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 17	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 11	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 24	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 23	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 6	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 25	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		77.77 6	83.11 6	71.54 5	77.52 6	80.15 9	82.81 7	57.37 13	84.71 8	62.96 14	87.31 6	85.76 5	65.28 4	78.00 18	76.77 23	83.31 8	89.06 9

SteuartSystems-ACMMP		75.23 14	79.60 16	70.13 14	76.81 7	78.92 13	81.74 9	57.99 6	75.30 30	59.83 28	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 29	90.29 4

HPM-MVS++		76.01 11	80.47 13	70.81 10	76.60 9	74.96 37	80.18 18	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 35	87.46 19

MCST-MVS		73.67 25	77.39 27	69.33 19	76.26 10	78.19 18	78.77 27	54.54 31	75.33 28	59.99 27	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 10	57.12 14	79.77 17	63.04 13	70.69 26	81.15 17	62.99 12	80.23 5	79.54 3	83.11 9	89.16 8

NCCC		74.27 20	77.83 25	70.13 14	75.70 12	77.41 24	80.51 16	57.09 15	78.25 21	62.28 19	65.54 38	78.26 26	62.18 19	79.13 8	78.51 10	83.01 11	87.68 18

CSCG		74.68 17	79.22 17	69.40 18	75.69 13	80.01 10	79.12 25	52.83 42	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 12	54.83 27	75.96 26	62.06 20	63.96 50	76.58 32	58.55 41	76.66 34	76.77 23	82.60 20	83.68 41

TPM-MVS					75.48 15	76.70 31	79.31 22			62.34 18	64.71 43	77.88 29	56.94 55			81.88 33	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 8	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 14	57.44 12	80.45 15	59.32 29	85.28 9	80.82 19	63.96 8	76.89 29	76.08 29	81.58 40	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 47	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 19	56.05 21	74.87 33	58.97 30	81.83 12	79.76 22	61.05 26	77.39 26	76.01 30	81.71 38	85.61 31

TSAR-MVS + MP.		75.22 15	80.06 14	69.56 17	74.61 20	72.74 50	80.59 15	55.70 24	80.80 14	62.65 16	86.25 7	82.92 10	62.07 20	76.89 29	75.66 32	81.77 37	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 26	55.24 26	81.04 13	62.71 15	80.18 13	82.61 11	61.70 22	75.43 41	73.92 44	82.44 23	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 13	57.09 15	81.38 12	63.89 10	79.02 14	80.48 20	62.24 18	80.05 6	79.12 4	82.94 12	88.64 10

HFP-MVS		74.87 16	78.86 21	70.21 13	73.99 23	77.91 19	80.36 17	56.63 17	78.41 20	64.27 8	74.54 21	77.75 30	62.96 13	78.70 12	77.82 13	83.02 10	86.91 22

AdaColmap		67.89 46	68.85 61	66.77 30	73.73 24	74.30 44	75.28 42	53.58 37	70.24 48	57.59 37	51.19 124	59.19 113	60.74 29	75.33 43	73.72 46	79.69 55	77.96 77

MP-MVS		74.31 19	78.87 19	68.99 22	73.49 25	78.56 16	79.25 24	56.51 18	75.33 28	60.69 25	75.30 20	79.12 24	61.81 21	77.78 22	77.93 12	82.18 31	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 28	48.80 68	79.34 18	55.32 43	85.04 10	81.49 16	58.57 40	75.06 44	73.75 45	75.35 122	85.61 31

CDPH-MVS		71.47 33	75.82 33	66.41 33	72.97 27	77.15 26	78.14 31	54.71 28	69.88 50	53.07 66	70.98 25	74.83 38	56.95 54	76.22 35	76.57 25	82.62 18	85.09 35

PGM-MVS		72.89 26	77.13 28	67.94 26	72.47 28	77.25 25	79.27 23	54.63 30	73.71 37	57.95 36	72.38 24	75.33 36	60.75 28	78.25 16	77.36 18	82.57 21	85.62 30

ACMMPR		73.79 24	78.41 22	68.40 25	72.35 29	77.79 21	79.32 21	56.38 19	77.67 24	58.30 34	74.16 22	76.66 31	61.40 23	78.32 14	77.80 14	82.68 16	86.51 23

OPM-MVS		69.33 38	71.05 47	67.32 28	72.34 30	75.70 34	79.57 20	56.34 20	55.21 92	53.81 63	59.51 83	68.96 59	59.67 35	77.61 24	76.44 27	82.19 29	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 34	55.88 23	72.75 41	54.48 59	64.39 45	74.47 39	54.19 80	77.84 21	77.37 17	82.21 28	85.85 28

HQP-MVS		70.88 35	75.02 35	66.05 36	71.69 32	74.47 42	77.51 33	53.17 39	72.89 40	54.88 49	70.03 29	70.48 53	57.26 49	76.02 37	75.01 36	81.78 36	86.21 24

MAR-MVS		68.04 45	70.74 49	64.90 43	71.68 33	76.33 33	74.63 45	50.48 56	63.81 58	55.52 42	54.88 104	69.90 55	57.39 48	75.42 42	74.79 38	79.71 52	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 29				81.54 15

MGCNet		72.45 30	77.44 26	66.61 31	71.08 36	77.81 20	76.74 35	49.30 62	73.12 39	61.17 21	73.70 23	78.08 27	58.78 38	76.75 33	76.52 26	82.61 19	86.14 26

CLD-MVS		67.02 50	71.57 44	61.71 52	71.01 37	74.81 39	71.62 53	38.91 183	71.86 44	60.70 24	64.97 42	67.88 68	51.88 107	76.77 32	74.98 37	76.11 110	69.75 144
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 32	56.01 22	75.65 27	58.82 31	69.16 31	76.48 33	60.46 31	77.66 23	77.20 20	81.65 39	86.97 21

ACMM	60.30 7	67.58 48	68.82 62	66.13 35	70.59 39	72.01 54	76.54 37	54.26 33	65.64 56	54.78 53	50.35 127	61.72 102	58.74 39	75.79 39	75.03 35	81.88 33	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 46			54.48 59		74.47 39				82.24 26

X-MVStestdata					70.49 40	76.96 27	74.36 46			54.48 59		74.47 39				82.24 26

ACMMP		71.57 32	75.84 32	66.59 32	70.30 42	76.85 30	78.46 29	53.95 35	73.52 38	55.56 41	70.13 28	71.36 51	58.55 41	77.00 28	76.23 28	82.71 15	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 55	51.72 48	60.77 66	55.06 46	62.14 63	66.40 80	58.13 44	76.13 36	74.79 38	80.19 49	82.04 50

MSLP-MVS++		68.17 44	70.72 50	65.19 40	69.41 44	70.64 58	74.99 43	45.76 79	70.20 49	60.17 26	56.42 96	73.01 45	61.14 24	72.80 55	70.54 61	79.70 53	81.42 52

LGP-MVS_train		68.87 40	72.03 43	65.18 41	69.33 45	74.03 45	76.67 36	53.88 36	68.46 51	52.05 73	63.21 53	63.89 89	56.31 58	75.99 38	74.43 40	82.83 14	84.18 37

ACMP	61.42 5	68.72 43	71.37 45	65.64 39	69.06 46	74.45 43	75.88 40	53.30 38	68.10 52	55.74 40	61.53 69	62.29 96	56.97 53	74.70 47	74.23 42	82.88 13	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 37	54.35 32	74.92 32	58.64 33	65.18 40	74.04 44	62.62 15	77.92 20	77.02 21	82.16 32	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 49	47.90 69	63.86 57	54.84 52	67.51 35	74.36 42	57.62 45	74.22 49	73.57 48	80.56 45	82.36 47

TSAR-MVS + GP.		69.71 36	73.92 37	64.80 44	68.27 49	70.56 59	71.90 51	50.75 52	71.38 45	57.46 38	68.68 32	75.42 35	60.10 34	73.47 52	73.99 43	80.32 48	83.97 39

