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.

MSP-MVS		78.77 1	84.89 1	71.62 3	78.04 3	82.05 1	81.64 9	57.96 5	87.53 1	66.64 1	88.77 1	86.31 1	63.16 8	79.99 5	78.56 6	82.31 21	91.03 1

DPE-MVS		78.11 2	83.84 2	71.42 4	77.82 5	81.32 2	82.92 5	57.81 7	84.04 6	63.19 12	88.63 2	86.00 2	64.52 3	78.71 9	77.63 14	82.26 22	90.57 3

DVP-MVS		77.82 3	83.46 3	71.24 7	75.26 15	80.22 6	82.95 4	57.85 6	85.90 2	64.79 4	88.54 3	83.43 5	66.24 1	78.21 16	78.56 6	80.34 44	89.39 6

TSAR-MVS + MP.		75.22 12	80.06 11	69.56 16	74.61 17	72.74 49	80.59 13	55.70 23	80.80 12	62.65 15	86.25 4	82.92 7	62.07 19	76.89 28	75.66 29	81.77 33	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
APDe-MVS		77.58 4	82.93 4	71.35 5	77.86 4	80.55 5	83.38 1	57.61 8	85.57 3	61.11 20	86.10 5	82.98 6	64.76 2	78.29 13	76.78 21	83.40 6	90.20 4

APD-MVS		75.80 9	80.90 9	69.86 15	75.42 14	78.48 15	81.43 12	57.44 11	80.45 14	59.32 26	85.28 6	80.82 16	63.96 5	76.89 28	76.08 26	81.58 37	88.30 11
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + ACMM		72.56 28	79.07 15	64.96 40	73.24 24	73.16 48	78.50 26	48.80 64	79.34 17	55.32 40	85.04 7	81.49 13	58.57 36	75.06 43	73.75 44	75.35 100	85.61 30

xxxxxxxxxxxxxcwj		74.63 15	77.07 26	71.79 1	79.32 1	80.76 3	82.96 2	57.49 9	82.82 7	64.79 4	83.69 8	52.03 115	62.83 12	77.13 25	75.21 30	83.35 7	87.85 15

SF-MVS		77.13 6	81.70 6	71.79 1	79.32 1	80.76 3	82.96 2	57.49 9	82.82 7	64.79 4	83.69 8	84.46 3	62.83 12	77.13 25	75.21 30	83.35 7	87.85 15

train_agg		73.89 21	78.25 20	68.80 23	75.25 16	72.27 51	79.75 17	56.05 20	74.87 32	58.97 27	81.83 10	79.76 20	61.05 25	77.39 24	76.01 27	81.71 34	85.61 30

SD-MVS		74.43 16	78.87 16	69.26 19	74.39 18	73.70 45	79.06 24	55.24 25	81.04 11	62.71 14	80.18 11	82.61 8	61.70 21	75.43 40	73.92 43	82.44 20	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
ACMMP_NAP		76.15 7	81.17 7	70.30 10	74.09 19	79.47 9	81.59 11	57.09 13	81.38 10	63.89 10	79.02 12	80.48 17	62.24 17	80.05 4	79.12 4	82.94 12	88.64 8

HPM-MVS++		76.01 8	80.47 10	70.81 8	76.60 7	74.96 35	80.18 16	58.36 2	81.96 9	63.50 11	78.80 13	82.53 9	64.40 4	78.74 8	78.84 5	81.81 31	87.46 18

SMA-MVS		77.32 5	82.51 5	71.26 6	75.43 13	80.19 7	82.22 6	58.26 3	84.83 5	64.36 7	78.19 14	83.46 4	63.61 6	81.00 1	80.28 1	83.66 4	89.62 5

DeepPCF-MVS	66.49 1	74.25 19	80.97 8	66.41 31	67.75 51	78.87 12	75.61 38	54.16 33	84.86 4	58.22 32	77.94 15	81.01 15	62.52 15	78.34 11	77.38 15	80.16 47	88.40 10

TSAR-MVS + COLMAP		62.65 64	69.90 52	54.19 93	46.31 178	66.73 83	65.49 83	41.36 135	76.57 24	46.31 74	76.80 16	56.68 96	53.27 77	69.50 74	66.65 98	72.40 136	76.36 83

SteuartSystems-ACMMP		75.23 11	79.60 13	70.13 12	76.81 6	78.92 11	81.74 7	57.99 4	75.30 29	59.83 25	75.69 17	78.45 23	60.48 28	80.58 2	79.77 2	83.94 3	88.52 9
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS		74.31 17	78.87 16	68.99 21	73.49 22	78.56 14	79.25 22	56.51 16	75.33 27	60.69 22	75.30 18	79.12 22	61.81 20	77.78 20	77.93 10	82.18 27	88.06 13
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HFP-MVS		74.87 13	78.86 18	70.21 11	73.99 20	77.91 17	80.36 15	56.63 15	78.41 19	64.27 8	74.54 19	77.75 27	62.96 10	78.70 10	77.82 11	83.02 10	86.91 21

ACMMPR		73.79 23	78.41 19	68.40 24	72.35 27	77.79 18	79.32 20	56.38 18	77.67 23	58.30 31	74.16 20	76.66 28	61.40 22	78.32 12	77.80 12	82.68 16	86.51 22

PGM-MVS		72.89 25	77.13 25	67.94 25	72.47 26	77.25 23	79.27 21	54.63 29	73.71 34	57.95 33	72.38 21	75.33 34	60.75 26	78.25 14	77.36 17	82.57 19	85.62 29

CDPH-MVS		71.47 31	75.82 31	66.41 31	72.97 25	77.15 24	78.14 29	54.71 27	69.88 47	53.07 55	70.98 22	74.83 36	56.95 50	76.22 33	76.57 23	82.62 17	85.09 34

CNVR-MVS		75.62 10	79.91 12	70.61 9	75.76 9	78.82 13	81.66 8	57.12 12	79.77 16	63.04 13	70.69 23	81.15 14	62.99 9	80.23 3	79.54 3	83.11 9	89.16 7

CSCG		74.68 14	79.22 14	69.40 17	75.69 11	80.01 8	79.12 23	52.83 41	79.34 17	63.99 9	70.49 24	82.02 10	60.35 30	77.48 23	77.22 18	84.38 1	87.97 14

ACMMP		71.57 30	75.84 30	66.59 30	70.30 39	76.85 28	78.46 27	53.95 34	73.52 35	55.56 38	70.13 25	71.36 47	58.55 37	77.00 27	76.23 25	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
HQP-MVS		70.88 33	75.02 33	66.05 34	71.69 30	74.47 40	77.51 31	53.17 38	72.89 36	54.88 44	70.03 26	70.48 49	57.26 46	76.02 35	75.01 35	81.78 32	86.21 24

PHI-MVS		69.27 38	74.84 34	62.76 50	66.83 53	74.83 36	73.88 46	49.32 60	70.61 44	50.93 59	69.62 27	74.84 35	57.25 47	75.53 39	74.32 40	78.35 63	84.17 37

