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 15	79.22 15	69.40 18	75.69 12	80.01 9	79.12 24	52.83 42	79.34 18	63.99 10	70.49 25	82.02 11	60.35 31	77.48 24	77.22 19	84.38 1	87.97 14

MCST-MVS		73.67 25	77.39 25	69.33 19	76.26 9	78.19 17	78.77 26	54.54 31	75.33 28	59.99 25	67.96 32	79.23 22	62.43 17	78.00 18	75.71 29	84.02 2	87.30 19

SteuartSystems-ACMMP		75.23 12	79.60 14	70.13 13	76.81 7	78.92 12	81.74 8	57.99 5	75.30 30	59.83 26	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 9
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		77.32 6	82.51 6	71.26 7	75.43 14	80.19 8	82.22 7	58.26 3	84.83 6	64.36 8	78.19 15	83.46 5	63.61 7	81.00 1	80.28 1	83.66 4	89.62 5
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DeepC-MVS	66.32 2	73.85 23	78.10 22	68.90 23	67.92 50	79.31 11	78.16 29	59.28 1	78.24 22	61.13 20	67.36 36	76.10 33	63.40 8	79.11 8	78.41 10	83.52 5	88.16 12
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 5	82.93 5	71.35 6	77.86 5	80.55 6	83.38 1	57.61 9	85.57 4	61.11 21	86.10 6	82.98 7	64.76 3	78.29 14	76.78 22	83.40 6	90.20 4

xxxxxxxxxxxxxcwj		74.63 16	77.07 27	71.79 2	79.32 1	80.76 4	82.96 2	57.49 10	82.82 8	64.79 5	83.69 9	52.03 118	62.83 13	77.13 26	75.21 31	83.35 7	87.85 15

SF-MVS		77.13 7	81.70 7	71.79 2	79.32 1	80.76 4	82.96 2	57.49 10	82.82 8	64.79 5	83.69 9	84.46 4	62.83 13	77.13 26	75.21 31	83.35 7	87.85 15

CNVR-MVS		75.62 11	79.91 13	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 17	63.04 14	70.69 24	81.15 15	62.99 10	80.23 4	79.54 3	83.11 9	89.16 7

HFP-MVS		74.87 14	78.86 19	70.21 12	73.99 21	77.91 18	80.36 16	56.63 16	78.41 20	64.27 9	74.54 20	77.75 28	62.96 11	78.70 11	77.82 12	83.02 10	86.91 21

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 23	80.51 15	57.09 14	78.25 21	62.28 18	65.54 37	78.26 25	62.18 19	79.13 7	78.51 9	83.01 11	87.68 17

ACMMP_NAP		76.15 8	81.17 8	70.30 11	74.09 20	79.47 10	81.59 12	57.09 14	81.38 11	63.89 11	79.02 13	80.48 18	62.24 18	80.05 5	79.12 4	82.94 12	88.64 8

ACMP	61.42 5	68.72 43	71.37 44	65.64 38	69.06 45	74.45 42	75.88 38	53.30 38	68.10 50	55.74 38	61.53 56	62.29 74	56.97 50	74.70 45	74.23 42	82.88 13	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		68.87 40	72.03 42	65.18 40	69.33 44	74.03 45	76.67 34	53.88 36	68.46 49	52.05 59	63.21 45	63.89 67	56.31 55	75.99 37	74.43 40	82.83 14	84.18 36

ACMMP		71.57 31	75.84 31	66.59 31	70.30 40	76.85 29	78.46 28	53.95 35	73.52 36	55.56 39	70.13 26	71.36 48	58.55 38	77.00 28	76.23 26	82.71 15	85.81 28
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 24	78.41 20	68.40 25	72.35 28	77.79 19	79.32 21	56.38 19	77.67 24	58.30 32	74.16 21	76.66 29	61.40 23	78.32 13	77.80 13	82.68 16	86.51 22

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 3	81.96 2	82.94 5	58.16 4	86.82 2	67.66 1	88.29 4	86.15 2	66.42 1	80.41 3	78.65 6	82.65 17	90.92 2

CDPH-MVS		71.47 32	75.82 32	66.41 32	72.97 26	77.15 25	78.14 30	54.71 28	69.88 48	53.07 56	70.98 23	74.83 37	56.95 51	76.22 34	76.57 24	82.62 18	85.09 34

DPM-MVS		72.80 27	75.90 30	69.19 21	75.51 13	77.68 20	81.62 11	54.83 27	75.96 26	62.06 19	63.96 43	76.58 30	58.55 38	76.66 33	76.77 23	82.60 19	83.68 42

PGM-MVS		72.89 26	77.13 26	67.94 26	72.47 27	77.25 24	79.27 22	54.63 30	73.71 35	57.95 34	72.38 22	75.33 35	60.75 27	78.25 15	77.36 18	82.57 20	85.62 29

SD-MVS		74.43 17	78.87 17	69.26 20	74.39 19	73.70 46	79.06 25	55.24 26	81.04 12	62.71 15	80.18 12	82.61 9	61.70 22	75.43 41	73.92 44	82.44 21	85.22 32
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 4	82.05 1	81.64 10	57.96 6	87.53 1	66.64 2	88.77 1	86.31 1	63.16 9	79.99 6	78.56 7	82.31 22	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 3	83.84 3	71.42 5	77.82 6	81.32 3	82.92 6	57.81 8	84.04 7	63.19 13	88.63 2	86.00 3	64.52 4	78.71 10	77.63 15	82.26 23	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 38	76.96 26	74.36 45			54.48 49		74.47 38				82.24 24

X-MVStestdata					70.49 38	76.96 26	74.36 45			54.48 49		74.47 38				82.24 24

X-MVS		71.18 33	75.66 33	65.96 36	71.71 30	76.96 26	77.26 33	55.88 23	72.75 38	54.48 49	64.39 41	74.47 38	54.19 65	77.84 20	77.37 17	82.21 26	85.85 27

OPM-MVS		69.33 38	71.05 46	67.32 28	72.34 29	75.70 33	79.57 20	56.34 20	55.21 71	53.81 54	59.51 61	68.96 54	59.67 33	77.61 23	76.44 25	82.19 27	83.88 40

MP-MVS		74.31 18	78.87 17	68.99 22	73.49 23	78.56 15	79.25 23	56.51 17	75.33 28	60.69 23	75.30 19	79.12 23	61.81 21	77.78 21	77.93 11	82.18 28	88.06 13
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 30	76.11 29	67.21 29	68.93 46	77.46 21	76.54 35	54.35 32	74.92 32	58.64 31	65.18 38	74.04 43	62.62 15	77.92 19	77.02 21	82.16 29	86.21 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		74.25 20	77.97 23	69.91 15	73.43 24	74.06 44	79.69 19	56.44 18	80.74 14	64.98 4	68.72 30	79.98 20	62.92 12	78.24 16	77.77 14	81.99 30	86.30 23

