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.

CSCG		74.68 18	79.22 18	69.40 19	75.69 14	80.01 11	79.12 27	52.83 44	79.34 19	63.99 9	70.49 28	82.02 14	60.35 34	77.48 26	77.22 19	84.38 1	87.97 17

MCST-MVS		73.67 26	77.39 28	69.33 20	76.26 11	78.19 19	78.77 29	54.54 33	75.33 29	59.99 29	67.96 34	79.23 24	62.43 18	78.00 19	75.71 32	84.02 2	87.30 21

SteuartSystems-ACMMP		75.23 15	79.60 17	70.13 15	76.81 8	78.92 14	81.74 11	57.99 6	75.30 31	59.83 30	75.69 20	78.45 26	60.48 31	80.58 2	79.77 2	83.94 3	88.52 12
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		77.32 9	82.51 9	71.26 9	75.43 17	80.19 9	82.22 10	58.26 3	84.83 8	64.36 7	78.19 17	83.46 8	63.61 10	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
MED-MVS		78.08 5	83.64 5	71.58 5	77.52 6	80.94 5	83.32 2	57.38 13	86.43 3	62.22 20	87.31 6	86.02 4	65.39 4	78.54 13	77.20 20	83.65 5	89.06 9

DeepC-MVS	66.32 2	73.85 24	78.10 25	68.90 24	67.92 52	79.31 13	78.16 32	59.28 1	78.24 23	61.13 24	67.36 37	76.10 35	63.40 11	79.11 9	78.41 11	83.52 6	88.16 15
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		77.58 8	82.93 8	71.35 8	77.86 4	80.55 7	83.38 1	57.61 10	85.57 6	61.11 25	86.10 9	82.98 10	64.76 6	78.29 16	76.78 23	83.40 7	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		77.13 10	81.70 10	71.79 3	79.32 1	80.76 6	82.96 3	57.49 11	82.82 11	64.79 5	83.69 12	84.46 7	62.83 15	77.13 28	75.21 34	83.35 8	87.85 18

TestfortrainingZip							82.75 8	57.21 14		62.96 14						83.21 9

ME-MVS		77.69 7	83.11 7	71.36 7	77.52 6	80.15 10	82.75 8	57.21 14	84.71 9	62.22 20	87.31 6	85.76 6	65.28 5	78.00 19	76.77 24	83.21 9	89.06 9

CNVR-MVS		75.62 14	79.91 16	70.61 12	75.76 12	78.82 16	81.66 12	57.12 16	79.77 18	63.04 13	70.69 27	81.15 18	62.99 13	80.23 5	79.54 3	83.11 11	89.16 8

HFP-MVS		74.87 17	78.86 22	70.21 14	73.99 24	77.91 20	80.36 19	56.63 19	78.41 21	64.27 8	74.54 22	77.75 31	62.96 14	78.70 12	77.82 13	83.02 12	86.91 23

NCCC		74.27 21	77.83 26	70.13 15	75.70 13	77.41 25	80.51 18	57.09 17	78.25 22	62.28 19	65.54 39	78.26 27	62.18 20	79.13 8	78.51 10	83.01 13	87.68 19

ACMMP_NAP		76.15 11	81.17 11	70.30 13	74.09 23	79.47 12	81.59 15	57.09 17	81.38 13	63.89 10	79.02 15	80.48 21	62.24 19	80.05 6	79.12 4	82.94 14	88.64 11

ACMP	61.42 5	68.72 44	71.37 46	65.64 40	69.06 47	74.45 44	75.88 42	53.30 40	68.10 53	55.74 42	61.53 77	62.29 106	56.97 56	74.70 49	74.23 43	82.88 15	84.31 37
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		68.87 41	72.03 44	65.18 42	69.33 46	74.03 46	76.67 38	53.88 38	68.46 52	52.05 76	63.21 56	63.89 98	56.31 61	75.99 39	74.43 41	82.83 16	84.18 38

ACMMP		71.57 33	75.84 33	66.59 33	70.30 43	76.85 31	78.46 31	53.95 37	73.52 39	55.56 43	70.13 29	71.36 52	58.55 43	77.00 29	76.23 29	82.71 17	85.81 30
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
ACMMPR		73.79 25	78.41 23	68.40 26	72.35 30	77.79 22	79.32 23	56.38 21	77.67 25	58.30 36	74.16 23	76.66 32	61.40 24	78.32 15	77.80 14	82.68 18	86.51 24

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 5	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 19	90.92 2

CDPH-MVS		71.47 34	75.82 34	66.41 34	72.97 28	77.15 27	78.14 33	54.71 30	69.88 51	53.07 69	70.98 26	74.83 39	56.95 57	76.22 36	76.57 26	82.62 20	85.09 36

MGCNet		72.45 31	77.44 27	66.61 32	71.08 37	77.81 21	76.74 37	49.30 64	73.12 40	61.17 23	73.70 24	78.08 28	58.78 40	76.75 34	76.52 27	82.61 21	86.14 27

DPM-MVS		72.80 28	75.90 32	69.19 22	75.51 15	77.68 23	81.62 14	54.83 29	75.96 27	62.06 22	63.96 52	76.58 33	58.55 43	76.66 35	76.77 24	82.60 22	83.68 42

PGM-MVS		72.89 27	77.13 29	67.94 27	72.47 29	77.25 26	79.27 25	54.63 32	73.71 38	57.95 38	72.38 25	75.33 37	60.75 29	78.25 17	77.36 18	82.57 23	85.62 31

EC-MVSNet		67.01 53	70.27 56	63.21 50	67.21 54	70.47 63	69.01 76	46.96 77	59.16 80	53.23 68	64.01 50	69.71 60	60.37 33	74.92 47	71.24 58	82.50 24	82.41 47

SD-MVS		74.43 19	78.87 20	69.26 21	74.39 22	73.70 47	79.06 28	55.24 28	81.04 14	62.71 15	80.18 14	82.61 12	61.70 23	75.43 43	73.92 45	82.44 25	85.22 34
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
DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 13	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 12	79.99 7	78.56 7	82.31 26	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
DPE-MVS		78.11 4	83.84 4	71.42 6	77.82 5	81.32 4	82.92 6	57.81 9	84.04 10	63.19 12	88.63 2	86.00 5	64.52 7	78.71 11	77.63 15	82.26 27	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
XVS					70.49 41	76.96 28	74.36 48			54.48 62		74.47 40				82.24 28

X-MVStestdata					70.49 41	76.96 28	74.36 48			54.48 62		74.47 40				82.24 28

X-MVS		71.18 35	75.66 35	65.96 38	71.71 32	76.96 28	77.26 36	55.88 25	72.75 42	54.48 62	64.39 46	74.47 40	54.19 85	77.84 22	77.37 17	82.21 30	85.85 29

DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 9	81.93 3	82.92 6	58.10 5	85.86 5	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 31	90.29 4

OPM-MVS		69.33 39	71.05 49	67.32 29	72.34 31	75.70 35	79.57 22	56.34 22	55.21 101	53.81 66	59.51 91	68.96 63	59.67 36	77.61 25	76.44 28	82.19 31	83.88 41
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MP-MVS		74.31 20	78.87 20	68.99 23	73.49 26	78.56 17	79.25 26	56.51 20	75.33 29	60.69 27	75.30 21	79.12 25	61.81 22	77.78 23	77.93 12	82.18 33	88.06 16
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	65.08 3	72.00 32	76.11 31	67.21 30	68.93 48	77.46 24	76.54 39	54.35 34	74.92 33	58.64 35	65.18 41	74.04 45	62.62 16	77.92 21	77.02 22	82.16 34	86.21 25
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TPM-MVS					75.48 16	76.70 32	79.31 24			62.34 18	64.71 44	77.88 30	56.94 58			81.88 35	83.68 42
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
ACMM	60.30 7	67.58 50	68.82 65	66.13 36	70.59 40	72.01 56	76.54 39	54.26 35	65.64 57	54.78 56	50.35 137	61.72 112	58.74 41	75.79 40	75.03 36	81.88 35	81.17 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS++		76.01 12	80.47 14	70.81 11	76.60 10	74.96 38	80.18 20	58.36 2	81.96 12	63.50 11	78.80 16	82.53 13	64.40 8	78.74 10	78.84 5	81.81 37	87.46 20

HQP-MVS		70.88 36	75.02 36	66.05 37	71.69 33	74.47 43	77.51 35	53.17 41	72.89 41	54.88 51	70.03 30	70.48 55	57.26 51	76.02 38	75.01 37	81.78 38	86.21 25

TSAR-MVS + MP.		75.22 16	80.06 15	69.56 18	74.61 21	72.74 51	80.59 17	55.70 26	80.80 15	62.65 16	86.25 8	82.92 11	62.07 21	76.89 30	75.66 33	81.77 39	85.19 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		73.89 23	78.25 24	68.80 25	75.25 20	72.27 54	79.75 21	56.05 23	74.87 34	58.97 32	81.83 13	79.76 23	61.05 27	77.39 27	76.01 31	81.71 40	85.61 32