3Dnovator+	62.63 4	69.51 37	72.62 40	65.88 38	68.21 50	76.47 32	73.50 50	52.74 43	70.85 46	58.65 32	55.97 98	69.95 54	61.11 25	76.80 31	75.09 34	81.09 43	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 30	59.28 1	78.24 22	61.13 22	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 41	54.16 34	84.86 6	58.22 35	77.94 17	81.01 18	62.52 16	78.34 13	77.38 16	80.16 50	88.40 12

EC-MVSNet		67.01 51	70.27 54	63.21 48	67.21 53	70.47 60	69.01 70	46.96 73	59.16 75	53.23 65	64.01 49	69.71 57	60.37 32	74.92 45	71.24 56	82.50 22	82.41 46

UA-Net		58.50 111	64.68 96	51.30 140	66.97 54	67.13 99	53.68 184	45.65 82	49.51 127	31.58 172	62.91 55	68.47 61	35.85 201	68.20 117	67.28 101	74.03 137	69.24 154

PHI-MVS		69.27 39	74.84 36	62.76 51	66.83 55	74.83 38	73.88 48	49.32 61	70.61 47	50.93 77	69.62 30	74.84 37	57.25 50	75.53 40	74.32 41	78.35 70	84.17 38

3Dnovator	60.86 6	66.99 52	70.32 52	63.11 49	66.63 56	74.52 40	71.56 54	45.76 79	67.37 54	55.00 48	54.31 109	68.19 64	58.49 43	73.97 50	73.63 47	81.22 42	80.23 57

EPNet		65.14 62	69.54 58	60.00 70	66.61 57	67.67 89	67.53 79	55.32 25	62.67 62	46.22 98	67.74 34	65.93 83	48.07 130	72.17 58	72.12 50	76.28 106	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 80	65.75 87	59.39 74	66.47 58	69.52 63	64.26 117	43.07 142	61.34 65	50.19 80	47.29 145	64.41 88	54.60 77	70.18 83	68.62 82	77.73 77	78.89 66

ACMH	52.42 13	58.24 118	59.56 138	56.70 100	66.34 59	69.59 62	66.71 89	49.12 63	46.08 161	28.90 185	42.67 196	41.20 218	52.60 99	71.39 65	70.28 63	76.51 102	75.72 111
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 113	58.97 144	57.85 91	66.27 60	66.23 108	67.72 76	42.33 146	53.43 100	43.68 110	43.39 184	45.35 195	49.75 119	68.66 106	67.77 91	77.38 88	67.96 159

QAPM		65.27 58	69.49 59	60.35 66	65.43 61	72.20 53	65.69 102	47.23 71	63.46 59	49.14 82	53.56 110	71.04 52	57.01 52	72.60 57	71.41 54	77.62 81	82.14 49

CPTT-MVS		68.76 42	73.01 38	63.81 47	65.42 62	73.66 47	76.39 39	52.08 44	72.61 42	50.33 79	60.73 75	72.65 47	59.43 36	73.32 53	72.12 50	79.19 61	85.99 27

MS-PatchMatch		58.19 120	60.20 125	55.85 107	65.17 63	64.16 129	64.82 109	41.48 157	50.95 117	42.17 119	45.38 166	56.42 125	48.08 129	68.30 112	66.70 112	73.39 155	69.46 152

PCF-MVS	59.98 8	67.32 49	71.04 48	62.97 50	64.77 64	74.49 41	74.78 44	49.54 58	67.44 53	54.39 62	58.35 90	72.81 46	55.79 64	71.54 64	69.24 72	78.57 64	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EG-PatchMatch MVS		56.98 127	58.24 151	55.50 109	64.66 65	68.62 68	61.48 126	43.63 125	38.44 222	41.44 123	38.05 213	46.18 190	43.95 148	71.71 63	70.61 60	77.87 71	74.08 124

Effi-MVS+-dtu		60.34 96	62.32 108	58.03 86	64.31 66	67.44 94	65.99 96	42.26 147	49.55 125	42.00 122	48.92 135	59.79 111	56.27 59	68.07 121	67.03 104	77.35 89	75.45 114

FC-MVSNet-train		58.40 114	63.15 105	52.85 130	64.29 67	61.84 145	55.98 166	46.47 75	53.06 104	34.96 156	61.95 65	56.37 127	39.49 170	68.67 105	68.36 84	75.92 116	71.81 132

Effi-MVS+		63.28 77	65.96 86	60.17 68	64.26 68	68.06 81	68.78 73	45.71 81	54.08 96	46.64 93	55.92 99	63.13 93	55.94 62	70.38 79	71.43 53	79.68 56	78.70 67

LS3D		60.20 97	61.70 109	58.45 81	64.18 69	67.77 86	67.19 82	48.84 67	61.67 64	41.27 126	45.89 160	51.81 144	54.18 81	68.78 103	66.50 122	75.03 126	69.48 150

ACMH+	53.71 12	59.26 103	60.28 122	58.06 84	64.17 70	68.46 69	67.51 80	50.93 51	52.46 112	35.83 152	40.83 202	45.12 199	52.32 102	69.88 87	69.00 77	77.59 84	76.21 108

GeoE		62.43 83	64.79 95	59.68 73	64.15 71	67.17 98	68.80 72	44.42 98	55.65 91	47.38 87	51.54 121	62.51 94	54.04 83	69.99 86	68.07 86	79.28 59	78.57 68

DELS-MVS		65.87 54	70.30 53	60.71 65	64.05 72	72.68 51	70.90 56	45.43 83	57.49 86	49.05 84	64.43 44	68.66 60	55.11 72	74.31 48	73.02 49	79.70 53	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 82	63.94 73	71.05 56	64.49 114	43.18 138	74.08 34	47.35 88	64.17 47	71.97 48	51.17 112	71.87 60	70.74 58	78.51 67	80.56 55

canonicalmvs		65.62 55	72.06 41	58.11 82	63.94 73	71.05 56	64.49 114	43.18 138	74.08 34	47.35 88	64.17 47	71.97 48	51.17 112	71.87 60	70.74 58	78.51 67	80.56 55

EIA-MVS		61.53 91	63.79 101	58.89 79	63.82 75	67.61 90	65.35 105	42.15 150	49.98 122	45.66 101	57.47 94	56.62 123	56.59 57	70.91 72	69.15 73	79.78 51	74.80 118

Anonymous202405211			60.60 118		63.44 76	66.71 105	61.00 131	47.23 71	50.62 120		36.85 216	60.63 108	43.03 156	69.17 99	67.72 93	75.41 119	72.54 129

ETV-MVS		63.23 78	66.08 85	59.91 71	63.13 77	68.13 75	67.62 78	44.62 94	53.39 101	46.23 97	58.74 87	58.19 116	57.45 47	73.60 51	71.38 55	80.39 46	79.13 63

viewcassd2359sk11		64.22 63	67.08 67	60.87 60	63.08 78	68.05 83	70.51 62	43.92 116	59.80 69	55.05 47	62.49 61	66.89 72	55.09 73	69.39 95	66.19 129	77.60 82	76.77 97

E3new		64.18 65	67.01 70	60.89 58	63.07 79	68.08 79	70.57 60	43.95 113	59.33 72	54.87 51	61.94 67	66.76 75	55.16 70	69.60 92	66.42 125	77.70 78	76.92 90

E2		64.19 64	67.06 68	60.84 62	63.07 79	68.02 84	70.44 63	43.88 117	59.94 68	55.15 45	62.73 57	66.97 71	55.01 74	69.18 98	65.98 133	77.53 86	76.63 99

E3		64.18 65	67.01 70	60.89 58	63.07 79	68.07 80	70.57 60	43.94 114	59.32 73	54.88 49	61.95 65	66.78 74	55.16 70	69.60 92	66.43 124	77.70 78	76.92 90

