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.

MTMP										95.70 1		96.90 20

MTAPA										95.36 2		97.46 15

MPTG		96.98 11	96.68 19	97.33 2	99.09 3	98.71 9	98.43 6	96.01 11	96.11 12	95.19 3	92.89 28	97.32 17	96.84 9	97.20 13	96.09 32	98.44 23	98.46 26

APDe-MVS		97.79 1	97.96 2	97.60 1	99.20 1	99.10 3	98.88 1	96.68 2	96.81 3	94.64 4	97.84 1	98.02 7	97.24 2	97.74 4	97.02 9	98.97 1	99.16 2

SD-MVS		97.35 4	97.73 3	96.90 10	97.35 38	98.66 10	97.85 22	96.25 7	96.86 2	94.54 5	96.75 8	99.13 2	96.99 5	96.94 19	96.58 18	98.39 32	99.20 1

MSLP-MVS++		96.05 23	95.63 27	96.55 17	98.33 24	98.17 35	96.94 31	94.61 28	94.70 33	94.37 6	89.20 44	95.96 28	96.81 10	95.57 45	97.33 4	98.24 58	98.47 24

HSP-MVS		97.51 3	97.70 4	97.29 3	99.00 10	99.17 1	98.61 3	96.41 5	95.88 14	94.34 7	97.72 2	99.04 3	96.93 8	97.29 12	95.90 35	98.45 22	98.94 8

CNVR-MVS		97.30 6	97.41 7	97.18 6	99.02 9	98.60 17	98.15 14	96.24 8	96.12 11	94.10 8	95.54 20	97.99 8	96.99 5	97.97 1	97.17 5	98.57 11	98.50 22

PLC	90.69 4	94.32 39	92.99 48	95.87 24	97.91 28	96.49 83	95.95 45	94.12 29	94.94 28	94.09 9	85.90 56	90.77 53	95.58 27	94.52 72	93.32 82	97.55 107	95.00 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + MP.		97.31 5	97.64 5	96.92 9	97.28 40	98.56 19	98.61 3	95.48 22	96.72 4	94.03 10	96.73 9	98.29 5	97.15 3	97.61 8	96.42 21	98.96 2	99.13 3

APD-MVS		97.12 8	97.05 13	97.19 5	99.04 6	98.63 15	98.45 5	96.54 3	94.81 31	93.50 11	96.10 14	97.40 16	96.81 10	97.05 16	96.82 14	98.80 5	98.56 16
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
AdaColmap		95.02 32	93.71 41	96.54 18	98.51 21	97.76 48	96.69 34	95.94 14	93.72 40	93.50 11	89.01 45	90.53 56	96.49 18	94.51 73	93.76 68	98.07 76	96.69 81

ESAPD		97.65 2	97.98 1	97.27 4	99.12 2	99.14 2	98.66 2	96.80 1	95.74 15	93.46 13	97.72 2	99.48 1	96.76 13	97.77 2	96.92 12	98.83 4	99.07 6

CNLPA		93.69 44	92.50 53	95.06 31	97.11 43	97.36 55	93.88 76	93.30 32	95.64 18	93.44 14	80.32 96	90.73 54	94.99 32	93.58 94	93.33 81	97.67 102	96.57 91

CSCG		95.68 26	95.46 31	95.93 23	98.71 19	99.07 4	97.13 30	93.55 31	95.48 20	93.35 15	90.61 39	93.82 39	95.16 30	94.60 70	95.57 40	97.70 99	99.08 5

HFP-MVS		97.11 9	97.19 11	97.00 8	98.97 12	98.73 8	98.37 9	95.69 16	96.60 5	93.28 16	96.87 5	96.64 22	97.27 1	96.64 24	96.33 27	98.44 23	98.56 16

HPM-MVS++		97.22 7	97.40 8	97.01 7	99.08 4	98.55 20	98.19 12	96.48 4	96.02 13	93.28 16	96.26 12	98.71 4	96.76 13	97.30 11	96.25 29	98.30 46	98.68 10

3Dnovator+	90.56 5	95.06 31	94.56 36	95.65 27	98.11 26	98.15 36	97.19 28	91.59 46	95.11 26	93.23 18	81.99 89	94.71 36	95.43 29	96.48 28	96.88 13	98.35 35	98.63 12

CP-MVS		96.68 16	96.59 22	96.77 13	98.85 17	98.58 18	98.18 13	95.51 20	95.34 21	92.94 19	95.21 23	96.25 24	96.79 12	96.44 31	95.77 37	98.35 35	98.56 16

ACMMPR		96.92 13	96.96 14	96.87 11	98.99 11	98.78 7	98.38 8	95.52 19	96.57 6	92.81 20	96.06 15	95.90 29	97.07 4	96.60 26	96.34 26	98.46 19	98.42 27

NCCC		96.75 15	96.67 20	96.85 12	99.03 8	98.44 28	98.15 14	96.28 6	96.32 8	92.39 21	92.16 30	97.55 14	96.68 16	97.32 9	96.65 17	98.55 12	98.26 31

CPTT-MVS		95.54 27	95.07 32	96.10 21	97.88 30	97.98 42	97.92 21	94.86 26	94.56 34	92.16 22	91.01 37	95.71 30	96.97 7	94.56 71	93.50 77	96.81 156	98.14 38

DeepC-MVS_fast	93.32 1	96.48 18	96.42 23	96.56 16	98.70 20	98.31 32	97.97 19	95.76 15	96.31 9	92.01 23	91.43 35	95.42 33	96.46 19	97.65 7	97.69 1	98.49 16	98.12 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		97.10 10	97.49 6	96.65 14	98.97 12	98.95 5	98.43 6	95.96 12	95.12 24	91.46 24	96.85 6	97.60 13	96.37 21	97.76 3	97.16 6	98.68 6	98.97 7
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator	90.28 7	94.70 37	94.34 39	95.11 30	98.06 27	98.21 33	96.89 32	91.03 52	94.72 32	91.45 25	82.87 80	93.10 42	94.61 34	96.24 37	97.08 8	98.63 9	98.16 36

abl_6				94.78 32	97.46 37	97.99 41	95.76 46	91.80 43	93.72 40	91.25 26	91.33 36	96.47 23	94.28 39			98.14 66	97.39 63

TSAR-MVS + GP.		95.86 24	96.95 16	94.60 37	94.07 78	98.11 37	96.30 38	91.76 44	95.67 16	91.07 27	96.82 7	97.69 12	95.71 26	95.96 40	95.75 38	98.68 6	98.63 12

CANet		94.85 33	94.92 33	94.78 32	97.25 41	98.52 23	97.20 27	91.81 42	93.25 43	91.06 28	86.29 52	94.46 37	92.99 53	97.02 17	96.68 15	98.34 37	98.20 34

ACMMP_Plus		96.93 12	97.27 10	96.53 19	99.06 5	98.95 5	98.24 11	96.06 10	95.66 17	90.96 29	95.63 19	97.71 11	96.53 17	97.66 6	96.68 15	98.30 46	98.61 15

MCST-MVS		96.83 14	97.06 12	96.57 15	98.88 16	98.47 26	98.02 18	96.16 9	95.58 19	90.96 29	95.78 18	97.84 10	96.46 19	97.00 18	96.17 31	98.94 3	98.55 21

MP-MVS		96.56 17	96.72 18	96.37 20	98.93 15	98.48 24	98.04 17	95.55 18	94.32 35	90.95 31	95.88 17	97.02 19	96.29 22	96.77 22	96.01 34	98.47 17	98.56 16

PVSNet_BlendedMVS		92.80 48	92.44 55	93.23 49	96.02 54	97.83 46	93.74 79	90.58 54	91.86 52	90.69 32	85.87 58	82.04 88	90.01 85	96.39 32	95.26 44	98.34 37	97.81 51

