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.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 5	76.83 8	94.16 1	86.57 2	90.85 6	87.07 1	86.18 1	86.36 7	85.08 13	88.67 35	98.21 3

DVP-MVS		88.07 2	90.73 2	84.97 5	91.98 10	95.01 2	87.86 12	76.88 7	93.90 2	85.15 3	90.11 8	86.90 2	79.46 13	86.26 10	84.67 18	88.50 43	98.25 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
DPE-MVS		87.60 6	90.44 4	84.29 8	92.09 9	93.44 6	88.69 4	75.11 11	93.06 5	80.80 8	94.23 3	86.70 3	81.44 7	84.84 18	83.52 28	87.64 70	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		85.24 13	88.27 10	81.72 16	91.74 12	90.71 21	86.71 15	73.16 21	90.56 11	74.33 22	83.07 19	85.88 4	77.16 22	86.28 9	85.58 7	87.23 85	95.77 15
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
ME-MVS		87.94 4	89.84 5	85.72 3	91.74 12	92.20 14	88.32 8	77.84 4	92.47 6	85.03 4	94.60 2	85.70 5	81.31 8	83.94 25	83.57 27	90.10 6	96.41 14

DVP-MVS++		87.98 3	89.76 6	85.89 2	92.57 6	94.57 3	88.34 6	76.61 9	92.40 7	83.40 5	89.26 11	85.57 6	86.04 2	86.24 11	84.89 15	88.39 46	95.42 22

SD-MVS		84.31 16	86.96 15	81.22 17	88.98 32	88.68 47	85.65 20	73.85 17	89.09 14	79.63 10	87.34 13	84.84 7	73.71 36	82.66 36	81.60 50	85.48 134	94.51 31
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
9.14												84.47 8

HPM-MVS++		85.64 11	88.43 8	82.39 13	92.65 4	90.24 27	85.83 19	74.21 13	90.68 10	75.63 19	86.77 14	84.15 9	78.68 17	86.33 8	85.26 10	87.32 80	95.60 19

TSAR-MVS + GP.		82.27 25	85.98 21	77.94 33	80.72 72	88.25 60	81.12 46	67.71 46	87.10 18	73.31 24	85.23 16	83.68 10	76.64 24	80.43 63	81.47 53	88.15 53	95.66 18

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 20	82.52 21	83.34 11	83.53 4			89.62 11	90.78 90
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
SF-MVS		87.30 7	88.71 7	85.64 4	94.57 1	94.55 4	91.01 1	79.94 1	89.15 13	79.85 9	92.37 4	83.29 12	79.75 10	83.52 27	82.72 34	88.75 34	95.37 25

MSP-MVS		87.87 5	90.57 3	84.73 6	89.38 28	91.60 18	88.24 10	74.15 14	93.55 3	82.28 6	94.99 1	83.21 13	85.96 3	87.67 4	84.67 18	88.32 47	98.29 1
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
TSAR-MVS + MP.		84.39 15	86.58 19	81.83 15	88.09 40	86.47 86	85.63 21	73.62 19	90.13 12	79.24 11	89.67 10	82.99 14	77.72 20	81.22 54	80.92 67	86.68 99	94.66 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CSCG		82.90 22	84.52 25	81.02 19	91.85 11	93.43 7	87.14 14	74.01 16	81.96 33	76.14 16	70.84 39	82.49 15	69.71 81	82.32 42	85.18 12	87.26 84	95.40 24

TSAR-MVS + ACMM		81.59 27	85.84 22	76.63 39	89.82 24	86.53 85	86.32 18	66.72 54	85.96 22	65.43 47	88.98 12	82.29 16	67.57 101	82.06 47	81.33 56	83.93 178	93.75 44

train_agg		83.35 20	86.93 16	79.17 28	89.70 25	88.41 54	85.60 22	72.89 23	86.31 21	66.58 44	90.48 7	82.24 17	73.06 42	83.10 32	82.64 35	87.21 89	95.30 26

DPM-MVS		85.41 12	86.72 18	83.89 11	91.66 14	91.92 16	90.49 2	78.09 3	86.90 19	73.95 23	74.52 37	82.01 18	79.29 14	90.24 1	90.65 1	89.86 8	90.78 90

CNVR-MVS		85.96 9	87.58 12	84.06 9	92.58 5	92.40 12	87.62 13	77.77 6	88.44 15	75.93 18	79.49 27	81.97 19	81.65 6	87.04 6	86.58 4	88.79 32	97.18 7

APDe-MVS		86.37 8	88.41 9	84.00 10	91.43 16	91.83 17	88.34 6	74.67 12	91.19 8	81.76 7	91.13 5	81.94 20	80.07 9	83.38 28	82.58 36	87.69 68	96.78 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepPCF-MVS	76.94 1	83.08 21	87.77 11	77.60 35	90.11 21	90.96 20	78.48 61	72.63 24	93.10 4	65.84 46	80.67 25	81.55 21	74.80 30	85.94 13	85.39 9	83.75 180	96.77 12

MGCNet		83.82 18	86.88 17	80.26 22	88.48 33	93.17 8	82.93 34	67.66 47	88.28 16	74.90 21	77.08 34	80.93 22	78.09 18	85.83 14	85.88 6	89.53 16	96.96 10

SR-MVS					86.33 48			67.54 48				80.78 23

MCST-MVS		85.75 10	86.99 14	84.31 7	94.07 3	92.80 9	88.15 11	79.10 2	85.66 23	70.72 32	76.50 35	80.45 24	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

ACMMP_NAP		83.54 19	86.37 20	80.25 23	89.57 27	90.10 29	85.27 23	71.66 25	87.38 17	73.08 25	84.23 18	80.16 25	75.31 26	84.85 17	83.64 24	86.57 101	94.21 36

APD-MVS		84.83 14	87.00 13	82.30 14	89.61 26	89.21 37	86.51 17	73.64 18	90.98 9	77.99 14	89.89 9	80.04 26	79.18 15	82.00 49	81.37 55	86.88 94	95.49 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MTAPA										78.32 13		79.42 27

NCCC		84.16 17	85.46 23	82.64 12	92.34 8	90.57 24	86.57 16	76.51 10	86.85 20	72.91 26	77.20 33	78.69 28	79.09 16	84.64 20	84.88 16	88.44 44	95.41 23

SteuartSystems-ACMMP		82.51 23	85.35 24	79.20 27	90.25 19	89.39 35	84.79 24	70.95 27	82.86 29	68.32 40	86.44 15	77.19 29	73.07 41	83.63 26	83.64 24	87.82 62	94.34 33
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		80.94 28	83.49 28	77.96 32	88.48 33	88.16 61	82.82 35	69.34 36	80.79 39	69.67 36	82.35 22	77.13 30	71.60 61	80.97 59	80.96 66	85.87 119	94.06 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTMP										76.04 17		76.65 31

HFP-MVS		82.48 24	84.12 26	80.56 20	90.15 20	87.55 69	84.28 26	69.67 34	85.22 24	77.95 15	84.69 17	75.94 32	75.04 28	81.85 50	81.17 62	86.30 108	92.40 67

CANet		80.90 29	82.93 30	78.53 31	86.83 46	92.26 13	81.19 45	66.95 51	81.60 36	69.90 35	66.93 49	74.80 33	76.79 23	84.68 19	84.77 17	89.50 18	95.50 20

PHI-MVS		79.43 34	84.06 27	74.04 67	86.15 49	91.57 19	80.85 49	68.90 40	82.22 32	51.81 121	78.10 29	74.28 34	70.39 78	84.01 24	84.00 22	86.14 112	94.24 34

CP-MVS		79.44 33	81.51 35	77.02 38	86.95 44	85.96 96	82.00 37	68.44 43	81.82 34	67.39 41	77.43 31	73.68 35	71.62 60	79.56 77	79.58 87	85.73 124	92.51 63

ACMMPR		80.62 30	82.98 29	77.87 34	88.41 35	87.05 77	83.02 31	69.18 37	83.91 26	68.35 39	82.89 20	73.64 36	72.16 52	80.78 60	81.13 63	86.10 113	91.43 80

GG-mvs-BLEND		54.54 217	77.58 53	27.67 249	0.03 264	90.09 30	77.20 83	0.02 261	66.83 76	0.05 266	59.90 71	73.33 37	0.04 260	78.40 95	79.30 91	88.65 36	95.20 27

MVSTER		76.92 50	79.92 40	73.42 73	74.98 135	82.97 119	78.15 71	63.41 88	78.02 48	64.41 52	67.54 47	72.80 38	71.05 69	83.29 31	83.73 23	88.53 42	91.12 85