CP-MVS		72.63 29	76.95 30	67.59 28	70.67 39	75.53 36	77.95 34	56.01 24	75.65 28	58.82 33	69.16 32	76.48 34	60.46 32	77.66 24	77.20 20	81.65 41	86.97 22

APD-MVS		75.80 13	80.90 13	69.86 17	75.42 18	78.48 18	81.43 16	57.44 12	80.45 16	59.32 31	85.28 10	80.82 20	63.96 9	76.89 30	76.08 30	81.58 42	88.30 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		65.88 56	69.71 60	61.41 57	61.76 100	68.14 79	67.65 83	44.00 114	59.14 81	52.69 70	65.19 40	68.13 69	60.90 28	74.74 48	71.58 54	81.46 43	81.04 56

3Dnovator	60.86 6	66.99 54	70.32 54	63.11 51	66.63 57	74.52 41	71.56 57	45.76 84	67.37 55	55.00 50	54.31 119	68.19 68	58.49 45	73.97 52	73.63 48	81.22 44	80.23 59

3Dnovator+	62.63 4	69.51 38	72.62 41	65.88 39	68.21 51	76.47 33	73.50 52	52.74 45	70.85 47	58.65 34	55.97 107	69.95 56	61.11 26	76.80 32	75.09 35	81.09 45	83.23 46

SPE-MVS-test		65.18 63	68.70 66	61.07 59	61.92 97	68.06 86	67.09 94	45.18 92	58.47 86	52.02 77	65.76 38	66.44 87	59.24 38	72.71 59	70.05 68	80.98 46	79.40 65

CANet		68.77 42	73.01 39	63.83 47	68.30 49	75.19 37	73.73 51	47.90 72	63.86 59	54.84 55	67.51 36	74.36 43	57.62 47	74.22 51	73.57 49	80.56 47	82.36 48

ETV-MVS		63.23 83	66.08 93	59.91 75	63.13 82	68.13 80	67.62 84	44.62 99	53.39 111	46.23 108	58.74 96	58.19 126	57.45 49	73.60 53	71.38 57	80.39 48	79.13 66

MSP-MVS		77.82 6	83.46 6	71.24 10	75.26 19	80.22 8	82.95 4	57.85 8	85.90 4	64.79 5	88.54 3	83.43 9	66.24 3	78.21 18	78.56 7	80.34 49	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
TSAR-MVS + GP.		69.71 37	73.92 38	64.80 45	68.27 50	70.56 62	71.90 53	50.75 54	71.38 46	57.46 40	68.68 33	75.42 36	60.10 35	73.47 54	73.99 44	80.32 50	83.97 40

MVSMamba_PlusPlus		67.64 48	71.37 46	63.30 49	66.37 61	72.40 53	70.80 60	48.42 71	62.82 63	54.87 53	63.02 59	70.51 54	59.13 39	75.59 41	73.57 49	80.21 51	81.67 52

MVS_111021_HR		67.62 49	70.39 53	64.39 46	69.77 44	70.45 64	71.44 58	51.72 50	60.77 70	55.06 48	62.14 71	66.40 88	58.13 46	76.13 37	74.79 39	80.19 52	82.04 51

DeepPCF-MVS	66.49 1	74.25 22	80.97 12	66.41 34	67.75 53	78.87 15	75.61 43	54.16 36	84.86 7	58.22 37	77.94 18	81.01 19	62.52 17	78.34 14	77.38 16	80.16 53	88.40 13

EIA-MVS		61.53 98	63.79 111	58.89 84	63.82 79	67.61 95	65.35 116	42.15 158	49.98 132	45.66 112	57.47 103	56.62 133	56.59 60	70.91 77	69.15 75	79.78 54	74.80 128

MAR-MVS		68.04 46	70.74 51	64.90 44	71.68 34	76.33 34	74.63 47	50.48 58	63.81 60	55.52 44	54.88 114	69.90 57	57.39 50	75.42 44	74.79 39	79.71 55	80.03 60
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
MSLP-MVS++		68.17 45	70.72 52	65.19 41	69.41 45	70.64 61	74.99 45	45.76 84	70.20 50	60.17 28	56.42 105	73.01 46	61.14 25	72.80 58	70.54 63	79.70 56	81.42 54

DELS-MVS		65.87 57	70.30 55	60.71 69	64.05 76	72.68 52	70.90 59	45.43 88	57.49 94	49.05 90	64.43 45	68.66 64	55.11 76	74.31 50	73.02 51	79.70 56	81.51 53
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
AdaColmap		67.89 47	68.85 64	66.77 31	73.73 25	74.30 45	75.28 44	53.58 39	70.24 49	57.59 39	51.19 134	59.19 123	60.74 30	75.33 45	73.72 47	79.69 58	77.96 81

Effi-MVS+		63.28 82	65.96 94	60.17 72	64.26 72	68.06 86	68.78 79	45.71 86	54.08 106	46.64 103	55.92 108	63.13 102	55.94 66	70.38 84	71.43 55	79.68 59	78.70 70

Casviewmamba		66.44 55	70.12 57	62.15 54	66.40 60	71.79 57	71.67 55	47.32 74	64.01 58	51.09 81	64.00 51	69.72 59	57.04 54	72.83 57	69.10 77	79.37 60	79.41 64

casdiffmvs_mvg		65.26 62	69.48 63	60.33 71	62.99 92	69.34 67	69.80 74	45.27 90	63.38 62	51.11 80	65.12 42	69.75 58	53.51 93	71.74 65	68.86 81	79.33 61	78.19 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		63.65 80	66.92 77	59.83 77	60.03 115	73.44 49	66.33 100	48.95 66	52.20 124	50.81 83	56.07 106	60.25 119	53.56 91	73.23 56	70.01 69	79.30 62	83.24 45

GeoE		62.43 88	64.79 104	59.68 78	64.15 75	67.17 103	68.80 78	44.42 103	55.65 100	47.38 95	51.54 131	62.51 103	54.04 88	69.99 91	68.07 90	79.28 63	78.57 71

EPP-MVSNet		59.39 112	65.45 99	52.32 144	60.96 108	67.70 93	58.42 156	44.75 97	49.71 134	27.23 210	59.03 93	62.20 109	43.34 164	70.71 78	69.13 76	79.25 64	79.63 63

CPTT-MVS		68.76 43	73.01 39	63.81 48	65.42 65	73.66 48	76.39 41	52.08 46	72.61 43	50.33 84	60.73 83	72.65 48	59.43 37	73.32 55	72.12 52	79.19 65	85.99 28

viewdifsd2359ckpt09		65.38 60	68.69 67	61.53 56	62.15 94	71.64 58	71.84 54	47.45 73	58.95 82	51.79 78	61.73 76	65.71 93	57.08 53	72.17 61	70.82 59	78.87 66	79.79 61

casdiffseed414692147		63.90 77	66.17 92	61.24 58	64.92 67	69.27 68	70.00 73	46.18 81	58.66 84	51.43 79	55.30 111	62.51 103	56.20 64	70.93 76	68.62 85	78.73 67	77.90 82

Fast-Effi-MVS+		60.36 105	63.35 114	56.87 105	58.70 123	65.86 116	65.08 119	37.11 216	53.00 116	45.36 114	52.12 128	56.07 139	56.27 62	71.28 70	69.42 73	78.71 68	75.69 122

PCF-MVS	59.98 8	67.32 51	71.04 50	62.97 52	64.77 68	74.49 42	74.78 46	49.54 60	67.44 54	54.39 65	58.35 99	72.81 47	55.79 68	71.54 67	69.24 74	78.57 69	83.41 44
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		64.09 71	68.13 69	59.37 80	61.81 98	68.32 76	68.48 81	44.45 102	61.95 67	49.12 89	63.04 58	69.67 61	53.83 89	70.46 81	66.06 137	78.55 70	77.43 85
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet_NR-MVSNet		56.94 139	61.14 122	52.05 146	60.02 116	65.21 126	57.44 161	52.93 43	49.37 138	24.31 226	54.62 118	50.54 161	39.04 186	68.69 111	68.84 82	78.53 71	70.72 147

hybridcas		64.37 66	68.25 68	59.84 76	63.43 81	68.95 70	70.14 71	43.11 149	62.73 65	49.21 87	62.50 68	69.22 62	54.64 81	70.95 75	66.48 129	78.51 72	76.90 100

sasdasda		65.62 58	72.06 42	58.11 87	63.94 77	71.05 59	64.49 125	43.18 144	74.08 35	47.35 96	64.17 48	71.97 49	51.17 117	71.87 63	70.74 60	78.51 72	80.56 57

canonicalmvs		65.62 58	72.06 42	58.11 87	63.94 77	71.05 59	64.49 125	43.18 144	74.08 35	47.35 96	64.17 48	71.97 49	51.17 117	71.87 63	70.74 60	78.51 72	80.56 57