CP-MVS		72.63 27	76.95 27	67.59 26	70.67 35	75.53 33	77.95 30	56.01 21	75.65 26	58.82 28	69.16 28	76.48 30	60.46 29	77.66 21	77.20 19	81.65 35	86.97 20

zzz-MVS		74.25 19	77.97 22	69.91 14	73.43 23	74.06 43	79.69 18	56.44 17	80.74 13	64.98 3	68.72 29	79.98 19	62.92 11	78.24 15	77.77 13	81.99 29	86.30 23

TSAR-MVS + GP.		69.71 34	73.92 36	64.80 42	68.27 47	70.56 56	71.90 50	50.75 51	71.38 41	57.46 35	68.68 30	75.42 33	60.10 31	73.47 50	73.99 42	80.32 45	83.97 38

MCST-MVS		73.67 24	77.39 24	69.33 18	76.26 8	78.19 16	78.77 25	54.54 30	75.33 27	59.99 24	67.96 31	79.23 21	62.43 16	78.00 17	75.71 28	84.02 2	87.30 19

EPNet		65.14 55	69.54 53	60.00 56	66.61 55	67.67 73	67.53 61	55.32 24	62.67 59	46.22 76	67.74 32	65.93 63	48.07 105	72.17 55	72.12 49	76.28 86	78.47 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CANet		68.77 40	73.01 37	63.83 46	68.30 46	75.19 34	73.73 47	47.90 65	63.86 54	54.84 45	67.51 33	74.36 40	57.62 41	74.22 46	73.57 47	80.56 42	82.36 46

MVS_0304		69.49 36	73.96 35	64.28 45	67.92 49	76.13 31	74.90 41	47.60 66	63.29 57	54.09 52	67.44 34	76.35 31	59.53 33	75.81 37	75.03 33	81.62 36	83.70 41

DeepC-MVS	66.32 2	73.85 22	78.10 21	68.90 22	67.92 49	79.31 10	78.16 28	59.28 1	78.24 21	61.13 19	67.36 35	76.10 32	63.40 7	79.11 7	78.41 9	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
NCCC		74.27 18	77.83 23	70.13 12	75.70 10	77.41 22	80.51 14	57.09 13	78.25 20	62.28 17	65.54 36	78.26 24	62.18 18	79.13 6	78.51 8	83.01 11	87.68 17

DeepC-MVS_fast	65.08 3	72.00 29	76.11 28	67.21 28	68.93 45	77.46 20	76.54 34	54.35 31	74.92 31	58.64 30	65.18 37	74.04 42	62.62 14	77.92 18	77.02 20	82.16 28	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
CLD-MVS		67.02 49	71.57 42	61.71 51	71.01 34	74.81 37	71.62 51	38.91 152	71.86 40	60.70 21	64.97 38	67.88 60	51.88 87	76.77 31	74.98 36	76.11 90	69.75 119
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DELS-MVS		65.87 51	70.30 51	60.71 53	64.05 70	72.68 50	70.90 54	45.43 78	57.49 66	49.05 67	64.43 39	68.66 54	55.11 62	74.31 45	73.02 48	79.70 50	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
X-MVS		71.18 32	75.66 32	65.96 35	71.71 29	76.96 25	77.26 32	55.88 22	72.75 37	54.48 48	64.39 40	74.47 37	54.19 64	77.84 19	77.37 16	82.21 25	85.85 27

canonicalmvs		65.62 52	72.06 40	58.11 65	63.94 71	71.05 54	64.49 90	43.18 120	74.08 33	47.35 69	64.17 41	71.97 46	51.17 90	71.87 56	70.74 54	78.51 61	80.56 53

DPM-MVS		72.80 26	75.90 29	69.19 20	75.51 12	77.68 19	81.62 10	54.83 26	75.96 25	62.06 18	63.96 42	76.58 29	58.55 37	76.66 32	76.77 22	82.60 18	83.68 42

diffmvs		61.64 67	66.55 60	55.90 84	56.63 117	63.71 108	67.13 66	41.27 136	59.49 65	46.70 72	63.93 43	68.01 59	50.46 91	67.30 109	65.51 116	73.24 124	77.87 67

LGP-MVS_train		68.87 39	72.03 41	65.18 39	69.33 43	74.03 44	76.67 33	53.88 35	68.46 48	52.05 58	63.21 44	63.89 65	56.31 54	75.99 36	74.43 39	82.83 14	84.18 36

casdiffmvs		64.09 56	68.13 57	59.37 60	61.81 76	68.32 65	68.48 57	44.45 90	61.95 60	49.12 66	63.04 45	69.67 52	53.83 67	70.46 66	66.06 108	78.55 59	77.43 69

UA-Net		58.50 85	64.68 74	51.30 113	66.97 52	67.13 80	53.68 152	45.65 77	49.51 99	31.58 141	62.91 46	68.47 55	35.85 162	68.20 91	67.28 88	74.03 110	69.24 129

abl_6				64.36 44	70.08 40	77.45 21	72.88 49	50.15 56	71.31 42	54.77 47	62.79 47	77.99 26	56.80 51			81.50 38	83.91 39

OMC-MVS		65.16 54	71.35 44	57.94 69	52.95 141	68.82 61	69.00 55	38.28 159	79.89 15	55.20 41	62.76 48	68.31 56	56.14 57	71.30 60	68.70 71	76.06 92	79.67 56

MVS_Test		62.40 65	66.23 63	57.94 69	59.77 90	64.77 102	66.50 71	41.76 131	57.26 67	49.33 64	62.68 49	67.47 61	53.50 72	68.57 84	66.25 105	76.77 79	76.58 78

UGNet		57.03 100	65.25 70	47.44 148	46.54 177	66.73 83	56.30 131	43.28 118	50.06 93	32.99 133	62.57 50	63.26 68	33.31 171	68.25 88	67.58 85	72.20 139	78.29 64
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
Vis-MVSNet		58.48 86	65.70 68	50.06 120	53.40 138	67.20 79	60.24 110	43.32 117	48.83 108	30.23 147	62.38 51	61.61 76	40.35 141	71.03 63	69.77 63	72.82 127	79.11 59
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS_111021_HR		67.62 46	70.39 49	64.39 43	69.77 41	70.45 57	71.44 53	51.72 47	60.77 63	55.06 42	62.14 52	66.40 62	58.13 40	76.13 34	74.79 37	80.19 46	82.04 49

MVS_111021_LR		63.05 61	66.43 61	59.10 61	61.33 80	63.77 107	65.87 78	43.58 108	60.20 64	53.70 54	62.09 53	62.38 70	55.84 59	70.24 70	68.08 76	74.30 107	78.28 65

FC-MVSNet-train		58.40 88	63.15 80	52.85 106	64.29 65	61.84 116	55.98 136	46.47 70	53.06 79	34.96 130	61.95 54	56.37 100	39.49 143	68.67 81	68.36 75	75.92 94	71.81 107