PVSNet_Blended		92.80 48	92.44 55	93.23 49	96.02 54	97.83 46	93.74 79	90.58 54	91.86 52	90.69 32	85.87 58	82.04 88	90.01 85	96.39 32	95.26 44	98.34 37	97.81 51

PGM-MVS		96.16 20	96.33 24	95.95 22	99.04 6	98.63 15	98.32 10	92.76 36	93.42 42	90.49 34	96.30 11	95.31 34	96.71 15	96.46 29	96.02 33	98.38 33	98.19 35

OMC-MVS		94.49 38	94.36 38	94.64 35	97.17 42	97.73 49	95.49 50	92.25 38	96.18 10	90.34 35	88.51 46	92.88 43	94.90 33	94.92 55	94.17 57	97.69 100	96.15 106

DELS-MVS		93.71 43	93.47 43	94.00 39	96.82 47	98.39 30	96.80 33	91.07 51	89.51 81	89.94 36	83.80 76	89.29 62	90.95 76	97.32 9	97.65 2	98.42 26	98.32 30
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
ACMMP		95.54 27	95.49 30	95.61 28	98.27 25	98.53 22	97.16 29	94.86 26	94.88 30	89.34 37	95.36 22	91.74 47	95.50 28	95.51 46	94.16 58	98.50 15	98.22 33
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
DeepPCF-MVS	92.65 2	95.50 29	96.96 14	93.79 45	96.44 50	98.21 33	93.51 84	94.08 30	96.94 1	89.29 38	93.08 26	96.77 21	93.82 46	97.68 5	97.40 3	95.59 181	98.65 11

EPNet		93.92 42	94.40 37	93.36 48	97.89 29	96.55 80	96.08 41	92.14 39	91.65 55	89.16 39	94.07 25	90.17 60	87.78 106	95.24 48	94.97 48	97.09 123	98.15 37
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CLD-MVS		92.50 52	91.96 63	93.13 52	93.93 83	96.24 91	95.69 47	88.77 82	92.92 45	89.01 40	88.19 48	81.74 91	93.13 52	93.63 92	93.08 93	98.23 59	97.91 48
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DeepC-MVS	92.10 3	95.22 30	94.77 34	95.75 26	97.77 32	98.54 21	97.63 24	95.96 12	95.07 27	88.85 41	85.35 60	91.85 46	95.82 24	96.88 21	97.10 7	98.44 23	98.63 12
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_111021_LR		94.84 34	95.57 28	94.00 39	97.11 43	97.72 51	94.88 56	91.16 50	95.24 23	88.74 42	96.03 16	91.52 50	94.33 38	95.96 40	95.01 47	97.79 91	97.49 59

MVSTER		91.73 62	91.61 66	91.86 63	93.18 103	94.56 102	94.37 59	87.90 94	90.16 71	88.69 43	89.23 43	81.28 93	88.92 100	95.75 43	93.95 65	98.12 68	96.37 95

IB-MVS	85.10 14	87.98 106	87.97 100	87.99 111	94.55 69	96.86 75	84.52 198	88.21 89	86.48 108	88.54 44	74.41 132	77.74 107	74.10 205	89.65 158	92.85 96	98.06 78	97.80 53
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
XVS					95.68 56	98.66 10	94.96 54			88.03 45		96.06 25				98.46 19

X-MVStestdata					95.68 56	98.66 10	94.96 54			88.03 45		96.06 25				98.46 19

X-MVS		96.07 22	96.33 24	95.77 25	98.94 14	98.66 10	97.94 20	95.41 24	95.12 24	88.03 45	93.00 27	96.06 25	95.85 23	96.65 23	96.35 24	98.47 17	98.48 23

PHI-MVS		95.86 24	96.93 17	94.61 36	97.60 36	98.65 14	96.49 35	93.13 34	94.07 37	87.91 48	97.12 4	97.17 18	93.90 45	96.46 29	96.93 11	98.64 8	98.10 42

train_agg		96.15 21	96.64 21	95.58 29	98.44 22	98.03 39	98.14 16	95.40 25	93.90 39	87.72 49	96.26 12	98.10 6	95.75 25	96.25 36	95.45 42	98.01 82	98.47 24

DWT-MVSNet_training		86.83 116	84.44 141	89.61 90	92.75 109	93.82 116	91.66 115	82.85 146	88.57 88	87.48 50	79.00 101	64.24 191	88.82 102	85.18 200	87.50 190	94.07 194	92.79 171

canonicalmvs		93.08 46	93.09 46	93.07 55	94.24 71	97.86 44	95.45 51	87.86 98	94.00 38	87.47 51	88.32 47	82.37 87	95.13 31	93.96 87	96.41 22	98.27 53	98.73 9

PVSNet_Blended_VisFu		91.92 58	92.39 57	91.36 76	95.45 64	97.85 45	92.25 102	89.54 72	88.53 90	87.47 51	79.82 98	90.53 56	85.47 147	96.31 35	95.16 46	97.99 84	98.56 16

ACMM	88.76 10	91.70 63	90.43 72	93.19 51	95.56 59	95.14 100	93.35 87	91.48 47	92.26 51	87.12 53	84.02 75	79.34 98	93.99 42	94.07 82	92.68 100	97.62 106	95.50 125
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dps		85.00 138	83.21 161	87.08 122	90.73 130	92.55 161	89.34 159	75.29 201	84.94 123	87.01 54	79.27 100	67.69 153	87.27 114	84.22 207	83.56 207	92.83 199	90.25 195

MVS_0304		94.30 40	94.68 35	93.86 44	96.33 52	98.48 24	97.41 25	91.20 48	92.75 47	86.96 55	86.03 55	93.81 40	92.64 57	96.89 20	96.54 20	98.61 10	98.24 32

PatchMatch-RL		90.30 74	88.93 88	91.89 62	95.41 65	95.68 96	90.94 118	88.67 84	89.80 78	86.95 56	85.90 56	72.51 124	92.46 58	93.56 97	92.18 109	96.93 141	92.89 170

TSAR-MVS + ACMM		96.19 19	97.39 9	94.78 32	97.70 34	98.41 29	97.72 23	95.49 21	96.47 7	86.66 57	96.35 10	97.85 9	93.99 42	97.19 14	96.37 23	97.12 121	99.13 3

OpenMVS	88.18 11	92.51 51	91.61 66	93.55 47	97.74 33	98.02 40	95.66 48	90.46 56	89.14 83	86.50 58	75.80 123	90.38 59	92.69 56	94.99 51	95.30 43	98.27 53	97.63 55

MSDG		90.42 73	88.25 97	92.94 56	96.67 49	94.41 108	93.96 72	92.91 35	89.59 80	86.26 59	76.74 115	80.92 94	90.43 82	92.60 110	92.08 113	97.44 111	91.41 183

MVS_111021_HR		94.84 34	95.91 26	93.60 46	97.35 38	98.46 27	95.08 53	91.19 49	94.18 36	85.97 60	95.38 21	92.56 44	93.61 47	96.61 25	96.25 29	98.40 30	97.92 46

TAPA-MVS	90.35 6	93.69 44	93.52 42	93.90 42	96.89 46	97.62 52	96.15 39	91.67 45	94.94 28	85.97 60	87.72 49	91.96 45	94.40 35	93.76 88	93.06 95	98.30 46	95.58 124
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DI_MVS_plusplus_trai		91.05 67	90.15 75	92.11 61	92.67 110	96.61 78	96.03 42	88.44 86	90.25 66	85.92 62	73.73 133	84.89 75	91.92 61	94.17 80	94.07 62	97.68 101	97.31 65