E6new		64.03 69	66.63 78	60.99 56	63.04 82	68.16 72	70.80 57	44.14 100	57.66 84	54.63 54	60.32 77	66.05 81	55.49 65	70.14 84	67.09 102	77.85 72	76.94 88

E6		64.03 69	66.63 78	60.99 56	63.04 82	68.16 72	70.80 57	44.14 100	57.66 84	54.63 54	60.32 77	66.05 81	55.49 65	70.14 84	67.09 102	77.85 72	76.94 88

E4		64.06 68	66.79 75	60.87 60	63.03 84	68.11 76	70.61 59	44.00 109	58.24 81	54.56 56	61.00 74	66.64 76	55.22 68	69.80 88	66.69 113	77.81 74	77.07 87

E5new		64.00 71	66.77 76	60.77 63	63.02 85	68.11 76	70.42 64	43.97 111	58.41 79	54.52 57	61.10 71	66.52 77	54.97 75	69.61 90	66.52 119	77.74 75	77.09 85

E5		64.00 71	66.77 76	60.77 63	63.02 85	68.11 76	70.42 64	43.97 111	58.41 79	54.52 57	61.10 71	66.52 77	54.97 75	69.61 90	66.52 119	77.74 75	77.09 85

casdiffmvs_mvg		65.26 59	69.48 60	60.33 67	62.99 87	69.34 64	69.80 68	45.27 85	63.38 60	51.11 76	65.12 41	69.75 56	53.51 88	71.74 62	68.86 78	79.33 57	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 73	67.03 69	60.10 69	62.56 88	68.92 66	69.73 69	43.49 130	57.96 82	52.16 72	61.09 73	65.39 86	55.20 69	70.36 80	67.48 98	77.48 87	78.00 76

viewdifsd2359ckpt09		65.38 57	68.69 64	61.53 53	62.15 89	71.64 55	71.84 52	47.45 70	58.95 77	51.79 75	61.73 68	65.71 85	57.08 51	72.17 58	70.82 57	78.87 62	79.79 59

viewdifsd2359ckpt07		61.71 87	65.49 89	57.31 94	62.12 90	65.52 114	68.53 74	38.21 193	56.37 88	48.07 86	61.11 70	65.85 84	52.82 97	68.34 111	64.46 156	74.08 134	76.80 94

gg-mvs-nofinetune		49.07 195	52.56 195	45.00 197	61.99 91	59.78 164	53.55 186	41.63 155	31.62 239	12.08 236	29.56 234	53.28 138	29.57 216	66.27 154	64.49 154	71.19 185	62.92 202

SPE-MVS-test		65.18 60	68.70 63	61.07 55	61.92 92	68.06 81	67.09 86	45.18 87	58.47 78	52.02 74	65.76 37	66.44 79	59.24 37	72.71 56	70.05 66	80.98 44	79.40 62

DCV-MVSNet		59.49 99	64.00 100	54.23 116	61.81 93	64.33 127	61.42 127	43.77 119	52.85 109	38.94 140	55.62 101	62.15 100	43.24 155	69.39 95	67.66 95	76.22 108	75.97 109

casdiffmvs		64.09 67	68.13 65	59.37 75	61.81 93	68.32 71	68.48 75	44.45 97	61.95 63	49.12 83	63.04 54	69.67 58	53.83 84	70.46 76	66.06 130	78.55 65	77.43 80
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 95	68.14 74	67.65 77	44.00 109	59.14 76	52.69 67	65.19 39	68.13 65	60.90 27	74.74 46	71.58 52	81.46 41	81.04 54

Anonymous20231211		57.71 123	60.79 115	54.13 118	61.68 96	65.81 112	60.81 132	43.70 123	51.97 115	39.67 135	34.82 221	63.59 90	43.31 153	68.55 109	66.63 116	75.59 117	74.13 123

IS_MVSNet		57.95 121	64.26 98	50.60 142	61.62 97	65.25 119	57.18 152	45.42 84	50.79 118	26.49 203	57.81 92	60.05 110	34.51 205	71.24 68	70.20 65	78.36 69	74.44 120

viewmanbaseed2359cas		63.67 74	67.42 66	59.30 77	61.34 98	67.42 95	70.01 67	40.50 170	59.53 70	52.60 68	62.56 60	67.34 70	54.44 79	70.33 81	66.93 108	76.91 96	77.82 79

NR-MVSNet		55.35 144	59.46 139	50.56 143	61.33 99	62.97 137	57.91 148	51.80 46	48.62 142	20.59 218	51.99 119	44.73 205	34.10 208	68.58 107	68.64 81	77.66 80	70.67 141

MVS_111021_LR		63.05 79	66.43 82	59.10 78	61.33 99	63.77 133	65.87 99	43.58 126	60.20 67	53.70 64	62.09 64	62.38 95	55.84 63	70.24 82	68.08 85	74.30 131	78.28 73

viewmacassd2359aftdt		63.43 76	66.95 72	59.32 76	61.27 101	67.48 93	70.15 66	40.54 167	57.82 83	52.27 71	60.49 76	66.81 73	54.58 78	70.67 74	67.39 100	77.08 95	78.02 75

MGCFI-Net		61.46 92	69.72 56	51.83 137	61.00 102	66.16 109	56.50 159	40.73 165	73.98 36	35.18 153	64.23 46	71.42 50	42.45 158	69.22 97	64.01 160	75.09 125	79.03 65

EPP-MVSNet		59.39 102	65.45 90	52.32 134	60.96 103	67.70 88	58.42 145	44.75 92	49.71 124	27.23 197	59.03 84	62.20 99	43.34 152	70.71 73	69.13 74	79.25 60	79.63 61

TransMVSNet (Re)		51.92 170	55.38 169	47.88 174	60.95 104	59.90 163	53.95 179	45.14 88	39.47 210	24.85 208	43.87 179	46.51 186	29.15 217	67.55 131	65.23 145	73.26 160	65.16 191

gm-plane-assit		44.74 218	45.95 226	43.33 205	60.88 105	46.79 234	36.97 243	32.24 233	24.15 247	11.79 237	29.26 235	32.97 241	46.64 135	65.09 169	62.95 173	71.45 182	60.42 214

baseline1		54.48 153	58.69 145	49.57 149	60.63 106	58.29 187	55.70 168	44.95 90	49.20 130	29.62 181	54.77 105	54.75 132	35.29 202	67.15 141	64.08 158	71.21 184	62.58 207

test2506		55.82 139	59.57 137	51.46 138	60.39 107	64.55 125	58.69 143	48.87 65	53.91 97	26.99 198	48.97 133	41.72 217	37.71 183	70.96 70	69.49 69	76.08 111	67.37 164

ECVR-MVS		56.44 134	60.74 116	51.42 139	60.39 107	64.55 125	58.69 143	48.87 65	53.91 97	26.76 200	45.55 165	53.43 137	37.71 183	70.96 70	69.49 69	76.08 111	67.32 166

DI_MVS_pp		61.88 85	65.17 92	58.06 84	60.05 109	65.26 117	66.03 95	44.22 99	55.75 90	46.73 91	54.64 107	68.12 66	54.13 82	69.13 100	66.66 114	77.18 91	76.61 100

PVSNet_Blended_VisFu		63.65 75	66.92 73	59.83 72	60.03 110	73.44 48	66.33 92	48.95 64	52.20 114	50.81 78	56.07 97	60.25 109	53.56 86	73.23 54	70.01 67	79.30 58	83.24 44

UniMVSNet_NR-MVSNet		56.94 129	61.14 112	52.05 136	60.02 111	65.21 120	57.44 150	52.93 41	49.37 128	24.31 211	54.62 108	50.54 150	39.04 172	68.69 104	68.84 79	78.53 66	70.72 137

