.77 241	47.03 245	64.07 216	49.98 241

PatchT		48.08 207	51.03 212	44.64 202	42.96 224	50.12 222	40.36 243	35.09 219	43.17 184	39.59 138	42.00 202	39.96 229	46.63 137	58.97 203	60.31 191	63.21 219	62.66 208

CVMVSNet		46.38 218	52.01 206	39.81 223	42.40 225	50.26 221	46.15 224	37.68 205	40.03 211	15.09 234	46.56 152	47.56 173	33.72 213	56.50 224	55.65 216	63.80 218	67.53 162

TinyColmap		47.08 213	47.56 228	46.52 186	42.35 226	53.44 210	51.77 202	40.70 168	43.44 182	31.92 174	29.78 237	23.72 256	45.04 146	61.99 184	59.54 195	67.35 205	61.03 215

ET-MVSNet_ETH3D		58.38 116	61.57 111	54.67 114	42.15 227	65.26 118	65.70 102	43.82 120	48.84 136	42.34 119	59.76 82	47.76 170	56.68 56	67.02 145	68.60 84	77.33 92	73.73 128

blended_shiyan6		49.22 194	52.60 197	45.26 195	41.68 228	58.46 181	52.42 195	38.16 197	38.60 219	28.50 195	40.28 208	47.09 179	36.76 198	59.62 194	57.25 204	74.06 137	66.92 171

blended_shiyan8		49.21 195	52.59 198	45.27 194	41.67 229	58.47 179	52.41 196	38.16 197	38.60 219	28.53 194	40.26 209	47.07 180	36.78 197	59.62 194	57.26 203	74.06 137	66.88 174

wanda-best-256-512		49.05 199	52.38 202	45.17 198	41.54 230	58.31 186	52.24 198	38.00 199	38.58 221	28.56 192	40.23 210	47.00 182	36.88 194	59.28 197	56.77 205	73.78 144	66.45 177

FE-blended-shiyan7		49.05 199	52.38 202	45.17 198	41.54 230	58.31 186	52.24 198	38.00 199	38.58 221	28.56 192	40.23 210	47.00 182	36.88 194	59.28 197	56.77 205	73.78 144	66.45 177

usedtu_blend_shiyan5		50.12 185	53.15 190	46.58 185	41.54 230	58.31 186	53.69 187	38.00 199	38.58 221	34.13 161	42.68 196	49.24 159	38.37 178	59.28 197	56.77 205	73.78 144	67.20 169

FE-MVSNET3		49.99 188	53.11 191	46.34 187	41.54 230	58.31 186	52.24 198	38.00 199	38.58 221	34.13 161	42.68 196	49.24 159	38.37 178	59.28 197	56.77 205	73.78 144	66.92 171

MIMVSNet		43.79 226	48.53 224	38.27 227	41.46 234	48.97 226	50.81 204	32.88 236	44.55 169	22.07 219	32.05 230	47.15 178	24.76 230	58.73 205	56.09 214	57.63 236	52.14 233

WB-MVS		29.70 248	35.40 249	23.05 248	40.96 235	39.59 250	18.79 258	40.20 177	25.26 249	1.88 264	33.33 228	21.97 258	3.36 257	48.69 249	44.60 249	33.11 256	34.39 251

N_pmnet		32.67 247	36.85 248	27.79 246	40.55 236	32.13 253	35.80 249	26.79 246	37.24 231	9.10 249	32.02 231	30.94 249	16.30 244	47.22 251	41.21 250	38.21 254	37.21 250

anonymousdsp		52.84 160	57.78 156	47.06 180	40.24 237	58.95 175	53.70 186	33.54 231	36.51 233	32.69 171	43.88 180	45.40 198	47.97 132	67.17 140	70.28 63	74.22 134	82.29 48

FE-MVSNET2		45.69 220	49.95 219	40.72 220	40.11 238	56.16 202	46.59 221	41.89 154	36.97 232	13.66 237	29.00 240	37.59 238	28.96 224	63.26 175	63.93 165	73.13 165	62.72 207

gbinet_0.2-2-1-0.02		48.89 201	52.69 194	44.45 204	39.54 239	59.33 169	52.39 197	38.76 190	35.41 234	26.17 208	39.15 214	47.39 176	36.41 202	60.29 192	57.58 202	73.45 157	69.65 146