UGNet		91.52 64	93.41 44	89.32 95	94.13 73	97.15 67	91.83 113	89.01 79	90.62 62	85.86 63	86.83 50	91.73 48	77.40 195	94.68 67	94.43 53	97.71 97	98.40 29
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
diffmvs		91.35 65	91.81 64	90.82 81	92.80 107	95.62 97	93.74 79	86.04 107	93.17 44	85.82 64	84.48 70	89.74 61	90.23 84	90.49 144	92.45 102	96.29 167	96.72 79

MAR-MVS		92.71 50	92.63 51	92.79 57	97.70 34	97.15 67	93.75 78	87.98 92	90.71 60	85.76 65	86.28 53	86.38 66	94.35 37	94.95 53	95.49 41	97.22 115	97.44 61
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
QAPM		94.13 41	94.33 40	93.90 42	97.82 31	98.37 31	96.47 36	90.89 53	92.73 48	85.63 66	85.35 60	93.87 38	94.17 40	95.71 44	95.90 35	98.40 30	98.42 27

GBi-Net		90.21 75	90.11 76	90.32 83	88.66 146	93.65 123	94.25 68	85.78 111	90.03 73	85.56 67	77.38 109	86.13 67	89.38 91	93.97 84	94.16 58	98.31 43	95.47 126

test1		90.21 75	90.11 76	90.32 83	88.66 146	93.65 123	94.25 68	85.78 111	90.03 73	85.56 67	77.38 109	86.13 67	89.38 91	93.97 84	94.16 58	98.31 43	95.47 126

FMVSNet3		90.19 77	90.06 78	90.34 82	88.69 145	93.85 115	94.58 57	85.78 111	90.03 73	85.56 67	77.38 109	86.13 67	89.22 94	93.29 103	94.36 55	98.20 62	95.40 130

ACMP	89.13 9	92.03 56	91.70 65	92.41 59	94.92 67	96.44 86	93.95 74	89.96 59	91.81 54	85.48 70	90.97 38	79.12 99	92.42 59	93.28 104	92.55 101	97.76 93	97.74 54
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tpm cat1		84.13 158	81.99 185	86.63 128	91.74 117	91.50 186	90.68 120	75.69 200	86.12 109	85.44 71	72.39 142	70.72 133	85.16 149	80.89 217	81.56 216	91.07 213	90.71 191

CostFormer		86.78 118	86.05 123	87.62 118	92.15 112	93.20 141	91.55 116	75.83 199	88.11 93	85.29 72	81.76 90	76.22 116	87.80 105	84.45 205	85.21 201	93.12 197	93.42 165

RPSCF		89.68 82	89.24 83	90.20 86	92.97 105	92.93 151	92.30 100	87.69 100	90.44 65	85.12 73	91.68 34	85.84 72	90.69 79	87.34 190	86.07 194	92.46 204	90.37 194

PCF-MVS	90.19 8	92.98 47	92.07 61	94.04 38	96.39 51	97.87 43	96.03 42	95.47 23	87.16 99	85.09 74	84.81 68	93.21 41	93.46 50	91.98 119	91.98 116	97.78 92	97.51 58
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FMVSNet2		89.61 83	89.14 85	90.16 87	88.66 146	93.65 123	94.25 68	85.44 118	88.57 88	84.96 75	73.53 135	83.82 77	89.38 91	94.23 78	94.68 52	98.31 43	95.47 126

CHOSEN 280x420		90.77 69	92.14 60	89.17 97	93.86 90	92.81 155	93.16 88	80.22 180	90.21 68	84.67 76	89.89 41	91.38 51	90.57 81	94.94 54	92.11 111	92.52 203	93.65 162

EPP-MVSNet		92.13 55	93.06 47	91.05 79	93.66 96	97.30 58	92.18 105	87.90 94	90.24 67	83.63 77	86.14 54	90.52 58	90.76 78	94.82 64	94.38 54	98.18 64	97.98 43

tpmp4_e23		85.67 130	84.28 143	87.30 120	91.96 115	92.00 178	92.06 110	76.27 197	87.95 94	83.59 78	76.97 114	70.88 132	87.52 110	84.80 204	84.73 203	92.40 205	92.61 178

MVS_Test		91.81 61	92.19 59	91.37 75	93.24 102	96.95 72	94.43 58	86.25 106	91.45 57	83.45 79	86.31 51	85.15 73	92.93 54	93.99 83	94.71 51	97.92 87	96.77 78

FC-MVSNet-train		90.55 71	90.19 74	90.97 80	93.78 92	95.16 99	92.11 109	88.85 81	87.64 95	83.38 80	84.36 73	78.41 102	89.53 88	94.69 66	93.15 91	98.15 65	97.92 46

CDPH-MVS		94.80 36	95.50 29	93.98 41	98.34 23	98.06 38	97.41 25	93.23 33	92.81 46	82.98 81	92.51 29	94.82 35	93.53 48	96.08 39	96.30 28	98.42 26	97.94 44

FMVSNet1		87.33 112	86.00 126	88.89 99	87.13 189	92.83 154	93.08 90	84.46 129	81.35 151	82.20 82	66.33 181	77.96 105	88.96 97	93.97 84	94.16 58	97.54 108	95.38 131

OPM-MVS		91.08 66	89.34 82	93.11 54	96.18 53	96.13 94	96.39 37	92.39 37	82.97 142	81.74 83	82.55 86	80.20 95	93.97 44	94.62 68	93.23 84	98.00 83	95.73 119

conf0.002		89.25 94	87.21 115	91.62 64	93.87 89	97.35 56	94.31 63	89.83 61	85.87 110	81.62 84	78.72 104	63.89 192	91.76 64	94.90 62	93.98 64	98.33 41	95.77 117

conf0.01		89.34 90	87.39 114	91.61 65	93.88 88	97.34 57	94.31 63	89.82 63	85.87 110	81.53 85	77.93 108	66.15 175	91.76 64	94.90 62	93.51 71	98.32 42	96.05 110

thres200		89.49 86	87.72 104	91.55 67	93.95 81	97.25 62	94.34 61	89.74 67	85.66 118	81.18 86	76.12 122	70.19 140	91.80 62	94.92 55	93.51 71	98.27 53	96.40 94

thres100view900		89.36 88	87.61 107	91.39 73	93.90 84	96.86 75	94.35 60	89.66 71	85.87 110	81.15 87	76.46 117	70.38 135	91.17 73	94.09 81	93.43 79	98.13 67	96.16 105

tfpn200view9		89.55 84	87.86 101	91.53 68	93.90 84	97.26 59	94.31 63	89.74 67	85.87 110	81.15 87	76.46 117	70.38 135	91.76 64	94.92 55	93.51 71	98.28 52	96.61 84

tfpn111		90.16 78	88.99 87	91.52 70	93.90 84	97.26 59	94.31 63	89.75 64	85.87 110	81.10 89	84.41 71	70.38 135	91.76 64	94.92 55	93.51 71	98.29 50	96.61 84

conf200view11		89.55 84	87.86 101	91.52 70	93.90 84	97.26 59	94.31 63	89.75 64	85.87 110	81.10 89	76.46 117	70.38 135	91.76 64	94.92 55	93.51 71	98.29 50	96.61 84

thres400		89.40 87	87.58 109	91.53 68	94.06 79	97.21 64	94.19 71	89.83 61	85.69 116	81.08 91	75.50 125	69.76 141	91.80 62	94.79 65	93.51 71	98.20 62	96.60 89

pmmvs4		86.00 127	84.28 143	88.00 110	87.80 157	92.01 177	89.94 148	84.91 124	86.79 102	80.98 92	73.41 138	66.34 168	88.12 104	89.31 168	88.90 186	96.24 169	93.20 168

view600		89.29 92	87.48 111	91.41 72	94.10 76	97.21 64	93.96 72	89.70 70	85.67 117	80.75 93	75.29 127	69.35 142	91.70 69	94.92 55	93.23 84	98.26 57	96.69 81

thres600view7		89.28 93	87.47 112	91.39 73	94.12 75	97.25 62	93.94 75	89.74 67	85.62 120	80.63 94	75.24 130	69.33 143	91.66 70	94.92 55	93.23 84	98.27 53	96.72 79