DeepC-MVS_fast	75.41 2	81.69 26	82.10 33	81.20 18	91.04 18	87.81 68	83.42 29	74.04 15	83.77 27	71.09 30	66.88 50	72.44 39	79.48 12	85.08 15	84.97 14	88.12 54	93.78 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					82.43 56	86.27 91	75.70 90			61.07 82		72.27 40				85.67 128

X-MVStestdata					82.43 56	86.27 91	75.70 90			61.07 82		72.27 40				85.67 128

X-MVS		78.16 41	80.55 38	75.38 48	87.99 41	86.27 91	81.05 47	68.98 38	78.33 47	61.07 82	75.25 36	72.27 40	67.52 103	80.03 68	80.52 79	85.66 131	91.20 84

CDPH-MVS		79.39 36	82.13 32	76.19 42	89.22 31	88.34 56	84.20 27	71.00 26	79.67 45	56.97 99	77.77 30	72.24 43	68.50 94	81.33 53	82.74 31	87.23 85	92.84 59

PGM-MVS		79.42 35	81.84 34	76.60 40	88.38 37	86.69 81	82.97 33	65.75 60	80.39 40	64.94 49	81.95 24	72.11 44	71.41 65	80.45 62	80.55 78	86.18 110	90.76 93

QAPM		77.50 46	77.43 54	77.59 36	91.52 15	92.00 15	81.41 42	70.63 29	66.22 77	58.05 94	54.70 93	71.79 45	74.49 34	82.46 38	82.04 38	89.46 20	92.79 61

MSLP-MVS++		78.57 38	77.33 55	80.02 24	88.39 36	84.79 104	84.62 25	66.17 58	75.96 54	78.40 12	61.59 64	71.47 46	73.54 39	78.43 94	78.88 94	88.97 29	90.18 102

UA-Net		64.62 149	68.23 134	60.42 176	77.53 113	81.38 134	60.08 211	57.47 159	47.01 177	44.75 151	60.68 68	71.32 47	41.84 221	73.27 154	72.25 178	80.83 215	71.68 224

CPTT-MVS		75.43 59	77.13 58	73.44 71	81.43 66	82.55 125	80.96 48	64.35 68	77.95 50	61.39 78	69.20 42	70.94 48	69.38 88	73.89 145	73.32 162	83.14 191	92.06 75

3Dnovator+	70.16 6	77.87 42	77.29 56	78.55 30	89.25 30	88.32 57	80.09 52	67.95 45	74.89 59	71.83 28	52.05 117	70.68 49	76.27 25	82.27 43	82.04 38	85.92 116	90.77 92

mPP-MVS					86.96 43							70.61 50

EPNet		79.28 37	82.25 31	75.83 44	88.31 38	90.14 28	79.43 56	68.07 44	81.76 35	61.26 79	77.26 32	70.08 51	70.06 79	82.43 40	82.00 40	87.82 62	92.09 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	74.46 3	80.30 31	81.05 36	79.42 25	87.42 42	88.50 51	83.23 30	73.27 20	82.78 30	71.01 31	62.86 61	69.93 52	74.80 30	84.30 21	84.20 21	86.79 97	94.77 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EC-MVSNet		76.05 55	78.87 45	72.77 79	78.87 98	86.63 82	77.50 79	57.04 171	75.34 55	61.68 76	64.20 56	69.56 53	73.96 35	82.12 45	80.65 76	87.57 72	93.57 46

PCF-MVS	70.85 4	75.73 57	76.55 63	74.78 57	83.67 54	88.04 66	81.47 40	70.62 31	69.24 72	57.52 97	60.59 70	69.18 54	70.65 75	77.11 109	77.65 110	84.75 161	94.01 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DI_MVS_pp		73.94 74	74.85 72	72.88 78	76.57 123	86.80 79	80.41 51	61.47 120	62.35 100	59.44 91	47.91 135	68.12 55	72.24 51	82.84 35	81.50 52	87.15 91	94.42 32

MAR-MVS		77.19 49	78.37 51	75.81 45	89.87 23	90.58 23	79.33 57	65.56 62	77.62 51	58.33 93	59.24 74	67.98 56	74.83 29	82.37 41	83.12 30	86.95 92	87.67 133
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
EPP-MVSNet		67.58 129	71.10 107	63.48 153	75.71 130	83.35 117	66.85 171	57.83 154	53.02 158	41.15 172	55.82 85	67.89 57	56.01 170	74.40 138	72.92 170	83.33 186	90.30 100

3Dnovator	70.49 5	78.42 39	76.77 60	80.35 21	91.43 16	90.27 26	81.84 39	70.79 28	72.10 61	71.95 27	50.02 127	67.86 58	77.47 21	82.89 33	84.24 20	88.61 38	89.99 105

OMC-MVS		74.03 73	75.82 67	71.95 87	79.56 79	80.98 139	75.35 98	63.21 89	84.48 25	61.83 73	61.54 65	66.89 59	69.41 87	76.60 115	74.07 152	82.34 201	86.15 144

ETV-MVS		76.25 53	80.22 39	71.63 90	78.23 105	87.95 67	72.75 120	60.27 137	77.50 52	57.73 95	71.53 38	66.60 60	73.16 40	80.99 58	81.23 61	87.63 71	95.73 16

DELS-MVS		79.49 32	79.84 41	79.08 29	88.26 39	92.49 10	84.12 28	70.63 29	65.27 85	69.60 38	61.29 66	66.50 61	72.75 45	88.07 3	88.03 2	89.13 26	97.22 6
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
CostFormer		72.18 91	73.90 80	70.18 98	79.47 80	86.19 94	76.94 87	48.62 219	66.07 81	60.40 87	54.14 100	65.82 62	67.98 95	75.84 123	76.41 121	87.67 69	92.83 60

ACMMP		77.61 45	79.59 42	75.30 49	85.87 50	85.58 97	81.42 41	67.38 50	79.38 46	62.61 65	78.53 28	65.79 63	68.80 93	78.56 91	78.50 99	85.75 121	90.80 89
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
sasdasda		77.65 43	79.59 42	75.39 46	81.52 64	89.83 33	81.32 43	60.74 131	80.05 41	66.72 42	68.43 43	65.09 64	74.72 32	78.87 85	82.73 32	87.32 80	92.16 70

canonicalmvs		77.65 43	79.59 42	75.39 46	81.52 64	89.83 33	81.32 43	60.74 131	80.05 41	66.72 42	68.43 43	65.09 64	74.72 32	78.87 85	82.73 32	87.32 80	92.16 70

SPE-MVS-test		75.09 63	77.84 52	71.87 89	79.27 87	86.92 78	70.53 148	60.36 135	75.13 56	63.13 62	67.92 46	65.08 66	71.43 63	78.15 100	78.51 98	86.53 103	93.16 52

CHOSEN 280x420		62.23 173	66.57 146	57.17 203	59.88 219	68.92 225	61.20 208	42.28 242	54.17 154	39.57 177	47.78 137	64.97 67	62.68 127	73.85 146	69.52 201	77.43 230	86.75 137

HQP-MVS		78.26 40	80.91 37	75.17 50	85.67 51	84.33 111	83.01 32	69.38 35	79.88 43	55.83 100	79.85 26	64.90 68	70.81 72	82.46 38	81.78 44	86.30 108	93.18 51

MGCFI-Net		74.26 68	78.69 46	69.10 106	80.64 73	87.32 71	73.21 119	59.20 140	79.76 44	50.18 131	68.10 45	64.86 69	64.65 117	78.28 98	80.83 70	86.69 98	91.69 79

OpenMVS	67.62 8	74.92 64	73.91 79	76.09 43	90.10 22	90.38 25	78.01 72	66.35 56	66.09 80	62.80 63	46.33 152	64.55 70	71.77 59	79.92 70	80.88 68	87.52 74	89.20 114

CS-MVS		75.84 56	78.61 47	72.61 82	79.03 93	86.74 80	74.43 110	60.27 137	74.15 60	62.78 64	66.26 52	64.25 71	72.81 44	83.36 29	81.69 49	86.32 106	93.85 42

MVS_111021_HR		77.42 47	78.40 50	76.28 41	86.95 44	90.68 22	77.41 80	70.56 32	66.21 79	62.48 67	66.17 53	63.98 72	72.08 54	82.87 34	83.15 29	88.24 50	95.71 17

gg-mvs-nofinetune		62.34 168	66.19 150	57.86 193	76.15 126	88.61 48	71.18 140	41.24 248	25.74 248	13.16 252	22.91 242	63.97 73	54.52 176	85.06 16	85.25 11	90.92 3	91.78 78