ACMM	60.30 7	67.58 48	68.82 57	66.13 34	70.59 37	72.01 54	76.54 35	54.26 33	65.64 54	54.78 47	50.35 103	61.72 78	58.74 36	75.79 39	75.03 34	81.88 31	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS++		76.01 9	80.47 11	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 12	78.80 14	82.53 10	64.40 5	78.74 9	78.84 5	81.81 32	87.46 18

HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 39	72.89 37	54.88 45	70.03 27	70.48 50	57.26 47	76.02 36	75.01 36	81.78 33	86.21 24

TSAR-MVS + MP.		75.22 13	80.06 12	69.56 17	74.61 18	72.74 50	80.59 14	55.70 24	80.80 13	62.65 16	86.25 5	82.92 8	62.07 20	76.89 29	75.66 30	81.77 34	85.19 33
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 22	78.25 21	68.80 24	75.25 17	72.27 52	79.75 18	56.05 21	74.87 33	58.97 28	81.83 11	79.76 21	61.05 26	77.39 25	76.01 28	81.71 35	85.61 30

CP-MVS		72.63 28	76.95 28	67.59 27	70.67 36	75.53 34	77.95 31	56.01 22	75.65 27	58.82 29	69.16 29	76.48 31	60.46 30	77.66 22	77.20 20	81.65 36	86.97 20

MVS_0304		69.49 37	73.96 36	64.28 46	67.92 50	76.13 32	74.90 42	47.60 67	63.29 58	54.09 53	67.44 35	76.35 32	59.53 34	75.81 38	75.03 34	81.62 37	83.70 41

APD-MVS		75.80 10	80.90 10	69.86 16	75.42 15	78.48 16	81.43 13	57.44 12	80.45 15	59.32 27	85.28 7	80.82 17	63.96 6	76.89 29	76.08 27	81.58 38	88.30 11
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
abl_6				64.36 45	70.08 41	77.45 22	72.88 50	50.15 57	71.31 43	54.77 48	62.79 48	77.99 27	56.80 52			81.50 39	83.91 39

CS-MVS		63.45 59	65.72 68	60.80 53	64.20 69	67.86 71	68.46 61	43.50 115	53.86 75	49.90 64	56.44 72	60.45 85	57.27 46	73.56 50	70.13 63	81.45 40	77.73 70

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 49	66.63 55	74.52 39	71.56 54	45.76 75	67.37 52	55.00 44	54.31 86	68.19 58	58.49 40	73.97 48	73.63 47	81.22 41	80.23 55

3Dnovator+	62.63 4	69.51 36	72.62 40	65.88 37	68.21 49	76.47 30	73.50 49	52.74 43	70.85 44	58.65 30	55.97 75	69.95 51	61.11 25	76.80 31	75.09 33	81.09 42	83.23 45

test_part1		63.06 62	65.27 71	60.47 55	66.24 60	70.17 59	71.86 52	45.36 81	53.75 76	49.61 65	44.85 145	65.53 65	48.93 99	71.39 60	70.65 56	80.82 43	80.59 53

CANet		68.77 41	73.01 38	63.83 47	68.30 47	75.19 35	73.73 48	47.90 66	63.86 55	54.84 46	67.51 34	74.36 41	57.62 42	74.22 47	73.57 48	80.56 44	82.36 46

ETV-MVS		63.23 61	66.08 65	59.91 59	63.13 77	68.13 68	67.62 63	44.62 89	53.39 79	46.23 78	58.74 63	58.19 93	57.45 44	73.60 49	71.38 54	80.39 45	79.13 59

MSP-MVS		77.82 4	83.46 4	71.24 8	75.26 16	80.22 7	82.95 4	57.85 7	85.90 3	64.79 5	88.54 3	83.43 6	66.24 2	78.21 17	78.56 7	80.34 46	89.39 6
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 35	73.92 37	64.80 43	68.27 48	70.56 57	71.90 51	50.75 52	71.38 42	57.46 36	68.68 31	75.42 34	60.10 32	73.47 51	73.99 43	80.32 47	83.97 38

MVS_111021_HR		67.62 47	70.39 50	64.39 44	69.77 42	70.45 58	71.44 55	51.72 48	60.77 64	55.06 43	62.14 53	66.40 63	58.13 41	76.13 35	74.79 38	80.19 48	82.04 49

DeepPCF-MVS	66.49 1	74.25 20	80.97 9	66.41 32	67.75 52	78.87 13	75.61 39	54.16 34	84.86 5	58.22 33	77.94 16	81.01 16	62.52 16	78.34 12	77.38 16	80.16 49	88.40 10

EIA-MVS		61.53 73	63.79 81	58.89 65	63.82 75	67.61 76	65.35 87	42.15 133	49.98 97	45.66 81	57.47 70	56.62 100	56.59 54	70.91 66	69.15 68	79.78 50	74.80 95

MAR-MVS		68.04 45	70.74 48	64.90 42	71.68 32	76.33 31	74.63 44	50.48 56	63.81 56	55.52 40	54.88 81	69.90 52	57.39 45	75.42 42	74.79 38	79.71 51	80.03 56
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 44	70.72 49	65.19 39	69.41 43	70.64 56	74.99 41	45.76 75	70.20 47	60.17 24	56.42 73	73.01 44	61.14 24	72.80 54	70.54 58	79.70 52	81.42 51

DELS-MVS		65.87 52	70.30 52	60.71 54	64.05 73	72.68 51	70.90 56	45.43 79	57.49 67	49.05 69	64.43 40	68.66 55	55.11 63	74.31 46	73.02 49	79.70 52	81.51 50
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 46	68.85 56	66.77 30	73.73 22	74.30 43	75.28 40	53.58 37	70.24 46	57.59 35	51.19 100	59.19 90	60.74 28	75.33 43	73.72 46	79.69 54	77.96 68

Effi-MVS+		63.28 60	65.96 66	60.17 57	64.26 68	68.06 69	68.78 59	45.71 77	54.08 74	46.64 76	55.92 76	63.13 71	55.94 59	70.38 71	71.43 52	79.68 55	78.70 62

PVSNet_Blended_VisFu		63.65 58	66.92 59	59.83 60	60.03 90	73.44 48	66.33 75	48.95 63	52.20 89	50.81 61	56.07 74	60.25 86	53.56 71	73.23 53	70.01 64	79.30 56	83.24 44

GeoE		62.43 67	64.79 76	59.68 61	64.15 72	67.17 82	68.80 58	44.42 93	55.65 70	47.38 71	51.54 97	62.51 72	54.04 68	69.99 74	68.07 79	79.28 57	78.57 63

EPP-MVSNet		59.39 79	65.45 70	52.32 113	60.96 85	67.70 74	58.42 121	44.75 87	49.71 99	27.23 166	59.03 62	62.20 75	43.34 130	70.71 67	69.13 69	79.25 58	79.63 58

CPTT-MVS		68.76 42	73.01 38	63.81 48	65.42 62	73.66 47	76.39 37	52.08 44	72.61 39	50.33 62	60.73 57	72.65 46	59.43 35	73.32 52	72.12 50	79.19 59	85.99 26

Fast-Effi-MVS+		60.36 75	63.35 82	56.87 82	58.70 95	65.86 94	65.08 89	37.11 168	53.00 84	45.36 83	52.12 94	56.07 105	56.27 56	71.28 63	69.42 66	78.71 60	75.69 90