IS_MVSNet		57.95 131	64.26 107	50.60 152	61.62 102	65.25 125	57.18 163	45.42 89	50.79 128	26.49 216	57.81 101	60.05 120	34.51 220	71.24 71	70.20 67	78.36 75	74.44 130

PHI-MVS		69.27 40	74.84 37	62.76 53	66.83 56	74.83 39	73.88 50	49.32 63	70.61 48	50.93 82	69.62 31	74.84 38	57.25 52	75.53 42	74.32 42	78.35 76	84.17 39

EG-PatchMatch MVS		56.98 137	58.24 161	55.50 117	64.66 69	68.62 73	61.48 137	43.63 131	38.44 236	41.44 134	38.05 227	46.18 205	43.95 160	71.71 66	70.61 62	77.87 77	74.08 134

E6new		64.03 73	66.63 84	60.99 60	63.04 87	68.16 77	70.80 60	44.14 105	57.66 92	54.63 57	60.32 85	66.05 89	55.49 69	70.14 89	67.09 106	77.85 78	76.94 95

E6		64.03 73	66.63 84	60.99 60	63.04 87	68.16 77	70.80 60	44.14 105	57.66 92	54.63 57	60.32 85	66.05 89	55.49 69	70.14 89	67.09 106	77.85 78	76.94 95

E4		64.06 72	66.79 81	60.87 64	63.03 89	68.11 81	70.61 63	44.00 114	58.24 89	54.56 59	61.00 82	66.64 84	55.22 72	69.80 93	66.69 119	77.81 80	77.07 94

E5new		64.00 75	66.77 82	60.77 67	63.02 90	68.11 81	70.42 68	43.97 116	58.41 87	54.52 60	61.10 79	66.52 85	54.97 79	69.61 95	66.52 125	77.74 81	77.09 92

E5		64.00 75	66.77 82	60.77 67	63.02 90	68.11 81	70.42 68	43.97 116	58.41 87	54.52 60	61.10 79	66.52 85	54.97 79	69.61 95	66.52 125	77.74 81	77.09 92

OpenMVS	57.13 9	62.81 85	65.75 96	59.39 79	66.47 59	69.52 66	64.26 128	43.07 150	61.34 69	50.19 85	47.29 155	64.41 97	54.60 82	70.18 88	68.62 85	77.73 83	78.89 69

E3new		64.18 69	67.01 74	60.89 62	63.07 84	68.08 84	70.57 64	43.95 118	59.33 77	54.87 53	61.94 75	66.76 83	55.16 74	69.60 97	66.42 132	77.70 84	76.92 97

E3		64.18 69	67.01 74	60.89 62	63.07 84	68.07 85	70.57 64	43.94 119	59.32 78	54.88 51	61.95 73	66.78 82	55.16 74	69.60 97	66.43 131	77.70 84	76.92 97

NR-MVSNet		55.35 154	59.46 149	50.56 153	61.33 104	62.97 145	57.91 159	51.80 48	48.62 152	20.59 233	51.99 129	44.73 220	34.10 223	68.58 114	68.64 84	77.66 86	70.67 151

QAPM		65.27 61	69.49 62	60.35 70	65.43 64	72.20 55	65.69 113	47.23 75	63.46 61	49.14 88	53.56 120	71.04 53	57.01 55	72.60 60	71.41 56	77.62 87	82.14 50

viewcassd2359sk11		64.22 67	67.08 71	60.87 64	63.08 83	68.05 88	70.51 66	43.92 121	59.80 73	55.05 49	62.49 69	66.89 80	55.09 77	69.39 101	66.19 136	77.60 88	76.77 105

IB-MVS	54.11 11	58.36 126	60.70 127	55.62 116	58.67 124	68.02 89	61.56 135	43.15 147	46.09 170	44.06 120	44.24 187	50.99 160	48.71 132	66.70 157	70.33 64	77.60 88	78.50 72
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
ACMH+	53.71 12	59.26 113	60.28 132	58.06 89	64.17 74	68.46 74	67.51 86	50.93 53	52.46 122	35.83 163	40.83 215	45.12 214	52.32 107	69.88 92	69.00 80	77.59 90	76.21 117

TranMVSNet+NR-MVSNet		55.87 147	60.14 137	50.88 151	59.46 121	63.82 139	57.93 158	52.98 42	48.94 144	20.52 234	52.87 123	47.33 188	36.81 207	69.12 107	69.03 79	77.56 91	69.89 153

E2		64.19 68	67.06 72	60.84 66	63.07 84	68.02 89	70.44 67	43.88 122	59.94 72	55.15 47	62.73 63	66.97 79	55.01 78	69.18 104	65.98 140	77.53 92	76.63 108

viewdifsd2359ckpt13		63.83 78	67.03 73	60.10 73	62.56 93	68.92 71	69.73 75	43.49 136	57.96 90	52.16 75	61.09 81	65.39 94	55.20 73	70.36 85	67.48 102	77.48 93	78.00 80

MSDG		58.46 123	58.97 154	57.85 96	66.27 63	66.23 113	67.72 82	42.33 154	53.43 110	43.68 121	43.39 197	45.35 210	49.75 127	68.66 113	67.77 95	77.38 94	67.96 170

Effi-MVS+-dtu		60.34 106	62.32 118	58.03 91	64.31 70	67.44 99	65.99 106	42.26 155	49.55 135	42.00 133	48.92 145	59.79 121	56.27 62	68.07 129	67.03 108	77.35 95	75.45 124

ET-MVSNet_ETH3D		58.38 125	61.57 120	54.67 123	42.15 236	65.26 123	65.70 111	43.82 123	48.84 145	42.34 128	59.76 90	47.76 181	56.68 59	67.02 153	68.60 87	77.33 96	73.73 137

DI_MVS_pp		61.88 92	65.17 101	58.06 89	60.05 114	65.26 123	66.03 104	44.22 104	55.75 99	46.73 101	54.64 117	68.12 70	54.13 87	69.13 106	66.66 120	77.18 97	76.61 109

v1144		58.88 116	60.16 136	57.39 98	58.03 130	67.26 101	67.14 92	44.46 101	45.17 176	44.33 119	47.81 152	49.92 166	53.20 101	67.77 135	66.62 123	77.15 98	76.58 110

v1192		58.51 120	59.66 143	57.17 100	57.82 132	67.72 92	66.21 102	44.83 96	44.15 185	43.49 122	46.68 157	47.94 178	53.55 92	67.39 143	66.51 127	77.13 99	77.20 89

UniMVSNet (Re)		55.15 159	60.39 131	49.03 167	55.31 162	64.59 131	55.77 178	50.63 55	48.66 151	20.95 232	51.47 132	50.40 162	34.41 222	67.81 134	67.89 92	77.11 100	71.88 141

viewmacassd2359aftdt		63.43 81	66.95 76	59.32 81	61.27 106	67.48 98	70.15 70	40.54 176	57.82 91	52.27 74	60.49 84	66.81 81	54.58 83	70.67 79	67.39 104	77.08 101	78.02 79

viewmanbaseed2359cas		63.67 79	67.42 70	59.30 82	61.34 103	67.42 100	70.01 72	40.50 179	59.53 75	52.60 71	62.56 67	67.34 78	54.44 84	70.33 86	66.93 112	76.91 102	77.82 84

v10		59.17 115	60.60 128	57.50 97	57.95 131	66.73 107	67.09 94	44.11 107	46.85 164	45.42 113	48.18 151	51.07 157	53.63 90	67.84 133	66.59 124	76.79 103	76.92 97

MVS_Test		62.40 89	66.23 90	57.94 92	59.77 119	64.77 130	66.50 99	41.76 161	57.26 96	49.33 86	62.68 64	67.47 77	53.50 95	68.57 115	66.25 133	76.77 104	76.58 110

FA-MVS(training)		60.00 108	63.14 116	56.33 109	59.50 120	64.30 135	65.15 118	38.75 200	56.20 98	45.77 110	53.08 121	56.45 134	52.10 110	69.04 109	67.67 98	76.69 105	75.27 127

v144192		58.23 129	59.40 150	56.87 105	57.56 134	66.89 105	65.70 111	45.01 94	44.06 186	42.88 124	46.61 159	48.09 177	53.49 96	66.94 154	65.90 143	76.61 106	77.29 87

v2v482		58.69 119	60.12 139	57.03 102	57.16 152	66.05 115	67.17 91	43.52 134	46.33 168	45.19 115	49.46 141	51.02 158	52.51 105	67.30 146	66.03 139	76.61 106	74.62 129