TAPA-MVS	67.10 9	71.45 97	73.47 86	69.10 106	77.04 118	80.78 142	73.81 114	62.10 110	80.80 38	51.28 122	60.91 67	63.80 74	67.98 95	74.59 135	72.42 176	82.37 200	80.97 193
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_Blended_VisFu		71.76 94	73.54 85	69.69 101	79.01 94	87.16 75	72.05 127	61.80 115	56.46 136	59.66 90	53.88 104	62.48 75	59.08 153	81.17 55	78.90 93	86.53 103	94.74 29

IS_MVSNet		67.29 133	71.98 99	61.82 168	76.92 119	84.32 112	65.90 179	58.22 145	55.75 142	39.22 181	54.51 96	62.47 76	45.99 211	78.83 89	78.52 97	84.70 162	89.47 111

GBi-Net		69.21 111	70.40 115	67.81 121	69.49 166	78.65 161	74.54 103	60.97 127	65.32 82	51.06 123	47.37 140	62.05 77	63.43 122	77.49 104	78.22 101	87.37 77	83.73 165

test1		69.21 111	70.40 115	67.81 121	69.49 166	78.65 161	74.54 103	60.97 127	65.32 82	51.06 123	47.37 140	62.05 77	63.43 122	77.49 104	78.22 101	87.37 77	83.73 165

FMVSNet3		70.41 103	71.89 101	68.68 112	70.89 161	79.42 155	75.63 92	60.97 127	65.32 82	51.06 123	47.37 140	62.05 77	64.90 114	82.49 37	82.27 37	88.64 37	84.34 162

UGNet		67.57 130	71.69 103	62.76 160	69.88 164	82.58 124	66.43 175	58.64 143	54.71 151	51.87 120	61.74 63	62.01 80	45.46 213	74.78 134	74.99 136	84.24 173	91.02 86
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
test-LLR		68.23 123	71.61 104	64.28 147	71.37 156	81.32 136	63.98 186	61.03 125	58.62 116	42.96 162	52.74 108	61.65 81	57.74 164	75.64 126	78.09 104	88.61 38	93.21 48

TESTMET0.1,1		67.38 132	71.61 104	62.45 163	66.05 193	81.32 136	63.98 186	55.36 189	58.62 116	42.96 162	52.74 108	61.65 81	57.74 164	75.64 126	78.09 104	88.61 38	93.21 48

MVS_Test		75.22 60	76.69 61	73.51 68	79.30 86	88.82 44	80.06 53	58.74 142	69.77 68	57.50 98	59.78 73	61.35 83	75.31 26	82.07 46	83.60 26	90.13 5	91.41 82

Vis-MVSNet (Re-imp)		62.25 171	68.74 126	54.68 213	73.70 141	78.74 160	56.51 220	57.49 158	55.22 145	26.86 228	54.56 95	61.35 83	31.06 230	73.10 156	74.90 137	82.49 198	83.31 171

casdiffmvs_mvg		75.57 58	76.04 65	75.02 52	80.48 75	89.31 36	80.79 50	64.04 75	66.95 75	63.87 55	57.52 78	61.33 85	72.90 43	82.01 48	81.99 41	88.03 56	93.16 52
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		72.89 83	74.46 77	71.07 91	75.99 127	87.50 70	74.57 102	60.49 134	70.72 65	57.60 96	60.63 69	60.97 86	70.79 73	75.27 129	76.33 122	86.94 93	89.79 108

EIA-MVS		73.48 77	76.05 64	70.47 96	78.12 106	87.21 74	71.78 130	60.63 133	69.66 69	55.56 104	64.86 55	60.69 87	69.53 84	77.35 108	78.59 95	87.22 87	94.01 40

ET-MVSNet_ETH3D		71.38 98	74.70 74	67.51 124	51.61 236	88.06 65	77.29 81	60.95 130	63.61 90	48.36 137	66.60 51	60.67 88	79.55 11	73.56 151	80.58 77	87.30 83	89.80 107

0.3-1-1-0.015		70.01 108	70.93 109	68.93 110	67.63 182	84.94 103	74.17 113	62.69 105	62.88 95	53.78 112	51.37 120	60.47 89	67.27 105	73.70 150	74.70 141	88.00 57	88.47 125

usedtu_blend_shiyan5		62.84 166	63.39 165	62.21 166	48.58 241	75.44 192	74.43 110	57.47 159	39.26 214	53.78 112	52.14 114	60.47 89	53.51 179	66.38 206	66.54 213	85.46 135	83.46 169

blend_shiyan4		66.60 137	67.24 141	65.85 133	68.02 175	76.25 183	75.94 89	58.03 148	64.52 88	53.78 112	52.14 114	60.47 89	53.51 179	67.10 204	66.76 211	85.79 120	83.46 169

FE-MVSNET3		61.91 177	63.26 166	60.33 177	48.58 241	75.44 192	63.15 195	57.47 159	39.27 211	53.78 112	52.14 114	60.47 89	53.51 179	66.38 206	66.54 213	85.46 135	82.59 180

baseline1		71.47 96	72.02 98	70.82 93	80.56 74	84.51 107	76.61 88	66.93 52	56.22 138	48.66 135	55.40 91	60.43 93	62.55 129	83.35 30	80.99 64	89.60 12	83.28 173

0.4-1-1-0.2		70.06 107	70.92 111	69.06 109	67.65 180	84.98 102	74.41 112	62.76 100	63.03 94	53.95 110	51.07 121	60.32 94	67.52 103	73.73 149	74.85 139	88.04 55	88.45 126

casdiffmvs		75.20 61	75.69 68	74.63 58	79.26 88	89.07 39	78.47 62	63.59 85	67.05 74	63.79 56	55.72 88	60.32 94	73.58 37	82.16 44	81.78 44	89.08 28	93.72 45
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_LR		74.26 68	75.95 66	72.27 84	79.43 81	85.04 100	72.71 121	65.27 65	70.92 64	63.58 57	69.32 41	60.31 96	69.43 86	77.01 111	77.15 113	83.22 188	91.93 77

0.4-1-1-0.1		69.62 109	70.57 114	68.51 115	67.55 184	84.77 105	73.54 115	62.45 107	62.23 101	53.25 116	50.57 125	60.25 97	66.36 107	73.49 153	74.34 149	87.90 60	88.30 128

OPM-MVS		72.74 86	70.93 109	74.85 56	85.30 52	84.34 110	82.82 35	69.79 33	49.96 166	55.39 106	54.09 101	60.14 98	70.04 80	80.38 64	79.43 89	85.74 123	88.20 129
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		74.32 67	75.42 69	73.04 77	75.60 131	87.27 72	78.20 70	62.96 93	68.66 73	61.89 72	59.79 72	59.84 99	71.80 58	78.30 97	79.87 82	87.80 64	94.23 35
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		73.73 76	74.73 73	72.56 83	75.05 134	87.15 76	77.82 76	62.29 109	66.22 77	61.10 81	57.92 76	59.72 100	71.43 63	78.25 99	79.68 85	87.71 67	94.17 37

SCA		63.90 156	66.67 144	60.66 173	73.75 140	71.78 215	59.87 212	43.66 236	61.13 107	45.03 149	51.64 118	59.45 101	57.92 161	70.96 180	70.80 192	83.71 181	80.92 194

CLD-MVS		77.36 48	77.29 56	77.45 37	82.21 60	88.11 63	81.92 38	68.96 39	77.97 49	69.62 37	62.08 62	59.44 102	73.57 38	81.75 51	81.27 59	88.41 45	90.39 98
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PMMVS		70.37 104	75.06 71	64.90 140	71.46 155	81.88 127	64.10 183	55.64 183	71.31 63	46.69 141	70.69 40	58.56 103	69.53 84	79.03 81	75.63 130	81.96 205	88.32 127

test-mter		64.06 155	69.24 122	58.01 191	59.07 223	77.40 174	59.13 214	48.11 222	55.64 143	39.18 182	51.56 119	58.54 104	55.38 173	73.52 152	76.00 126	87.22 87	92.05 76

thisisatest0530		68.38 122	70.98 108	65.35 136	72.61 149	84.42 108	68.21 161	57.98 149	59.77 112	50.80 126	54.63 94	58.48 105	57.92 161	76.99 112	77.47 111	84.60 166	85.07 155

CANet_DTU		72.84 84	76.63 62	68.43 117	76.81 120	86.62 84	75.54 95	54.71 198	72.06 62	43.54 157	67.11 48	58.46 106	72.40 48	81.13 57	80.82 71	87.57 72	90.21 101