PMMVS		89.88 79	91.19 69	88.35 104	89.73 137	91.97 179	90.62 121	81.92 159	90.57 63	80.58 95	92.16 30	86.85 65	91.17 73	92.31 113	91.35 126	96.11 170	93.11 169

view800		89.21 95	87.44 113	91.27 77	94.13 73	97.18 66	93.74 79	89.53 73	85.60 121	80.34 96	75.29 127	68.89 144	91.57 71	94.97 52	93.36 80	98.34 37	96.79 77

TSAR-MVS + COLMAP		92.39 53	92.31 58	92.47 58	95.35 66	96.46 84	96.13 40	92.04 41	95.33 22	80.11 97	94.95 24	77.35 111	94.05 41	94.49 74	93.08 93	97.15 118	94.53 148

IS_MVSNet		91.87 59	93.35 45	90.14 88	94.09 77	97.73 49	93.09 89	88.12 90	88.71 86	79.98 98	84.49 69	90.63 55	87.49 111	97.07 15	96.96 10	98.07 76	97.88 50

tfpn		88.67 98	86.57 118	91.12 78	94.14 72	97.15 67	93.51 84	89.37 74	85.49 122	79.91 99	75.26 129	62.24 198	91.39 72	95.00 50	93.95 65	98.41 28	96.88 75

HQP-MVS		92.39 53	92.49 54	92.29 60	95.65 58	95.94 95	95.64 49	92.12 40	92.46 50	79.65 100	91.97 32	82.68 84	92.92 55	93.47 99	92.77 98	97.74 95	98.12 40

CDS-MVSNet		88.34 104	88.71 91	87.90 113	90.70 132	94.54 103	92.38 96	86.02 108	80.37 161	79.42 101	79.30 99	83.43 78	82.04 177	93.39 101	94.01 63	96.86 154	95.93 112
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LS3D		91.97 57	90.98 70	93.12 53	97.03 45	97.09 70	95.33 52	95.59 17	92.47 49	79.26 102	81.60 92	82.77 83	94.39 36	94.28 76	94.23 56	97.14 120	94.45 150

UA-Net		90.81 68	92.58 52	88.74 102	94.87 68	97.44 54	92.61 94	88.22 88	82.35 145	78.93 103	85.20 62	95.61 31	79.56 189	96.52 27	96.57 19	98.23 59	94.37 151

IterMVS-LS		88.60 99	88.45 93	88.78 101	92.02 114	92.44 167	92.00 112	83.57 139	86.52 106	78.90 104	78.61 105	81.34 92	89.12 95	90.68 140	93.18 89	97.10 122	96.35 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn_ndepth		89.72 81	89.91 79	89.49 92	93.56 100	96.67 77	92.34 99	89.25 75	90.85 59	78.68 105	84.25 74	77.39 110	84.84 153	93.58 94	92.76 99	98.30 46	93.90 158

LGP-MVS_train		91.83 60	92.04 62	91.58 66	95.46 62	96.18 93	95.97 44	89.85 60	90.45 64	77.76 106	91.92 33	80.07 96	92.34 60	94.27 77	93.47 78	98.11 70	97.90 49

Fast-Effi-MVS+		88.56 103	87.99 99	89.22 96	91.56 120	95.21 98	92.29 101	82.69 148	86.82 101	77.73 107	76.24 121	73.39 123	93.36 51	94.22 79	93.64 69	97.65 103	96.43 93

conf0.05thres1000		87.90 107	85.88 129	90.26 85	93.74 93	96.39 88	92.67 93	88.94 80	80.97 154	77.71 108	70.15 152	68.40 149	90.42 83	94.46 75	93.29 83	98.09 72	97.49 59

CHOSEN 1792x2688		88.57 102	87.82 103	89.44 94	95.46 62	96.89 74	93.74 79	85.87 110	89.63 79	77.42 109	61.38 206	83.31 79	88.80 103	93.44 100	93.16 90	95.37 186	96.95 72

HyFIR lowres test		87.87 108	86.42 120	89.57 91	95.56 59	96.99 71	92.37 97	84.15 132	86.64 103	77.17 110	57.65 211	83.97 76	91.08 75	92.09 118	92.44 103	97.09 123	95.16 142

MDTV_nov1_ep13		86.64 120	87.50 110	85.65 143	90.73 130	93.69 122	89.96 147	78.03 192	89.48 82	76.85 111	84.92 67	82.42 86	86.14 131	86.85 195	86.15 193	92.17 207	88.97 201

tfpn1000		89.30 91	89.72 81	88.81 100	93.83 91	96.50 82	91.53 117	88.74 83	91.20 58	76.74 112	84.96 66	75.44 119	83.50 168	93.63 92	92.42 104	98.51 13	93.88 159

Effi-MVS+		89.79 80	89.83 80	89.74 89	92.98 104	96.45 85	93.48 86	84.24 130	87.62 96	76.45 113	81.76 90	77.56 109	93.48 49	94.61 69	93.59 70	97.82 90	97.22 66

MS-PatchMatch		87.63 109	87.61 107	87.65 116	93.95 81	94.09 112	92.60 95	81.52 164	86.64 103	76.41 114	73.46 137	85.94 70	85.01 152	92.23 116	90.00 169	96.43 164	90.93 189

Vis-MVSNet (Re-imp)		90.54 72	92.76 50	87.94 112	93.73 94	96.94 73	92.17 107	87.91 93	88.77 85	76.12 115	83.68 77	90.80 52	79.49 190	96.34 34	96.35 24	98.21 61	96.46 92

COLMAP_ROB	84.39 15	87.61 110	86.03 124	89.46 93	95.54 61	94.48 105	91.77 114	90.14 58	87.16 99	75.50 116	73.41 138	76.86 114	87.33 113	90.05 152	89.76 176	96.48 162	90.46 193
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Vis-MVSNet		89.36 88	91.49 68	86.88 124	92.10 113	97.60 53	92.16 108	85.89 109	84.21 133	75.20 117	82.58 84	87.13 63	77.40 195	95.90 42	95.63 39	98.51 13	97.36 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet (Re)		86.22 122	85.46 135	87.11 121	88.34 150	94.42 107	89.65 157	87.10 105	84.39 130	74.61 118	70.41 150	68.10 150	85.10 151	91.17 130	91.79 118	97.84 89	97.94 44

thresconf0.02		88.86 96	88.70 92	89.04 98	93.59 99	96.40 87	92.97 91	89.75 64	90.16 71	74.34 119	84.41 71	71.00 131	85.16 149	93.32 102	93.12 92	98.41 28	92.52 179

EPMVS		85.77 128	86.24 122	85.23 151	92.76 108	93.78 118	89.91 149	73.60 208	90.19 69	74.22 120	82.18 88	78.06 104	87.55 109	85.61 199	85.38 200	93.32 196	88.48 204

Baseline_NR-MVSNet		85.28 135	83.42 152	87.46 119	87.77 159	90.80 193	89.90 151	87.69 100	83.93 137	74.16 121	64.72 196	66.43 165	87.48 112	90.14 147	90.83 129	97.73 96	97.11 69

FMVSNet5		84.47 149	84.72 139	84.18 169	83.30 211	88.43 206	88.09 174	79.42 186	84.25 132	74.14 122	73.15 140	78.74 100	83.65 166	91.19 129	91.19 127	96.46 163	86.07 210

v148		83.61 170	82.10 182	85.37 147	87.34 177	92.94 150	87.48 178	85.72 114	78.92 180	73.87 123	65.71 191	64.69 187	81.78 181	87.82 184	89.35 182	96.01 171	95.26 136