IterMVS-LS		58.30 117	61.39 111	54.71 112	59.92 112	58.40 180	59.42 137	43.64 124	48.71 139	40.25 133	57.53 93	58.55 115	52.15 104	65.42 167	65.34 142	72.85 163	75.77 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 145	59.98 130	49.71 148	59.80 113	64.10 130	56.48 160	49.34 60	52.27 113	21.56 216	44.49 173	51.96 143	35.93 200	70.59 75	69.07 75	75.13 124	67.40 162

MVS_Test		62.40 84	66.23 84	57.94 87	59.77 114	64.77 123	66.50 91	41.76 153	57.26 87	49.33 81	62.68 58	67.47 69	53.50 90	68.57 108	66.25 126	76.77 98	76.58 101

FA-MVS(training)		60.00 98	63.14 106	56.33 102	59.50 115	64.30 128	65.15 107	38.75 188	56.20 89	45.77 99	53.08 111	56.45 124	52.10 105	69.04 102	67.67 94	76.69 99	75.27 117

TranMVSNet+NR-MVSNet		55.87 137	60.14 127	50.88 141	59.46 116	63.82 132	57.93 147	52.98 40	48.94 134	20.52 219	52.87 113	47.33 173	36.81 193	69.12 101	69.03 76	77.56 85	69.89 143

Fast-Effi-MVS+		60.36 95	63.35 104	56.87 98	58.70 117	65.86 111	65.08 108	37.11 204	53.00 106	45.36 103	52.12 118	56.07 129	56.27 59	71.28 67	69.42 71	78.71 63	75.69 112

IB-MVS	54.11 11	58.36 116	60.70 117	55.62 108	58.67 118	68.02 84	61.56 124	43.15 140	46.09 160	44.06 109	44.24 175	50.99 149	48.71 124	66.70 147	70.33 62	77.60 82	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		56.30 135	59.29 141	52.82 131	58.64 119	64.89 121	65.56 103	32.89 230	45.80 163	35.04 155	45.89 160	54.14 134	49.41 120	67.16 140	66.45 123	75.37 121	70.69 139

CNLPA		62.78 81	66.31 83	58.65 80	58.47 120	68.41 70	65.98 97	41.22 161	78.02 23	56.04 39	46.65 148	59.50 112	57.50 46	69.67 89	65.27 144	72.70 169	76.67 98

tpm cat1		53.30 158	53.41 183	53.17 127	58.16 121	59.15 171	63.73 120	38.27 192	50.73 119	46.98 90	45.57 164	44.00 211	49.20 121	55.90 226	54.02 225	62.65 217	64.50 196

v1144		58.88 106	60.16 126	57.39 93	58.03 122	67.26 96	67.14 84	44.46 96	45.17 166	44.33 108	47.81 142	49.92 155	53.20 96	67.77 127	66.62 117	77.15 92	76.58 101

v10		59.17 105	60.60 118	57.50 92	57.95 123	66.73 102	67.09 86	44.11 102	46.85 154	45.42 102	48.18 141	51.07 146	53.63 85	67.84 125	66.59 118	76.79 97	76.92 90

v1192		58.51 110	59.66 133	57.17 95	57.82 124	67.72 87	66.21 94	44.83 91	44.15 174	43.49 111	46.68 147	47.94 164	53.55 87	67.39 134	66.51 121	77.13 93	77.20 83

viewmambaseed2359dif		60.40 94	64.15 99	56.03 104	57.79 125	63.53 135	65.91 98	41.64 154	54.98 93	46.47 94	60.16 80	64.71 87	50.76 114	66.25 155	62.83 175	73.61 153	76.57 103

v144192		58.23 119	59.40 140	56.87 98	57.56 126	66.89 100	65.70 100	45.01 89	44.06 175	42.88 113	46.61 149	48.09 163	53.49 91	66.94 145	65.90 136	76.61 100	77.29 81

v1921920		57.89 122	59.02 143	56.58 101	57.55 127	66.66 106	64.72 111	44.70 93	43.55 179	42.73 114	46.17 157	46.93 181	53.51 88	66.78 146	65.75 138	76.29 105	77.28 82

Vis-MVSNet (Re-imp)		50.37 180	57.73 157	41.80 212	57.53 128	54.35 203	45.70 222	45.24 86	49.80 123	13.43 233	58.23 91	56.42 125	20.11 236	62.96 177	63.36 169	68.76 195	58.96 219

CostFormer		56.57 132	59.13 142	53.60 121	57.52 129	61.12 152	66.94 88	35.95 211	53.44 99	44.68 106	55.87 100	54.44 133	48.21 127	60.37 190	58.33 198	68.27 197	70.33 142

thres400		52.38 164	55.51 167	48.74 160	57.49 130	60.10 162	55.45 171	43.54 127	42.90 186	26.72 201	43.34 186	45.03 203	36.61 196	66.20 157	64.53 153	72.66 170	66.43 177

thres600view7		51.91 171	55.14 171	48.14 170	57.43 131	60.18 160	54.60 177	43.73 121	42.61 190	25.20 206	43.10 189	44.47 208	35.19 203	66.36 151	63.28 170	72.66 170	66.01 184

thres200		52.39 163	55.37 170	48.90 158	57.39 132	60.18 160	55.60 169	43.73 121	42.93 185	27.41 195	43.35 185	45.09 200	36.61 196	66.36 151	63.92 165	72.66 170	65.78 186

baseline2		55.89 136	57.82 154	53.64 120	57.36 133	61.09 153	59.75 136	40.45 171	47.38 152	41.26 127	51.23 123	46.90 182	48.11 128	65.63 164	64.38 157	74.90 127	68.16 158

v8		58.88 106	60.57 120	56.92 97	57.35 134	65.69 113	66.69 90	42.64 144	47.89 149	45.77 99	49.04 132	52.98 139	52.77 98	67.51 132	65.57 139	76.26 107	75.30 116

thres100view900		52.04 168	54.81 175	48.80 159	57.31 135	59.33 168	55.30 173	42.92 143	42.85 187	27.81 193	43.00 190	45.06 201	36.99 189	64.74 170	63.51 167	72.47 173	65.21 190

tfpn200view9		52.53 161	55.51 167	49.06 156	57.31 135	60.24 159	55.42 172	43.77 119	42.85 187	27.81 193	43.00 190	45.06 201	37.32 187	66.38 150	64.54 152	72.71 168	66.54 174

v1240		57.55 124	58.63 147	56.29 103	57.30 137	66.48 107	63.77 119	44.56 95	42.77 189	42.48 116	45.64 163	46.28 188	53.46 92	66.32 153	65.80 137	76.16 109	77.13 84

dmvs_re		52.07 166	55.11 172	48.54 165	57.27 138	51.93 212	57.73 149	43.13 141	43.65 177	26.57 202	44.52 172	50.00 154	36.53 198	66.58 149	62.15 181	69.97 191	66.91 171

CHOSEN 1792x2688		55.85 138	58.01 152	53.33 123	57.26 139	62.82 139	63.29 123	41.55 156	46.65 156	38.34 141	34.55 222	53.50 135	52.43 101	67.10 142	67.56 97	67.13 201	73.92 126

PVSNet_BlendedMVS		61.63 89	64.82 93	57.91 89	57.21 140	67.55 91	63.47 121	46.08 77	54.72 94	52.46 69	58.59 88	60.73 105	51.82 108	70.46 76	65.20 146	76.44 103	76.50 105