Vis-MVSNet		65.53 144	69.83 120	60.52 174	70.80 162	84.59 106	66.37 177	55.47 188	48.40 173	40.62 176	57.67 77	58.43 107	45.37 214	77.49 104	76.24 124	84.47 169	85.99 147
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
viewmanbaseed2359cas		74.53 66	74.69 75	74.35 61	79.37 84	88.90 43	78.96 58	64.07 74	63.67 89	62.19 68	56.95 82	58.42 108	72.04 55	80.08 67	81.92 42	89.47 19	92.91 56

E2		75.18 62	75.21 70	75.15 51	79.77 77	89.10 38	78.62 59	64.19 71	65.19 86	65.90 45	58.15 75	58.36 109	72.56 47	80.74 61	81.78 44	89.84 9	93.19 50

MS-PatchMatch		70.34 105	69.00 124	71.91 88	85.20 53	85.35 98	77.84 75	61.77 116	58.01 125	55.40 105	41.26 172	58.34 110	61.69 133	81.70 52	78.29 100	89.56 13	80.02 196

PVSNet_BlendedMVS		76.84 51	78.47 48	74.95 53	82.37 58	89.90 31	75.45 96	65.45 63	74.99 57	70.66 33	63.07 59	58.27 111	67.60 98	84.24 22	81.70 47	88.18 51	97.10 8

PVSNet_Blended		76.84 51	78.47 48	74.95 53	82.37 58	89.90 31	75.45 96	65.45 63	74.99 57	70.66 33	63.07 59	58.27 111	67.60 98	84.24 22	81.70 47	88.18 51	97.10 8

AdaColmap		76.23 54	73.55 84	79.35 26	89.38 28	85.00 101	79.99 54	73.04 22	76.60 53	71.17 29	55.18 92	57.99 113	77.87 19	76.82 113	76.82 116	84.67 163	86.45 140

tttt0517		67.99 125	70.61 113	64.94 139	71.94 154	83.96 114	67.62 165	57.98 149	59.30 114	49.90 132	54.50 97	57.98 114	57.92 161	76.48 116	77.47 111	84.24 173	84.58 159

viewcassd2359sk11		74.75 65	74.61 76	74.90 55	79.62 78	88.96 42	78.47 62	64.08 73	63.51 92	65.27 48	57.02 81	57.89 115	72.25 50	80.30 66	81.57 51	89.72 10	93.04 54

PatchmatchNet		65.43 145	67.71 137	62.78 159	73.49 144	82.83 120	66.42 176	45.40 229	60.40 110	45.27 146	49.22 130	57.60 116	60.01 145	70.61 183	71.38 188	86.08 114	81.91 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmambaseed2359dif		72.54 90	72.88 89	72.13 85	74.78 137	86.45 87	77.24 82	61.65 119	62.61 97	61.83 73	55.85 84	57.51 117	70.64 76	75.71 124	77.90 109	86.65 100	94.16 38

E3		74.17 70	73.83 81	74.57 59	79.40 82	88.76 45	78.30 68	63.89 79	61.22 104	64.40 53	55.64 90	57.35 118	71.86 57	79.73 74	81.27 59	89.55 14	92.86 57

E3new		74.17 70	73.83 81	74.57 59	79.40 82	88.76 45	78.30 68	63.89 79	61.21 105	64.38 54	55.65 89	57.34 119	71.87 56	79.73 74	81.28 58	89.55 14	92.86 57

FMVSNet2		68.06 124	68.57 127	67.45 126	69.49 166	78.65 161	74.54 103	60.23 139	56.29 137	49.64 133	42.13 168	57.08 120	63.43 122	81.15 56	80.99 64	87.37 77	83.73 165

viewmacassd2359aftdt		73.00 82	72.63 93	73.44 71	78.70 99	88.45 53	78.52 60	63.49 87	57.74 127	60.15 89	52.57 111	57.01 121	70.69 74	78.85 88	81.29 57	89.10 27	92.48 64

E5new		73.48 77	72.84 90	74.23 63	79.06 90	88.52 49	78.32 65	63.99 76	58.33 119	63.34 59	54.07 102	56.89 122	71.29 66	78.99 82	80.82 71	89.35 21	92.26 68

E5		73.48 77	72.84 90	74.23 63	79.06 90	88.52 49	78.32 65	63.99 76	58.33 119	63.34 59	54.07 102	56.89 122	71.29 66	78.99 82	80.82 71	89.35 21	92.26 68

Anonymous20231211		68.44 120	66.37 148	70.86 92	77.58 112	83.49 116	75.15 99	61.89 113	52.54 159	58.50 92	28.89 230	56.78 124	69.29 89	74.96 133	76.61 117	82.73 194	91.36 83

E4		73.32 80	72.68 92	74.06 66	79.06 90	88.47 52	77.98 73	63.57 86	57.73 128	63.18 61	53.48 105	56.74 125	71.26 68	78.95 84	80.84 69	89.30 23	92.55 62

viewdifsd2359ckpt13		74.11 72	74.06 78	74.18 65	79.34 85	89.07 39	78.31 67	64.25 70	62.52 98	62.06 69	55.80 86	56.70 126	72.29 49	80.35 65	81.47 53	88.80 31	92.47 66

viewdifsd2359ckpt07		72.78 85	72.24 95	73.41 74	78.58 102	88.14 62	76.95 86	63.73 83	57.28 129	63.47 58	54.45 98	56.62 127	69.16 90	78.86 87	79.98 81	88.58 41	90.33 99

viewdifsd2359ckpt09		73.89 75	73.57 83	74.26 62	78.54 103	88.37 55	78.34 64	63.79 81	63.31 93	64.90 50	57.29 80	56.53 128	72.15 53	79.12 79	77.91 108	87.83 61	92.48 64

CNLPA		71.37 99	70.27 117	72.66 81	80.79 71	81.33 135	71.07 143	65.75 60	82.36 31	64.80 51	42.46 165	56.49 129	72.70 46	73.00 159	70.52 196	80.84 214	85.76 150

FA-MVS(training)		70.24 106	71.77 102	68.45 116	77.52 114	86.03 95	73.33 117	49.12 218	63.55 91	55.77 101	48.91 132	56.26 130	67.78 97	77.60 103	79.62 86	87.19 90	90.40 97

EPNet_dtu		66.17 139	70.13 118	61.54 170	81.04 67	77.39 175	68.87 158	62.50 106	69.78 67	33.51 215	63.77 58	56.22 131	37.65 227	72.20 167	72.18 179	85.69 127	79.38 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13		65.21 146	67.28 140	62.79 158	70.91 160	81.72 128	69.28 156	49.50 217	58.08 122	43.94 156	50.50 126	56.02 132	58.86 154	70.72 182	73.37 160	84.24 173	80.52 195

CR-MVSNet		62.31 169	64.75 156	59.47 183	68.63 172	71.29 218	67.53 166	43.18 238	55.83 140	41.40 169	41.04 174	55.85 133	57.29 167	72.76 162	73.27 164	78.77 226	83.23 174

HyFIR lowres test		68.39 121	68.28 133	68.52 114	80.85 69	88.11 63	71.08 142	58.09 147	54.87 150	47.80 140	27.55 234	55.80 134	64.97 113	79.11 80	79.14 92	88.31 48	93.35 47

E6new		72.71 87	72.05 96	73.49 69	79.01 94	88.31 58	77.06 84	62.71 103	56.63 133	62.00 70	52.31 112	55.75 135	70.93 70	78.51 92	80.72 74	89.20 24	92.14 72

E6		72.71 87	72.05 96	73.49 69	79.01 94	88.31 58	77.06 84	62.71 103	56.63 133	62.00 70	52.31 112	55.75 135	70.93 70	78.51 92	80.72 74	89.20 24	92.14 72

IterMVS-LS		66.08 140	66.56 147	65.51 134	73.67 142	74.88 199	70.89 145	53.55 205	50.42 164	48.32 138	50.59 124	55.66 137	61.83 132	73.93 144	74.42 147	84.82 159	86.01 146
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LGP-MVS_train		72.02 93	73.18 87	70.67 95	82.13 61	80.26 148	79.58 55	63.04 91	70.09 66	51.98 119	65.06 54	55.62 138	62.49 130	75.97 122	76.32 123	84.80 160	88.93 117

DCV-MVSNet		69.13 115	69.07 123	69.21 104	77.65 111	77.52 173	74.68 101	57.85 153	54.92 148	55.34 107	55.74 87	55.56 139	66.35 108	75.05 130	76.56 119	83.35 185	88.13 130