PCF-MVS	59.98 8	67.32 49	71.04 47	62.97 50	64.77 64	74.49 40	74.78 43	49.54 59	67.44 51	54.39 52	58.35 66	72.81 45	55.79 61	71.54 59	69.24 67	78.57 61	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		64.09 57	68.13 58	59.37 63	61.81 79	68.32 67	68.48 60	44.45 92	61.95 61	49.12 68	63.04 46	69.67 53	53.83 69	70.46 68	66.06 111	78.55 62	77.43 71

UniMVSNet_NR-MVSNet		56.94 106	61.14 89	52.05 115	60.02 91	65.21 102	57.44 125	52.93 41	49.37 103	24.31 176	54.62 85	50.54 125	39.04 148	68.69 83	68.84 72	78.53 63	70.72 114

canonicalmvs		65.62 53	72.06 41	58.11 68	63.94 74	71.05 55	64.49 93	43.18 123	74.08 34	47.35 72	64.17 42	71.97 47	51.17 92	71.87 57	70.74 55	78.51 64	80.56 54

IS_MVSNet		57.95 98	64.26 79	50.60 118	61.62 82	65.25 101	57.18 127	45.42 80	50.79 93	26.49 169	57.81 68	60.05 87	34.51 169	71.24 64	70.20 62	78.36 65	74.44 97

PHI-MVS		69.27 39	74.84 35	62.76 51	66.83 54	74.83 37	73.88 47	49.32 61	70.61 45	50.93 60	69.62 28	74.84 36	57.25 48	75.53 40	74.32 41	78.35 66	84.17 37

EG-PatchMatch MVS		56.98 104	58.24 125	55.50 90	64.66 65	68.62 64	61.48 104	43.63 110	38.44 187	41.44 101	38.05 177	46.18 155	43.95 126	71.71 58	70.61 57	77.87 67	74.08 101

OpenMVS	57.13 9	62.81 64	65.75 67	59.39 62	66.47 57	69.52 61	64.26 95	43.07 125	61.34 63	50.19 63	47.29 120	64.41 66	54.60 64	70.18 73	68.62 75	77.73 68	78.89 61

NR-MVSNet		55.35 119	59.46 113	50.56 119	61.33 83	62.97 113	57.91 124	51.80 46	48.62 117	20.59 182	51.99 95	44.73 170	34.10 172	68.58 86	68.64 74	77.66 69	70.67 118

QAPM		65.27 54	69.49 55	60.35 56	65.43 61	72.20 53	65.69 84	47.23 68	63.46 57	49.14 67	53.56 87	71.04 49	57.01 49	72.60 55	71.41 53	77.62 70	82.14 48

IB-MVS	54.11 11	58.36 93	60.70 93	55.62 89	58.67 96	68.02 70	61.56 102	43.15 124	46.09 134	44.06 89	44.24 148	50.99 124	48.71 102	66.70 122	70.33 59	77.60 71	78.50 64
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 80	60.28 98	58.06 69	64.17 71	68.46 65	67.51 65	50.93 51	52.46 88	35.83 130	40.83 170	45.12 164	52.32 85	69.88 75	69.00 71	77.59 72	76.21 86

TranMVSNet+NR-MVSNet		55.87 113	60.14 103	50.88 117	59.46 94	63.82 109	57.93 123	52.98 40	48.94 109	20.52 183	52.87 89	47.33 142	36.81 162	69.12 81	69.03 70	77.56 73	69.89 120

MSDG		58.46 90	58.97 118	57.85 76	66.27 59	66.23 92	67.72 62	42.33 129	53.43 78	43.68 90	43.39 156	45.35 160	49.75 96	68.66 85	67.77 84	77.38 74	67.96 136

Effi-MVS+-dtu		60.34 76	62.32 85	58.03 71	64.31 66	67.44 79	65.99 79	42.26 130	49.55 100	42.00 100	48.92 110	59.79 88	56.27 56	68.07 98	67.03 92	77.35 75	75.45 92

ET-MVSNet_ETH3D		58.38 92	61.57 87	54.67 94	42.15 194	65.26 99	65.70 82	43.82 103	48.84 110	42.34 97	59.76 60	47.76 136	56.68 53	67.02 119	68.60 76	77.33 76	73.73 104

DI_MVS_plusplus_trai		61.88 69	65.17 73	58.06 69	60.05 89	65.26 99	66.03 78	44.22 94	55.75 69	46.73 74	54.64 84	68.12 59	54.13 67	69.13 80	66.66 100	77.18 77	76.61 79

v1144		58.88 83	60.16 102	57.39 78	58.03 100	67.26 80	67.14 68	44.46 91	45.17 140	44.33 88	47.81 117	49.92 129	53.20 80	67.77 104	66.62 103	77.15 78	76.58 80

v1192		58.51 87	59.66 108	57.17 79	57.82 102	67.72 73	66.21 77	44.83 86	44.15 148	43.49 91	46.68 122	47.94 133	53.55 72	67.39 111	66.51 105	77.13 79	77.20 74

UniMVSNet (Re)		55.15 123	60.39 97	49.03 132	55.31 126	64.59 106	55.77 140	50.63 53	48.66 116	20.95 181	51.47 98	50.40 126	34.41 171	67.81 103	67.89 81	77.11 80	71.88 108

v10		59.17 82	60.60 94	57.50 77	57.95 101	66.73 86	67.09 70	44.11 95	46.85 128	45.42 82	48.18 116	51.07 121	53.63 70	67.84 102	66.59 104	76.79 81	76.92 76

MVS_Test		62.40 68	66.23 64	57.94 72	59.77 93	64.77 105	66.50 74	41.76 134	57.26 68	49.33 66	62.68 50	67.47 62	53.50 74	68.57 87	66.25 108	76.77 82	76.58 80

v144192		58.23 96	59.40 114	56.87 82	57.56 103	66.89 84	65.70 82	45.01 84	44.06 149	42.88 93	46.61 124	48.09 132	53.49 75	66.94 120	65.90 115	76.61 83	77.29 72

v2v482		58.69 86	60.12 105	57.03 80	57.16 118	66.05 93	67.17 67	43.52 113	46.33 132	45.19 84	49.46 107	51.02 122	52.51 83	67.30 112	66.03 112	76.61 83	74.62 96

ACMH	52.42 13	58.24 95	59.56 112	56.70 84	66.34 58	69.59 60	66.71 72	49.12 62	46.08 135	28.90 158	42.67 165	41.20 182	52.60 82	71.39 60	70.28 60	76.51 85	75.72 89
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PVSNet_BlendedMVS		61.63 71	64.82 74	57.91 74	57.21 116	67.55 77	63.47 99	46.08 73	54.72 72	52.46 57	58.59 64	60.73 81	51.82 90	70.46 68	65.20 125	76.44 86	76.50 83