TAMVS		84.94 140	84.95 136	84.93 160	88.82 142	93.18 143	88.44 172	81.28 166	77.16 191	73.76 124	75.43 126	76.57 115	82.04 177	90.59 141	90.79 130	95.22 188	90.94 188

UniMVSNet_NR-MVSNet		86.80 117	85.86 130	87.89 114	88.17 152	94.07 113	90.15 140	88.51 85	84.20 134	73.45 125	72.38 143	70.30 139	88.95 98	90.25 146	92.21 108	98.12 68	97.62 56

DU-MVS		86.12 124	84.81 138	87.66 115	87.77 159	93.78 118	90.15 140	87.87 96	84.40 128	73.45 125	70.59 147	64.82 186	88.95 98	90.14 147	92.33 105	97.76 93	97.62 56

tpmrst		83.72 166	83.45 150	84.03 171	92.21 111	91.66 183	88.74 169	73.58 209	88.14 92	72.67 127	77.37 112	72.11 127	86.34 124	82.94 211	82.05 213	90.63 216	89.86 198

PatchmatchNet		85.70 129	86.65 116	84.60 163	91.79 116	93.40 133	89.27 160	73.62 207	90.19 69	72.63 128	82.74 83	81.93 90	87.64 107	84.99 201	84.29 206	92.64 201	89.00 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pm-mvs1		84.55 145	83.46 149	85.82 138	88.16 154	93.39 134	89.05 165	85.36 120	74.03 206	72.43 129	65.08 194	71.11 130	82.30 176	93.48 98	91.70 120	97.64 104	95.43 129

ACMH+	85.75 12	87.19 114	86.02 125	88.56 103	93.42 101	94.41 108	89.91 149	87.66 102	83.45 140	72.25 130	76.42 120	71.99 128	90.78 77	89.86 153	90.94 128	97.32 112	95.11 144

v18		84.21 155	82.90 167	85.74 141	87.63 163	89.75 195	90.56 122	80.82 170	81.42 149	72.24 131	67.16 164	67.23 155	86.27 126	89.25 172	90.24 152	96.92 145	95.27 135

tfpn_n400		88.58 100	88.91 89	88.19 106	93.63 97	96.34 89	92.22 103	89.04 77	87.37 97	72.14 132	85.12 63	73.93 120	84.04 164	93.65 90	93.20 87	98.09 72	92.77 172

tfpnconf		88.58 100	88.91 89	88.19 106	93.63 97	96.34 89	92.22 103	89.04 77	87.37 97	72.14 132	85.12 63	73.93 120	84.04 164	93.65 90	93.20 87	98.09 72	92.77 172

tfpnview11		88.80 97	89.21 84	88.31 105	93.70 95	96.24 91	92.35 98	89.11 76	89.90 77	72.14 132	85.12 63	73.93 120	84.20 159	93.75 89	92.85 96	98.38 33	92.68 177

v16		84.14 157	82.86 169	85.64 144	87.61 164	89.71 197	90.36 125	80.70 172	81.36 150	71.99 135	66.91 171	67.19 156	86.23 129	89.32 166	90.25 149	96.94 138	95.29 133

v17		84.10 159	82.83 170	85.57 146	87.58 165	89.72 196	90.30 134	80.70 172	81.00 153	71.72 136	67.01 166	67.24 154	86.19 130	89.32 166	90.25 149	96.95 136	95.29 133

NR-MVSNet		85.46 134	84.54 140	86.52 129	88.33 151	93.78 118	90.45 124	87.87 96	84.40 128	71.61 137	70.59 147	62.09 201	82.79 171	91.75 121	91.75 119	98.10 71	97.44 61

Effi-MVS+-dtu		87.51 111	88.13 98	86.77 126	91.10 125	94.90 101	90.91 119	82.67 149	83.47 139	71.55 138	81.11 95	77.04 112	89.41 90	92.65 109	91.68 122	95.00 192	96.09 108

v8		84.45 150	83.30 159	85.80 139	87.53 167	92.95 149	90.31 131	82.46 153	80.46 160	71.43 139	66.99 167	67.16 158	86.14 131	89.26 169	90.22 158	96.94 138	96.06 109

pmmvs-eth3d		79.78 201	77.58 205	82.34 194	81.57 214	87.46 211	82.92 202	81.28 166	75.33 204	71.34 140	61.88 204	52.41 218	81.59 183	87.56 188	86.90 192	95.36 187	91.48 182

TDRefinement		84.97 139	83.39 153	86.81 125	92.97 105	94.12 111	92.18 105	87.77 99	82.78 143	71.31 141	68.43 159	68.07 151	81.10 185	89.70 157	89.03 185	95.55 183	91.62 181

V42		84.48 148	83.36 155	85.79 140	87.14 188	93.28 138	90.03 144	83.98 134	80.30 162	71.20 142	66.90 173	67.17 157	85.55 145	89.35 163	90.27 146	96.82 155	96.27 102

v6		84.67 142	83.36 155	86.20 131	87.53 167	93.49 127	90.34 126	85.16 123	80.58 157	71.13 143	66.97 168	67.10 159	86.11 135	89.25 172	90.22 158	96.93 141	95.89 113

CR-MVSNet		85.48 133	86.29 121	84.53 165	91.08 127	92.10 171	89.18 162	73.30 212	84.75 124	71.08 144	73.12 141	77.91 106	86.27 126	91.48 124	90.75 133	96.27 168	93.94 156

Patchmtry						92.39 168	89.18 162	73.30 212		71.08 144

PatchT		83.86 163	85.51 134	81.94 196	88.41 149	91.56 185	78.79 211	71.57 215	84.08 136	71.08 144	70.62 146	76.13 117	86.27 126	91.48 124	90.75 133	95.52 184	93.94 156

v1neww		84.65 143	83.34 157	86.18 133	87.53 167	93.49 127	90.32 127	85.17 121	80.57 158	71.02 147	66.93 169	67.04 161	86.13 133	89.26 169	90.23 155	96.93 141	95.88 114

v7new		84.65 143	83.34 157	86.18 133	87.53 167	93.49 127	90.32 127	85.17 121	80.57 158	71.02 147	66.93 169	67.04 161	86.13 133	89.26 169	90.23 155	96.93 141	95.88 114

USDC		86.73 119	85.96 127	87.63 117	91.64 118	93.97 114	92.76 92	84.58 128	88.19 91	70.67 149	80.10 97	67.86 152	89.43 89	91.81 120	89.77 175	96.69 160	90.05 197

tfpnnormal		83.80 165	81.26 194	86.77 126	89.60 138	93.26 140	89.72 156	87.60 103	72.78 208	70.44 150	60.53 209	61.15 206	85.55 145	92.72 107	91.44 124	97.71 97	96.92 73

pmmvs6		80.90 197	78.77 201	83.38 178	85.84 199	91.61 184	86.01 191	82.54 151	64.17 221	70.43 151	54.14 219	67.06 160	80.73 186	90.50 143	89.17 184	94.74 193	94.75 146

v15		83.67 168	82.37 175	85.19 152	87.39 175	89.63 198	90.19 138	80.43 174	79.49 175	70.27 152	66.37 178	66.33 169	85.88 140	89.34 165	90.23 155	96.96 135	95.22 140

V14		83.66 169	82.38 174	85.16 153	87.37 176	89.62 199	90.15 140	80.33 176	79.51 173	70.26 153	66.30 184	66.37 167	85.87 141	89.38 162	90.24 152	96.98 131	95.22 140

v12		83.59 172	82.32 178	85.07 155	87.32 183	89.57 201	89.87 154	80.19 181	79.46 176	70.19 154	66.05 186	66.23 174	85.84 142	89.44 160	90.26 148	97.01 128	95.26 136