PLC	64.00 12	68.54 119	66.66 145	70.74 94	80.28 76	74.88 199	72.64 122	63.70 84	69.26 71	55.71 102	47.24 143	55.31 140	70.42 77	72.05 170	70.67 194	81.66 208	77.19 204
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Effi-MVS+		70.42 101	71.23 106	69.47 102	78.04 107	85.24 99	75.57 94	58.88 141	59.56 113	48.47 136	52.73 110	54.94 141	69.69 82	78.34 96	77.06 114	86.18 110	90.73 94

test2506		69.26 110	70.79 112	67.48 125	78.64 100	86.40 88	72.22 125	62.75 101	58.05 123	45.24 147	50.76 122	54.93 142	58.05 159	79.82 71	79.70 83	87.96 58	85.90 148

EPMVS		66.21 138	67.49 139	64.73 141	75.81 128	84.20 113	68.94 157	44.37 234	61.55 103	48.07 139	49.21 131	54.87 143	62.88 126	71.82 171	71.40 187	88.28 49	79.37 199

GeoE		68.96 117	69.32 121	68.54 113	76.61 122	83.12 118	71.78 130	56.87 173	60.21 111	54.86 108	45.95 154	54.79 144	64.27 118	74.59 135	75.54 133	86.84 96	91.01 87

baseline2		71.22 100	73.01 88	69.13 105	75.76 129	86.34 90	71.23 138	62.78 99	62.62 96	52.85 117	57.32 79	54.31 145	63.27 125	79.74 73	79.31 90	88.89 30	91.43 80

RPSCF		55.07 213	58.06 203	51.57 220	48.87 240	58.95 246	53.68 225	41.26 247	62.42 99	45.88 143	54.38 99	54.26 146	53.75 178	57.15 236	53.53 247	66.01 248	65.75 238

tpmrst		67.15 134	68.12 135	66.03 132	76.21 125	80.98 139	71.27 137	45.05 230	60.69 109	50.63 127	46.95 148	54.15 147	65.30 111	71.80 174	71.77 180	87.72 66	90.48 96

ACMM	66.70 10	70.42 101	68.49 128	72.67 80	82.85 55	77.76 171	77.70 78	64.76 67	64.61 87	60.74 86	49.29 129	53.97 148	65.86 110	74.97 131	75.57 132	84.13 177	83.29 172
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous202405211			66.35 149		78.00 108	84.41 109	74.85 100	63.18 90	51.00 162		31.37 225	53.73 149	69.67 83	76.28 117	76.84 115	83.21 190	90.85 88

ACMP	68.86 7	72.15 92	72.25 94	72.03 86	80.96 68	80.87 141	77.93 74	64.13 72	69.29 70	60.79 85	64.04 57	53.54 150	63.91 120	73.74 148	75.27 135	84.45 170	88.98 116
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tpm		64.85 148	66.02 152	63.48 153	74.52 138	78.38 164	70.98 144	44.99 232	51.61 161	43.28 161	47.66 138	53.18 151	60.57 140	70.58 185	71.30 190	86.54 102	89.45 112

RPMNet		58.63 198	62.80 174	53.76 218	67.59 183	71.29 218	54.60 223	38.13 250	55.83 140	35.70 206	41.58 171	53.04 152	47.89 202	66.10 212	67.38 205	78.65 228	84.40 161

tpm cat1		67.47 131	67.05 143	67.98 120	76.63 121	81.51 133	74.49 108	47.65 224	61.18 106	61.12 80	42.51 164	53.02 153	64.74 116	70.11 191	71.50 183	83.22 188	89.49 110

viewdifsd2359ckpt11		69.15 113	68.30 130	70.14 99	73.44 146	82.79 121	72.24 123	61.20 123	54.59 153	61.70 75	53.16 106	52.89 154	67.57 101	71.81 173	72.73 173	84.66 164	90.10 103

viewmsd2359difaftdt		69.14 114	68.29 131	70.13 100	73.44 146	82.79 121	72.24 123	61.20 123	54.60 152	61.68 76	53.16 106	52.87 155	67.58 100	71.82 171	72.73 173	84.66 164	90.10 103

FMVSNet5		58.86 195	60.24 193	57.25 200	52.66 235	66.25 231	63.77 189	52.86 210	57.85 126	37.92 193	36.12 204	52.22 156	51.37 190	70.88 181	71.43 186	84.92 150	66.91 236

TSAR-MVS + COLMAP		73.09 81	76.86 59	68.71 111	74.97 136	82.49 126	74.51 107	61.83 114	83.16 28	49.31 134	82.22 23	51.62 157	68.94 92	78.76 90	75.52 134	82.67 196	84.23 163

casdiffseed414692147		71.49 95	70.06 119	73.15 76	79.11 89	87.26 73	77.82 76	62.34 108	58.44 118	60.33 88	46.19 153	51.26 158	71.53 62	77.07 110	79.56 88	87.80 64	90.61 95

Effi-MVS+-dtu		64.58 150	64.08 160	65.16 137	73.04 148	75.17 198	70.68 147	56.23 177	54.12 155	44.71 152	47.42 139	51.10 159	63.82 121	68.08 201	66.32 221	82.47 199	86.38 141

CDS-MVSNet		64.22 153	65.89 153	62.28 165	70.05 163	80.59 143	69.91 151	57.98 149	43.53 192	46.58 142	48.22 134	50.76 160	46.45 208	75.68 125	76.08 125	82.70 195	86.34 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 1792x2688		72.55 89	71.98 99	73.22 75	86.57 47	92.41 11	75.63 92	66.77 53	62.08 102	52.32 118	30.27 228	50.74 161	66.14 109	86.22 12	85.41 8	91.90 1	96.75 13

PatchT		60.46 186	63.85 162	56.51 206	65.95 195	75.68 189	47.34 235	41.39 245	53.89 156	41.40 169	37.84 192	50.30 162	57.29 167	72.76 162	73.27 164	85.67 128	83.23 174

FMVSNet1		63.48 159	63.07 169	63.97 149	65.31 198	76.37 182	71.77 132	57.90 152	43.32 193	45.66 144	35.06 211	49.43 163	58.57 155	77.49 104	78.22 101	84.59 167	81.60 191

IterMVS		61.87 178	63.55 163	59.90 179	67.29 186	72.20 212	67.34 169	48.56 220	47.48 176	37.86 194	47.07 145	48.27 164	54.08 177	72.12 168	73.71 155	84.30 172	83.99 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		60.21 188	62.97 170	57.00 204	66.64 190	71.84 213	67.53 166	46.93 227	47.56 175	36.77 199	46.85 149	48.21 165	52.51 183	70.36 188	72.40 177	71.63 246	83.53 168

ECVR-MVS		67.93 126	68.49 128	67.28 128	78.64 100	86.40 88	72.22 125	62.75 101	58.05 123	44.06 155	40.92 176	48.20 166	58.05 159	79.82 71	79.70 83	87.96 58	86.32 143

TAMVS		58.86 195	60.91 188	56.47 207	62.38 212	77.57 172	58.97 215	52.98 208	38.76 217	36.17 201	42.26 167	47.94 167	46.45 208	70.23 190	70.79 193	81.86 206	78.82 201

FC-MVSNet-train		68.83 118	68.29 131	69.47 102	78.35 104	79.94 149	64.72 180	66.38 55	54.96 147	54.51 109	56.75 83	47.91 168	66.91 106	75.57 128	75.75 128	85.92 116	87.12 135

test1111		66.72 136	67.80 136	65.45 135	77.42 116	86.63 82	69.69 152	62.98 92	55.29 144	39.47 178	40.12 181	47.11 169	55.70 171	79.96 69	80.00 80	87.47 75	85.49 153

Fast-Effi-MVS+		67.59 128	67.56 138	67.62 123	73.67 142	81.14 138	71.12 141	54.79 197	58.88 115	50.61 128	46.70 150	47.05 170	69.12 91	76.06 121	76.44 120	86.43 105	86.65 138

Fast-Effi-MVS+-dtu		63.05 162	64.72 158	61.11 171	71.21 159	76.81 179	70.72 146	43.13 240	52.51 160	35.34 208	46.55 151	46.36 171	61.40 136	71.57 177	71.44 185	84.84 155	87.79 132

CVMVSNet		54.92 216	58.16 202	51.13 223	62.61 211	68.44 226	55.45 222	52.38 211	42.28 196	21.45 236	47.10 144	46.10 172	37.96 226	64.42 223	63.81 228	76.92 233	75.01 210