PVSNet_Blended		61.63 71	64.82 74	57.91 74	57.21 116	67.55 77	63.47 99	46.08 73	54.72 72	52.46 57	58.59 64	60.73 81	51.82 90	70.46 68	65.20 125	76.44 86	76.50 83

v1921920		57.89 99	59.02 117	56.58 85	57.55 104	66.66 90	64.72 92	44.70 88	43.55 152	42.73 94	46.17 132	46.93 146	53.51 73	66.78 121	65.75 117	76.29 88	77.28 73

EPNet		65.14 56	69.54 54	60.00 58	66.61 56	67.67 75	67.53 64	55.32 25	62.67 60	46.22 79	67.74 33	65.93 64	48.07 108	72.17 56	72.12 50	76.28 89	78.47 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v8		58.88 83	60.57 96	56.92 81	57.35 111	65.69 96	66.69 73	42.64 127	47.89 123	45.77 80	49.04 108	52.98 114	52.77 81	67.51 109	65.57 118	76.26 90	75.30 94

DCV-MVSNet		59.49 78	64.00 80	54.23 95	61.81 79	64.33 107	61.42 105	43.77 104	52.85 85	38.94 118	55.62 78	62.15 76	43.24 133	69.39 78	67.66 87	76.22 91	75.97 87

v1240		57.55 101	58.63 121	56.29 86	57.30 114	66.48 91	63.77 97	44.56 90	42.77 162	42.48 96	45.64 138	46.28 153	53.46 76	66.32 127	65.80 116	76.16 92	77.13 75

CLD-MVS		67.02 50	71.57 43	61.71 52	71.01 35	74.81 38	71.62 53	38.91 155	71.86 41	60.70 22	64.97 39	67.88 61	51.88 89	76.77 32	74.98 37	76.11 93	69.75 121
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v7n		55.67 115	57.46 133	53.59 101	56.06 122	65.29 98	61.06 108	43.26 122	40.17 178	37.99 122	40.79 171	45.27 163	47.09 112	67.67 106	66.21 109	76.08 94	76.82 77

OMC-MVS		65.16 55	71.35 45	57.94 72	52.95 144	68.82 63	69.00 57	38.28 162	79.89 16	55.20 42	62.76 49	68.31 57	56.14 58	71.30 62	68.70 73	76.06 95	79.67 57

DU-MVS		55.41 118	59.59 109	50.54 120	54.60 132	62.97 113	57.44 125	51.80 46	48.62 117	24.31 176	51.99 95	47.00 145	39.04 148	68.11 96	67.75 85	76.03 96	70.72 114

FC-MVSNet-train		58.40 91	63.15 83	52.85 109	64.29 67	61.84 119	55.98 139	46.47 71	53.06 82	34.96 133	61.95 55	56.37 103	39.49 146	68.67 84	68.36 77	75.92 97	71.81 109

Anonymous20231211		57.71 100	60.79 92	54.13 97	61.68 81	65.81 95	60.81 110	43.70 108	51.97 90	39.67 113	34.82 185	63.59 68	43.31 131	68.55 88	66.63 102	75.59 98	74.13 100

MVSTER		57.19 102	61.11 90	52.62 111	50.82 164	58.79 146	61.55 103	37.86 165	48.81 112	41.31 103	57.43 71	52.10 117	48.60 103	68.19 95	66.75 98	75.56 99	75.68 91

Anonymous202405211			60.60 94		63.44 76	66.71 89	61.00 109	47.23 68	50.62 95		36.85 180	60.63 84	43.03 134	69.17 79	67.72 86	75.41 100	72.54 106

thisisatest0530		56.68 108	59.68 107	53.19 105	52.97 143	60.96 129	59.41 116	40.51 145	48.26 120	41.06 106	52.67 90	46.30 152	49.78 94	67.66 107	67.83 82	75.39 101	74.07 102

Fast-Effi-MVS+-dtu		56.30 111	59.29 115	52.82 110	58.64 97	64.89 103	65.56 85	32.89 191	45.80 137	35.04 132	45.89 135	54.14 110	49.41 97	67.16 115	66.45 107	75.37 102	70.69 116

TSAR-MVS + ACMM		72.56 29	79.07 16	64.96 41	73.24 25	73.16 49	78.50 27	48.80 65	79.34 18	55.32 41	85.04 8	81.49 14	58.57 37	75.06 44	73.75 45	75.35 103	85.61 30

tttt0517		56.53 110	59.59 109	52.95 108	52.66 146	60.99 128	59.21 118	40.51 145	47.89 123	40.40 109	52.50 93	46.04 156	49.78 94	67.75 105	67.83 82	75.15 104	74.17 99

LS3D		60.20 77	61.70 86	58.45 67	64.18 70	67.77 72	67.19 66	48.84 64	61.67 62	41.27 104	45.89 135	51.81 119	54.18 66	68.78 82	66.50 106	75.03 105	69.48 127

baseline2		55.89 112	57.82 128	53.64 99	57.36 110	61.09 127	59.75 114	40.45 147	47.38 126	41.26 105	51.23 99	46.90 147	48.11 106	65.63 137	64.38 134	74.90 106	68.16 135

HyFIR lowres test		56.87 107	58.60 122	54.84 92	56.62 121	69.27 62	64.77 91	42.21 131	45.66 138	37.50 125	33.08 188	57.47 98	53.33 77	65.46 139	67.94 80	74.60 107	71.35 111

PLC	52.09 14	59.21 81	62.47 84	55.41 91	53.24 142	64.84 104	64.47 94	40.41 149	65.92 53	44.53 87	46.19 131	55.69 106	55.33 62	68.24 93	65.30 122	74.50 108	71.09 112
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GA-MVS		55.67 115	58.33 123	52.58 112	55.23 129	63.09 112	61.08 107	40.15 151	42.95 157	37.02 128	52.61 91	47.68 137	47.51 110	65.92 133	65.35 120	74.49 109	70.68 117

MVS_111021_LR		63.05 63	66.43 62	59.10 64	61.33 83	63.77 110	65.87 81	43.58 111	60.20 65	53.70 55	62.09 54	62.38 73	55.84 60	70.24 72	68.08 78	74.30 110	78.28 67

anonymousdsp		52.84 133	57.78 129	47.06 152	40.24 197	58.95 145	53.70 154	33.54 187	36.51 194	32.69 140	43.88 150	45.40 159	47.97 109	67.17 114	70.28 60	74.22 111	82.29 47

CANet_DTU		58.88 83	64.68 77	52.12 114	55.77 124	66.75 85	63.92 96	37.04 169	53.32 80	37.45 126	59.81 59	61.81 77	44.43 125	68.25 91	67.47 90	74.12 112	75.33 93

UA-Net		58.50 88	64.68 77	51.30 116	66.97 53	67.13 83	53.68 155	45.65 78	49.51 102	31.58 145	62.91 47	68.47 56	35.85 165	68.20 94	67.28 91	74.03 113	69.24 131

WR-MVS		48.78 163	55.06 145	41.45 178	55.50 125	60.40 132	43.77 193	49.99 58	41.92 166	8.10 209	45.24 143	45.56 158	17.47 198	61.57 156	64.60 130	73.85 114	66.14 149

v148		55.58 117	57.61 132	53.20 104	54.59 134	61.86 118	61.18 106	38.70 160	44.30 147	42.25 98	47.53 118	50.24 128	48.73 101	65.15 141	62.61 151	73.79 115	71.61 110