ACMP	61.42 5	68.72 42	71.37 43	65.64 37	69.06 44	74.45 41	75.88 37	53.30 37	68.10 49	55.74 37	61.53 55	62.29 71	56.97 49	74.70 44	74.23 41	82.88 13	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CPTT-MVS		68.76 41	73.01 37	63.81 47	65.42 60	73.66 46	76.39 36	52.08 43	72.61 38	50.33 61	60.73 56	72.65 45	59.43 34	73.32 51	72.12 49	79.19 56	85.99 26

baseline		55.19 119	60.88 88	48.55 136	49.87 165	58.10 152	58.70 117	34.75 174	52.82 83	39.48 114	60.18 57	60.86 77	45.41 117	61.05 154	60.74 157	63.10 174	72.41 105

CANet_DTU		58.88 80	64.68 74	52.12 111	55.77 121	66.75 82	63.92 93	37.04 166	53.32 77	37.45 123	59.81 58	61.81 74	44.43 122	68.25 88	67.47 87	74.12 109	75.33 91

ET-MVSNet_ETH3D		58.38 89	61.57 84	54.67 91	42.15 190	65.26 96	65.70 79	43.82 100	48.84 107	42.34 94	59.76 59	47.76 133	56.68 52	67.02 116	68.60 74	77.33 73	73.73 102

OPM-MVS		69.33 37	71.05 45	67.32 27	72.34 28	75.70 32	79.57 19	56.34 19	55.21 69	53.81 53	59.51 60	68.96 53	59.67 32	77.61 22	76.44 24	82.19 26	83.88 40

EPP-MVSNet		59.39 76	65.45 69	52.32 110	60.96 82	67.70 72	58.42 118	44.75 85	49.71 96	27.23 162	59.03 61	62.20 72	43.34 127	70.71 65	69.13 67	79.25 55	79.63 57

ETV-MVS		63.23 60	66.08 64	59.91 57	63.13 74	68.13 66	67.62 60	44.62 87	53.39 76	46.23 75	58.74 62	58.19 90	57.45 43	73.60 48	71.38 53	80.39 43	79.13 58

PVSNet_BlendedMVS		61.63 68	64.82 72	57.91 71	57.21 113	67.55 75	63.47 96	46.08 72	54.72 70	52.46 56	58.59 63	60.73 78	51.82 88	70.46 66	65.20 122	76.44 83	76.50 81

PVSNet_Blended		61.63 68	64.82 72	57.91 71	57.21 113	67.55 75	63.47 96	46.08 72	54.72 70	52.46 56	58.59 63	60.73 78	51.82 88	70.46 66	65.20 122	76.44 83	76.50 81

PCF-MVS	59.98 8	67.32 48	71.04 46	62.97 49	64.77 62	74.49 39	74.78 42	49.54 58	67.44 50	54.39 51	58.35 65	72.81 44	55.79 60	71.54 58	69.24 65	78.57 58	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Vis-MVSNet (Re-imp)		50.37 148	57.73 128	41.80 174	57.53 102	54.35 164	45.70 182	45.24 80	49.80 95	13.43 191	58.23 66	56.42 98	20.11 193	62.96 145	63.36 139	68.76 155	58.96 180

IS_MVSNet		57.95 95	64.26 76	50.60 115	61.62 79	65.25 98	57.18 124	45.42 79	50.79 90	26.49 165	57.81 67	60.05 84	34.51 166	71.24 62	70.20 60	78.36 62	74.44 95

IterMVS-LS		58.30 91	61.39 85	54.71 90	59.92 89	58.40 147	59.42 112	43.64 106	48.71 111	40.25 108	57.53 68	58.55 89	52.15 85	65.42 137	65.34 118	72.85 125	75.77 86
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EIA-MVS		61.53 70	63.79 78	58.89 62	63.82 72	67.61 74	65.35 84	42.15 130	49.98 94	45.66 78	57.47 69	56.62 97	56.59 53	70.91 64	69.15 66	79.78 48	74.80 93

MVSTER		57.19 99	61.11 87	52.62 108	50.82 161	58.79 143	61.55 100	37.86 162	48.81 109	41.31 100	57.43 70	52.10 114	48.60 100	68.19 92	66.75 95	75.56 96	75.68 89

CS-MVS		63.45 58	65.72 67	60.80 52	64.20 67	67.86 69	68.46 58	43.50 112	53.86 73	49.90 63	56.44 71	60.45 82	57.27 45	73.56 49	70.13 61	81.45 39	77.73 68

MSLP-MVS++		68.17 43	70.72 48	65.19 38	69.41 42	70.64 55	74.99 40	45.76 74	70.20 46	60.17 23	56.42 72	73.01 43	61.14 23	72.80 53	70.54 56	79.70 50	81.42 51

PVSNet_Blended_VisFu		63.65 57	66.92 58	59.83 58	60.03 87	73.44 47	66.33 72	48.95 62	52.20 86	50.81 60	56.07 73	60.25 83	53.56 69	73.23 52	70.01 62	79.30 54	83.24 44

3Dnovator+	62.63 4	69.51 35	72.62 39	65.88 36	68.21 48	76.47 29	73.50 48	52.74 42	70.85 43	58.65 29	55.97 74	69.95 50	61.11 24	76.80 30	75.09 32	81.09 41	83.23 45

Effi-MVS+		63.28 59	65.96 65	60.17 55	64.26 66	68.06 67	68.78 56	45.71 76	54.08 72	46.64 73	55.92 75	63.13 69	55.94 58	70.38 69	71.43 51	79.68 53	78.70 61

CostFormer		56.57 106	59.13 113	53.60 97	57.52 103	61.12 123	66.94 68	35.95 170	53.44 74	44.68 83	55.87 76	54.44 106	48.21 102	60.37 158	58.33 165	68.27 157	70.33 117

DCV-MVSNet		59.49 75	64.00 77	54.23 92	61.81 76	64.33 104	61.42 102	43.77 101	52.85 82	38.94 115	55.62 77	62.15 73	43.24 130	69.39 75	67.66 84	76.22 88	75.97 85

PMMVS		49.20 157	54.28 147	43.28 168	34.13 198	45.70 194	48.98 166	26.09 200	46.31 130	34.92 131	55.22 78	53.47 109	47.48 108	59.43 160	59.04 163	68.05 158	60.77 173

EPNet_dtu		52.05 137	58.26 121	44.81 160	54.10 134	50.09 179	52.01 157	40.82 140	53.03 80	27.41 160	54.90 79	57.96 94	26.72 183	62.97 144	62.70 147	67.78 159	66.19 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MAR-MVS		68.04 44	70.74 47	64.90 41	71.68 31	76.33 30	74.63 43	50.48 55	63.81 55	55.52 39	54.88 80	69.90 51	57.39 44	75.42 41	74.79 37	79.71 49	80.03 55
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
baseline1		54.48 124	58.69 116	49.57 121	60.63 85	58.29 150	55.70 138	44.95 83	49.20 102	29.62 150	54.77 81	54.75 105	35.29 163	67.15 113	64.08 132	71.21 146	62.58 168