LS3D		64.54 152	62.14 179	67.34 127	80.85 69	75.79 187	69.99 149	65.87 59	60.77 108	44.35 153	42.43 166	45.95 173	65.01 112	69.88 192	68.69 203	77.97 229	71.43 226

IB-MVS	64.48 11	69.02 116	68.97 125	69.09 108	81.75 63	89.01 41	64.50 181	64.91 66	56.65 132	62.59 66	47.89 136	45.23 174	51.99 184	69.18 197	81.88 43	88.77 33	92.93 55
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
ADS-MVSNet		58.40 199	59.16 200	57.52 196	65.80 197	74.57 204	60.26 209	40.17 249	50.51 163	38.01 192	40.11 182	44.72 175	59.36 150	64.91 218	66.55 212	81.53 209	72.72 221

test0.0.03 1		57.35 208	59.89 196	54.38 216	71.37 156	73.45 208	52.71 226	61.03 125	46.11 183	26.33 229	41.73 170	44.08 176	29.72 232	71.43 178	70.90 191	85.10 146	71.56 225

dmvs_re		67.60 127	67.21 142	68.06 119	74.07 139	79.01 157	73.31 118	68.74 41	58.27 121	42.07 168	49.72 128	43.96 177	60.66 139	76.79 114	78.04 106	89.51 17	84.69 158

gm-plane-assit		54.99 214	57.99 205	51.49 222	69.27 170	54.42 250	32.32 254	42.59 241	21.18 252	13.71 250	23.61 239	43.84 178	60.21 144	87.09 5	86.55 5	90.81 4	89.28 113

dps		64.08 154	63.22 167	65.08 138	75.27 133	79.65 152	66.68 173	46.63 228	56.94 130	55.67 103	43.96 156	43.63 179	64.00 119	69.50 196	69.82 198	82.25 202	79.02 200

FC-MVSNet-test		47.24 237	54.37 219	38.93 244	59.49 222	58.25 248	34.48 253	53.36 206	45.66 185	6.66 259	50.62 123	42.02 180	16.62 252	58.39 232	61.21 236	62.99 250	64.40 241

GA-MVS		64.55 151	65.76 154	63.12 155	69.68 165	81.56 132	69.59 153	58.16 146	45.23 187	35.58 207	47.01 147	41.82 181	59.41 149	79.62 76	78.54 96	86.32 106	86.56 139

usedtu_dtu_shiyan1		62.43 167	64.08 160	60.50 175	59.68 221	80.58 144	66.18 178	61.75 118	53.08 157	36.05 203	36.33 203	41.74 182	51.86 185	77.70 101	77.95 107	87.47 75	81.17 192

gbinet_0.2-2-1-0.02		56.72 210	57.64 210	55.64 209	45.57 249	74.69 202	62.04 203	57.17 169	35.71 229	35.71 205	33.73 218	41.66 183	48.54 200	66.06 213	66.43 217	84.83 158	85.22 154

thres100view900		67.14 135	66.09 151	68.38 118	77.70 109	83.84 115	74.52 106	66.33 57	49.16 170	43.40 159	43.24 157	41.34 184	62.59 128	79.31 78	75.92 127	85.73 124	89.81 106

tfpn200view9		65.90 141	64.96 155	67.00 129	77.70 109	81.58 131	71.71 133	62.94 96	49.16 170	43.40 159	43.24 157	41.34 184	61.42 135	76.24 118	74.63 143	84.84 155	88.52 123

thres200		65.58 142	64.74 157	66.56 130	77.52 114	81.61 129	73.44 116	62.95 94	46.23 182	42.45 166	42.76 159	41.18 186	58.12 157	76.24 118	75.59 131	84.89 153	89.58 109

UniMVSNet_NR-MVSNet		62.30 170	63.51 164	60.89 172	69.48 169	77.83 169	64.07 184	63.94 78	50.03 165	31.17 220	44.82 155	41.12 187	51.37 190	71.02 179	74.81 140	85.30 142	84.95 156

MSDG		65.57 143	61.57 183	70.24 97	82.02 62	76.47 180	74.46 109	68.73 42	56.52 135	50.33 129	38.47 187	41.10 188	62.42 131	72.12 168	72.94 169	83.47 184	73.37 218

v8		63.44 160	62.58 175	64.43 144	68.28 174	78.07 166	71.82 129	54.85 195	46.70 180	45.20 148	39.40 184	40.91 189	60.54 141	72.85 161	74.39 148	85.92 116	85.76 150

thres400		65.18 147	64.44 159	66.04 131	76.40 124	82.63 123	71.52 135	64.27 69	44.93 188	40.69 175	41.86 169	40.79 190	58.12 157	77.67 102	74.64 142	85.26 143	88.56 122

MIMVSNet		57.78 202	59.71 197	55.53 210	54.79 231	77.10 177	63.89 188	45.02 231	46.59 181	36.79 198	28.36 232	40.77 191	45.84 212	74.97 131	76.58 118	86.87 95	73.60 216

V42		62.86 165	62.97 170	62.74 161	60.84 216	78.99 159	71.46 136	57.13 170	46.85 178	44.28 154	38.87 185	40.73 192	57.63 166	72.60 165	74.14 150	85.09 148	88.63 121

UniMVSNet (Re)		60.62 185	62.93 172	57.92 192	67.64 181	77.90 168	61.75 205	61.24 122	49.83 167	29.80 224	42.57 162	40.62 193	43.36 217	70.49 187	73.27 164	83.76 179	85.81 149

pm-mvs1		59.21 193	59.58 198	58.77 189	67.97 177	77.07 178	64.12 182	57.20 167	34.73 231	36.86 196	35.34 208	40.54 194	43.34 218	74.32 141	73.30 163	83.13 192	81.77 190

wanda-best-256-512		57.69 203	57.90 206	57.46 198	48.58 241	75.44 192	63.15 195	57.47 159	39.27 211	38.64 185	34.66 213	40.34 195	51.44 188	66.38 206	66.54 213	85.46 135	82.64 178

FE-blended-shiyan7		57.69 203	57.90 206	57.46 198	48.58 241	75.44 192	63.15 195	57.47 159	39.27 211	38.64 185	34.66 213	40.34 195	51.44 188	66.38 206	66.54 213	85.46 135	82.64 178

blended_shiyan8		57.49 207	57.71 209	57.24 201	48.52 245	75.34 196	62.85 199	57.32 166	38.77 216	38.43 188	34.41 216	40.31 197	50.92 193	66.25 211	66.37 218	85.37 139	82.55 182

blended_shiyan6		57.50 206	57.73 208	57.23 202	48.51 246	75.34 196	62.85 199	57.33 164	38.78 215	38.38 189	34.46 215	40.29 198	50.91 194	66.27 210	66.37 218	85.37 139	82.59 180

thres600view7		63.77 157	63.14 168	64.51 143	75.49 132	81.61 129	69.59 153	62.95 94	43.96 191	38.90 183	41.09 173	40.24 199	55.25 174	76.24 118	71.54 182	84.89 153	87.30 134

thisisatest0515		59.37 192	60.68 190	57.84 194	64.39 202	75.65 190	58.56 216	53.86 203	41.55 200	42.12 167	40.40 179	39.59 200	47.09 206	71.69 176	73.79 154	81.02 213	82.08 188

CMPMVS	43.63 17	57.67 205	55.43 216	60.28 178	72.01 152	79.00 158	62.77 201	53.23 207	41.77 198	45.42 145	30.74 227	39.03 201	53.01 182	64.81 220	64.65 227	75.26 238	68.03 234
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v10		63.00 163	62.22 178	63.90 151	67.88 178	77.78 170	71.59 134	54.34 199	45.37 186	42.76 165	38.53 186	38.93 202	61.05 138	74.39 139	74.52 146	85.75 121	86.04 145

v148		62.00 176	61.19 186	62.96 156	67.46 185	79.49 154	67.87 162	57.66 155	42.30 195	45.02 150	38.20 190	38.89 203	54.77 175	69.83 193	72.60 175	84.96 149	87.01 136

v2v482		63.68 158	62.85 173	64.65 142	68.01 176	80.46 146	71.90 128	57.60 156	44.26 189	42.82 164	39.80 183	38.62 204	61.56 134	73.06 157	74.86 138	86.03 115	88.90 119

v1144		63.00 163	62.39 177	63.70 152	67.72 179	80.27 147	71.23 138	56.40 174	42.51 194	40.81 174	38.12 191	37.73 205	60.42 143	74.46 137	74.55 145	85.64 132	89.12 115