ACMH	52.42 13	58.24 128	59.56 148	56.70 107	66.34 62	69.59 65	66.71 97	49.12 65	46.08 171	28.90 198	42.67 209	41.20 233	52.60 104	71.39 68	70.28 65	76.51 108	75.72 121
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PVSNet_BlendedMVS		61.63 96	64.82 102	57.91 94	57.21 148	67.55 96	63.47 132	46.08 82	54.72 103	52.46 72	58.59 97	60.73 115	51.82 113	70.46 81	65.20 154	76.44 109	76.50 114

PVSNet_Blended		61.63 96	64.82 102	57.91 94	57.21 148	67.55 96	63.47 132	46.08 82	54.72 103	52.46 72	58.59 97	60.73 115	51.82 113	70.46 81	65.20 154	76.44 109	76.50 114

v1921920		57.89 132	59.02 153	56.58 108	57.55 135	66.66 111	64.72 122	44.70 98	43.55 190	42.73 125	46.17 167	46.93 196	53.51 93	66.78 156	65.75 145	76.29 111	77.28 88

EPNet		65.14 65	69.54 61	60.00 74	66.61 58	67.67 94	67.53 85	55.32 27	62.67 66	46.22 109	67.74 35	65.93 91	48.07 140	72.17 61	72.12 52	76.28 112	78.47 73
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v8		58.88 116	60.57 130	56.92 103	57.35 142	65.69 118	66.69 98	42.64 152	47.89 159	45.77 110	49.04 142	52.98 150	52.77 103	67.51 141	65.57 146	76.26 113	75.30 126

DCV-MVSNet		59.49 109	64.00 110	54.23 126	61.81 98	64.33 134	61.42 138	43.77 124	52.85 119	38.94 151	55.62 110	62.15 110	43.24 167	69.39 101	67.66 99	76.22 114	75.97 119

v1240		57.55 134	58.63 157	56.29 110	57.30 145	66.48 112	63.77 130	44.56 100	42.77 201	42.48 127	45.64 173	46.28 203	53.46 97	66.32 163	65.80 144	76.16 115	77.13 91

CLD-MVS		67.02 52	71.57 45	61.71 55	71.01 38	74.81 40	71.62 56	38.91 194	71.86 45	60.70 26	64.97 43	67.88 72	51.88 112	76.77 33	74.98 38	76.11 116	69.75 154
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test2506		55.82 149	59.57 147	51.46 148	60.39 112	64.55 132	58.69 154	48.87 67	53.91 107	26.99 211	48.97 143	41.72 232	37.71 197	70.96 73	69.49 71	76.08 117	67.37 175

ECVR-MVS		56.44 144	60.74 126	51.42 149	60.39 112	64.55 132	58.69 154	48.87 67	53.91 107	26.76 213	45.55 175	53.43 148	37.71 197	70.96 73	69.49 71	76.08 117	67.32 177

v7n		55.67 150	57.46 169	53.59 132	56.06 157	65.29 122	61.06 141	43.26 143	40.17 220	37.99 155	40.79 216	45.27 213	47.09 144	67.67 138	66.21 134	76.08 117	76.82 101

OMC-MVS		65.16 64	71.35 48	57.94 92	52.95 181	68.82 72	69.00 77	38.28 203	79.89 17	55.20 46	62.76 62	68.31 66	56.14 65	71.30 69	68.70 83	76.06 120	79.67 62

DU-MVS		55.41 153	59.59 144	50.54 154	54.60 169	62.97 145	57.44 161	51.80 48	48.62 152	24.31 226	51.99 129	47.00 193	39.04 186	68.11 127	67.75 96	76.03 121	70.72 147

FC-MVSNet-train		58.40 124	63.15 115	52.85 140	64.29 71	61.84 155	55.98 177	46.47 79	53.06 114	34.96 167	61.95 73	56.37 137	39.49 184	68.67 112	68.36 88	75.92 122	71.81 142

Anonymous20231211		57.71 133	60.79 125	54.13 128	61.68 101	65.81 117	60.81 143	43.70 129	51.97 125	39.67 146	34.82 235	63.59 99	43.31 165	68.55 116	66.63 122	75.59 123	74.13 133

MVSTER		57.19 135	61.11 123	52.62 142	50.82 201	58.79 185	61.55 136	37.86 213	48.81 147	41.31 136	57.43 104	52.10 153	48.60 134	68.19 126	66.75 117	75.56 124	75.68 123

Anonymous202405211			60.60 128		63.44 80	66.71 110	61.00 142	47.23 75	50.62 130		36.85 230	60.63 118	43.03 168	69.17 105	67.72 97	75.41 125	72.54 139

thisisatest0530		56.68 141	59.68 142	53.19 136	52.97 180	60.96 165	59.41 149	40.51 177	48.26 155	41.06 139	52.67 124	46.30 202	49.78 125	67.66 139	67.83 93	75.39 126	74.07 135

Fast-Effi-MVS+-dtu		56.30 145	59.29 151	52.82 141	58.64 125	64.89 127	65.56 114	32.89 244	45.80 173	35.04 166	45.89 170	54.14 144	49.41 128	67.16 149	66.45 130	75.37 127	70.69 149

TSAR-MVS + ACMM		72.56 30	79.07 19	64.96 43	73.24 27	73.16 50	78.50 30	48.80 70	79.34 19	55.32 45	85.04 11	81.49 17	58.57 42	75.06 46	73.75 46	75.35 128	85.61 32

tttt0517		56.53 143	59.59 144	52.95 139	52.66 183	60.99 164	59.21 151	40.51 177	47.89 159	40.40 142	52.50 127	46.04 206	49.78 125	67.75 136	67.83 93	75.15 129	74.17 132

test1111		55.24 155	59.98 140	49.71 158	59.80 118	64.10 137	56.48 171	49.34 62	52.27 123	21.56 231	44.49 185	51.96 154	35.93 215	70.59 80	69.07 78	75.13 130	67.40 173

MGCFI-Net		61.46 99	69.72 59	51.83 147	61.00 107	66.16 114	56.50 170	40.73 174	73.98 37	35.18 164	64.23 47	71.42 51	42.45 170	69.22 103	64.01 169	75.09 131	79.03 68

LS3D		60.20 107	61.70 119	58.45 86	64.18 73	67.77 91	67.19 89	48.84 69	61.67 68	41.27 137	45.89 170	51.81 155	54.18 86	68.78 110	66.50 128	75.03 132	69.48 161

baseline2		55.89 146	57.82 164	53.64 130	57.36 141	61.09 163	59.75 147	40.45 180	47.38 162	41.26 138	51.23 133	46.90 197	48.11 138	65.63 174	64.38 166	74.90 133	68.16 169

HyFIR lowres test		56.87 140	58.60 158	54.84 120	56.62 156	69.27 68	64.77 121	42.21 156	45.66 174	37.50 158	33.08 239	57.47 131	53.33 98	65.46 176	67.94 91	74.60 134	71.35 144

PLC	52.09 14	59.21 114	62.47 117	55.41 118	53.24 179	64.84 128	64.47 127	40.41 182	65.92 56	44.53 118	46.19 166	55.69 140	55.33 71	68.24 123	65.30 151	74.50 135	71.09 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GA-MVS		55.67 150	58.33 159	52.58 143	55.23 166	63.09 144	61.08 140	40.15 185	42.95 196	37.02 161	52.61 125	47.68 182	47.51 142	65.92 170	65.35 148	74.49 136	70.68 150

MVS_111021_LR		63.05 84	66.43 88	59.10 83	61.33 104	63.77 140	65.87 110	43.58 132	60.20 71	53.70 67	62.09 72	62.38 105	55.84 67	70.24 87	68.08 89	74.30 137	78.28 76

anonymousdsp		52.84 169	57.78 165	47.06 189	40.24 246	58.95 184	53.70 197	33.54 240	36.51 244	32.69 180	43.88 190	45.40 209	47.97 141	67.17 148	70.28 65	74.22 138	82.29 49

CANet_DTU		58.88 116	64.68 105	52.12 145	55.77 160	66.75 106	63.92 129	37.04 217	53.32 112	37.45 159	59.81 89	61.81 111	44.43 158	68.25 121	67.47 103	74.12 139	75.33 125

viewdifsd2359ckpt07		61.71 94	65.49 98	57.31 99	62.12 95	65.52 120	68.53 80	38.21 205	56.37 97	48.07 94	61.11 78	65.85 92	52.82 102	68.34 118	64.46 165	74.08 140	76.80 102

blended_shiyan8		49.21 204	52.59 208	45.27 203	41.67 238	58.47 188	52.41 207	38.16 206	38.60 230	28.53 203	40.26 219	47.07 191	36.78 208	59.62 204	57.26 213	74.06 141	66.88 183

blended_shiyan6		49.22 203	52.60 207	45.26 204	41.68 237	58.46 190	52.42 206	38.16 206	38.60 230	28.50 204	40.28 218	47.09 190	36.76 209	59.62 204	57.25 214	74.06 141	66.92 180