PVSNet_Blended		61.63 89	64.82 93	57.91 89	57.21 140	67.55 91	63.47 121	46.08 77	54.72 94	52.46 69	58.59 88	60.73 105	51.82 108	70.46 76	65.20 146	76.44 103	76.50 105

viewdifsd2359ckpt11		59.45 100	63.57 102	54.65 114	57.17 142	62.71 141	64.67 112	38.99 180	52.96 107	42.12 120	58.97 85	62.23 97	51.18 110	67.35 135	63.98 161	73.75 146	76.80 94

viewmsd2359difaftdt		59.45 100	63.57 102	54.65 114	57.17 142	62.71 141	64.67 112	38.99 180	52.96 107	42.12 120	58.97 85	62.22 98	51.18 110	67.35 135	63.98 161	73.75 146	76.80 94

v2v482		58.69 109	60.12 129	57.03 96	57.16 144	66.05 110	67.17 83	43.52 128	46.33 158	45.19 104	49.46 131	51.02 147	52.51 100	67.30 137	66.03 132	76.61 100	74.62 119

tfpnnormal		50.16 182	52.19 201	47.78 176	56.86 145	58.37 181	54.15 178	44.01 108	38.35 224	25.94 204	36.10 217	37.89 231	34.50 206	65.93 159	63.42 168	71.26 183	65.28 189

diffmvs_AUTHOR		61.79 86	66.80 74	55.95 105	56.69 146	63.92 131	67.27 81	41.28 159	59.32 73	46.43 95	63.31 52	68.30 63	50.56 115	68.30 112	66.06 130	73.48 154	78.36 71

diffmvs		61.64 88	66.55 81	55.90 106	56.63 147	63.71 134	67.13 85	41.27 160	59.49 71	46.70 92	63.93 51	68.01 67	50.46 116	67.30 137	65.51 140	73.24 161	77.87 78
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		56.87 130	58.60 148	54.84 111	56.62 148	69.27 65	64.77 110	42.21 148	45.66 164	37.50 147	33.08 225	57.47 121	53.33 93	65.46 166	67.94 87	74.60 128	71.35 134

v7n		55.67 140	57.46 159	53.59 122	56.06 149	65.29 116	61.06 130	43.26 137	40.17 207	37.99 144	40.79 203	45.27 198	47.09 134	67.67 129	66.21 127	76.08 111	76.82 93

dps		50.42 178	51.20 207	49.51 150	55.88 150	56.07 199	53.73 180	38.89 184	43.66 176	40.36 132	45.66 162	37.63 233	45.23 143	59.05 199	56.18 209	62.94 216	60.16 215

CANet_DTU		58.88 106	64.68 96	52.12 135	55.77 151	66.75 101	63.92 118	37.04 205	53.32 102	37.45 148	59.81 81	61.81 101	44.43 147	68.25 114	67.47 99	74.12 133	75.33 115

WR-MVS		48.78 199	55.06 173	41.45 213	55.50 152	60.40 158	43.77 230	49.99 57	41.92 194	8.10 247	45.24 169	45.56 193	17.47 237	61.57 185	64.60 151	73.85 140	66.14 183

UniMVSNet (Re)		55.15 149	60.39 121	49.03 157	55.31 153	64.59 124	55.77 167	50.63 53	48.66 141	20.95 217	51.47 122	50.40 151	34.41 207	67.81 126	67.89 88	77.11 94	71.88 131

test-LLR		49.28 189	50.29 211	48.10 171	55.26 154	47.16 229	49.52 202	43.48 132	39.22 211	31.98 168	43.65 182	47.93 165	41.29 164	56.80 216	55.36 215	67.08 202	61.94 208

test0.0.03 1		43.15 223	46.95 225	38.72 222	55.26 154	50.56 216	42.48 233	43.48 132	38.16 226	15.11 228	35.07 220	44.69 206	16.47 239	55.95 225	54.34 224	59.54 225	49.87 239

GA-MVS		55.67 140	58.33 149	52.58 133	55.23 156	63.09 136	61.08 129	40.15 176	42.95 184	37.02 150	52.61 115	47.68 168	47.51 132	65.92 160	65.35 141	74.49 130	70.68 140

DTE-MVSNet		48.03 205	53.28 185	41.91 211	54.64 157	57.50 194	44.63 229	51.66 49	41.02 201	7.97 248	46.26 154	40.90 219	20.24 235	60.45 189	62.89 174	72.33 176	63.97 197

pmmvs4		54.66 152	56.07 163	53.00 128	54.63 158	57.08 196	60.43 134	44.10 103	51.69 116	40.55 130	46.55 152	44.79 204	45.95 140	62.54 179	63.66 166	72.36 175	66.20 181

DU-MVS		55.41 143	59.59 134	50.54 144	54.60 159	62.97 137	57.44 150	51.80 46	48.62 142	24.31 211	51.99 119	47.00 178	39.04 172	68.11 119	67.75 92	76.03 115	70.72 137

Baseline_NR-MVSNet		53.50 156	57.89 153	48.37 168	54.60 159	59.25 170	56.10 162	51.84 45	49.32 129	17.92 226	45.38 166	47.68 168	36.93 190	68.11 119	65.95 134	72.84 164	69.57 148

v148		55.58 142	57.61 158	53.20 125	54.59 161	61.86 144	61.18 128	38.70 189	44.30 173	42.25 118	47.53 143	50.24 153	48.73 123	65.15 168	62.61 179	73.79 141	71.61 133

PEN-MVS		49.21 192	54.32 177	43.24 207	54.33 162	59.26 169	47.04 215	51.37 50	41.67 197	9.97 242	46.22 155	41.80 216	22.97 232	60.52 188	64.03 159	73.73 148	66.75 173

pm-mvs1		51.02 175	55.55 166	45.73 188	54.16 163	58.52 175	50.92 198	42.56 145	40.32 205	25.67 205	43.66 181	50.34 152	30.06 215	65.85 161	63.97 163	70.99 187	66.21 180

EPNet_dtu		52.05 167	58.26 150	44.81 198	54.10 164	50.09 219	52.01 196	40.82 164	53.03 105	27.41 195	54.90 103	57.96 120	26.72 223	62.97 176	62.70 178	67.78 199	66.19 182
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 198	51.27 206	45.96 187	54.10 164	47.35 228	56.05 163	30.23 234	46.70 155	43.21 112	52.54 116	47.55 171	37.28 188	54.11 231	50.50 235	54.90 235	60.12 216

CDS-MVSNet		52.42 162	57.06 161	47.02 179	53.92 166	58.30 186	55.50 170	46.47 75	42.52 191	29.38 183	49.50 130	52.85 140	28.49 221	66.70 147	66.89 109	68.34 196	62.63 206
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 232	44.20 233	35.92 230	53.73 167	49.05 220	38.54 240	43.49 130	32.55 236	9.54 243	27.88 238	39.12 227	12.24 244	56.28 222	54.69 221	57.96 230	49.83 240

Vis-MVSNet		58.48 112	65.70 88	50.06 147	53.40 168	67.20 97	60.24 135	43.32 135	48.83 136	30.23 178	62.38 62	61.61 103	40.35 167	71.03 69	69.77 68	72.82 165	79.11 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PLC	52.09 14	59.21 104	62.47 107	55.41 110	53.24 169	64.84 122	64.47 116	40.41 173	65.92 55	44.53 107	46.19 156	55.69 130	55.33 67	68.24 116	65.30 143	74.50 129	71.09 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 131	59.68 132	53.19 126	52.97 170	60.96 155	59.41 138	40.51 168	48.26 145	41.06 128	52.67 114	46.30 187	49.78 117	67.66 130	67.83 89	75.39 120	74.07 125

OMC-MVS		65.16 61	71.35 46	57.94 87	52.95 171	68.82 67	69.00 71	38.28 191	79.89 16	55.20 44	62.76 56	68.31 62	56.14 61	71.30 66	68.70 80	76.06 114	79.67 60

tpmrst		48.08 203	49.88 216	45.98 186	52.71 172	48.11 225	53.62 185	33.70 225	48.70 140	39.74 134	48.96 134	46.23 189	40.29 168	50.14 241	49.28 237	55.80 232	57.71 222

tttt0517		56.53 133	59.59 134	52.95 129	52.66 173	60.99 154	59.21 140	40.51 168	47.89 149	40.40 131	52.50 117	46.04 191	49.78 117	67.75 128	67.83 89	75.15 123	74.17 122