TAPA-MVS	54.74 10	60.85 71	66.61 59	54.12 95	47.38 174	65.33 94	65.35 84	36.51 168	75.16 30	48.82 68	54.70 82	63.51 67	53.31 76	68.36 86	64.97 126	73.37 119	74.27 96
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DI_MVS_plusplus_trai		61.88 66	65.17 71	58.06 66	60.05 86	65.26 96	66.03 75	44.22 91	55.75 68	46.73 71	54.64 83	68.12 58	54.13 66	69.13 77	66.66 97	77.18 74	76.61 77

UniMVSNet_NR-MVSNet		56.94 103	61.14 86	52.05 112	60.02 88	65.21 99	57.44 122	52.93 40	49.37 100	24.31 172	54.62 84	50.54 122	39.04 145	68.69 80	68.84 70	78.53 60	70.72 112

3Dnovator	60.86 6	66.99 50	70.32 50	63.11 48	66.63 54	74.52 38	71.56 52	45.76 74	67.37 51	55.00 43	54.31 85	68.19 57	58.49 39	73.97 47	73.63 46	81.22 40	80.23 54

QAPM		65.27 53	69.49 54	60.35 54	65.43 59	72.20 52	65.69 81	47.23 67	63.46 56	49.14 65	53.56 86	71.04 48	57.01 48	72.60 54	71.41 52	77.62 67	82.14 48

FC-MVSNet-test		39.65 192	48.35 181	29.49 197	44.43 183	39.28 203	30.23 206	40.44 145	43.59 148	3.12 211	53.00 87	42.03 176	10.02 208	55.09 187	54.77 179	48.66 201	50.71 193

TranMVSNet+NR-MVSNet		55.87 110	60.14 100	50.88 114	59.46 91	63.82 106	57.93 120	52.98 39	48.94 106	20.52 178	52.87 88	47.33 139	36.81 159	69.12 78	69.03 68	77.56 70	69.89 118

thisisatest0530		56.68 105	59.68 104	53.19 102	52.97 140	60.96 126	59.41 113	40.51 142	48.26 117	41.06 103	52.67 89	46.30 149	49.78 92	67.66 104	67.83 79	75.39 98	74.07 100

GA-MVS		55.67 112	58.33 120	52.58 109	55.23 126	63.09 109	61.08 104	40.15 148	42.95 154	37.02 125	52.61 90	47.68 134	47.51 107	65.92 130	65.35 117	74.49 106	70.68 115

tpm		48.82 159	51.27 167	45.96 153	54.10 134	47.35 186	56.05 133	30.23 191	46.70 126	43.21 89	52.54 91	47.55 137	37.28 156	54.11 190	50.50 193	54.90 193	60.12 177

tttt0517		56.53 107	59.59 106	52.95 105	52.66 143	60.99 125	59.21 115	40.51 142	47.89 120	40.40 106	52.50 92	46.04 153	49.78 92	67.75 102	67.83 79	75.15 101	74.17 97

Fast-Effi-MVS+		60.36 72	63.35 79	56.87 79	58.70 92	65.86 91	65.08 86	37.11 165	53.00 81	45.36 80	52.12 93	56.07 102	56.27 55	71.28 61	69.42 64	78.71 57	75.69 88

DU-MVS		55.41 115	59.59 106	50.54 117	54.60 129	62.97 110	57.44 122	51.80 45	48.62 114	24.31 172	51.99 94	47.00 142	39.04 145	68.11 93	67.75 82	76.03 93	70.72 112

NR-MVSNet		55.35 116	59.46 110	50.56 116	61.33 80	62.97 110	57.91 121	51.80 45	48.62 114	20.59 177	51.99 94	44.73 167	34.10 169	68.58 83	68.64 72	77.66 66	70.67 116

UniMVSNet (Re)		55.15 120	60.39 94	49.03 129	55.31 123	64.59 103	55.77 137	50.63 52	48.66 113	20.95 176	51.47 96	50.40 123	34.41 168	67.81 100	67.89 78	77.11 77	71.88 106

baseline2		55.89 109	57.82 125	53.64 96	57.36 107	61.09 124	59.75 111	40.45 144	47.38 123	41.26 102	51.23 97	46.90 144	48.11 103	65.63 134	64.38 131	74.90 103	68.16 133

AdaColmap		67.89 45	68.85 55	66.77 29	73.73 21	74.30 42	75.28 39	53.58 36	70.24 45	57.59 34	51.19 98	59.19 87	60.74 27	75.33 42	73.72 45	79.69 52	77.96 66

IterMVS-SCA-FT		52.18 136	57.75 127	45.68 155	51.01 159	62.06 114	55.10 145	34.75 174	44.85 138	32.86 135	51.13 99	51.22 117	48.74 97	62.47 148	61.51 152	51.61 200	71.02 111

IterMVS		53.45 128	57.12 131	49.17 126	49.23 167	60.93 127	59.05 116	34.63 176	44.53 140	33.22 132	51.09 100	51.01 120	48.38 101	62.43 149	60.79 156	70.54 150	69.05 130
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMM	60.30 7	67.58 47	68.82 56	66.13 33	70.59 36	72.01 53	76.54 34	54.26 32	65.64 53	54.78 46	50.35 101	61.72 75	58.74 35	75.79 38	75.03 33	81.88 30	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPMVS		44.66 179	47.86 183	40.92 177	47.97 172	44.70 196	47.58 173	33.27 185	48.11 118	29.58 151	49.65 102	44.38 171	34.65 165	51.71 193	47.90 197	52.49 198	48.57 199

SCA		50.99 145	53.22 155	48.40 138	51.07 157	56.78 159	50.25 161	39.05 151	48.31 116	41.38 99	49.54 103	46.70 147	46.00 114	58.31 168	56.28 168	62.65 176	56.60 185

CDS-MVSNet		52.42 133	57.06 132	47.02 150	53.92 136	58.30 149	55.50 140	46.47 70	42.52 161	29.38 152	49.50 104	52.85 112	28.49 181	66.70 119	66.89 93	68.34 156	62.63 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v2v482		58.69 83	60.12 102	57.03 77	57.16 115	66.05 90	67.17 64	43.52 110	46.33 129	45.19 81	49.46 105	51.02 119	52.51 81	67.30 109	66.03 109	76.61 80	74.62 94

v8		58.88 80	60.57 93	56.92 78	57.35 108	65.69 93	66.69 70	42.64 124	47.89 120	45.77 77	49.04 106	52.98 111	52.77 79	67.51 106	65.57 115	76.26 87	75.30 92

tpmrst		48.08 164	49.88 176	45.98 152	52.71 142	48.11 184	53.62 153	33.70 183	48.70 112	39.74 109	48.96 107	46.23 151	40.29 142	50.14 198	49.28 195	55.80 190	57.71 183

Effi-MVS+-dtu		60.34 73	62.32 82	58.03 68	64.31 64	67.44 77	65.99 76	42.26 127	49.55 97	42.00 97	48.92 108	59.79 85	56.27 55	68.07 95	67.03 89	77.35 72	75.45 90