V9		83.61 170	82.33 177	85.11 154	87.34 177	89.59 200	90.10 143	80.25 177	79.38 177	70.17 155	66.15 185	66.33 169	85.82 143	89.41 161	90.24 152	96.99 130	95.23 139

ACMH	85.51 13	87.31 113	86.59 117	88.14 109	93.96 80	94.51 104	89.00 166	87.99 91	81.58 147	70.15 156	78.41 106	71.78 129	90.60 80	91.30 128	91.99 115	97.17 117	96.58 90
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v1		84.40 151	83.01 164	86.03 135	87.41 173	93.42 130	90.31 131	85.52 116	79.51 173	70.13 157	66.66 175	66.40 166	85.89 139	89.15 177	90.19 160	96.89 149	95.74 118

v1141		84.40 151	83.00 165	86.03 135	87.41 173	93.42 130	90.28 135	85.53 115	79.58 170	70.12 158	66.62 177	66.27 172	85.94 137	89.16 175	90.19 160	96.89 149	95.73 119

divwei89l23v2f112		84.40 151	83.00 165	86.02 137	87.42 172	93.42 130	90.28 135	85.52 116	79.57 171	70.11 159	66.64 176	66.29 171	85.91 138	89.16 175	90.19 160	96.90 147	95.73 119

TranMVSNet+NR-MVSNet		85.57 132	84.41 142	86.92 123	87.67 162	93.34 135	90.31 131	88.43 87	83.07 141	70.11 159	69.99 154	65.28 181	86.96 117	89.73 155	92.27 106	98.06 78	97.17 68

v748		81.57 196	80.68 198	82.60 191	85.55 202	92.07 173	83.57 200	82.06 158	74.64 205	69.97 161	63.11 202	61.46 204	78.09 193	87.30 191	89.88 172	96.37 165	96.32 98

v13		83.55 174	82.29 179	85.01 157	87.31 184	89.55 203	89.89 152	80.13 182	79.34 178	69.93 162	65.92 189	66.25 173	85.80 144	89.45 159	90.27 146	97.01 128	95.25 138

TinyColmap		84.04 161	82.01 184	86.42 130	90.87 128	91.84 180	88.89 168	84.07 133	82.11 146	69.89 163	71.08 145	60.81 207	89.04 96	90.52 142	89.19 183	95.76 174	88.50 203

v2v482		84.51 146	83.05 163	86.20 131	87.25 185	93.28 138	90.22 137	85.40 119	79.94 167	69.78 164	67.74 162	65.15 183	87.57 108	89.12 178	90.55 139	96.97 132	95.60 123

MIMVSNet		82.97 182	84.00 146	81.77 198	82.23 212	92.25 170	87.40 181	72.73 214	81.48 148	69.55 165	68.79 158	72.42 125	81.82 180	92.23 116	92.25 107	96.89 149	88.61 202

ADS-MVSNet		84.08 160	84.95 136	83.05 183	91.53 122	91.75 182	88.16 173	70.70 217	89.96 76	69.51 166	78.83 102	76.97 113	86.29 125	84.08 208	84.60 204	92.13 209	88.48 204

v7		84.37 154	83.23 160	85.69 142	87.34 177	93.19 142	90.32 127	83.10 145	79.88 169	69.33 167	66.33 181	65.75 176	87.06 115	90.83 135	90.38 142	96.97 132	96.26 103

test-LLR		86.88 115	88.28 95	85.24 150	91.22 123	92.07 173	87.41 179	83.62 137	84.58 126	69.33 167	83.00 78	82.79 81	84.24 157	92.26 114	89.81 173	95.64 179	93.44 163

TESTMET0.1,1		86.11 125	88.28 95	83.59 174	87.80 157	92.07 173	87.41 179	77.12 194	84.58 126	69.33 167	83.00 78	82.79 81	84.24 157	92.26 114	89.81 173	95.64 179	93.44 163

v10		84.18 156	83.17 162	85.37 147	87.34 177	92.68 157	90.32 127	81.33 165	79.93 168	69.23 170	66.33 181	65.74 178	87.03 116	90.84 134	90.38 142	96.97 132	96.29 101

v11		83.72 166	82.61 173	85.02 156	87.34 177	89.56 202	89.89 152	79.92 183	79.55 172	69.21 171	66.36 180	65.48 179	86.84 119	91.43 127	90.51 141	96.92 145	95.37 132

RPMNet		84.82 141	85.90 128	83.56 175	91.10 125	92.10 171	88.73 170	71.11 216	84.75 124	68.79 172	73.56 134	77.62 108	85.33 148	90.08 151	89.43 181	96.32 166	93.77 161

CANet_DTU		90.74 70	92.93 49	88.19 106	94.36 70	96.61 78	94.34 61	84.66 126	90.66 61	68.75 173	90.41 40	86.89 64	89.78 87	95.46 47	94.87 49	97.25 114	95.62 122

CMPMVS	61.19 17	79.86 200	77.46 207	82.66 190	91.54 121	91.82 181	83.25 201	81.57 163	70.51 216	68.64 174	59.89 210	66.77 164	79.63 188	84.00 209	84.30 205	91.34 211	84.89 213
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test-mter		86.09 126	88.38 94	83.43 177	87.89 156	92.61 159	86.89 184	77.11 195	84.30 131	68.62 175	82.57 85	82.45 85	84.34 156	92.40 112	90.11 167	95.74 175	94.21 154

tmp_tt				50.24 229	68.55 229	46.86 236	48.90 234	18.28 234	86.51 107	68.32 176	70.19 151	65.33 180	26.69 234	74.37 224	66.80 228	70.72 233

TransMVSNet (Re)		82.67 185	80.93 197	84.69 162	88.71 144	91.50 186	87.90 175	87.15 104	71.54 214	68.24 177	63.69 199	64.67 188	78.51 192	91.65 123	90.73 135	97.64 104	92.73 176

WR-MVS_H		82.86 184	82.66 172	83.10 181	87.44 171	93.33 136	85.71 196	83.20 144	77.36 190	68.20 178	66.37 178	65.23 182	76.05 200	89.35 163	90.13 163	97.99 84	96.89 74

v1144		84.03 162	82.88 168	85.37 147	87.17 187	93.15 146	90.18 139	83.31 142	78.83 181	67.85 179	65.99 187	64.99 184	86.79 120	90.75 137	90.33 145	96.90 147	96.15 106

test0.0.03 1		85.58 131	87.69 106	83.11 180	91.22 123	92.54 162	85.60 197	83.62 137	85.66 118	67.84 180	82.79 82	79.70 97	73.51 207	91.15 131	90.79 130	96.88 152	91.23 186

CP-MVSNet		83.11 181	82.15 181	84.23 168	87.20 186	92.70 156	86.42 188	83.53 140	77.83 188	67.67 181	66.89 174	60.53 209	82.47 174	89.23 174	90.65 137	98.08 75	97.20 67

MVS-HIRNet		78.16 203	77.57 206	78.83 203	85.83 200	87.76 209	76.67 212	70.22 218	75.82 202	67.39 182	55.61 214	70.52 134	81.96 179	86.67 196	85.06 202	90.93 215	81.58 219

v144192		83.48 175	82.23 180	84.94 159	86.65 194	92.84 152	89.63 158	82.48 152	77.87 187	67.36 183	65.33 193	63.50 193	86.51 122	89.72 156	89.99 170	97.03 126	96.35 96

pmmvs5		83.37 176	82.68 171	84.18 169	87.13 189	93.18 143	86.74 185	82.08 157	76.48 195	67.28 184	71.26 144	62.70 196	84.71 154	90.77 136	90.12 166	97.15 118	94.24 152