GBi-Net		55.20 146	60.25 123	49.31 151	52.42 174	61.44 147	57.03 153	44.04 105	49.18 131	30.47 174	48.28 137	58.19 116	38.22 178	68.05 122	66.96 105	73.69 149	69.65 145

test1		55.20 146	60.25 123	49.31 151	52.42 174	61.44 147	57.03 153	44.04 105	49.18 131	30.47 174	48.28 137	58.19 116	38.22 178	68.05 122	66.96 105	73.69 149	69.65 145

FMVSNet2		55.04 150	59.95 131	49.31 151	52.42 174	61.44 147	57.03 153	44.08 104	49.55 125	30.40 177	46.89 146	58.84 114	38.22 178	67.07 143	66.21 127	73.69 149	69.65 145

FMVSNet3		54.78 151	59.58 136	49.17 154	52.37 177	61.31 151	56.72 158	44.04 105	49.18 131	30.47 174	48.28 137	58.19 116	38.09 181	65.48 165	65.20 146	73.31 158	69.45 153

testgi		38.71 235	43.64 235	32.95 235	52.30 178	48.63 224	35.59 246	35.05 215	31.58 240	9.03 246	30.29 230	40.75 221	11.19 250	55.30 227	53.47 230	54.53 237	45.48 243

Anonymous20231206		42.28 224	45.89 227	38.07 224	51.96 179	48.98 221	43.66 231	38.81 187	38.74 215	14.32 231	26.74 239	40.90 219	20.94 233	56.64 219	54.67 222	58.71 226	54.59 227

pmmvs6		48.35 201	51.64 203	44.51 200	51.92 180	57.94 192	49.44 204	42.17 149	34.45 232	24.62 210	28.87 237	46.90 182	29.07 219	64.60 171	63.08 171	69.83 192	65.68 187

PatchmatchNet		49.92 187	51.29 205	48.32 169	51.83 181	51.86 213	53.38 187	37.63 203	47.90 148	40.83 129	48.54 136	45.30 196	45.19 144	56.86 215	53.99 227	61.08 223	54.57 228
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 206	53.67 180	40.63 217	51.45 182	59.74 165	44.71 228	49.37 59	40.69 203	7.61 249	46.04 158	44.34 210	17.32 238	57.79 211	61.18 185	73.30 159	65.86 185

LTVRE_ROB	44.17 16	47.06 211	50.15 214	43.44 204	51.39 183	58.42 179	42.90 232	43.51 129	22.27 250	14.85 230	41.94 200	34.57 238	45.43 141	62.28 182	62.77 177	62.56 219	68.83 156
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		48.37 200	53.53 181	42.34 209	51.35 184	58.01 191	46.56 217	50.54 54	41.62 198	10.61 238	46.53 153	40.68 222	23.18 230	58.71 204	61.83 182	71.81 179	67.36 165

PS-CasMVS		48.18 202	53.25 186	42.27 210	51.26 185	57.94 192	46.51 218	50.52 55	41.30 199	10.56 239	45.35 168	40.34 224	23.04 231	58.66 205	61.79 183	71.74 181	67.38 163

our_test_3					51.15 186	57.31 195	55.12 174

SCA		50.99 176	53.22 187	48.40 167	51.07 187	56.78 197	50.25 200	39.05 179	48.31 144	41.38 124	49.54 129	46.70 185	46.00 139	58.31 207	56.28 208	62.65 217	56.60 225

UniMVSNet_ETH3D		52.62 160	55.98 164	48.70 162	51.04 188	60.71 157	56.87 156	46.74 74	42.52 191	26.96 199	42.50 197	45.95 192	37.87 182	66.22 156	65.15 149	72.74 166	68.78 157

IterMVS-SCA-FT		52.18 165	57.75 156	45.68 189	51.01 189	62.06 143	55.10 175	34.75 216	44.85 167	32.86 166	51.13 125	51.22 145	48.74 122	62.47 180	61.51 184	51.61 242	71.02 136

FMVSNet1		54.08 154	58.68 146	48.71 161	50.90 190	61.35 150	56.73 157	43.94 114	45.91 162	29.32 184	42.72 192	56.26 128	37.70 185	68.05 122	66.96 105	73.69 149	69.50 149

pmmvs-eth3d		51.33 173	52.25 200	50.26 146	50.82 191	54.65 202	56.03 164	43.45 134	43.51 180	37.20 149	39.20 210	39.04 228	42.28 159	61.85 184	62.78 176	71.78 180	64.72 194

MVSTER		57.19 125	61.11 113	52.62 132	50.82 191	58.79 173	61.55 125	37.86 201	48.81 137	41.31 125	57.43 95	52.10 142	48.60 125	68.19 118	66.75 111	75.56 118	75.68 113

ambc			45.54 230		50.66 193	52.63 210	40.99 237		38.36 223	24.67 209	22.62 245	13.94 256	29.14 218	65.71 163	58.06 199	58.60 228	67.43 161

thisisatest0515		53.85 155	56.84 162	50.37 145	50.25 194	58.17 188	55.99 165	39.90 177	41.88 195	38.16 143	45.91 159	45.30 196	44.58 146	66.15 158	66.89 109	73.36 157	73.57 128

baseline		55.19 148	60.88 114	48.55 164	49.87 195	58.10 190	58.70 142	34.75 216	52.82 110	39.48 139	60.18 79	60.86 104	45.41 142	61.05 186	60.74 189	63.10 215	72.41 130

MDTV_nov1_ep13		50.32 181	52.43 197	47.86 175	49.87 195	54.70 201	58.10 146	34.29 220	45.59 165	37.71 145	47.44 144	47.42 172	41.86 161	58.07 210	55.21 218	65.34 209	58.56 220

IterMVS		53.45 157	57.12 160	49.17 154	49.23 197	60.93 156	59.05 141	34.63 218	44.53 169	33.22 162	51.09 126	51.01 148	48.38 126	62.43 181	60.79 188	70.54 189	69.05 155
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 169	54.86 174	48.63 163	49.13 198	61.73 146	60.53 133	36.57 208	53.14 103	32.95 165	37.10 214	38.68 229	40.49 166	65.72 162	63.08 171	72.11 178	64.60 195
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 177	52.61 192	47.98 173	49.03 199	52.94 207	48.27 207	38.86 185	44.41 170	39.59 136	44.34 174	44.65 207	46.63 136	58.97 201	60.31 190	65.48 207	62.66 204

V42		56.97 128	60.14 127	53.28 124	48.16 200	62.78 140	66.30 93	37.93 200	47.44 151	42.68 115	48.19 140	52.59 141	51.90 106	67.46 133	65.94 135	72.72 167	76.55 104

MDTV_nov1_ep13_2view		47.62 207	49.72 217	45.18 194	48.05 201	53.70 205	54.90 176	33.80 224	39.90 209	29.79 180	38.85 211	41.89 215	39.17 171	58.99 200	55.55 214	65.34 209	59.17 218

EPMVS		44.66 219	47.86 223	40.92 215	47.97 202	44.70 238	47.58 212	33.27 227	48.11 147	29.58 182	49.65 128	44.38 209	34.65 204	51.71 235	47.90 239	52.49 240	48.57 241

usedtu_dtu_shiyan1		51.41 172	55.78 165	46.30 185	47.91 203	59.47 166	52.99 189	42.13 151	48.17 146	24.88 207	40.95 201	48.18 162	35.95 199	64.48 172	64.49 154	73.94 139	64.75 193

RPMNet		46.41 212	48.72 219	43.72 202	47.77 204	52.94 207	46.02 221	33.92 222	44.41 170	31.82 171	36.89 215	37.42 235	37.41 186	53.88 232	54.02 225	65.37 208	61.47 210

TAPA-MVS	54.74 10	60.85 93	66.61 80	54.12 119	47.38 205	65.33 115	65.35 105	36.51 209	75.16 31	48.82 85	54.70 106	63.51 91	53.31 94	68.36 110	64.97 150	73.37 156	74.27 121
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 208	50.25 213	44.41 201	47.30 206	54.31 204	47.81 210	40.36 174	33.76 233	19.93 221	43.75 180	32.77 242	42.07 160	59.82 191	60.94 187	68.98 193	66.37 179