PatchmatchNet		49.92 152	51.29 166	48.32 140	51.83 151	51.86 173	53.38 155	37.63 164	47.90 119	40.83 104	48.54 109	45.30 158	45.19 119	56.86 175	53.99 186	61.08 181	54.57 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GBi-Net		55.20 117	60.25 96	49.31 123	52.42 144	61.44 118	57.03 125	44.04 95	49.18 103	30.47 143	48.28 110	58.19 90	38.22 148	68.05 96	66.96 90	73.69 114	69.65 120

test1		55.20 117	60.25 96	49.31 123	52.42 144	61.44 118	57.03 125	44.04 95	49.18 103	30.47 143	48.28 110	58.19 90	38.22 148	68.05 96	66.96 90	73.69 114	69.65 120

FMVSNet3		54.78 122	59.58 108	49.17 126	52.37 147	61.31 122	56.72 130	44.04 95	49.18 103	30.47 143	48.28 110	58.19 90	38.09 151	65.48 135	65.20 122	73.31 121	69.45 128

V42		56.97 102	60.14 100	53.28 100	48.16 170	62.78 113	66.30 73	37.93 161	47.44 122	42.68 92	48.19 113	52.59 113	51.90 86	67.46 107	65.94 111	72.72 129	76.55 80

v10		59.17 79	60.60 91	57.50 74	57.95 98	66.73 83	67.09 67	44.11 92	46.85 125	45.42 79	48.18 114	51.07 118	53.63 68	67.84 99	66.59 101	76.79 78	76.92 74

v1144		58.88 80	60.16 99	57.39 75	58.03 97	67.26 78	67.14 65	44.46 89	45.17 137	44.33 85	47.81 115	49.92 126	53.20 78	67.77 101	66.62 100	77.15 75	76.58 78

v148		55.58 114	57.61 129	53.20 101	54.59 131	61.86 115	61.18 103	38.70 157	44.30 144	42.25 95	47.53 116	50.24 125	48.73 98	65.15 138	62.61 148	73.79 112	71.61 108

MDTV_nov1_ep13		50.32 149	52.43 160	47.86 146	49.87 165	54.70 162	58.10 119	34.29 178	45.59 136	37.71 120	47.44 117	47.42 138	41.86 135	58.07 171	55.21 177	65.34 168	58.56 181

OpenMVS	57.13 9	62.81 62	65.75 66	59.39 59	66.47 56	69.52 59	64.26 92	43.07 122	61.34 62	50.19 62	47.29 118	64.41 64	54.60 63	70.18 71	68.62 73	77.73 65	78.89 60

FMVSNet2		55.04 121	59.95 103	49.31 123	52.42 144	61.44 118	57.03 125	44.08 94	49.55 97	30.40 146	46.89 119	58.84 88	38.22 148	67.07 115	66.21 106	73.69 114	69.65 120

v1192		58.51 84	59.66 105	57.17 76	57.82 99	67.72 71	66.21 74	44.83 84	44.15 145	43.49 88	46.68 120	47.94 130	53.55 70	67.39 108	66.51 102	77.13 76	77.20 72

CNLPA		62.78 63	66.31 62	58.65 63	58.47 95	68.41 64	65.98 77	41.22 137	78.02 22	56.04 36	46.65 121	59.50 86	57.50 42	69.67 73	65.27 120	72.70 131	76.67 76

v144192		58.23 93	59.40 111	56.87 79	57.56 100	66.89 81	65.70 79	45.01 82	44.06 146	42.88 90	46.61 122	48.09 129	53.49 73	66.94 117	65.90 112	76.61 80	77.29 70

pmmvs5		47.07 171	51.02 170	42.46 170	45.18 181	51.47 174	48.23 170	33.09 186	38.17 186	28.62 156	46.60 123	43.48 174	30.74 174	58.28 169	58.63 164	68.92 154	60.48 174

CVMVSNet		46.38 175	52.01 163	39.81 180	42.40 188	50.26 177	46.15 179	37.68 163	40.03 175	15.09 188	46.56 124	47.56 136	33.72 170	56.50 180	55.65 173	63.80 172	67.53 135

pmmvs4		54.66 123	56.07 134	53.00 104	54.63 128	57.08 158	60.43 109	44.10 93	51.69 88	40.55 105	46.55 125	44.79 166	45.95 115	62.54 147	63.66 136	72.36 137	66.20 145

CP-MVSNet		48.37 161	53.53 150	42.34 171	51.35 154	58.01 153	46.56 177	50.54 53	41.62 166	10.61 195	46.53 126	40.68 183	23.18 188	58.71 166	61.83 150	71.81 141	67.36 138

DTE-MVSNet		48.03 166	53.28 153	41.91 173	54.64 127	57.50 156	44.63 189	51.66 48	41.02 169	7.97 204	46.26 127	40.90 180	20.24 192	60.45 157	62.89 144	72.33 138	63.97 160

PEN-MVS		49.21 156	54.32 146	43.24 169	54.33 132	59.26 139	47.04 176	51.37 49	41.67 165	9.97 198	46.22 128	41.80 178	22.97 190	60.52 156	64.03 133	73.73 113	66.75 139

PLC	52.09 14	59.21 78	62.47 81	55.41 88	53.24 139	64.84 101	64.47 91	40.41 146	65.92 52	44.53 84	46.19 129	55.69 103	55.33 61	68.24 90	65.30 119	74.50 105	71.09 110
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v1921920		57.89 96	59.02 114	56.58 82	57.55 101	66.66 87	64.72 89	44.70 86	43.55 149	42.73 91	46.17 130	46.93 143	53.51 71	66.78 118	65.75 114	76.29 85	77.28 71

WR-MVS_H		47.65 167	53.67 149	40.63 178	51.45 152	59.74 136	44.71 188	49.37 59	40.69 171	7.61 205	46.04 131	44.34 172	17.32 195	57.79 172	61.18 153	73.30 122	65.86 149

thisisatest0515		53.85 126	56.84 133	50.37 118	50.25 164	58.17 151	55.99 135	39.90 149	41.88 164	38.16 118	45.91 132	45.30 158	44.58 121	66.15 128	66.89 93	73.36 120	73.57 103

Fast-Effi-MVS+-dtu		56.30 108	59.29 112	52.82 107	58.64 94	64.89 100	65.56 82	32.89 187	45.80 134	35.04 129	45.89 133	54.14 107	49.41 95	67.16 112	66.45 104	75.37 99	70.69 114

LS3D		60.20 74	61.70 83	58.45 64	64.18 68	67.77 70	67.19 63	48.84 63	61.67 61	41.27 101	45.89 133	51.81 116	54.18 65	68.78 79	66.50 103	75.03 102	69.48 125

dps		50.42 147	51.20 168	49.51 122	55.88 120	56.07 160	53.73 150	38.89 153	43.66 147	40.36 107	45.66 135	37.63 194	45.23 118	59.05 161	56.18 169	62.94 175	60.16 176

v1240		57.55 98	58.63 118	56.29 83	57.30 111	66.48 88	63.77 94	44.56 88	42.77 159	42.48 93	45.64 136	46.28 150	53.46 74	66.32 124	65.80 113	76.16 89	77.13 73

tpm cat1		53.30 129	53.41 151	53.17 103	58.16 96	59.15 141	63.73 95	38.27 160	50.73 91	46.98 70	45.57 137	44.00 173	49.20 96	55.90 185	54.02 184	62.65 176	64.50 159