EU-MVSNet		40.63 234	45.65 233	34.78 237	39.11 240	46.94 236	40.02 244	34.03 226	33.50 238	10.37 245	35.57 223	37.80 236	23.65 233	51.90 238	50.21 240	61.49 227	63.62 204

FPMVS		38.36 240	40.41 244	35.97 233	38.92 241	39.85 248	45.50 228	25.79 249	41.13 203	18.70 228	30.10 235	24.56 254	31.86 216	49.42 247	46.80 246	55.04 238	51.03 236

TESTMET0.1,1		46.09 219	50.29 215	41.18 218	36.91 242	47.16 233	49.52 207	20.32 253	39.22 214	31.98 172	43.65 185	47.93 168	41.29 165	56.80 219	55.36 219	67.08 207	61.94 212

FMVSNet5		40.96 231	45.81 232	35.29 236	34.30 243	44.55 243	47.28 219	28.84 242	40.76 205	21.62 220	29.85 236	42.44 217	24.77 229	57.53 214	55.00 223	54.93 239	50.56 239

PMMVS		49.20 197	54.28 179	43.28 210	34.13 244	45.70 240	48.98 210	26.09 248	46.31 160	34.92 159	55.22 103	53.47 137	47.48 134	59.43 196	59.04 197	68.05 203	60.77 216

PMVS	27.84 18	33.81 245	35.28 250	32.09 241	34.13 244	24.81 256	32.51 253	26.48 247	26.41 248	19.37 227	23.76 247	24.02 255	25.18 228	50.78 240	47.24 244	54.89 241	49.95 242
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 221	50.37 214	39.38 224	33.65 246	46.99 235	47.59 216	18.59 254	38.75 217	28.00 196	43.28 190	46.82 188	41.50 164	57.28 216	55.78 215	66.93 209	63.70 202

CHOSEN 280x420		40.80 232	45.05 235	35.84 235	32.95 247	29.57 254	44.98 231	23.71 251	37.54 230	18.42 229	31.36 233	47.07 180	46.41 139	56.71 221	54.65 227	48.55 250	58.47 225

PM-MVS		44.55 224	48.13 226	40.37 222	32.85 248	46.82 237	46.11 225	29.28 241	40.48 207	29.99 183	39.98 212	34.39 243	41.80 163	56.08 228	53.88 233	62.19 225	65.31 190

FE-MVSNET		39.75 237	44.50 236	34.21 238	32.01 249	48.77 227	37.71 247	38.94 184	30.91 245	6.25 257	26.24 245	32.10 248	23.68 232	57.28 216	59.53 196	66.68 210	56.64 228

TDRefinement		49.31 191	52.44 200	45.67 193	30.44 250	59.42 168	59.24 141	39.78 180	48.76 139	31.20 177	35.73 222	29.90 250	42.81 158	64.24 174	62.59 181	70.55 193	66.43 179

Gipuma		25.87 249	26.91 252	24.66 247	28.98 251	20.17 257	20.46 256	34.62 224	29.55 246	9.10 249	4.91 260	5.31 264	15.76 245	49.37 248	49.10 242	39.03 253	29.95 253
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 230	43.15 241	39.27 225	28.74 252	52.68 213	44.95 232	40.84 165	32.89 239	18.13 230	31.61 232	22.09 257	38.97 177	50.45 244	56.11 213	64.01 217	56.23 230

E-PMN		15.09 252	13.19 256	17.30 250	27.80 253	12.62 260	7.81 262	27.54 244	14.62 258	3.19 259	6.89 257	2.52 267	15.09 246	15.93 256	20.22 255	22.38 257	19.53 256

MIMVSNet1		35.51 243	41.41 242	28.63 244	27.53 254	43.36 244	38.09 246	33.82 228	32.01 241	6.77 255	21.63 251	35.43 241	11.97 250	55.05 233	53.99 231	53.59 244	48.36 246