Baseline_NR-MVSNet		59.47 191	60.28 192	58.54 190	66.69 188	73.90 206	61.63 206	62.90 97	49.15 172	26.87 227	35.18 210	37.62 206	48.20 201	69.67 194	73.61 156	84.92 150	82.82 177

pmmvs4		63.14 161	62.46 176	63.94 150	66.03 194	76.40 181	66.82 172	57.60 156	56.74 131	50.26 130	40.81 177	37.51 207	59.26 151	71.75 175	71.48 184	83.68 183	82.53 183

ACMH+	60.36 13	61.16 181	58.38 201	64.42 145	77.37 117	74.35 205	68.45 159	62.81 98	45.86 184	38.48 187	35.71 206	37.35 208	59.81 146	67.24 203	69.80 200	79.58 222	78.32 202

EG-PatchMatch MVS		58.73 197	58.03 204	59.55 182	72.32 150	80.49 145	63.44 192	55.55 185	32.49 236	38.31 190	28.87 231	37.22 209	42.84 219	74.30 142	75.70 129	84.84 155	77.14 205

DU-MVS		60.87 184	61.82 181	59.76 181	66.69 188	75.87 185	64.07 184	61.96 111	49.31 168	31.17 220	42.76 159	36.95 210	51.37 190	69.67 194	73.20 167	83.30 187	84.95 156

TranMVSNet+NR-MVSNet		60.38 187	61.30 185	59.30 185	68.34 173	75.57 191	63.38 193	63.78 82	46.74 179	27.73 226	42.56 163	36.84 211	47.66 203	70.36 188	74.59 144	84.91 152	82.46 184

WR-MVS		51.02 226	54.56 218	46.90 233	63.84 204	69.23 223	44.78 243	56.38 175	38.19 218	14.19 248	37.38 193	36.82 212	22.39 244	60.14 230	66.20 223	79.81 220	73.95 215

v144192		62.05 175	61.46 184	62.73 162	66.59 191	79.87 150	69.30 155	55.88 179	41.50 201	39.41 180	37.23 194	36.45 213	59.62 147	72.69 164	73.51 157	85.61 133	88.93 117

PatchMatch-RL		62.22 174	60.69 189	64.01 148	68.74 171	75.75 188	59.27 213	60.35 136	56.09 139	53.80 111	47.06 146	36.45 213	64.80 115	68.22 200	67.22 207	77.10 232	74.02 213

pmmvs6		54.20 219	53.54 221	54.97 211	63.22 208	72.98 210	60.17 210	52.32 212	26.77 247	34.30 212	23.29 241	36.23 215	40.33 224	68.77 198	68.76 202	79.47 224	78.00 203

anonymousdsp		54.99 214	57.24 211	52.36 219	53.82 233	71.75 216	51.49 228	48.14 221	33.74 232	33.66 214	38.34 188	36.13 216	47.54 204	64.53 222	70.60 195	79.53 223	85.59 152

pmmvs5		59.72 189	60.24 193	59.11 187	62.77 210	77.33 176	63.17 194	54.00 202	40.21 206	37.23 195	40.41 178	35.99 217	51.75 186	72.55 166	72.74 172	85.72 126	82.45 185

v1192		62.25 171	61.64 182	62.96 156	66.88 187	79.72 151	69.96 150	55.77 181	41.58 199	39.42 179	37.05 196	35.96 218	60.50 142	74.30 142	74.09 151	85.24 144	88.76 120

TransMVSNet (Re)		57.83 200	56.90 212	58.91 188	72.26 151	74.69 202	63.57 191	61.42 121	32.30 237	32.65 216	33.97 217	35.96 218	39.17 225	73.84 147	72.84 171	84.37 171	74.69 211

WR-MVS_H		49.62 232	52.63 227	46.11 236	58.80 224	67.58 228	46.14 241	54.94 192	36.51 223	13.63 251	36.75 200	35.67 220	22.10 245	56.43 239	62.76 233	81.06 212	72.73 220

v1921920		61.66 179	61.10 187	62.31 164	66.32 192	79.57 153	68.41 160	55.49 187	41.03 202	38.69 184	36.64 202	35.27 221	59.60 148	73.23 155	73.41 159	85.37 139	88.51 124

UniMVSNet_ETH3D		57.83 200	56.46 215	59.43 184	63.24 207	73.22 209	67.70 163	55.58 184	36.17 225	36.84 197	32.64 220	35.14 222	51.50 187	65.81 214	69.81 199	81.73 207	82.44 186

v1240		61.09 182	60.55 191	61.72 169	65.92 196	79.28 156	67.16 170	54.91 194	39.79 208	38.10 191	36.08 205	34.64 223	59.15 152	72.86 160	73.36 161	85.10 146	87.84 131

ACMH	59.42 14	61.59 180	59.22 199	64.36 146	78.92 97	78.26 165	67.65 164	67.48 49	39.81 207	30.98 222	38.25 189	34.59 224	61.37 137	70.55 186	73.47 158	79.74 221	79.59 197
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	51.17 15	55.13 212	52.90 225	57.73 195	73.47 145	67.21 229	62.13 202	55.82 180	47.83 174	34.39 211	31.60 224	34.24 225	44.90 215	63.88 225	62.52 234	75.67 236	63.02 244
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MDTV_nov1_ep13_2view		54.47 218	54.61 217	54.30 217	60.50 217	73.82 207	57.92 217	43.38 237	39.43 210	32.51 217	33.23 219	34.05 226	47.26 205	62.36 226	66.21 222	84.24 173	73.19 219

MVS-HIRNet		53.86 221	53.02 223	54.85 212	60.30 218	72.36 211	44.63 244	42.20 243	39.45 209	43.47 158	21.66 245	34.00 227	55.47 172	65.42 216	67.16 208	83.02 193	71.08 228

NR-MVSNet		61.08 183	62.09 180	59.90 179	71.96 153	75.87 185	63.60 190	61.96 111	49.31 168	27.95 225	42.76 159	33.85 228	48.82 199	74.35 140	74.05 153	85.13 145	84.45 160

v7n		57.04 209	56.64 213	57.52 196	62.85 209	74.75 201	61.76 204	51.80 213	35.58 230	36.02 204	32.33 222	33.61 229	50.16 197	67.73 202	70.34 197	82.51 197	82.12 187

PEN-MVS		51.04 225	52.94 224	48.82 226	61.45 215	66.00 232	48.68 232	57.20 167	36.87 220	15.36 246	36.98 197	32.72 230	28.77 236	57.63 235	66.37 218	81.44 210	74.00 214

testgi		48.51 235	50.53 233	46.16 235	64.78 199	67.15 230	41.54 247	54.81 196	29.12 242	17.03 242	32.07 223	31.98 231	20.15 248	65.26 217	67.00 209	78.67 227	61.10 248

CP-MVSNet		50.57 227	52.60 228	48.21 230	58.77 225	65.82 233	48.17 233	56.29 176	37.41 219	16.59 243	37.14 195	31.95 232	29.21 233	56.60 238	63.71 229	80.22 217	75.56 208

DTE-MVSNet		49.82 231	51.92 231	47.37 232	61.75 214	64.38 237	45.89 242	57.33 164	36.11 226	12.79 253	36.87 198	31.93 233	25.73 241	58.01 233	65.22 225	80.75 216	70.93 229

test_method		28.15 250	34.48 250	20.76 251	6.76 263	21.18 259	21.03 257	18.41 258	36.77 221	17.52 241	15.67 255	31.63 234	24.05 243	41.03 253	26.69 255	36.82 257	68.38 231

Anonymous20231206		52.23 224	52.80 226	51.56 221	64.70 201	69.41 222	51.01 229	58.60 144	36.63 222	22.44 235	21.80 244	31.42 235	30.52 231	66.79 205	67.83 204	82.10 204	75.73 207

PS-CasMVS		50.17 229	52.02 229	48.02 231	58.60 226	65.54 234	48.04 234	56.19 178	36.42 224	16.42 245	35.68 207	31.33 236	28.85 235	56.42 240	63.54 231	80.01 218	75.18 209

EU-MVSNet		44.84 239	47.85 239	41.32 242	49.26 239	56.59 249	43.07 245	47.64 225	33.03 233	13.82 249	36.78 199	30.99 237	24.37 242	53.80 244	55.57 244	69.78 247	68.21 232

test20.03		47.23 238	48.69 238	45.53 237	63.28 206	64.39 236	41.01 248	56.93 172	29.16 241	15.21 247	23.90 238	30.76 238	17.51 251	64.63 221	65.26 224	79.21 225	62.71 245

pmnet_mix02		53.92 220	53.30 222	54.65 215	61.89 213	71.33 217	54.54 224	54.17 201	40.38 204	34.65 210	34.76 212	30.68 239	40.44 223	60.97 228	63.71 229	82.19 203	71.24 227