UA-Net		58.50 121	64.68 105	51.30 150	66.97 55	67.13 104	53.68 199	45.65 87	49.51 137	31.58 185	62.91 60	68.47 65	35.85 216	68.20 125	67.28 105	74.03 143	69.24 165

blend_shiyan4		50.41 190	53.51 192	46.79 193	44.79 227	58.47 188	52.51 205	36.99 218	41.74 209	34.13 170	42.68 206	49.24 169	38.37 189	58.53 218	56.69 219	73.96 144	67.20 178

usedtu_dtu_shiyan1		51.41 182	55.78 175	46.30 197	47.91 213	59.47 176	52.99 204	42.13 159	48.17 156	24.88 222	40.95 214	48.18 176	35.95 214	64.48 182	64.49 163	73.94 145	64.75 205

WR-MVS		48.78 212	55.06 183	41.45 226	55.50 161	60.40 168	43.77 246	49.99 59	41.92 207	8.10 263	45.24 179	45.56 208	17.47 252	61.57 195	64.60 160	73.85 146	66.14 194

v148		55.58 152	57.61 168	53.20 135	54.59 171	61.86 154	61.18 139	38.70 201	44.30 184	42.25 129	47.53 153	50.24 164	48.73 131	65.15 178	62.61 189	73.79 147	71.61 143

wanda-best-256-512		49.05 208	52.38 212	45.17 207	41.54 239	58.31 195	52.24 209	38.00 208	38.58 232	28.56 201	40.23 220	47.00 193	36.88 205	59.28 207	56.77 215	73.78 148	66.45 186

FE-blended-shiyan7		49.05 208	52.38 212	45.17 207	41.54 239	58.31 195	52.24 209	38.00 208	38.58 232	28.56 201	40.23 220	47.00 193	36.88 205	59.28 207	56.77 215	73.78 148	66.45 186

usedtu_blend_shiyan5		50.12 194	53.15 199	46.58 194	41.54 239	58.31 195	53.69 198	38.00 208	38.58 232	34.13 170	42.68 206	49.24 169	38.37 189	59.28 207	56.77 215	73.78 148	67.20 178

FE-MVSNET3		49.99 197	53.11 200	46.34 196	41.54 239	58.31 195	52.24 209	38.00 208	38.58 232	34.13 170	42.68 206	49.24 169	38.37 189	59.28 207	56.77 215	73.78 148	66.92 180

viewdifsd2359ckpt11		59.45 110	63.57 112	54.65 124	57.17 150	62.71 150	64.67 123	38.99 191	52.96 117	42.12 131	58.97 94	62.23 107	51.18 115	67.35 144	63.98 170	73.75 152	76.80 102

viewmsd2359difaftdt		59.45 110	63.57 112	54.65 124	57.17 150	62.71 150	64.67 123	38.99 191	52.96 117	42.12 131	58.97 94	62.22 108	51.18 115	67.35 144	63.98 170	73.75 152	76.80 102

PEN-MVS		49.21 204	54.32 187	43.24 220	54.33 172	59.26 180	47.04 231	51.37 52	41.67 210	9.97 258	46.22 165	41.80 231	22.97 247	60.52 198	64.03 168	73.73 154	66.75 184

GBi-Net		55.20 156	60.25 133	49.31 161	52.42 184	61.44 157	57.03 164	44.04 110	49.18 141	30.47 187	48.28 147	58.19 126	38.22 192	68.05 130	66.96 109	73.69 155	69.65 155

test1		55.20 156	60.25 133	49.31 161	52.42 184	61.44 157	57.03 164	44.04 110	49.18 141	30.47 187	48.28 147	58.19 126	38.22 192	68.05 130	66.96 109	73.69 155	69.65 155

FMVSNet2		55.04 160	59.95 141	49.31 161	52.42 184	61.44 157	57.03 164	44.08 109	49.55 135	30.40 190	46.89 156	58.84 124	38.22 192	67.07 152	66.21 134	73.69 155	69.65 155

FMVSNet1		54.08 164	58.68 156	48.71 171	50.90 200	61.35 160	56.73 168	43.94 119	45.91 172	29.32 197	42.72 205	56.26 138	37.70 199	68.05 130	66.96 109	73.69 155	69.50 160

dtuplus		60.38 104	64.02 109	56.13 111	58.12 129	63.10 143	66.05 103	41.59 164	54.56 105	46.60 104	59.27 92	64.90 95	50.72 122	66.90 155	63.35 179	73.68 159	76.05 118

viewmambaseed2359dif		60.40 103	64.15 108	56.03 112	57.79 133	63.53 142	65.91 109	41.64 162	54.98 102	46.47 105	60.16 88	64.71 96	50.76 121	66.25 165	62.83 185	73.61 160	76.57 112

diffmvs_AUTHOR		61.79 93	66.80 80	55.95 113	56.69 154	63.92 138	67.27 88	41.28 168	59.32 78	46.43 106	63.31 55	68.30 67	50.56 123	68.30 119	66.06 137	73.48 161	78.36 74

gbinet_0.2-2-1-0.02		48.89 210	52.69 204	44.45 213	39.54 249	59.33 178	52.39 208	38.76 199	35.41 245	26.17 218	39.15 224	47.39 187	36.41 213	60.29 202	57.58 211	73.45 162	69.65 155

viewmamba		62.28 91	66.90 78	56.89 104	58.53 126	64.79 129	67.28 87	43.17 146	59.60 74	48.15 93	63.20 57	67.57 76	50.82 120	69.05 108	66.77 116	73.41 163	77.32 86

MS-PatchMatch		58.19 130	60.20 135	55.85 115	65.17 66	64.16 136	64.82 120	41.48 166	50.95 127	42.17 130	45.38 176	56.42 135	48.08 139	68.30 119	66.70 118	73.39 164	69.46 163

TAPA-MVS	54.74 10	60.85 101	66.61 86	54.12 129	47.38 215	65.33 121	65.35 116	36.51 221	75.16 32	48.82 91	54.70 116	63.51 100	53.31 99	68.36 117	64.97 159	73.37 165	74.27 131
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		53.85 165	56.84 172	50.37 155	50.25 204	58.17 201	55.99 176	39.90 187	41.88 208	38.16 154	45.91 169	45.30 211	44.58 157	66.15 168	66.89 113	73.36 166	73.57 138

FMVSNet3		54.78 161	59.58 146	49.17 164	52.37 187	61.31 161	56.72 169	44.04 110	49.18 141	30.47 187	48.28 147	58.19 126	38.09 195	65.48 175	65.20 154	73.31 167	69.45 164

WR-MVS_H		47.65 219	53.67 190	40.63 232	51.45 192	59.74 175	44.71 244	49.37 61	40.69 216	7.61 265	46.04 168	44.34 225	17.32 253	57.79 223	61.18 195	73.30 168	65.86 196

TransMVSNet (Re)		51.92 180	55.38 179	47.88 184	60.95 109	59.90 173	53.95 194	45.14 93	39.47 224	24.85 223	43.87 191	46.51 201	29.15 232	67.55 140	65.23 153	73.26 169	65.16 203

diffmvs		61.64 95	66.55 87	55.90 114	56.63 155	63.71 141	67.13 93	41.27 169	59.49 76	46.70 102	63.93 53	68.01 71	50.46 124	67.30 146	65.51 147	73.24 170	77.87 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
onestephybrid01		62.35 90	66.85 79	57.10 101	59.33 122	65.58 119	67.18 90	43.71 128	57.48 95	48.34 92	62.61 65	67.84 73	50.93 119	69.40 100	66.88 115	73.15 171	78.12 78

FE-MVSNET2		45.69 231	49.95 229	40.72 231	40.11 247	56.16 212	46.59 232	41.89 160	36.97 243	13.66 248	29.00 250	37.59 249	28.96 235	63.26 184	63.93 173	73.13 172	62.72 218

IterMVS-LS		58.30 127	61.39 121	54.71 122	59.92 117	58.40 192	59.42 148	43.64 130	48.71 149	40.25 144	57.53 102	58.55 125	52.15 109	65.42 177	65.34 149	72.85 173	75.77 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		53.50 166	57.89 163	48.37 178	54.60 169	59.25 181	56.10 173	51.84 47	49.32 139	17.92 241	45.38 176	47.68 182	36.93 204	68.11 127	65.95 141	72.84 174	69.57 159

Vis-MVSNet		58.48 122	65.70 97	50.06 157	53.40 178	67.20 102	60.24 146	43.32 141	48.83 146	30.23 191	62.38 70	61.61 113	40.35 179	71.03 72	69.77 70	72.82 175	79.11 67
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_ETH3D		52.62 170	55.98 174	48.70 172	51.04 198	60.71 167	56.87 167	46.74 78	42.52 203	26.96 212	42.50 210	45.95 207	37.87 196	66.22 166	65.15 157	72.74 176	68.78 168