MS-PatchMatch		58.19 94	60.20 98	55.85 85	65.17 61	64.16 105	64.82 87	41.48 134	50.95 89	42.17 96	45.38 138	56.42 98	48.08 104	68.30 87	66.70 96	73.39 118	69.46 127

Baseline_NR-MVSNet		53.50 127	57.89 124	48.37 139	54.60 129	59.25 140	56.10 132	51.84 44	49.32 101	17.92 185	45.38 138	47.68 134	36.93 158	68.11 93	65.95 110	72.84 126	69.57 123

PS-CasMVS		48.18 163	53.25 154	42.27 172	51.26 155	57.94 154	46.51 178	50.52 54	41.30 167	10.56 196	45.35 140	40.34 185	23.04 189	58.66 167	61.79 151	71.74 143	67.38 137

WR-MVS		48.78 160	55.06 142	41.45 175	55.50 122	60.40 129	43.77 190	49.99 57	41.92 163	8.10 203	45.24 141	45.56 155	17.47 194	61.57 153	64.60 127	73.85 111	66.14 147

RPSCF		46.41 173	54.42 145	37.06 188	25.70 210	45.14 195	45.39 184	20.81 204	62.79 58	35.10 128	44.92 142	55.60 104	43.56 125	56.12 182	52.45 190	51.80 199	63.91 161

USDC		51.11 143	53.71 148	48.08 143	44.76 182	55.99 161	53.01 156	40.90 138	52.49 84	36.14 126	44.67 143	33.66 199	43.27 129	63.23 143	61.10 154	70.39 151	64.82 156

CR-MVSNet		50.47 146	52.61 157	47.98 144	49.03 169	52.94 168	48.27 168	38.86 154	44.41 141	39.59 111	44.34 144	44.65 169	46.63 111	58.97 163	60.31 158	65.48 166	62.66 165

IB-MVS	54.11 11	58.36 90	60.70 90	55.62 86	58.67 93	68.02 68	61.56 99	43.15 121	46.09 131	44.06 86	44.24 145	50.99 121	48.71 99	66.70 119	70.33 57	77.60 68	78.50 62
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
GG-mvs-BLEND		36.62 195	53.39 152	17.06 204	0.01 215	58.61 144	48.63 167	0.01 212	47.13 124	0.02 215	43.98 146	60.64 80	0.03 211	54.92 189	51.47 192	53.64 196	56.99 184

anonymousdsp		52.84 130	57.78 126	47.06 149	40.24 193	58.95 142	53.70 151	33.54 184	36.51 190	32.69 136	43.88 147	45.40 156	47.97 106	67.17 111	70.28 58	74.22 108	82.29 47

TransMVSNet (Re)		51.92 140	55.38 139	47.88 145	60.95 83	59.90 134	53.95 149	45.14 81	39.47 177	24.85 169	43.87 148	46.51 148	29.15 178	67.55 105	65.23 121	73.26 123	65.16 155

SixPastTwentyTwo		47.55 169	50.25 174	44.41 163	47.30 175	54.31 165	47.81 171	40.36 147	33.76 193	19.93 180	43.75 149	32.77 201	42.07 134	59.82 159	60.94 155	68.98 153	66.37 143

pm-mvs1		51.02 144	55.55 136	45.73 154	54.16 133	58.52 145	50.92 159	42.56 125	40.32 173	25.67 167	43.66 150	50.34 124	30.06 176	65.85 131	63.97 134	70.99 148	66.21 144

test-LLR		49.28 154	50.29 172	48.10 142	55.26 124	47.16 187	49.52 163	43.48 114	39.22 178	31.98 137	43.65 151	47.93 131	41.29 138	56.80 176	55.36 175	67.08 162	61.94 169

TESTMET0.1,1		46.09 176	50.29 172	41.18 176	36.91 196	47.16 187	49.52 163	20.32 205	39.22 178	31.98 137	43.65 151	47.93 131	41.29 138	56.80 176	55.36 175	67.08 162	61.94 169

MSDG		58.46 87	58.97 115	57.85 73	66.27 58	66.23 89	67.72 59	42.33 126	53.43 75	43.68 87	43.39 153	45.35 157	49.75 94	68.66 82	67.77 81	77.38 71	67.96 134

thres200		52.39 134	55.37 140	48.90 130	57.39 106	60.18 131	55.60 139	43.73 103	42.93 155	27.41 160	43.35 154	45.09 162	36.61 160	66.36 122	63.92 135	72.66 132	65.78 150

thres400		52.38 135	55.51 137	48.74 132	57.49 104	60.10 133	55.45 141	43.54 109	42.90 156	26.72 164	43.34 155	45.03 165	36.61 160	66.20 127	64.53 129	72.66 132	66.43 141

test-mter		45.30 177	50.37 171	39.38 181	33.65 200	46.99 189	47.59 172	18.59 206	38.75 181	28.00 157	43.28 156	46.82 146	41.50 137	57.28 174	55.78 172	66.93 164	63.70 162

TAMVS		44.02 181	49.18 178	37.99 186	47.03 176	45.97 193	45.04 185	28.47 195	39.11 180	20.23 179	43.22 157	48.52 127	28.49 181	58.15 170	57.95 167	58.71 184	51.36 191

thres600view7		51.91 141	55.14 141	48.14 141	57.43 105	60.18 131	54.60 147	43.73 103	42.61 160	25.20 168	43.10 158	44.47 170	35.19 164	66.36 122	63.28 140	72.66 132	66.01 148

thres100view900		52.04 138	54.81 144	48.80 131	57.31 109	59.33 138	55.30 143	42.92 123	42.85 157	27.81 158	43.00 159	45.06 163	36.99 157	64.74 140	63.51 137	72.47 135	65.21 154

tfpn200view9		52.53 132	55.51 137	49.06 128	57.31 109	60.24 130	55.42 142	43.77 101	42.85 157	27.81 158	43.00 159	45.06 163	37.32 155	66.38 121	64.54 128	72.71 130	66.54 140

FMVSNet1		54.08 125	58.68 117	48.71 133	50.90 160	61.35 121	56.73 129	43.94 99	45.91 133	29.32 153	42.72 161	56.26 101	37.70 153	68.05 96	66.96 90	73.69 114	69.50 124

ACMH	52.42 13	58.24 92	59.56 109	56.70 81	66.34 57	69.59 58	66.71 69	49.12 61	46.08 132	28.90 154	42.67 162	41.20 179	52.60 80	71.39 59	70.28 58	76.51 82	75.72 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_ETH3D		52.62 131	55.98 135	48.70 134	51.04 158	60.71 128	56.87 128	46.74 69	42.52 161	26.96 163	42.50 163	45.95 154	37.87 152	66.22 126	65.15 125	72.74 128	68.78 132