USDC		59.69 190	60.03 195	59.28 186	64.04 203	71.84 213	63.15 195	55.36 189	54.90 149	35.02 209	48.34 133	29.79 240	58.16 156	70.60 184	71.33 189	79.99 219	73.42 217

tfpnnormal		58.97 194	56.48 214	61.89 167	71.27 158	76.21 184	66.65 174	61.76 117	32.90 234	36.41 200	27.83 233	29.14 241	50.64 196	73.06 157	73.05 168	84.58 168	83.15 176

pmmvs-eth3d		55.20 211	53.95 220	56.65 205	57.34 229	67.77 227	57.54 218	53.74 204	40.93 203	41.09 173	31.19 226	29.10 242	49.07 198	65.54 215	67.28 206	81.14 211	75.81 206

FE-MVSNET2		50.42 228	51.98 230	48.61 228	44.79 250	68.96 224	52.01 227	55.50 186	32.55 235	19.88 240	21.60 246	28.20 243	35.80 228	68.31 199	71.76 181	83.69 182	72.45 222

TDRefinement		52.70 222	51.02 232	54.66 214	57.41 228	65.06 235	61.47 207	54.94 192	44.03 190	33.93 213	30.13 229	27.57 244	46.17 210	61.86 227	62.48 235	74.01 242	66.06 237

LTVRE_ROB	47.26 16	49.41 233	49.91 236	48.82 226	64.76 200	69.79 221	49.05 231	47.12 226	20.36 254	16.52 244	36.65 201	26.96 245	50.76 195	60.47 229	63.16 232	64.73 249	72.00 223
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
SixPastTwentyTwo		49.11 234	49.22 237	48.99 225	58.54 227	64.14 238	47.18 236	47.75 223	31.15 239	24.42 231	41.01 175	26.55 246	44.04 216	54.76 243	58.70 240	71.99 245	68.21 232

MIMVSNet1		40.84 245	43.46 242	37.79 245	32.14 254	58.92 247	39.24 250	50.83 215	27.00 246	11.29 255	16.76 253	26.53 247	17.75 250	57.14 237	61.12 237	75.46 237	56.78 249

PM-MVS		50.11 230	50.38 234	49.80 224	47.23 248	62.08 242	50.91 230	44.84 233	41.90 197	36.10 202	35.22 209	26.05 248	46.83 207	57.64 234	55.42 245	72.90 243	74.32 212

N_pmnet		47.67 236	47.00 240	48.45 229	54.72 232	62.78 240	46.95 237	51.25 214	36.01 227	26.09 230	26.59 236	25.93 249	35.50 229	55.67 242	59.01 238	76.22 234	63.04 243

FE-MVSNET		44.36 240	46.68 241	41.65 239	37.55 253	61.05 243	42.06 246	54.34 199	27.09 245	9.86 258	20.55 247	25.56 250	28.72 237	60.12 231	66.83 210	77.36 231	65.56 239

usedtu_dtu_shiyan2		40.99 244	42.22 247	39.56 243	22.63 259	59.44 245	46.80 238	43.69 235	19.05 256	21.04 237	16.27 254	23.77 251	27.46 239	53.16 245	55.09 246	75.73 235	68.78 230

tmp_tt				16.09 255	13.07 261	8.12 264	13.61 262	2.08 260	55.09 146	30.10 223	40.26 180	22.83 252	5.35 257	29.91 254	25.25 256	32.33 259

new-patchmatchnet		42.21 242	42.97 243	41.33 241	53.05 234	59.89 244	39.38 249	49.61 216	28.26 244	12.10 254	22.17 243	21.54 253	19.22 249	50.96 246	56.04 243	74.61 241	61.92 246

TinyColmap		52.66 223	50.09 235	55.65 208	59.72 220	64.02 239	57.15 219	52.96 209	40.28 205	32.51 217	32.42 221	20.97 254	56.65 169	63.95 224	65.15 226	74.91 239	63.87 242

pmmvs3		41.86 243	42.29 245	41.36 240	39.80 251	52.66 251	38.93 251	35.85 254	23.40 251	20.22 239	19.30 248	20.84 255	40.56 222	55.98 241	58.79 239	72.80 244	65.03 240

FPMVS		39.11 246	36.39 248	42.28 238	55.97 230	45.94 253	46.23 240	41.57 244	35.73 228	22.61 233	23.46 240	19.82 256	28.32 238	43.57 249	40.67 251	58.96 252	45.54 251

PMVS	27.44 18	32.08 248	29.07 252	35.60 246	48.33 247	24.79 257	26.97 256	41.34 246	20.45 253	22.50 234	17.11 252	18.64 257	20.44 247	41.99 251	38.06 252	54.02 254	42.44 252
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		33.19 247	35.52 249	30.47 247	27.55 258	45.31 254	29.29 255	30.92 255	29.00 243	9.88 257	18.77 249	17.64 258	26.77 240	44.07 248	45.98 249	58.41 253	47.87 250

WB-MVS		30.42 249	32.63 251	27.84 248	51.51 237	41.64 255	17.75 259	55.06 191	20.11 255	2.46 264	26.13 237	16.63 259	3.90 258	44.91 247	44.54 250	36.34 258	34.48 254

MDA-MVSNet-bldmvs		44.15 241	42.27 246	46.34 234	38.34 252	62.31 241	46.28 239	55.74 182	29.83 240	20.98 238	27.11 235	16.45 260	41.98 220	41.11 252	57.47 241	74.72 240	61.65 247

PMMVS2		20.45 252	22.31 254	18.27 254	20.52 260	26.73 256	14.85 261	28.43 257	13.69 257	0.79 265	10.35 256	9.10 261	3.83 259	27.64 255	32.87 253	41.17 255	35.81 253

ambc			42.30 244		50.36 238	49.51 252	35.47 252		32.04 238	23.53 232	17.36 250	8.95 262	29.06 234	64.88 219	56.26 242	61.29 251	67.12 235

DeepMVS_CX						19.81 261	17.01 260	10.02 259	23.61 250	5.85 260	17.21 251	8.03 263	21.13 246	22.60 256		21.42 262	30.01 255

Gipuma		24.91 251	24.61 253	25.26 250	31.47 255	21.59 258	18.06 258	37.53 251	25.43 249	10.03 256	4.18 260	4.25 264	14.85 253	43.20 250	47.03 248	39.62 256	26.55 257
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	15.98 19	14.37 255	16.36 255	12.04 256	7.72 262	20.24 260	5.90 265	29.05 256	8.28 260	3.92 261	4.72 259	2.42 265	9.57 256	18.89 257	31.46 254	16.07 263	28.53 256
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		14.40 254	10.71 257	18.70 253	28.15 257	12.09 263	7.06 263	36.89 252	11.00 258	3.56 263	4.95 258	2.27 266	13.91 254	10.13 259	16.06 258	22.63 261	18.51 259

E-PMN		15.08 253	11.65 256	19.08 252	28.73 256	12.31 262	6.95 264	36.87 253	10.71 259	3.63 262	5.13 257	2.22 267	13.81 255	11.34 258	18.50 257	24.49 260	21.32 258

testmvs		0.05 256	0.08 258	0.01 257	0.00 265	0.01 265	0.03 267	0.01 262	0.05 261	0.00 267	0.14 262	0.01 268	0.03 262	0.05 260	0.05 259	0.01 264	0.24 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 265	0.00 267	0.00 269	0.00 263	0.00 263	0.00 267	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 265	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 265	0.00 267	0.00 269	0.00 263	0.00 263	0.00 267	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 265	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 265	0.00 267	0.00 269	0.00 263	0.00 263	0.00 267	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 265	0.00 262

test123		0.05 256	0.08 258	0.01 257	0.00 265	0.01 265	0.01 268	0.00 263	0.05 261	0.00 267	0.16 261	0.00 269	0.04 260	0.02 261	0.05 259	0.00 265	0.26 260

TestfortrainingZip							88.32 8	77.84 4		88.26 1						90.10 6

RE-MVS-def										31.47 219

our_test_3					63.32 205	71.07 220	55.90 221

Patchmatch-RL test							2.17 266

NP-MVS									81.60 36

Patchmtry						78.06 167	67.53 166	43.18 238		41.40 169

High-resolution multi-view benchmark