V42		56.97 138	60.14 137	53.28 134	48.16 210	62.78 148	66.30 101	37.93 212	47.44 161	42.68 126	48.19 150	52.59 152	51.90 111	67.46 142	65.94 142	72.72 177	76.55 113

tfpn200view9		52.53 171	55.51 177	49.06 166	57.31 143	60.24 169	55.42 184	43.77 124	42.85 199	27.81 206	43.00 203	45.06 216	37.32 201	66.38 160	64.54 161	72.71 178	66.54 185

CNLPA		62.78 86	66.31 89	58.65 85	58.47 127	68.41 75	65.98 107	41.22 170	78.02 24	56.04 41	46.65 158	59.50 122	57.50 48	69.67 94	65.27 152	72.70 179	76.67 107

thres600view7		51.91 181	55.14 181	48.14 180	57.43 139	60.18 170	54.60 189	43.73 126	42.61 202	25.20 221	43.10 202	44.47 223	35.19 218	66.36 161	63.28 180	72.66 180	66.01 195

thres400		52.38 174	55.51 177	48.74 170	57.49 138	60.10 172	55.45 183	43.54 133	42.90 198	26.72 214	43.34 199	45.03 218	36.61 210	66.20 167	64.53 162	72.66 180	66.43 188

thres200		52.39 173	55.37 180	48.90 168	57.39 140	60.18 170	55.60 180	43.73 126	42.93 197	27.41 208	43.35 198	45.09 215	36.61 210	66.36 161	63.92 174	72.66 180	65.78 197

hybridnocas07		61.04 100	66.19 91	55.03 119	55.86 159	62.77 149	66.02 105	39.98 186	58.77 83	47.07 98	63.48 54	67.60 75	48.61 133	68.22 124	65.32 150	72.62 183	77.17 90

thres100view900		52.04 178	54.81 185	48.80 169	57.31 143	59.33 178	55.30 185	42.92 151	42.85 199	27.81 206	43.00 203	45.06 216	36.99 203	64.74 180	63.51 176	72.47 184	65.21 202

hybrid		60.72 102	65.86 95	54.73 121	55.25 165	62.37 152	65.92 108	39.45 189	58.64 85	46.85 100	62.81 61	67.76 74	48.44 135	67.71 137	65.01 158	72.46 185	76.72 106

TSAR-MVS + COLMAP		62.65 87	69.90 58	54.19 127	46.31 220	66.73 107	65.49 115	41.36 167	76.57 26	46.31 107	76.80 19	56.68 132	53.27 100	69.50 99	66.65 121	72.40 186	76.36 116

pmmvs4		54.66 162	56.07 173	53.00 138	54.63 168	57.08 210	60.43 145	44.10 108	51.69 126	40.55 141	46.55 162	44.79 219	45.95 150	62.54 189	63.66 175	72.36 187	66.20 192

DTE-MVSNet		48.03 218	53.28 196	41.91 224	54.64 167	57.50 208	44.63 245	51.66 51	41.02 214	7.97 264	46.26 164	40.90 234	20.24 250	60.45 199	62.89 184	72.33 188	63.97 210

UGNet		57.03 136	65.25 100	47.44 187	46.54 219	66.73 107	56.30 172	43.28 142	50.06 131	32.99 177	62.57 66	63.26 101	33.31 225	68.25 121	67.58 100	72.20 189	78.29 75
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
COLMAP_ROB	46.52 15	51.99 179	54.86 184	48.63 173	49.13 208	61.73 156	60.53 144	36.57 220	53.14 113	32.95 178	37.10 228	38.68 244	40.49 178	65.72 172	63.08 181	72.11 190	64.60 207
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CP-MVSNet		48.37 213	53.53 191	42.34 222	51.35 194	58.01 204	46.56 233	50.54 56	41.62 211	10.61 254	46.53 163	40.68 237	23.18 245	58.71 216	61.83 192	71.81 191	67.36 176

0.4-1-1-0.1		50.59 187	53.51 192	47.17 188	46.63 218	58.96 183	54.24 191	36.39 222	43.20 193	33.94 174	44.77 182	49.55 167	40.04 183	57.50 225	56.17 222	71.80 192	64.43 209

pmmvs-eth3d		51.33 183	52.25 214	50.26 156	50.82 201	54.65 216	56.03 175	43.45 140	43.51 191	37.20 160	39.20 223	39.04 243	42.28 171	61.85 194	62.78 186	71.78 193	64.72 206

PS-CasMVS		48.18 215	53.25 197	42.27 223	51.26 195	57.94 206	46.51 234	50.52 57	41.30 212	10.56 255	45.35 178	40.34 239	23.04 246	58.66 217	61.79 193	71.74 194	67.38 174

gm-plane-assit		44.74 233	45.95 241	43.33 218	60.88 110	46.79 248	36.97 259	32.24 247	24.15 262	11.79 253	29.26 249	32.97 256	46.64 145	65.09 179	62.95 183	71.45 195	60.42 229

0.3-1-1-0.015		50.11 195	52.80 202	46.98 191	46.15 222	58.39 193	53.96 193	35.90 225	42.52 203	34.13 170	43.69 193	49.24 169	40.30 180	56.60 233	55.53 228	71.41 196	63.65 213

tfpnnormal		50.16 193	52.19 215	47.78 186	56.86 153	58.37 194	54.15 192	44.01 113	38.35 238	25.94 219	36.10 231	37.89 246	34.50 221	65.93 169	63.42 177	71.26 197	65.28 201

baseline1		54.48 163	58.69 155	49.57 159	60.63 111	58.29 200	55.70 179	44.95 95	49.20 140	29.62 194	54.77 115	54.75 142	35.29 217	67.15 150	64.08 167	71.21 198	62.58 222

gg-mvs-nofinetune		49.07 207	52.56 209	45.00 209	61.99 96	59.78 174	53.55 201	41.63 163	31.62 254	12.08 252	29.56 248	53.28 149	29.57 231	66.27 164	64.49 163	71.19 199	62.92 217

0.4-1-1-0.2		49.99 197	52.69 204	46.83 192	45.99 223	58.16 202	53.71 196	35.75 226	42.13 206	34.14 169	44.08 188	49.28 168	40.24 182	56.44 235	55.24 231	71.18 200	63.49 215

pm-mvs1		51.02 185	55.55 176	45.73 200	54.16 173	58.52 187	50.92 214	42.56 153	40.32 218	25.67 220	43.66 194	50.34 163	30.06 230	65.85 171	63.97 172	70.99 201	66.21 191

TDRefinement		49.31 200	52.44 210	45.67 202	30.44 261	59.42 177	59.24 150	39.78 188	48.76 148	31.20 186	35.73 232	29.90 261	42.81 169	64.24 183	62.59 190	70.55 202	66.43 188

IterMVS		53.45 167	57.12 170	49.17 164	49.23 207	60.93 166	59.05 152	34.63 232	44.53 179	33.22 175	51.09 136	51.01 159	48.38 136	62.43 191	60.79 198	70.54 203	69.05 166
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		51.11 184	53.71 189	48.08 182	44.76 228	55.99 214	53.01 203	40.90 171	52.49 121	36.14 162	44.67 183	33.66 255	43.27 166	63.23 185	61.10 196	70.39 204	64.82 204

dmvs_re		52.07 176	55.11 182	48.54 175	57.27 146	51.93 226	57.73 160	43.13 148	43.65 188	26.57 215	44.52 184	50.00 165	36.53 212	66.58 159	62.15 191	69.97 205	66.91 182

pmmvs6		48.35 214	51.64 217	44.51 212	51.92 190	57.94 206	49.44 220	42.17 157	34.45 247	24.62 225	28.87 252	46.90 197	29.07 234	64.60 181	63.08 181	69.83 206	65.68 198

SixPastTwentyTwo		47.55 221	50.25 227	44.41 214	47.30 216	54.31 218	47.81 226	40.36 183	33.76 248	19.93 236	43.75 192	32.77 257	42.07 172	59.82 203	60.94 197	68.98 207	66.37 190

pmmvs5		47.07 224	51.02 223	42.46 221	45.18 226	51.47 228	48.23 225	33.09 243	38.17 239	28.62 200	46.60 160	43.48 227	30.74 228	58.28 220	58.63 207	68.92 208	60.48 228

Vis-MVSNet (Re-imp)		50.37 191	57.73 167	41.80 225	57.53 136	54.35 217	45.70 238	45.24 91	49.80 133	13.43 249	58.23 100	56.42 135	20.11 251	62.96 187	63.36 178	68.76 209	58.96 234

CDS-MVSNet		52.42 172	57.06 171	47.02 190	53.92 176	58.30 199	55.50 182	46.47 79	42.52 203	29.38 196	49.50 140	52.85 151	28.49 236	66.70 157	66.89 113	68.34 210	62.63 221
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		56.57 142	59.13 152	53.60 131	57.52 137	61.12 162	66.94 96	35.95 224	53.44 109	44.68 117	55.87 109	54.44 143	48.21 137	60.37 200	58.33 208	68.27 211	70.33 152