PEN-MVS		49.21 159	54.32 149	43.24 172	54.33 135	59.26 142	47.04 179	51.37 50	41.67 168	9.97 204	46.22 130	41.80 181	22.97 194	60.52 159	64.03 136	73.73 116	66.75 141

GBi-Net		55.20 120	60.25 99	49.31 126	52.42 147	61.44 121	57.03 128	44.04 98	49.18 106	30.47 147	48.28 112	58.19 93	38.22 151	68.05 99	66.96 93	73.69 117	69.65 122

test1		55.20 120	60.25 99	49.31 126	52.42 147	61.44 121	57.03 128	44.04 98	49.18 106	30.47 147	48.28 112	58.19 93	38.22 151	68.05 99	66.96 93	73.69 117	69.65 122

FMVSNet2		55.04 124	59.95 106	49.31 126	52.42 147	61.44 121	57.03 128	44.08 97	49.55 100	30.40 150	46.89 121	58.84 91	38.22 151	67.07 118	66.21 109	73.69 117	69.65 122

FMVSNet1		54.08 128	58.68 120	48.71 136	50.90 163	61.35 124	56.73 132	43.94 102	45.91 136	29.32 157	42.72 164	56.26 104	37.70 156	68.05 99	66.96 93	73.69 117	69.50 126

MS-PatchMatch		58.19 97	60.20 101	55.85 88	65.17 63	64.16 108	64.82 90	41.48 137	50.95 92	42.17 99	45.38 140	56.42 101	48.08 107	68.30 90	66.70 99	73.39 121	69.46 129

TAPA-MVS	54.74 10	60.85 74	66.61 60	54.12 98	47.38 177	65.33 97	65.35 87	36.51 171	75.16 31	48.82 70	54.70 83	63.51 69	53.31 78	68.36 89	64.97 129	73.37 122	74.27 98
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		53.85 129	56.84 136	50.37 121	50.25 167	58.17 154	55.99 138	39.90 152	41.88 167	38.16 121	45.91 134	45.30 161	44.58 124	66.15 131	66.89 96	73.36 123	73.57 105

FMVSNet3		54.78 125	59.58 111	49.17 129	52.37 150	61.31 125	56.72 133	44.04 98	49.18 106	30.47 147	48.28 112	58.19 93	38.09 154	65.48 138	65.20 125	73.31 124	69.45 130

WR-MVS_H		47.65 170	53.67 152	40.63 181	51.45 155	59.74 139	44.71 191	49.37 60	40.69 174	7.61 211	46.04 133	44.34 175	17.32 199	57.79 175	61.18 156	73.30 125	65.86 151

TransMVSNet (Re)		51.92 143	55.38 142	47.88 148	60.95 86	59.90 137	53.95 152	45.14 83	39.47 181	24.85 173	43.87 151	46.51 151	29.15 181	67.55 108	65.23 124	73.26 126	65.16 157

diffmvs		61.64 70	66.55 61	55.90 87	56.63 120	63.71 111	67.13 69	41.27 139	59.49 66	46.70 75	63.93 44	68.01 60	50.46 93	67.30 112	65.51 119	73.24 127	77.87 69

IterMVS-LS		58.30 94	61.39 88	54.71 93	59.92 92	58.40 150	59.42 115	43.64 109	48.71 114	40.25 111	57.53 69	58.55 92	52.15 87	65.42 140	65.34 121	72.85 128	75.77 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		53.50 130	57.89 127	48.37 142	54.60 132	59.25 143	56.10 135	51.84 45	49.32 104	17.92 190	45.38 140	47.68 137	36.93 161	68.11 96	65.95 113	72.84 129	69.57 125

Vis-MVSNet		58.48 89	65.70 69	50.06 123	53.40 141	67.20 81	60.24 113	43.32 120	48.83 111	30.23 151	62.38 52	61.61 79	40.35 144	71.03 65	69.77 65	72.82 130	79.11 60
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_ETH3D		52.62 134	55.98 138	48.70 137	51.04 161	60.71 131	56.87 131	46.74 70	42.52 164	26.96 167	42.50 166	45.95 157	37.87 155	66.22 129	65.15 128	72.74 131	68.78 134

V42		56.97 105	60.14 103	53.28 103	48.16 173	62.78 116	66.30 76	37.93 164	47.44 125	42.68 95	48.19 115	52.59 116	51.90 88	67.46 110	65.94 114	72.72 132	76.55 82

tfpn200view9		52.53 135	55.51 140	49.06 131	57.31 112	60.24 133	55.42 145	43.77 104	42.85 160	27.81 162	43.00 162	45.06 166	37.32 158	66.38 124	64.54 131	72.71 133	66.54 142

CNLPA		62.78 65	66.31 63	58.65 66	58.47 98	68.41 66	65.98 80	41.22 140	78.02 23	56.04 37	46.65 123	59.50 89	57.50 43	69.67 76	65.27 123	72.70 134	76.67 78

thres600view7		51.91 144	55.14 144	48.14 144	57.43 108	60.18 134	54.60 150	43.73 106	42.61 163	25.20 172	43.10 161	44.47 173	35.19 167	66.36 125	63.28 143	72.66 135	66.01 150

thres400		52.38 138	55.51 140	48.74 135	57.49 107	60.10 136	55.45 144	43.54 112	42.90 159	26.72 168	43.34 158	45.03 168	36.61 163	66.20 130	64.53 132	72.66 135	66.43 143

thres200		52.39 137	55.37 143	48.90 133	57.39 109	60.18 134	55.60 142	43.73 106	42.93 158	27.41 164	43.35 157	45.09 165	36.61 163	66.36 125	63.92 138	72.66 135	65.78 152

thres100view900		52.04 141	54.81 147	48.80 134	57.31 112	59.33 141	55.30 146	42.92 126	42.85 160	27.81 162	43.00 162	45.06 166	36.99 160	64.74 143	63.51 140	72.47 138	65.21 156

TSAR-MVS + COLMAP		62.65 66	69.90 53	54.19 96	46.31 181	66.73 86	65.49 86	41.36 138	76.57 25	46.31 77	76.80 17	56.68 99	53.27 79	69.50 77	66.65 101	72.40 139	76.36 85

pmmvs4		54.66 126	56.07 137	53.00 107	54.63 131	57.08 161	60.43 112	44.10 96	51.69 91	40.55 108	46.55 127	44.79 169	45.95 118	62.54 150	63.66 139	72.36 140	66.20 147

DTE-MVSNet		48.03 169	53.28 156	41.91 176	54.64 130	57.50 159	44.63 192	51.66 49	41.02 172	7.97 210	46.26 129	40.90 183	20.24 196	60.45 160	62.89 147	72.33 141	63.97 162