PM-MVS		80.29 199	79.30 200	81.45 199	81.91 213	88.23 207	82.61 203	79.01 187	79.99 166	67.15 185	69.07 157	51.39 219	82.92 170	87.55 189	85.59 197	95.08 189	93.28 166

tpm		83.16 178	83.64 147	82.60 191	90.75 129	91.05 189	88.49 171	73.99 205	82.36 144	67.08 186	78.10 107	68.79 145	84.17 160	85.95 198	85.96 196	91.09 212	93.23 167

V4		82.11 190	81.49 192	82.83 186	84.60 207	92.53 164	85.97 192	80.24 178	76.35 199	66.87 187	63.17 200	64.55 190	82.54 173	87.70 186	89.55 178	96.73 158	96.61 84

v52		82.11 190	81.50 191	82.82 187	84.59 208	92.51 166	85.96 194	80.24 178	76.38 198	66.83 188	63.12 201	64.62 189	82.56 172	87.70 186	89.55 178	96.73 158	96.61 84

v1192		83.56 173	82.35 176	84.98 158	86.84 193	92.84 152	90.01 146	82.70 147	78.54 183	66.48 189	64.88 195	62.91 194	86.91 118	90.72 138	90.25 149	96.94 138	96.32 98

WR-MVS		83.14 179	83.38 154	82.87 185	87.55 166	93.29 137	86.36 189	84.21 131	80.05 165	66.41 190	66.91 171	66.92 163	75.66 201	88.96 180	90.56 138	97.05 125	96.96 71

IterMVS		85.25 136	86.49 119	83.80 172	90.42 133	90.77 194	90.02 145	78.04 191	84.10 135	66.27 191	77.28 113	78.41 102	83.01 169	90.88 133	89.72 177	95.04 190	94.24 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v7n		82.25 189	81.54 189	83.07 182	85.55 202	92.58 160	86.68 187	81.10 169	76.54 194	65.97 192	62.91 203	60.56 208	82.36 175	91.07 132	90.35 144	96.77 157	96.80 76

v1921920		83.30 177	82.09 183	84.70 161	86.59 196	92.67 158	89.82 155	82.23 156	78.32 184	65.76 193	64.64 197	62.35 197	86.78 121	90.34 145	90.02 168	97.02 127	96.31 100

PS-CasMVS		82.53 186	81.54 189	83.68 173	87.08 191	92.54 162	86.20 190	83.46 141	76.46 196	65.73 194	65.71 191	59.41 214	81.61 182	89.06 179	90.55 139	98.03 80	97.07 70

EPNet_dtu		88.32 105	90.61 71	85.64 144	96.79 48	92.27 169	92.03 111	90.31 57	89.05 84	65.44 195	89.43 42	85.90 71	74.22 203	92.76 106	92.09 112	95.02 191	92.76 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		86.25 121	87.70 105	84.56 164	90.37 134	93.70 121	90.54 123	78.14 190	83.50 138	65.37 196	81.59 93	75.83 118	86.09 136	91.70 122	91.70 120	96.88 152	95.84 116

v1240		82.88 183	81.66 187	84.29 167	86.46 197	92.52 165	89.06 164	81.82 161	77.16 191	65.09 197	64.17 198	61.50 203	86.36 123	90.12 149	90.13 163	96.95 136	96.04 111

PEN-MVS		82.49 187	81.58 188	83.56 175	86.93 192	92.05 176	86.71 186	83.84 135	76.94 193	64.68 198	67.24 163	60.11 210	81.17 184	87.78 185	90.70 136	98.02 81	96.21 104

SixPastTwentyTwo		83.12 180	83.44 151	82.74 188	87.71 161	93.11 147	82.30 205	82.33 154	79.24 179	64.33 199	78.77 103	62.75 195	84.11 162	88.11 183	87.89 188	95.70 177	94.21 154

MDTV_nov1_ep13_2view		80.43 198	80.94 196	79.84 200	84.82 206	90.87 191	84.23 199	73.80 206	80.28 163	64.33 199	70.05 153	68.77 146	79.67 187	84.83 203	83.50 208	92.17 207	88.25 206

EG-PatchMatch MVS		81.70 195	81.31 193	82.15 195	88.75 143	93.81 117	87.14 182	78.89 188	71.57 212	64.12 201	61.20 208	68.46 147	76.73 198	91.48 124	90.77 132	97.28 113	91.90 180

anonymousdsp		84.51 146	85.85 131	82.95 184	86.30 198	93.51 126	85.77 195	80.38 175	78.25 186	63.42 202	73.51 136	72.20 126	84.64 155	93.21 105	92.16 110	97.19 116	98.14 38

DTE-MVSNet		81.76 194	81.04 195	82.60 191	86.63 195	91.48 188	85.97 192	83.70 136	76.45 197	62.44 203	67.16 164	59.98 211	78.98 191	87.15 192	89.93 171	97.88 88	95.12 143

GA-MVS		85.08 137	85.65 132	84.42 166	89.77 136	94.25 110	89.26 161	84.62 127	81.19 152	62.25 204	75.72 124	68.44 148	84.14 161	93.57 96	91.68 122	96.49 161	94.71 147

FC-MVSNet-test		86.15 123	89.10 86	82.71 189	89.83 135	93.18 143	87.88 176	84.69 125	86.54 105	62.18 205	82.39 87	83.31 79	74.18 204	92.52 111	91.86 117	97.50 109	93.88 159

testpf		74.66 209	76.34 210	72.71 214	87.34 177	80.91 220	73.15 220	60.30 231	78.73 182	61.68 206	69.83 155	62.22 199	67.48 210	76.83 222	78.17 223	86.28 225	87.68 207

LP		77.28 207	76.57 209	78.12 205	88.17 152	88.06 208	80.85 208	68.35 224	80.78 155	61.49 207	57.59 212	61.80 202	77.59 194	81.45 216	82.34 212	92.25 206	83.96 216

N_pmnet		77.55 206	76.68 208	78.56 204	85.43 204	87.30 212	78.84 210	81.88 160	78.30 185	60.61 208	61.46 205	62.15 200	74.03 206	82.04 212	80.69 219	90.59 217	84.81 214

CVMVSNet		83.83 164	85.53 133	81.85 197	89.60 138	90.92 190	87.81 177	83.21 143	80.11 164	60.16 209	76.47 116	78.57 101	76.79 197	89.76 154	90.13 163	93.51 195	92.75 175

ambc			67.96 218		73.69 225	79.79 223	73.82 217		71.61 211	59.80 210	46.00 224	20.79 236	66.15 214	86.92 194	80.11 221	89.13 223	90.50 192

testgi		81.94 192	84.09 145	79.43 202	89.53 140	90.83 192	82.49 204	81.75 162	80.59 156	59.46 211	82.82 81	65.75 176	67.97 209	90.10 150	89.52 180	95.39 185	89.03 199

PMVS	56.77 18	61.27 223	58.64 225	64.35 223	75.66 223	54.60 234	53.62 232	74.23 204	53.69 227	58.37 212	44.27 228	49.38 222	44.16 229	69.51 228	65.35 229	80.07 229	73.66 225
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		78.09 204	78.11 204	78.07 206	85.19 205	89.17 204	80.99 206	81.24 168	75.46 203	58.25 213	54.78 218	59.90 212	66.73 213	88.94 181	88.26 187	96.01 171	90.25 195

FPMVS		69.87 217	67.10 220	73.10 212	84.09 209	78.35 224	79.40 209	76.41 196	71.92 210	57.71 214	54.06 220	50.04 221	56.72 222	71.19 226	68.70 227	84.25 227	75.43 224