PMMVS		49.20 206	54.28 188	43.28 219	34.13 255	45.70 251	48.98 221	26.09 258	46.31 169	34.92 168	55.22 112	53.47 147	47.48 143	59.43 206	59.04 206	68.05 212	60.77 227

EPNet_dtu		52.05 177	58.26 160	44.81 210	54.10 174	50.09 233	52.01 212	40.82 173	53.03 115	27.41 208	54.90 113	57.96 130	26.72 238	62.97 186	62.70 188	67.78 213	66.19 193
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		47.08 223	47.56 239	46.52 195	42.35 235	53.44 220	51.77 213	40.70 175	43.44 192	31.92 183	29.78 247	23.72 267	45.04 156	61.99 193	59.54 204	67.35 214	61.03 226

CHOSEN 1792x2688		55.85 148	58.01 162	53.33 133	57.26 147	62.82 147	63.29 134	41.55 165	46.65 166	38.34 152	34.55 236	53.50 146	52.43 106	67.10 151	67.56 101	67.13 215	73.92 136

test-LLR		49.28 201	50.29 225	48.10 181	55.26 163	47.16 243	49.52 218	43.48 138	39.22 225	31.98 181	43.65 195	47.93 179	41.29 176	56.80 229	55.36 229	67.08 216	61.94 223

TESTMET0.1,1		46.09 229	50.29 225	41.18 228	36.91 253	47.16 243	49.52 218	20.32 264	39.22 225	31.98 181	43.65 195	47.93 179	41.29 176	56.80 229	55.36 229	67.08 216	61.94 223

test-mter		45.30 232	50.37 224	39.38 235	33.65 257	46.99 245	47.59 227	18.59 265	38.75 228	28.00 205	43.28 200	46.82 199	41.50 175	57.28 226	55.78 225	66.93 218	63.70 212

FE-MVSNET		39.75 248	44.50 247	34.21 249	32.01 260	48.77 237	37.71 258	38.94 193	30.91 256	6.25 268	26.24 256	32.10 259	23.68 243	57.28 226	59.53 205	66.68 219	56.64 239

PatchMatch-RL		50.11 195	51.56 218	48.43 176	46.23 221	51.94 225	50.21 217	38.62 202	46.62 167	37.51 157	42.43 211	39.38 241	52.24 108	60.98 197	59.56 203	65.76 220	60.01 232

CR-MVSNet		50.47 188	52.61 206	47.98 183	49.03 209	52.94 221	48.27 223	38.86 196	44.41 180	39.59 147	44.34 186	44.65 222	46.63 146	58.97 213	60.31 200	65.48 221	62.66 219

RPMNet		46.41 226	48.72 234	43.72 215	47.77 214	52.94 221	46.02 237	33.92 236	44.41 180	31.82 184	36.89 229	37.42 250	37.41 200	53.88 246	54.02 239	65.37 222	61.47 225

MDTV_nov1_ep13_2view		47.62 220	49.72 231	45.18 206	48.05 211	53.70 219	54.90 188	33.80 238	39.90 223	29.79 193	38.85 225	41.89 230	39.17 185	58.99 212	55.55 227	65.34 223	59.17 233

MDTV_nov1_ep13		50.32 192	52.43 211	47.86 185	49.87 205	54.70 215	58.10 157	34.29 234	45.59 175	37.71 156	47.44 154	47.42 186	41.86 173	58.07 222	55.21 232	65.34 223	58.56 235

MVS-HIRNet		42.24 240	41.15 254	43.51 216	44.06 232	40.74 256	35.77 261	35.35 227	35.38 246	38.34 152	25.63 257	38.55 245	43.48 163	50.77 252	47.03 256	64.07 225	49.98 252

MDA-MVSNet-bldmvs		41.36 241	43.15 252	39.27 236	28.74 263	52.68 223	44.95 243	40.84 172	32.89 250	18.13 240	31.61 242	22.09 268	38.97 188	50.45 255	56.11 223	64.01 226	56.23 241

CVMVSNet		46.38 228	52.01 216	39.81 234	42.40 234	50.26 231	46.15 235	37.68 214	40.03 222	15.09 245	46.56 161	47.56 184	33.72 224	56.50 234	55.65 226	63.80 227	67.53 171

PatchT		48.08 216	51.03 222	44.64 211	42.96 233	50.12 232	40.36 254	35.09 228	43.17 194	39.59 147	42.00 212	39.96 240	46.63 146	58.97 213	60.31 200	63.21 228	62.66 219

baseline		55.19 158	60.88 124	48.55 174	49.87 205	58.10 203	58.70 153	34.75 230	52.82 120	39.48 150	60.18 87	60.86 114	45.41 152	61.05 196	60.74 199	63.10 229	72.41 140

dps		50.42 189	51.20 221	49.51 160	55.88 158	56.07 213	53.73 195	38.89 195	43.66 187	40.36 143	45.66 172	37.63 248	45.23 153	59.05 211	56.18 221	62.94 230	60.16 230

dtuonlycased		45.76 230	49.64 232	41.23 227	39.65 248	57.99 205	55.53 181	26.40 257	40.07 221	17.92 241	28.95 251	49.18 173	45.13 155	53.73 247	52.03 246	62.75 231	65.55 199

SCA		50.99 186	53.22 198	48.40 177	51.07 197	56.78 211	50.25 216	39.05 190	48.31 154	41.38 135	49.54 139	46.70 200	46.00 149	58.31 219	56.28 220	62.65 232	56.60 240

tpm cat1		53.30 168	53.41 194	53.17 137	58.16 128	59.15 182	63.73 131	38.27 204	50.73 129	46.98 99	45.57 174	44.00 226	49.20 129	55.90 240	54.02 239	62.65 232	64.50 208

LTVRE_ROB	44.17 16	47.06 225	50.15 228	43.44 217	51.39 193	58.42 191	42.90 248	43.51 135	22.27 265	14.85 246	41.94 213	34.57 253	45.43 151	62.28 192	62.77 187	62.56 234	68.83 167
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
PM-MVS		44.55 235	48.13 237	40.37 233	32.85 259	46.82 247	46.11 236	29.28 250	40.48 217	29.99 192	39.98 222	34.39 254	41.80 174	56.08 238	53.88 243	62.19 235	65.31 200

usedtu_dtu_shiyan2		36.29 253	39.77 256	32.23 251	19.53 269	48.11 239	41.99 252	36.59 219	23.95 263	12.80 250	22.03 261	32.26 258	20.73 249	50.69 254	50.64 249	61.72 236	50.72 248

EU-MVSNet		40.63 245	45.65 244	34.78 248	39.11 251	46.94 246	40.02 255	34.03 235	33.50 249	10.37 256	35.57 233	37.80 247	23.65 244	51.90 249	50.21 251	61.49 237	63.62 214

PatchmatchNet		49.92 199	51.29 219	48.32 179	51.83 191	51.86 227	53.38 202	37.63 215	47.90 158	40.83 140	48.54 146	45.30 211	45.19 154	56.86 228	53.99 241	61.08 238	54.57 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	37.70 17	49.24 202	52.71 203	45.19 205	45.97 224	51.23 229	47.44 229	29.31 249	43.04 195	44.69 116	34.45 237	48.35 175	43.64 161	62.59 188	59.82 202	60.08 239	69.48 161
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		43.15 238	46.95 240	38.72 237	55.26 163	50.56 230	42.48 249	43.48 138	38.16 240	15.11 244	35.07 234	44.69 221	16.47 254	55.95 239	54.34 238	59.54 240	49.87 254

Anonymous20231206		42.28 239	45.89 242	38.07 239	51.96 189	48.98 235	43.66 247	38.81 198	38.74 229	14.32 247	26.74 254	40.90 234	20.94 248	56.64 232	54.67 236	58.71 241	54.59 242

TAMVS		44.02 236	49.18 233	37.99 240	47.03 217	45.97 250	45.04 241	28.47 252	39.11 227	20.23 235	43.22 201	48.52 174	28.49 236	58.15 221	57.95 210	58.71 241	51.36 246

ambc			45.54 245		50.66 203	52.63 224	40.99 253		38.36 237	24.67 224	22.62 260	13.94 271	29.14 233	65.71 173	58.06 209	58.60 243	67.43 172

pmmvs3		35.10 255	38.47 257	31.17 253	26.37 267	40.47 257	34.51 263	18.09 266	24.75 261	16.88 243	23.05 259	26.69 263	32.69 226	50.73 253	51.60 247	58.46 244	51.98 245

test20.03		40.38 247	44.20 248	35.92 245	53.73 177	49.05 234	38.54 256	43.49 136	32.55 251	9.54 259	27.88 253	39.12 242	12.24 259	56.28 236	54.69 235	57.96 245	49.83 255