TAMVS		44.02 221	49.18 218	37.99 225	47.03 207	45.97 235	45.04 225	28.47 238	39.11 213	20.23 220	43.22 188	48.52 160	28.49 221	58.15 209	57.95 200	58.71 226	51.36 231

UGNet		57.03 126	65.25 91	47.44 177	46.54 208	66.73 102	56.30 161	43.28 136	50.06 121	32.99 164	62.57 59	63.26 92	33.31 210	68.25 114	67.58 96	72.20 177	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 82	69.90 55	54.19 117	46.31 209	66.73 102	65.49 104	41.36 158	76.57 25	46.31 96	76.80 18	56.68 122	53.27 95	69.50 94	66.65 115	72.40 174	76.36 107

PatchMatch-RL		50.11 184	51.56 204	48.43 166	46.23 210	51.94 211	50.21 201	38.62 190	46.62 157	37.51 146	42.43 198	39.38 226	52.24 103	60.98 187	59.56 193	65.76 206	60.01 217

0.4-1-1-0.2		49.99 185	52.69 191	46.83 180	45.99 211	58.16 189	53.71 181	35.75 212	42.13 193	34.14 158	44.08 176	49.28 156	40.24 169	56.44 221	55.24 217	71.18 186	63.49 201

CMPMVS	37.70 17	49.24 190	52.71 190	45.19 193	45.97 212	51.23 215	47.44 213	29.31 235	43.04 183	44.69 105	34.45 223	48.35 161	43.64 149	62.59 178	59.82 192	60.08 224	69.48 150
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 231	43.80 234	36.61 228	45.79 213	40.45 243	42.12 234	33.18 228	40.30 206	24.11 213	38.76 212	37.11 236	24.30 227	52.97 233	46.66 243	50.17 243	50.33 236

pmmvs5		47.07 210	51.02 209	42.46 208	45.18 214	51.47 214	48.23 209	33.09 229	38.17 225	28.62 187	46.60 150	43.48 212	30.74 213	58.28 208	58.63 197	68.92 194	60.48 213

blend_shiyan4		50.41 179	53.51 182	46.79 181	44.79 215	58.47 176	52.51 190	36.99 206	41.74 196	34.13 159	42.68 193	49.24 157	38.37 175	58.53 206	56.69 207	73.96 138	67.20 167

USDC		51.11 174	53.71 179	48.08 172	44.76 216	55.99 200	53.01 188	40.90 162	52.49 111	36.14 151	44.67 171	33.66 240	43.27 154	63.23 175	61.10 186	70.39 190	64.82 192

FC-MVSNet-test		39.65 234	48.35 221	29.49 239	44.43 217	39.28 247	30.23 249	40.44 172	43.59 178	3.12 256	53.00 112	42.03 214	10.02 252	55.09 228	54.77 220	48.66 244	50.71 234

ADS-MVSNet		40.67 229	43.38 236	37.50 226	44.36 218	39.79 245	42.09 235	32.67 232	44.34 172	28.87 186	40.76 204	40.37 223	30.22 214	48.34 246	45.87 244	46.81 246	44.21 245

new-patchmatchnet		33.24 242	37.20 243	28.62 241	44.32 219	38.26 248	29.68 250	36.05 210	31.97 238	6.33 251	26.59 240	27.33 247	11.12 251	50.08 242	41.05 247	44.23 247	45.15 244

MVS-HIRNet		42.24 225	41.15 239	43.51 203	44.06 220	40.74 241	35.77 245	35.35 213	35.38 231	38.34 141	25.63 242	38.55 230	43.48 151	50.77 237	47.03 241	64.07 211	49.98 237

PatchT		48.08 203	51.03 208	44.64 199	42.96 221	50.12 218	40.36 238	35.09 214	43.17 182	39.59 136	42.00 199	39.96 225	46.63 136	58.97 201	60.31 190	63.21 214	62.66 204

CVMVSNet		46.38 214	52.01 202	39.81 219	42.40 222	50.26 217	46.15 219	37.68 202	40.03 208	15.09 229	46.56 151	47.56 170	33.72 209	56.50 220	55.65 213	63.80 213	67.53 160

TinyColmap		47.08 209	47.56 224	46.52 183	42.35 223	53.44 206	51.77 197	40.70 166	43.44 181	31.92 170	29.78 233	23.72 252	45.04 145	61.99 183	59.54 194	67.35 200	61.03 211

ET-MVSNet_ETH3D		58.38 115	61.57 110	54.67 113	42.15 224	65.26 117	65.70 100	43.82 118	48.84 135	42.34 117	59.76 82	47.76 167	56.68 56	67.02 144	68.60 83	77.33 90	73.73 127

blended_shiyan6		49.22 191	52.60 193	45.26 192	41.68 225	58.46 178	52.42 191	38.16 194	38.60 216	28.50 191	40.28 205	47.09 175	36.76 195	59.62 192	57.25 202	74.06 135	66.92 169

blended_shiyan8		49.21 192	52.59 194	45.27 191	41.67 226	58.47 176	52.41 192	38.16 194	38.60 216	28.53 190	40.26 206	47.07 176	36.78 194	59.62 192	57.26 201	74.06 135	66.88 172

wanda-best-256-512		49.05 196	52.38 198	45.17 195	41.54 227	58.31 182	52.24 193	38.00 196	38.58 218	28.56 188	40.23 207	47.00 178	36.88 191	59.28 195	56.77 203	73.78 142	66.45 175

FE-blended-shiyan7		49.05 196	52.38 198	45.17 195	41.54 227	58.31 182	52.24 193	38.00 196	38.58 218	28.56 188	40.23 207	47.00 178	36.88 191	59.28 195	56.77 203	73.78 142	66.45 175

usedtu_blend_shiyan5		50.12 183	53.15 188	46.58 182	41.54 227	58.31 182	53.69 183	38.00 196	38.58 218	34.13 159	42.68 193	49.24 157	38.37 175	59.28 195	56.77 203	73.78 142	67.20 167

FE-MVSNET3		49.99 185	53.11 189	46.34 184	41.54 227	58.31 182	52.24 193	38.00 196	38.58 218	34.13 159	42.68 193	49.24 157	38.37 175	59.28 195	56.77 203	73.78 142	66.92 169

MIMVSNet		43.79 222	48.53 220	38.27 223	41.46 231	48.97 222	50.81 199	32.88 231	44.55 168	22.07 214	32.05 226	47.15 174	24.76 226	58.73 203	56.09 211	57.63 231	52.14 229

WB-MVS		29.70 244	35.40 245	23.05 244	40.96 232	39.59 246	18.79 253	40.20 175	25.26 245	1.88 259	33.33 224	21.97 254	3.36 253	48.69 245	44.60 245	33.11 251	34.39 247

N_pmnet		32.67 243	36.85 244	27.79 242	40.55 233	32.13 249	35.80 244	26.79 241	37.24 228	9.10 244	32.02 227	30.94 245	16.30 240	47.22 247	41.21 246	38.21 249	37.21 246

anonymousdsp		52.84 159	57.78 155	47.06 178	40.24 234	58.95 172	53.70 182	33.54 226	36.51 230	32.69 167	43.88 178	45.40 194	47.97 131	67.17 139	70.28 63	74.22 132	82.29 48

FE-MVSNET2		45.69 216	49.95 215	40.72 216	40.11 235	56.16 198	46.59 216	41.89 152	36.97 229	13.66 232	29.00 236	37.59 234	28.96 220	63.26 174	63.93 164	73.13 162	62.72 203

EU-MVSNet		40.63 230	45.65 229	34.78 233	39.11 236	46.94 232	40.02 239	34.03 221	33.50 234	10.37 240	35.57 219	37.80 232	23.65 229	51.90 234	50.21 236	61.49 222	63.62 200