UGNet		57.03 103	65.25 72	47.44 151	46.54 180	66.73 86	56.30 134	43.28 121	50.06 96	32.99 137	62.57 51	63.26 70	33.31 174	68.25 91	67.58 88	72.20 142	78.29 66
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	51.99 142	54.86 146	48.63 138	49.13 171	61.73 120	60.53 111	36.57 170	53.14 81	32.95 138	37.10 178	38.68 193	40.49 143	65.72 135	63.08 144	72.11 143	64.60 160
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CP-MVSNet		48.37 164	53.53 153	42.34 174	51.35 157	58.01 156	46.56 180	50.54 54	41.62 169	10.61 200	46.53 128	40.68 186	23.18 192	58.71 169	61.83 153	71.81 144	67.36 140

pmmvs-eth3d		51.33 145	52.25 164	50.26 122	50.82 164	54.65 166	56.03 137	43.45 119	43.51 153	37.20 127	39.20 174	39.04 192	42.28 136	61.85 155	62.78 148	71.78 145	64.72 159

PS-CasMVS		48.18 166	53.25 157	42.27 175	51.26 158	57.94 157	46.51 181	50.52 55	41.30 170	10.56 201	45.35 142	40.34 188	23.04 193	58.66 170	61.79 154	71.74 146	67.38 139

gm-plane-assit		44.74 181	45.95 189	43.33 170	60.88 87	46.79 195	36.97 204	32.24 194	24.15 209	11.79 199	29.26 198	32.97 204	46.64 113	65.09 142	62.95 146	71.45 147	60.42 177

tfpnnormal		50.16 153	52.19 165	47.78 150	56.86 119	58.37 151	54.15 151	44.01 101	38.35 189	25.94 170	36.10 181	37.89 195	34.50 170	65.93 132	63.42 141	71.26 148	65.28 155

baseline1		54.48 127	58.69 119	49.57 124	60.63 88	58.29 153	55.70 141	44.95 85	49.20 105	29.62 154	54.77 82	54.75 108	35.29 166	67.15 116	64.08 135	71.21 149	62.58 170

gg-mvs-nofinetune		49.07 161	52.56 161	45.00 162	61.99 78	59.78 138	53.55 157	41.63 135	31.62 203	12.08 198	29.56 197	53.28 113	29.57 180	66.27 128	64.49 133	71.19 150	62.92 166

pm-mvs1		51.02 147	55.55 139	45.73 157	54.16 136	58.52 148	50.92 162	42.56 128	40.32 176	25.67 171	43.66 153	50.34 127	30.06 179	65.85 134	63.97 137	70.99 151	66.21 146

TDRefinement		49.31 156	52.44 162	45.67 159	30.44 207	59.42 140	59.24 117	39.78 153	48.76 113	31.20 146	35.73 182	29.90 207	42.81 135	64.24 145	62.59 152	70.55 152	66.43 143

IterMVS		53.45 131	57.12 134	49.17 129	49.23 170	60.93 130	59.05 119	34.63 179	44.53 143	33.22 135	51.09 102	51.01 123	48.38 104	62.43 152	60.79 159	70.54 153	69.05 132
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		51.11 146	53.71 151	48.08 146	44.76 186	55.99 164	53.01 159	40.90 141	52.49 87	36.14 129	44.67 146	33.66 203	43.27 132	63.23 146	61.10 157	70.39 154	64.82 158

pmmvs6		48.35 165	51.64 167	44.51 165	51.92 153	57.94 157	49.44 168	42.17 132	34.45 196	24.62 175	28.87 199	46.90 147	29.07 183	64.60 144	63.08 144	69.83 155	65.68 153

SixPastTwentyTwo		47.55 172	50.25 177	44.41 166	47.30 178	54.31 168	47.81 174	40.36 150	33.76 197	19.93 185	43.75 152	32.77 205	42.07 137	59.82 162	60.94 158	68.98 156	66.37 145

pmmvs5		47.07 174	51.02 173	42.46 173	45.18 185	51.47 177	48.23 173	33.09 190	38.17 190	28.62 160	46.60 125	43.48 177	30.74 177	58.28 172	58.63 167	68.92 157	60.48 176

Vis-MVSNet (Re-imp)		50.37 151	57.73 131	41.80 177	57.53 105	54.35 167	45.70 185	45.24 82	49.80 98	13.43 196	58.23 67	56.42 101	20.11 197	62.96 148	63.36 142	68.76 158	58.96 182

CDS-MVSNet		52.42 136	57.06 135	47.02 153	53.92 139	58.30 152	55.50 143	46.47 71	42.52 164	29.38 156	49.50 106	52.85 115	28.49 184	66.70 122	66.89 96	68.34 159	62.63 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		56.57 109	59.13 116	53.60 100	57.52 106	61.12 126	66.94 71	35.95 173	53.44 77	44.68 86	55.87 77	54.44 109	48.21 105	60.37 161	58.33 168	68.27 160	70.33 119

PMMVS		49.20 160	54.28 150	43.28 171	34.13 202	45.70 197	48.98 169	26.09 204	46.31 133	34.92 134	55.22 79	53.47 112	47.48 111	59.43 163	59.04 166	68.05 161	60.77 175

EPNet_dtu		52.05 140	58.26 124	44.81 163	54.10 137	50.09 182	52.01 160	40.82 143	53.03 83	27.41 164	54.90 80	57.96 97	26.72 186	62.97 147	62.70 150	67.78 162	66.19 148
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		47.08 173	47.56 187	46.52 154	42.35 193	53.44 170	51.77 161	40.70 144	43.44 154	31.92 143	29.78 196	23.72 213	45.04 123	61.99 154	59.54 165	67.35 163	61.03 174

CHOSEN 1792x2688		55.85 114	58.01 126	53.33 102	57.26 115	62.82 115	63.29 101	41.55 136	46.65 130	38.34 119	34.55 186	53.50 111	52.43 84	67.10 117	67.56 89	67.13 164	73.92 103

test-LLR		49.28 157	50.29 175	48.10 145	55.26 127	47.16 190	49.52 166	43.48 117	39.22 182	31.98 141	43.65 154	47.93 134	41.29 141	56.80 179	55.36 178	67.08 165	61.94 171

TESTMET0.1,1		46.09 179	50.29 175	41.18 179	36.91 200	47.16 190	49.52 166	20.32 209	39.22 182	31.98 141	43.65 154	47.93 134	41.29 141	56.80 179	55.36 178	67.08 165	61.94 171

test-mter		45.30 180	50.37 174	39.38 184	33.65 204	46.99 192	47.59 175	18.59 210	38.75 185	28.00 161	43.28 159	46.82 149	41.50 140	57.28 177	55.78 175	66.93 167	63.70 164

PatchMatch-RL		50.11 154	51.56 168	48.43 140	46.23 182	51.94 175	50.21 165	38.62 161	46.62 131	37.51 124	42.43 167	39.38 190	52.24 86	60.98 158	59.56 164	65.76 168	60.01 180

CR-MVSNet		50.47 149	52.61 160	47.98 147	49.03 172	52.94 171	48.27 171	38.86 157	44.41 144	39.59 114	44.34 147	44.65 172	46.63 114	58.97 166	60.31 161	65.48 169	62.66 167