MIMVSNet1		73.19 213	73.70 213	72.60 216	65.42 231	86.69 214	75.56 214	79.65 184	67.87 219	55.30 215	45.24 227	56.41 216	63.79 216	86.98 193	87.66 189	95.85 173	85.04 212

MDA-MVSNet-bldmvs		73.81 211	72.56 215	75.28 209	72.52 227	88.87 205	74.95 215	82.67 149	71.57 212	55.02 216	65.96 188	42.84 230	76.11 199	70.61 227	81.47 217	90.38 218	86.59 208

new-patchmatchnet		72.32 214	71.09 216	73.74 211	81.17 216	84.86 216	72.21 222	77.48 193	68.32 218	54.89 217	55.10 216	49.31 223	63.68 217	79.30 219	76.46 224	93.03 198	84.32 215

EU-MVSNet		78.43 202	80.25 199	76.30 208	83.81 210	87.27 213	80.99 206	79.52 185	76.01 200	54.12 218	70.44 149	64.87 185	67.40 212	86.23 197	85.54 199	91.95 210	91.41 183

LTVRE_ROB	81.71 16	82.44 188	81.84 186	83.13 179	89.01 141	92.99 148	88.90 167	82.32 155	66.26 220	54.02 219	74.68 131	59.62 213	88.87 101	90.71 139	92.02 114	95.68 178	96.62 83
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
Anonymous20231211		69.76 218	67.18 219	72.76 213	78.31 218	83.47 217	74.12 216	78.37 189	51.44 230	52.48 220	36.04 229	45.46 229	62.33 218	80.49 218	82.43 211	90.96 214	90.93 189

pmmvs3		71.13 216	71.06 217	71.21 218	73.54 226	80.19 222	71.69 223	64.86 225	62.04 224	52.10 221	54.92 217	48.00 226	75.03 202	83.75 210	83.24 209	90.04 221	85.27 211

gm-plane-assit		77.65 205	78.50 202	76.66 207	87.96 155	85.43 215	64.70 225	74.50 203	64.15 222	51.26 222	61.32 207	58.17 215	84.11 162	95.16 49	93.83 67	97.45 110	91.41 183

test20.03		76.41 208	78.49 203	73.98 210	85.64 201	87.50 210	75.89 213	80.71 171	70.84 215	51.07 223	68.06 161	61.40 205	54.99 224	88.28 182	87.20 191	95.58 182	86.15 209

new_pmnet		72.29 215	73.25 214	71.16 219	75.35 224	81.38 218	73.72 218	69.27 220	75.97 201	49.84 224	56.27 213	56.12 217	69.08 208	81.73 213	80.86 218	89.72 222	80.44 220

testus		73.65 212	74.92 211	72.17 217	80.93 217	81.11 219	73.02 221	75.23 202	73.23 207	48.77 225	69.38 156	46.10 228	62.28 219	84.84 202	86.01 195	92.77 200	83.75 217

test2356		73.82 210	74.82 212	72.66 215	81.25 215	80.70 221	73.47 219	75.91 198	72.55 209	48.73 226	68.14 160	50.74 220	63.96 215	84.44 206	85.57 198	92.63 202	81.60 218

1111		66.22 219	66.42 221	65.98 220	75.69 221	76.42 225	58.90 226	63.25 226	57.86 225	48.33 227	45.46 225	49.13 224	61.32 220	81.57 214	82.80 210	88.38 224	71.69 229

.test1245		48.95 228	46.78 229	51.48 226	75.69 221	76.42 225	58.90 226	63.25 226	57.86 225	48.33 227	45.46 225	49.13 224	61.32 220	81.57 214	5.58 233	1.40 237	11.42 235

DeepMVS_CX						71.82 229	68.37 224	48.05 233	77.38 189	46.88 229	65.77 190	47.03 227	67.48 210	64.27 230		76.89 232	76.72 223

Gipuma		58.52 225	56.17 226	61.27 224	67.14 230	58.06 233	52.16 233	68.40 223	69.00 217	45.02 230	22.79 232	20.57 237	55.11 223	76.27 223	79.33 222	79.80 230	67.16 230
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
gg-mvs-nofinetune		81.83 193	83.58 148	79.80 201	91.57 119	96.54 81	93.79 77	68.80 221	62.71 223	43.01 231	55.28 215	85.06 74	83.65 166	96.13 38	94.86 50	97.98 86	94.46 149

testmv		65.29 220	65.25 222	65.34 221	77.73 219	75.55 227	58.75 228	73.56 210	53.22 228	38.47 232	49.33 221	38.30 231	53.38 225	79.13 220	81.65 214	90.15 219	79.58 221

test1235678		65.29 220	65.24 223	65.34 221	77.73 219	75.54 228	58.75 228	73.56 210	53.19 229	38.47 232	49.32 222	38.28 232	53.38 225	79.13 220	81.65 214	90.15 219	79.57 222

test12356		60.37 224	61.08 224	59.53 225	72.42 228	70.09 230	57.72 230	69.53 219	51.31 231	36.05 234	47.32 223	32.04 233	36.19 230	74.15 225	80.35 220	85.27 226	72.29 227

MVE	39.81 19	39.52 230	41.58 230	37.11 232	33.93 236	49.06 235	26.45 238	54.22 232	29.46 236	24.15 235	20.77 234	10.60 240	34.42 231	51.12 232	65.27 230	49.49 236	64.81 231
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
no-one		49.70 227	49.06 228	50.46 228	65.32 232	67.46 231	38.16 235	68.73 222	34.38 235	22.88 236	24.40 231	22.99 235	28.55 233	51.41 231	70.93 225	79.08 231	71.81 228

PMMVS2		53.68 226	55.72 227	51.30 227	58.84 233	67.02 232	54.23 231	60.97 230	47.50 232	19.42 237	34.81 230	31.97 234	30.88 232	65.84 229	69.99 226	83.47 228	72.92 226

E-PMN		40.00 229	35.74 231	44.98 230	57.69 235	39.15 238	28.05 236	62.70 228	35.52 234	17.78 238	20.90 233	14.36 239	44.47 228	35.89 233	47.86 231	59.15 234	56.47 232

EMVS		39.04 231	34.32 232	44.54 231	58.25 234	39.35 237	27.61 237	62.55 229	35.99 233	16.40 239	20.04 235	14.77 238	44.80 227	33.12 234	44.10 232	57.61 235	52.89 233

GG-mvs-BLEND		62.84 222	90.21 73	30.91 233	0.57 238	94.45 106	86.99 183	0.34 237	88.71 86	0.98 240	81.55 94	91.58 49	0.86 237	92.66 108	91.43 125	95.73 176	91.11 187

testmvs		4.35 232	6.54 233	1.79 234	0.60 237	1.82 239	3.06 240	0.95 235	7.22 237	0.88 241	12.38 236	1.25 241	3.87 236	6.09 235	5.58 233	1.40 237	11.42 235

test123		3.48 233	5.31 234	1.34 235	0.20 239	1.52 240	2.17 241	0.58 236	6.13 238	0.31 242	9.85 237	0.31 242	3.90 235	2.65 236	5.28 235	0.87 239	11.46 234

sosnet-low-res		0.00 234	0.00 235	0.00 236	0.00 240	0.00 241	0.00 242	0.00 238	0.00 239	0.00 243	0.00 238	0.00 243	0.00 238	0.00 237	0.00 236	0.00 240	0.00 237

sosnet		0.00 234	0.00 235	0.00 236	0.00 240	0.00 241	0.00 242	0.00 238	0.00 239	0.00 243	0.00 238	0.00 243	0.00 238	0.00 237	0.00 236	0.00 240	0.00 237

Patchmatch-RL test							18.47 239

mPP-MVS					98.76 18							95.49 32

NP-MVS									91.63 56

High-resolution multi-view benchmark