PatchMatch-RL		50.11 151	51.56 165	48.43 137	46.23 179	51.94 172	50.21 162	38.62 158	46.62 128	37.51 121	42.43 164	39.38 187	52.24 84	60.98 155	59.56 161	65.76 165	60.01 178

PatchT		48.08 164	51.03 169	44.64 161	42.96 187	50.12 178	40.36 196	35.09 172	43.17 152	39.59 111	42.00 165	39.96 186	46.63 111	58.97 163	60.31 158	63.21 173	62.66 165

LTVRE_ROB	44.17 16	47.06 172	50.15 175	43.44 166	51.39 153	58.42 146	42.90 192	43.51 111	22.27 206	14.85 189	41.94 166	34.57 197	45.43 116	62.28 150	62.77 146	62.56 178	68.83 131
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
ACMH+	53.71 12	59.26 77	60.28 95	58.06 66	64.17 69	68.46 63	67.51 62	50.93 50	52.46 85	35.83 127	40.83 167	45.12 161	52.32 83	69.88 72	69.00 69	77.59 69	76.21 84

v7n		55.67 112	57.46 130	53.59 98	56.06 119	65.29 95	61.06 105	43.26 119	40.17 174	37.99 119	40.79 168	45.27 160	47.09 109	67.67 103	66.21 106	76.08 91	76.82 75

ADS-MVSNet		40.67 189	43.38 194	37.50 187	44.36 184	39.79 202	42.09 194	32.67 189	44.34 143	28.87 155	40.76 169	40.37 184	30.22 175	48.34 202	45.87 201	46.81 203	44.21 203

PM-MVS		44.55 180	48.13 182	40.37 179	32.85 202	46.82 191	46.11 180	29.28 193	40.48 172	29.99 148	39.98 170	34.39 198	41.80 136	56.08 183	53.88 188	62.19 179	65.31 152

pmmvs-eth3d		51.33 142	52.25 161	50.26 119	50.82 161	54.65 163	56.03 134	43.45 116	43.51 150	37.20 124	39.20 171	39.04 189	42.28 133	61.85 152	62.78 145	71.78 142	64.72 157

MDTV_nov1_ep13_2view		47.62 168	49.72 177	45.18 158	48.05 171	53.70 166	54.90 146	33.80 182	39.90 176	29.79 149	38.85 172	41.89 177	39.17 144	58.99 162	55.55 174	65.34 168	59.17 179

EG-PatchMatch MVS		56.98 101	58.24 122	55.50 87	64.66 63	68.62 62	61.48 101	43.63 107	38.44 183	41.44 98	38.05 173	46.18 152	43.95 123	71.71 57	70.61 55	77.87 64	74.08 99

COLMAP_ROB	46.52 15	51.99 139	54.86 143	48.63 135	49.13 168	61.73 117	60.53 108	36.57 167	53.14 78	32.95 134	37.10 174	38.68 190	40.49 140	65.72 132	63.08 141	72.11 140	64.60 158
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPMNet		46.41 173	48.72 179	43.72 164	47.77 173	52.94 168	46.02 181	33.92 180	44.41 141	31.82 140	36.89 175	37.42 195	37.41 154	53.88 191	54.02 184	65.37 167	61.47 171

Anonymous202405211			60.60 91		63.44 73	66.71 86	61.00 106	47.23 67	50.62 92		36.85 176	60.63 81	43.03 131	69.17 76	67.72 83	75.41 97	72.54 104

tfpnnormal		50.16 150	52.19 162	47.78 147	56.86 116	58.37 148	54.15 148	44.01 98	38.35 185	25.94 166	36.10 177	37.89 192	34.50 167	65.93 129	63.42 138	71.26 145	65.28 153

TDRefinement		49.31 153	52.44 159	45.67 156	30.44 203	59.42 137	59.24 114	39.78 150	48.76 110	31.20 142	35.73 178	29.90 203	42.81 132	64.24 142	62.59 149	70.55 149	66.43 141

EU-MVSNet		40.63 190	45.65 189	34.78 193	39.11 194	46.94 190	40.02 197	34.03 179	33.50 194	10.37 197	35.57 179	37.80 193	23.65 187	51.90 192	50.21 194	61.49 180	63.62 163

test0.0.03 1		43.15 183	46.95 185	38.72 183	55.26 124	50.56 176	42.48 193	43.48 114	38.16 187	15.11 187	35.07 180	44.69 168	16.47 196	55.95 184	54.34 183	59.54 183	49.87 197

Anonymous20231211		57.71 97	60.79 89	54.13 94	61.68 78	65.81 92	60.81 107	43.70 105	51.97 87	39.67 110	34.82 181	63.59 66	43.31 128	68.55 85	66.63 99	75.59 95	74.13 98

CHOSEN 1792x2688		55.85 111	58.01 123	53.33 99	57.26 112	62.82 112	63.29 98	41.55 133	46.65 127	38.34 116	34.55 182	53.50 108	52.43 82	67.10 114	67.56 86	67.13 161	73.92 101

CMPMVS	37.70 17	49.24 155	52.71 156	45.19 157	45.97 180	51.23 175	47.44 174	29.31 192	43.04 153	44.69 82	34.45 183	48.35 128	43.64 124	62.59 146	59.82 160	60.08 182	69.48 125
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
HyFIR lowres test		56.87 104	58.60 119	54.84 89	56.62 118	69.27 60	64.77 88	42.21 128	45.66 135	37.50 122	33.08 184	57.47 95	53.33 75	65.46 136	67.94 77	74.60 104	71.35 109

MIMVSNet		43.79 182	48.53 180	38.27 184	41.46 191	48.97 182	50.81 160	32.88 188	44.55 139	22.07 174	32.05 185	47.15 140	24.76 186	58.73 165	56.09 171	57.63 189	52.14 189

N_pmnet		32.67 200	36.85 201	27.79 200	40.55 192	32.13 205	35.80 201	26.79 198	37.24 189	9.10 200	32.02 186	30.94 202	16.30 197	47.22 203	41.21 202	38.21 206	37.21 204

MDA-MVSNet-bldmvs		41.36 186	43.15 195	39.27 182	28.74 205	52.68 170	44.95 187	40.84 139	32.89 195	18.13 184	31.61 187	22.09 209	38.97 147	50.45 197	56.11 170	64.01 171	56.23 186

CHOSEN 280x420		40.80 188	45.05 191	35.84 191	32.95 201	29.57 206	44.98 186	23.71 203	37.54 188	18.42 183	31.36 188	47.07 141	46.41 113	56.71 178	54.65 182	48.55 202	58.47 182

testgi		38.71 193	43.64 193	32.95 194	52.30 148	48.63 183	35.59 203	35.05 173	31.58 200	9.03 202	30.29 189	40.75 182	11.19 206	55.30 186	53.47 189	54.53 195	45.48 201

FPMVS		38.36 194	40.41 198	35.97 189	38.92 195	39.85 201	45.50 183	25.79 201	41.13 168	18.70 182	30.10 190	24.56 206	31.86 173	49.42 200	46.80 200	55.04 191	51.03 192