RPMNet		46.41 176	48.72 182	43.72 167	47.77 176	52.94 171	46.02 184	33.92 183	44.41 144	31.82 144	36.89 179	37.42 198	37.41 157	53.88 194	54.02 187	65.37 170	61.47 173

MDTV_nov1_ep13_2view		47.62 171	49.72 180	45.18 161	48.05 174	53.70 169	54.90 149	33.80 185	39.90 180	29.79 153	38.85 175	41.89 180	39.17 147	58.99 165	55.55 177	65.34 171	59.17 181

MDTV_nov1_ep13		50.32 152	52.43 163	47.86 149	49.87 168	54.70 165	58.10 122	34.29 181	45.59 139	37.71 123	47.44 119	47.42 141	41.86 138	58.07 174	55.21 180	65.34 171	58.56 183

MVS-HIRNet		42.24 188	41.15 201	43.51 168	44.06 190	40.74 202	35.77 206	35.35 174	35.38 195	38.34 119	25.63 203	38.55 194	43.48 129	50.77 199	47.03 202	64.07 173	49.98 198

MDA-MVSNet-bldmvs		41.36 189	43.15 199	39.27 185	28.74 209	52.68 173	44.95 190	40.84 142	32.89 199	18.13 189	31.61 191	22.09 214	38.97 150	50.45 201	56.11 173	64.01 174	56.23 188

CVMVSNet		46.38 178	52.01 166	39.81 183	42.40 192	50.26 180	46.15 182	37.68 166	40.03 179	15.09 193	46.56 126	47.56 139	33.72 173	56.50 183	55.65 176	63.80 175	67.53 137

PatchT		48.08 167	51.03 172	44.64 164	42.96 191	50.12 181	40.36 200	35.09 175	43.17 155	39.59 114	42.00 168	39.96 189	46.63 114	58.97 166	60.31 161	63.21 176	62.66 167

baseline		55.19 122	60.88 91	48.55 139	49.87 168	58.10 155	58.70 120	34.75 177	52.82 86	39.48 117	60.18 58	60.86 80	45.41 120	61.05 157	60.74 160	63.10 177	72.41 107

dps		50.42 150	51.20 171	49.51 125	55.88 123	56.07 163	53.73 153	38.89 156	43.66 150	40.36 110	45.66 137	37.63 197	45.23 121	59.05 164	56.18 172	62.94 178	60.16 178

SCA		50.99 148	53.22 158	48.40 141	51.07 160	56.78 162	50.25 164	39.05 154	48.31 119	41.38 102	49.54 105	46.70 150	46.00 117	58.31 171	56.28 171	62.65 179	56.60 187

tpm cat1		53.30 132	53.41 154	53.17 106	58.16 99	59.15 144	63.73 98	38.27 163	50.73 94	46.98 73	45.57 139	44.00 176	49.20 98	55.90 188	54.02 187	62.65 179	64.50 161

LTVRE_ROB	44.17 16	47.06 175	50.15 178	43.44 169	51.39 156	58.42 149	42.90 195	43.51 114	22.27 211	14.85 194	41.94 169	34.57 201	45.43 119	62.28 153	62.77 149	62.56 181	68.83 133
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		44.55 183	48.13 185	40.37 182	32.85 206	46.82 194	46.11 183	29.28 197	40.48 175	29.99 152	39.98 173	34.39 202	41.80 139	56.08 186	53.88 191	62.19 182	65.31 154

EU-MVSNet		40.63 193	45.65 192	34.78 197	39.11 198	46.94 193	40.02 201	34.03 182	33.50 198	10.37 202	35.57 183	37.80 196	23.65 191	51.90 196	50.21 197	61.49 183	63.62 165

PatchmatchNet		49.92 155	51.29 169	48.32 143	51.83 154	51.86 176	53.38 158	37.63 167	47.90 122	40.83 107	48.54 111	45.30 161	45.19 122	56.86 178	53.99 189	61.08 184	54.57 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	37.70 17	49.24 158	52.71 159	45.19 160	45.97 183	51.23 178	47.44 177	29.31 196	43.04 156	44.69 85	34.45 187	48.35 131	43.64 127	62.59 149	59.82 163	60.08 185	69.48 127
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		43.15 186	46.95 188	38.72 186	55.26 127	50.56 179	42.48 196	43.48 117	38.16 191	15.11 192	35.07 184	44.69 171	16.47 200	55.95 187	54.34 186	59.54 186	49.87 200

Anonymous20231206		42.28 187	45.89 190	38.07 188	51.96 152	48.98 184	43.66 194	38.81 159	38.74 186	14.32 195	26.74 201	40.90 183	20.94 195	56.64 182	54.67 184	58.71 187	54.59 189

TAMVS		44.02 184	49.18 181	37.99 189	47.03 179	45.97 196	45.04 188	28.47 199	39.11 184	20.23 184	43.22 160	48.52 130	28.49 184	58.15 173	57.95 170	58.71 187	51.36 193

ambc			45.54 193		50.66 166	52.63 174	40.99 199		38.36 188	24.67 174	22.62 206	13.94 216	29.14 182	65.71 136	58.06 169	58.60 189	67.43 138

pmmvs3		35.10 201	38.47 203	31.17 200	26.37 213	40.47 203	34.51 208	18.09 211	24.75 208	16.88 191	23.05 205	26.69 209	32.69 175	50.73 200	51.60 194	58.46 190	51.98 192

test20.03		40.38 195	44.20 195	35.92 194	53.73 140	49.05 183	38.54 202	43.49 116	32.55 200	9.54 205	27.88 200	39.12 191	12.24 205	56.28 184	54.69 183	57.96 191	49.83 201

MIMVSNet		43.79 185	48.53 183	38.27 187	41.46 195	48.97 185	50.81 163	32.88 192	44.55 142	22.07 179	32.05 189	47.15 143	24.76 189	58.73 168	56.09 174	57.63 192	52.14 191

tpmrst		48.08 167	49.88 179	45.98 155	52.71 145	48.11 187	53.62 156	33.70 186	48.70 115	39.74 112	48.96 109	46.23 154	40.29 145	50.14 202	49.28 198	55.80 193	57.71 185

FPMVS		38.36 198	40.41 202	35.97 193	38.92 199	39.85 205	45.50 186	25.79 205	41.13 171	18.70 187	30.10 194	24.56 211	31.86 176	49.42 204	46.80 203	55.04 194	51.03 194

FMVSNet5		40.96 190	45.81 191	35.29 196	34.30 201	44.55 200	47.28 178	28.84 198	40.76 173	21.62 180	29.85 195	42.44 178	24.77 188	57.53 176	55.00 181	54.93 195	50.56 196

tpm		48.82 162	51.27 170	45.96 156	54.10 137	47.35 189	56.05 136	30.23 195	46.70 129	43.21 92	52.54 92	47.55 140	37.28 159	54.11 193	50.50 196	54.90 196	60.12 179