EMVS		14.49 253	12.45 257	16.87 252	27.02 255	12.56 261	8.13 261	27.19 245	15.05 257	3.14 260	6.69 258	2.67 266	15.08 247	14.60 258	18.05 256	20.67 258	17.56 258

pmmvs3		35.10 244	38.47 246	31.17 242	26.37 256	40.47 246	34.51 252	18.09 255	24.75 250	16.88 232	23.05 248	26.69 252	32.69 215	50.73 242	51.60 236	58.46 234	51.98 234

RPSCF		46.41 216	54.42 177	37.06 231	25.70 257	45.14 241	45.39 229	20.81 252	62.79 61	35.10 156	44.92 171	55.60 132	43.56 151	56.12 227	52.45 235	51.80 246	63.91 201

usedtu_dtu_shiyan2		36.29 242	39.77 245	32.23 240	19.53 258	48.11 229	41.99 241	36.59 210	23.95 252	12.80 239	22.03 250	32.26 247	20.73 238	50.69 243	50.64 238	61.72 226	50.72 237

new_pmnet		23.19 250	28.17 251	17.37 249	17.03 259	24.92 255	19.66 257	16.16 257	27.05 247	4.42 258	20.77 252	19.20 259	12.19 249	37.71 252	36.38 252	34.77 255	31.17 252

PMMVS2		15.84 251	19.68 253	11.35 253	15.74 260	16.95 258	13.31 259	17.64 256	16.08 256	0.36 265	13.12 254	11.47 261	1.69 259	28.82 253	27.24 254	19.38 260	24.09 255

MVE	12.28 19	13.53 254	15.72 254	10.96 254	7.39 261	15.71 259	6.05 263	23.73 250	10.29 260	3.01 262	5.77 259	3.41 265	11.91 251	20.11 254	29.79 253	13.67 261	24.98 254
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 256	3.97 262	2.35 264	3.26 265	0.44 260	17.56 255	12.09 240	11.48 256	7.14 262	1.98 258	15.68 257	15.49 257	10.69 262

test_method		12.44 255	14.66 255	9.85 255	1.30 263	3.32 263	13.00 260	3.21 258	22.42 253	10.22 246	14.13 253	25.64 253	11.43 253	19.75 255	11.61 258	19.96 259	5.79 259

GG-mvs-BLEND		36.62 241	53.39 186	17.06 251	0.01 264	58.61 177	48.63 211	0.01 261	47.13 154	0.02 266	43.98 179	60.64 108	0.03 260	54.92 234	51.47 237	53.64 243	56.99 227

uanet_test		0.00 258	0.00 260	0.00 257	0.00 265	0.00 265	0.00 268	0.00 262	0.00 263	0.00 267	0.00 263	0.00 268	0.00 263	0.00 261	0.00 261	0.00 264	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 257	0.00 265	0.00 265	0.00 268	0.00 262	0.00 263	0.00 267	0.00 263	0.00 268	0.00 263	0.00 261	0.00 261	0.00 264	0.00 262

sosnet		0.00 258	0.00 260	0.00 257	0.00 265	0.00 265	0.00 268	0.00 262	0.00 263	0.00 267	0.00 263	0.00 268	0.00 263	0.00 261	0.00 261	0.00 264	0.00 262

testmvs		0.01 256	0.02 258	0.00 257	0.00 265	0.00 265	0.01 267	0.00 262	0.01 261	0.00 267	0.03 262	0.00 268	0.01 261	0.01 260	0.01 259	0.00 264	0.06 261

test123		0.01 256	0.02 258	0.00 257	0.00 265	0.00 265	0.00 268	0.00 262	0.01 261	0.00 267	0.04 261	0.00 268	0.01 261	0.00 261	0.01 259	0.00 264	0.07 260

TestfortrainingZip							82.75 7	57.21 13		62.96 14						83.21 8

RE-MVS-def										33.01 167

9.14												81.81 14

MTAPA										65.14 4		80.20 21

MTMP										62.63 17		78.04 28

Patchmatch-RL test							1.04 266

NP-MVS									72.00 43

Patchmtry						47.61 231	48.27 212	38.86 187		39.59 138

DeepMVS_CX						6.95 262	5.98 264	2.25 259	11.73 259	2.07 263	11.85 255	5.43 263	11.75 252	11.40 259		8.10 263	18.38 257

High-resolution multi-view benchmark