FMVSNet5		40.96 187	45.81 188	35.29 192	34.30 197	44.55 197	47.28 175	28.84 194	40.76 170	21.62 175	29.85 191	42.44 175	24.77 185	57.53 173	55.00 178	54.93 192	50.56 194

TinyColmap		47.08 170	47.56 184	46.52 151	42.35 189	53.44 167	51.77 158	40.70 141	43.44 151	31.92 139	29.78 192	23.72 208	45.04 120	61.99 151	59.54 162	67.35 160	61.03 172

gg-mvs-nofinetune		49.07 158	52.56 158	45.00 159	61.99 75	59.78 135	53.55 154	41.63 132	31.62 199	12.08 193	29.56 193	53.28 110	29.57 177	66.27 125	64.49 130	71.19 147	62.92 164

gm-plane-assit		44.74 178	45.95 186	43.33 167	60.88 84	46.79 192	36.97 200	32.24 190	24.15 205	11.79 194	29.26 194	32.97 200	46.64 110	65.09 139	62.95 143	71.45 144	60.42 175

pmmvs6		48.35 162	51.64 164	44.51 162	51.92 150	57.94 154	49.44 165	42.17 129	34.45 192	24.62 171	28.87 195	46.90 144	29.07 180	64.60 141	63.08 141	69.83 152	65.68 151

test20.03		40.38 191	44.20 192	35.92 190	53.73 137	49.05 180	38.54 198	43.49 113	32.55 196	9.54 199	27.88 196	39.12 188	12.24 201	56.28 181	54.69 180	57.96 188	49.83 198

Anonymous20231206		42.28 184	45.89 187	38.07 185	51.96 149	48.98 181	43.66 191	38.81 156	38.74 182	14.32 190	26.74 197	40.90 180	20.94 191	56.64 179	54.67 181	58.71 184	54.59 187

new-patchmatchnet		33.24 199	37.20 200	28.62 199	44.32 185	38.26 204	29.68 207	36.05 169	31.97 198	6.33 207	26.59 198	27.33 204	11.12 207	50.08 199	41.05 203	44.23 204	45.15 202

MVS-HIRNet		42.24 185	41.15 197	43.51 165	44.06 186	40.74 199	35.77 202	35.35 171	35.38 191	38.34 116	25.63 199	38.55 191	43.48 126	50.77 195	47.03 199	64.07 170	49.98 195

PMVS	27.84 18	33.81 198	35.28 202	32.09 195	34.13 198	24.81 208	32.51 205	26.48 199	26.41 203	19.37 181	23.76 200	24.02 207	25.18 184	50.78 194	47.24 198	54.89 194	49.95 196
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		35.10 197	38.47 199	31.17 196	26.37 209	40.47 200	34.51 204	18.09 207	24.75 204	16.88 186	23.05 201	26.69 205	32.69 172	50.73 196	51.60 191	58.46 187	51.98 190

ambc			45.54 190		50.66 163	52.63 171	40.99 195		38.36 184	24.67 170	22.62 202	13.94 211	29.14 179	65.71 133	58.06 166	58.60 186	67.43 136

MIMVSNet1		35.51 196	41.41 196	28.63 198	27.53 207	43.36 198	38.09 199	33.82 181	32.01 197	6.77 206	21.63 203	35.43 196	11.97 203	55.05 188	53.99 186	53.59 197	48.36 200

new_pmnet		23.19 202	28.17 203	17.37 202	17.03 211	24.92 207	19.66 209	16.16 209	27.05 202	4.42 208	20.77 204	19.20 210	12.19 202	37.71 204	36.38 204	34.77 207	31.17 205

PMMVS2		15.84 203	19.68 205	11.35 206	15.74 212	16.95 210	13.31 210	17.64 208	16.08 208	0.36 214	13.12 205	11.47 212	1.69 210	28.82 205	27.24 206	19.38 210	24.09 208

DeepMVS_CX						6.95 214	5.98 214	2.25 210	11.73 211	2.07 213	11.85 206	5.43 214	11.75 205	11.40 210		8.10 213	18.38 210

tmp_tt				5.40 208	3.97 214	2.35 215	3.26 215	0.44 211	17.56 207	12.09 192	11.48 207	7.14 213	1.98 209	15.68 208	15.49 209	10.69 212

E-PMN		15.09 204	13.19 207	17.30 203	27.80 206	12.62 212	7.81 212	27.54 196	14.62 210	3.19 209	6.89 208	2.52 218	15.09 199	15.93 207	20.22 207	22.38 208	19.53 209

EMVS		14.49 205	12.45 208	16.87 205	27.02 208	12.56 213	8.13 211	27.19 197	15.05 209	3.14 210	6.69 209	2.67 217	15.08 200	14.60 209	18.05 208	20.67 209	17.56 211

MVE	12.28 19	13.53 206	15.72 206	10.96 207	7.39 213	15.71 211	6.05 213	23.73 202	10.29 212	3.01 212	5.77 210	3.41 216	11.91 204	20.11 206	29.79 205	13.67 211	24.98 207
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		25.87 201	26.91 204	24.66 201	28.98 204	20.17 209	20.46 208	34.62 177	29.55 201	9.10 200	4.91 211	5.31 215	15.76 198	49.37 201	49.10 196	39.03 205	29.95 206
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test123		0.01 207	0.02 209	0.00 209	0.00 216	0.00 216	0.00 218	0.00 213	0.01 213	0.00 216	0.04 212	0.00 219	0.01 212	0.00 212	0.01 210	0.00 214	0.07 212

testmvs		0.01 207	0.02 209	0.00 209	0.00 216	0.00 216	0.01 217	0.00 213	0.01 213	0.00 216	0.03 213	0.00 219	0.01 212	0.01 211	0.01 210	0.00 214	0.06 213

uanet_test		0.00 209	0.00 211	0.00 209	0.00 216	0.00 216	0.00 218	0.00 213	0.00 215	0.00 216	0.00 214	0.00 219	0.00 214	0.00 212	0.00 212	0.00 214	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 209	0.00 216	0.00 216	0.00 218	0.00 213	0.00 215	0.00 216	0.00 214	0.00 219	0.00 214	0.00 212	0.00 212	0.00 214	0.00 214

sosnet		0.00 209	0.00 211	0.00 209	0.00 216	0.00 216	0.00 218	0.00 213	0.00 215	0.00 216	0.00 214	0.00 219	0.00 214	0.00 212	0.00 212	0.00 214	0.00 214

9.14												81.81 11

SR-MVS					71.46 33			54.67 28				81.54 12

our_test_3					51.15 156	57.31 157	55.12 144

test_part1																	90.62 2

MTAPA										65.14 2		80.20 18

MTMP										62.63 16		78.04 25

Patchmatch-RL test							1.04 216

XVS					70.49 37	76.96 25	74.36 44			54.48 48		74.47 37				82.24 23

X-MVStestdata					70.49 37	76.96 25	74.36 44			54.48 48		74.47 37				82.24 23

mPP-MVS					71.67 32							74.36 40

NP-MVS									72.00 39

Patchmtry						47.61 185	48.27 168	38.86 154		39.59 111

High-resolution multi-view benchmark