MIMVSNet		43.79 237	48.53 235	38.27 238	41.46 243	48.97 236	50.81 215	32.88 245	44.55 178	22.07 229	32.05 240	47.15 189	24.76 241	58.73 215	56.09 224	57.63 246	52.14 244

tpmrst		48.08 216	49.88 230	45.98 198	52.71 182	48.11 239	53.62 200	33.70 239	48.70 150	39.74 145	48.96 144	46.23 204	40.29 181	50.14 256	49.28 252	55.80 247	57.71 237

dtuonly		47.41 222	53.02 201	40.88 230	39.20 250	46.62 249	54.26 190	25.80 259	44.41 180	26.35 217	45.20 180	53.69 145	44.32 159	60.37 200	57.56 212	55.34 248	63.26 216

FPMVS		38.36 251	40.41 255	35.97 244	38.92 252	39.85 259	45.50 239	25.79 260	41.13 213	18.70 238	30.10 245	24.56 265	31.86 227	49.42 258	46.80 257	55.04 249	51.03 247

FMVSNet5		40.96 242	45.81 243	35.29 247	34.30 254	44.55 254	47.28 230	28.84 251	40.76 215	21.62 230	29.85 246	42.44 228	24.77 240	57.53 224	55.00 233	54.93 250	50.56 250

tpm		48.82 211	51.27 220	45.96 199	54.10 174	47.35 242	56.05 174	30.23 248	46.70 165	43.21 123	52.54 126	47.55 185	37.28 202	54.11 245	50.50 250	54.90 251	60.12 231

PMVS	27.84 18	33.81 256	35.28 261	32.09 252	34.13 255	24.81 267	32.51 264	26.48 256	26.41 259	19.37 237	23.76 258	24.02 266	25.18 239	50.78 251	47.24 255	54.89 252	49.95 253
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testgi		38.71 250	43.64 250	32.95 250	52.30 188	48.63 238	35.59 262	35.05 229	31.58 255	9.03 262	30.29 244	40.75 236	11.19 265	55.30 241	53.47 244	54.53 253	45.48 258

GG-mvs-BLEND		36.62 252	53.39 195	17.06 262	0.01 275	58.61 186	48.63 222	0.01 272	47.13 163	0.02 277	43.98 189	60.64 117	0.03 271	54.92 244	51.47 248	53.64 254	56.99 238

MIMVSNet1		35.51 254	41.41 253	28.63 255	27.53 265	43.36 255	38.09 257	33.82 237	32.01 252	6.77 266	21.63 262	35.43 252	11.97 261	55.05 243	53.99 241	53.59 255	48.36 257

EPMVS		44.66 234	47.86 238	40.92 229	47.97 212	44.70 253	47.58 228	33.27 241	48.11 157	29.58 195	49.65 138	44.38 224	34.65 219	51.71 250	47.90 254	52.49 256	48.57 256

RPSCF		46.41 226	54.42 186	37.06 242	25.70 268	45.14 252	45.39 240	20.81 263	62.79 64	35.10 165	44.92 181	55.60 141	43.56 162	56.12 237	52.45 245	51.80 257	63.91 211

IterMVS-SCA-FT		52.18 175	57.75 166	45.68 201	51.01 199	62.06 153	55.10 187	34.75 230	44.85 177	32.86 179	51.13 135	51.22 156	48.74 130	62.47 190	61.51 194	51.61 258	71.02 146

pmnet_mix02		40.48 246	43.80 249	36.61 243	45.79 225	40.45 258	42.12 250	33.18 242	40.30 219	24.11 228	38.76 226	37.11 251	24.30 242	52.97 248	46.66 258	50.17 259	50.33 251

FC-MVSNet-test		39.65 249	48.35 236	29.49 254	44.43 229	39.28 262	30.23 265	40.44 181	43.59 189	3.12 272	53.00 122	42.03 229	10.02 267	55.09 242	54.77 234	48.66 260	50.71 249

CHOSEN 280x420		40.80 243	45.05 246	35.84 246	32.95 258	29.57 265	44.98 242	23.71 262	37.54 241	18.42 239	31.36 243	47.07 191	46.41 148	56.71 231	54.65 237	48.55 261	58.47 236

ADS-MVSNet		40.67 244	43.38 251	37.50 241	44.36 230	39.79 260	42.09 251	32.67 246	44.34 183	28.87 199	40.76 217	40.37 238	30.22 229	48.34 261	45.87 259	46.81 262	44.21 260

new-patchmatchnet		33.24 257	37.20 258	28.62 256	44.32 231	38.26 263	29.68 266	36.05 223	31.97 253	6.33 267	26.59 255	27.33 262	11.12 266	50.08 257	41.05 262	44.23 263	45.15 259

Gipuma		25.87 260	26.91 263	24.66 258	28.98 262	20.17 268	20.46 267	34.62 233	29.55 257	9.10 260	4.91 271	5.31 275	15.76 256	49.37 259	49.10 253	39.03 264	29.95 264
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
N_pmnet		32.67 258	36.85 259	27.79 257	40.55 245	32.13 264	35.80 260	26.79 255	37.24 242	9.10 260	32.02 241	30.94 260	16.30 255	47.22 262	41.21 261	38.21 265	37.21 261

new_pmnet		23.19 261	28.17 262	17.37 260	17.03 270	24.92 266	19.66 268	16.16 268	27.05 258	4.42 269	20.77 263	19.20 270	12.19 260	37.71 263	36.38 263	34.77 266	31.17 263

WB-MVS		29.70 259	35.40 260	23.05 259	40.96 244	39.59 261	18.79 269	40.20 184	25.26 260	1.88 275	33.33 238	21.97 269	3.36 268	48.69 260	44.60 260	33.11 267	34.39 262

E-PMN		15.09 263	13.19 267	17.30 261	27.80 264	12.62 271	7.81 273	27.54 253	14.62 269	3.19 270	6.89 268	2.52 278	15.09 257	15.93 267	20.22 266	22.38 268	19.53 267

EMVS		14.49 264	12.45 268	16.87 263	27.02 266	12.56 272	8.13 272	27.19 254	15.05 268	3.14 271	6.69 269	2.67 277	15.08 258	14.60 269	18.05 267	20.67 269	17.56 269

test_method		12.44 266	14.66 266	9.85 266	1.30 274	3.32 274	13.00 271	3.21 269	22.42 264	10.22 257	14.13 264	25.64 264	11.43 264	19.75 266	11.61 269	19.96 270	5.79 270

PMMVS2		15.84 262	19.68 264	11.35 264	15.74 271	16.95 269	13.31 270	17.64 267	16.08 267	0.36 276	13.12 265	11.47 272	1.69 270	28.82 264	27.24 265	19.38 271	24.09 266

MVE	12.28 19	13.53 265	15.72 265	10.96 265	7.39 272	15.71 270	6.05 274	23.73 261	10.29 271	3.01 273	5.77 270	3.41 276	11.91 262	20.11 265	29.79 264	13.67 272	24.98 265
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 267	3.97 273	2.35 275	3.26 276	0.44 271	17.56 266	12.09 251	11.48 267	7.14 273	1.98 269	15.68 268	15.49 268	10.69 273

DeepMVS_CX						6.95 273	5.98 275	2.25 270	11.73 270	2.07 274	11.85 266	5.43 274	11.75 263	11.40 270		8.10 274	18.38 268

uanet_test		0.00 269	0.00 271	0.00 268	0.00 276	0.00 276	0.00 279	0.00 273	0.00 274	0.00 278	0.00 274	0.00 279	0.00 274	0.00 272	0.00 272	0.00 275	0.00 273

sosnet-low-res		0.00 269	0.00 271	0.00 268	0.00 276	0.00 276	0.00 279	0.00 273	0.00 274	0.00 278	0.00 274	0.00 279	0.00 274	0.00 272	0.00 272	0.00 275	0.00 273

sosnet		0.00 269	0.00 271	0.00 268	0.00 276	0.00 276	0.00 279	0.00 273	0.00 274	0.00 278	0.00 274	0.00 279	0.00 274	0.00 272	0.00 272	0.00 275	0.00 273

testmvs		0.01 267	0.02 269	0.00 268	0.00 276	0.00 276	0.01 278	0.00 273	0.01 272	0.00 278	0.03 273	0.00 279	0.01 272	0.01 271	0.01 270	0.00 275	0.06 272

test123		0.01 267	0.02 269	0.00 268	0.00 276	0.00 276	0.00 279	0.00 273	0.01 272	0.00 278	0.04 272	0.00 279	0.01 272	0.00 272	0.01 270	0.00 275	0.07 271

RE-MVS-def										33.01 176

9.14												81.81 15

SR-MVS					71.46 36			54.67 31				81.54 16

our_test_3					51.15 196	57.31 209	55.12 186

MTAPA										65.14 4		80.20 22

MTMP										62.63 17		78.04 29

Patchmatch-RL test							1.04 277

mPP-MVS					71.67 35							74.36 43

NP-MVS									72.00 44

Patchmtry						47.61 241	48.27 223	38.86 196		39.59 147

High-resolution multi-view benchmark