FPMVS		38.36 236	40.41 240	35.97 229	38.92 237	39.85 244	45.50 223	25.79 244	41.13 200	18.70 223	30.10 231	24.56 250	31.86 212	49.42 243	46.80 242	55.04 233	51.03 232

TESTMET0.1,1		46.09 215	50.29 211	41.18 214	36.91 238	47.16 229	49.52 202	20.32 248	39.22 211	31.98 168	43.65 182	47.93 165	41.29 164	56.80 216	55.36 215	67.08 202	61.94 208

FMVSNet5		40.96 227	45.81 228	35.29 232	34.30 239	44.55 239	47.28 214	28.84 237	40.76 202	21.62 215	29.85 232	42.44 213	24.77 225	57.53 212	55.00 219	54.93 234	50.56 235

PMMVS		49.20 194	54.28 178	43.28 206	34.13 240	45.70 236	48.98 205	26.09 243	46.31 159	34.92 157	55.22 102	53.47 136	47.48 133	59.43 194	59.04 196	68.05 198	60.77 212

PMVS	27.84 18	33.81 241	35.28 246	32.09 237	34.13 240	24.81 252	32.51 248	26.48 242	26.41 244	19.37 222	23.76 243	24.02 251	25.18 224	50.78 236	47.24 240	54.89 236	49.95 238
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 217	50.37 210	39.38 220	33.65 242	46.99 231	47.59 211	18.59 249	38.75 214	28.00 192	43.28 187	46.82 184	41.50 163	57.28 213	55.78 212	66.93 204	63.70 199

CHOSEN 280x420		40.80 228	45.05 231	35.84 231	32.95 243	29.57 250	44.98 226	23.71 246	37.54 227	18.42 224	31.36 229	47.07 176	46.41 138	56.71 218	54.65 223	48.55 245	58.47 221

PM-MVS		44.55 220	48.13 222	40.37 218	32.85 244	46.82 233	46.11 220	29.28 236	40.48 204	29.99 179	39.98 209	34.39 239	41.80 162	56.08 224	53.88 229	62.19 220	65.31 188

FE-MVSNET		39.75 233	44.50 232	34.21 234	32.01 245	48.77 223	37.71 242	38.94 182	30.91 241	6.25 252	26.24 241	32.10 244	23.68 228	57.28 213	59.53 195	66.68 205	56.64 224

TDRefinement		49.31 188	52.44 196	45.67 190	30.44 246	59.42 167	59.24 139	39.78 178	48.76 138	31.20 173	35.73 218	29.90 246	42.81 157	64.24 173	62.59 180	70.55 188	66.43 177

Gipuma		25.87 245	26.91 248	24.66 243	28.98 247	20.17 253	20.46 251	34.62 219	29.55 242	9.10 244	4.91 256	5.31 260	15.76 241	49.37 244	49.10 238	39.03 248	29.95 249
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 226	43.15 237	39.27 221	28.74 248	52.68 209	44.95 227	40.84 163	32.89 235	18.13 225	31.61 228	22.09 253	38.97 174	50.45 240	56.11 210	64.01 212	56.23 226

E-PMN		15.09 248	13.19 252	17.30 246	27.80 249	12.62 256	7.81 257	27.54 239	14.62 254	3.19 254	6.89 253	2.52 263	15.09 242	15.93 252	20.22 251	22.38 252	19.53 252

MIMVSNet1		35.51 239	41.41 238	28.63 240	27.53 250	43.36 240	38.09 241	33.82 223	32.01 237	6.77 250	21.63 247	35.43 237	11.97 246	55.05 229	53.99 227	53.59 239	48.36 242

EMVS		14.49 249	12.45 253	16.87 248	27.02 251	12.56 257	8.13 256	27.19 240	15.05 253	3.14 255	6.69 254	2.67 262	15.08 243	14.60 254	18.05 252	20.67 253	17.56 254

pmmvs3		35.10 240	38.47 242	31.17 238	26.37 252	40.47 242	34.51 247	18.09 250	24.75 246	16.88 227	23.05 244	26.69 248	32.69 211	50.73 238	51.60 232	58.46 229	51.98 230

RPSCF		46.41 212	54.42 176	37.06 227	25.70 253	45.14 237	45.39 224	20.81 247	62.79 61	35.10 154	44.92 170	55.60 131	43.56 150	56.12 223	52.45 231	51.80 241	63.91 198

usedtu_dtu_shiyan2		36.29 238	39.77 241	32.23 236	19.53 254	48.11 225	41.99 236	36.59 207	23.95 248	12.80 234	22.03 246	32.26 243	20.73 234	50.69 239	50.64 234	61.72 221	50.72 233

new_pmnet		23.19 246	28.17 247	17.37 245	17.03 255	24.92 251	19.66 252	16.16 252	27.05 243	4.42 253	20.77 248	19.20 255	12.19 245	37.71 248	36.38 248	34.77 250	31.17 248

PMMVS2		15.84 247	19.68 249	11.35 249	15.74 256	16.95 254	13.31 254	17.64 251	16.08 252	0.36 260	13.12 250	11.47 257	1.69 255	28.82 249	27.24 250	19.38 255	24.09 251

MVE	12.28 19	13.53 250	15.72 250	10.96 250	7.39 257	15.71 255	6.05 258	23.73 245	10.29 256	3.01 257	5.77 255	3.41 261	11.91 247	20.11 250	29.79 249	13.67 256	24.98 250
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 252	3.97 258	2.35 260	3.26 260	0.44 255	17.56 251	12.09 235	11.48 252	7.14 258	1.98 254	15.68 253	15.49 253	10.69 257

test_method		12.44 251	14.66 251	9.85 251	1.30 259	3.32 259	13.00 255	3.21 253	22.42 249	10.22 241	14.13 249	25.64 249	11.43 249	19.75 251	11.61 254	19.96 254	5.79 255

GG-mvs-BLEND		36.62 237	53.39 184	17.06 247	0.01 260	58.61 174	48.63 206	0.01 256	47.13 153	0.02 261	43.98 177	60.64 107	0.03 256	54.92 230	51.47 233	53.64 238	56.99 223

uanet_test		0.00 254	0.00 256	0.00 253	0.00 261	0.00 261	0.00 263	0.00 257	0.00 259	0.00 262	0.00 259	0.00 264	0.00 259	0.00 257	0.00 257	0.00 259	0.00 258

sosnet-low-res		0.00 254	0.00 256	0.00 253	0.00 261	0.00 261	0.00 263	0.00 257	0.00 259	0.00 262	0.00 259	0.00 264	0.00 259	0.00 257	0.00 257	0.00 259	0.00 258

sosnet		0.00 254	0.00 256	0.00 253	0.00 261	0.00 261	0.00 263	0.00 257	0.00 259	0.00 262	0.00 259	0.00 264	0.00 259	0.00 257	0.00 257	0.00 259	0.00 258

testmvs		0.01 252	0.02 254	0.00 253	0.00 261	0.00 261	0.01 262	0.00 257	0.01 257	0.00 262	0.03 258	0.00 264	0.01 257	0.01 256	0.01 255	0.00 259	0.06 257

test123		0.01 252	0.02 254	0.00 253	0.00 261	0.00 261	0.00 263	0.00 257	0.01 257	0.00 262	0.04 257	0.00 264	0.01 257	0.00 257	0.01 255	0.00 259	0.07 256

RE-MVS-def										33.01 163

9.14												81.81 14

MTAPA										65.14 4		80.20 21

MTMP										62.63 17		78.04 28

Patchmatch-RL test							1.04 261

NP-MVS									72.00 43

Patchmtry						47.61 227	48.27 207	38.86 185		39.59 136

DeepMVS_CX						6.95 258	5.98 259	2.25 254	11.73 255	2.07 258	11.85 251	5.43 259	11.75 248	11.40 255		8.10 258	18.38 253

High-resolution multi-view benchmark