PMVS	27.84 18	33.81 202	35.28 206	32.09 199	34.13 202	24.81 212	32.51 209	26.48 203	26.41 207	19.37 186	23.76 204	24.02 212	25.18 187	50.78 198	47.24 201	54.89 197	49.95 199
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testgi		38.71 197	43.64 197	32.95 198	52.30 151	48.63 186	35.59 207	35.05 176	31.58 204	9.03 208	30.29 193	40.75 185	11.19 211	55.30 189	53.47 192	54.53 198	45.48 204

GG-mvs-BLEND		36.62 199	53.39 155	17.06 208	0.01 220	58.61 147	48.63 170	0.01 217	47.13 127	0.02 221	43.98 149	60.64 83	0.03 216	54.92 192	51.47 195	53.64 199	56.99 186

MIMVSNet1		35.51 200	41.41 200	28.63 202	27.53 211	43.36 201	38.09 203	33.82 184	32.01 201	6.77 212	21.63 207	35.43 200	11.97 207	55.05 191	53.99 189	53.59 200	48.36 203

EPMVS		44.66 182	47.86 186	40.92 180	47.97 175	44.70 199	47.58 176	33.27 188	48.11 121	29.58 155	49.65 104	44.38 174	34.65 168	51.71 197	47.90 200	52.49 201	48.57 202

RPSCF		46.41 176	54.42 148	37.06 191	25.70 214	45.14 198	45.39 187	20.81 208	62.79 59	35.10 131	44.92 144	55.60 107	43.56 128	56.12 185	52.45 193	51.80 202	63.91 163

IterMVS-SCA-FT		52.18 139	57.75 130	45.68 158	51.01 162	62.06 117	55.10 148	34.75 177	44.85 141	32.86 139	51.13 101	51.22 120	48.74 100	62.47 151	61.51 155	51.61 203	71.02 113

pmnet_mix02		40.48 194	43.80 196	36.61 192	45.79 184	40.45 204	42.12 197	33.18 189	40.30 177	24.11 178	38.76 176	37.11 199	24.30 190	52.97 195	46.66 204	50.17 204	50.33 197

FC-MVSNet-test		39.65 196	48.35 184	29.49 201	44.43 187	39.28 207	30.23 210	40.44 148	43.59 151	3.12 217	53.00 88	42.03 179	10.02 213	55.09 190	54.77 182	48.66 205	50.71 195

CHOSEN 280x420		40.80 191	45.05 194	35.84 195	32.95 205	29.57 210	44.98 189	23.71 207	37.54 192	18.42 188	31.36 192	47.07 144	46.41 116	56.71 181	54.65 185	48.55 206	58.47 184

ADS-MVSNet		40.67 192	43.38 198	37.50 190	44.36 188	39.79 206	42.09 198	32.67 193	44.34 146	28.87 159	40.76 172	40.37 187	30.22 178	48.34 206	45.87 205	46.81 207	44.21 206

new-patchmatchnet		33.24 203	37.20 204	28.62 203	44.32 189	38.26 208	29.68 211	36.05 172	31.97 202	6.33 213	26.59 202	27.33 208	11.12 212	50.08 203	41.05 207	44.23 208	45.15 205

Gipuma		25.87 205	26.91 208	24.66 205	28.98 208	20.17 213	20.46 212	34.62 180	29.55 205	9.10 206	4.91 216	5.31 220	15.76 202	49.37 205	49.10 199	39.03 209	29.95 209
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
N_pmnet		32.67 204	36.85 205	27.79 204	40.55 196	32.13 209	35.80 205	26.79 202	37.24 193	9.10 206	32.02 190	30.94 206	16.30 201	47.22 207	41.21 206	38.21 210	37.21 207

new_pmnet		23.19 206	28.17 207	17.37 206	17.03 215	24.92 211	19.66 213	16.16 213	27.05 206	4.42 214	20.77 208	19.20 215	12.19 206	37.71 208	36.38 208	34.77 211	31.17 208

E-PMN		15.09 208	13.19 212	17.30 207	27.80 210	12.62 216	7.81 217	27.54 200	14.62 215	3.19 215	6.89 213	2.52 223	15.09 203	15.93 212	20.22 211	22.38 212	19.53 212

EMVS		14.49 209	12.45 213	16.87 209	27.02 212	12.56 217	8.13 216	27.19 201	15.05 214	3.14 216	6.69 214	2.67 222	15.08 204	14.60 214	18.05 212	20.67 213	17.56 214

test_method		12.44 211	14.66 211	9.85 212	1.30 219	3.32 219	13.00 215	3.21 214	22.42 210	10.22 203	14.13 209	25.64 210	11.43 210	19.75 211	11.61 214	19.96 214	5.79 215

PMMVS2		15.84 207	19.68 209	11.35 210	15.74 216	16.95 214	13.31 214	17.64 212	16.08 213	0.36 220	13.12 210	11.47 217	1.69 215	28.82 209	27.24 210	19.38 215	24.09 211

MVE	12.28 19	13.53 210	15.72 210	10.96 211	7.39 217	15.71 215	6.05 218	23.73 206	10.29 217	3.01 218	5.77 215	3.41 221	11.91 208	20.11 210	29.79 209	13.67 216	24.98 210
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 213	3.97 218	2.35 220	3.26 220	0.44 216	17.56 212	12.09 197	11.48 212	7.14 218	1.98 214	15.68 213	15.49 213	10.69 217

DeepMVS_CX						6.95 218	5.98 219	2.25 215	11.73 216	2.07 219	11.85 211	5.43 219	11.75 209	11.40 215		8.10 218	18.38 213

uanet_test		0.00 214	0.00 216	0.00 214	0.00 221	0.00 221	0.00 223	0.00 218	0.00 220	0.00 222	0.00 219	0.00 224	0.00 219	0.00 217	0.00 217	0.00 219	0.00 218

sosnet-low-res		0.00 214	0.00 216	0.00 214	0.00 221	0.00 221	0.00 223	0.00 218	0.00 220	0.00 222	0.00 219	0.00 224	0.00 219	0.00 217	0.00 217	0.00 219	0.00 218

sosnet		0.00 214	0.00 216	0.00 214	0.00 221	0.00 221	0.00 223	0.00 218	0.00 220	0.00 222	0.00 219	0.00 224	0.00 219	0.00 217	0.00 217	0.00 219	0.00 218

testmvs		0.01 212	0.02 214	0.00 214	0.00 221	0.00 221	0.01 222	0.00 218	0.01 218	0.00 222	0.03 218	0.00 224	0.01 217	0.01 216	0.01 215	0.00 219	0.06 217

test123		0.01 212	0.02 214	0.00 214	0.00 221	0.00 221	0.00 223	0.00 218	0.01 218	0.00 222	0.04 217	0.00 224	0.01 217	0.00 217	0.01 215	0.00 219	0.07 216

RE-MVS-def										33.01 136

9.14												81.81 12

SR-MVS					71.46 34			54.67 29				81.54 13

our_test_3					51.15 159	57.31 160	55.12 147

MTAPA										65.14 3		80.20 19

MTMP										62.63 17		78.04 26

Patchmatch-RL test							1.04 221

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 40

Patchmtry						47.61 188	48.27 171	38.86 157		39.59 114

High-resolution multi-view benchmark