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.

HPM-MVS++		94.60 7	94.91 9	94.24 6	97.86 1	96.53 31	96.14 7	92.51 7	93.87 14	90.76 11	93.45 17	93.84 3	92.62 7	95.11 10	94.08 17	95.58 49	97.48 13

SMA-MVS		94.70 5	95.35 5	93.93 11	97.57 2	97.57 6	95.98 10	91.91 12	94.50 5	90.35 13	93.46 16	92.72 10	91.89 17	95.89 2	95.22 1	95.88 26	98.10 4

zzz-MVS		93.80 16	93.45 24	94.20 7	97.53 3	96.43 35	95.88 16	91.12 19	94.09 10	92.74 3	87.68 32	90.77 24	92.04 12	94.74 16	93.56 27	95.91 25	96.85 27

MP-MVS		93.35 19	93.59 22	93.08 22	97.39 4	96.82 21	95.38 24	90.71 23	90.82 35	88.07 26	92.83 20	90.29 28	91.32 26	94.03 28	93.19 37	95.61 47	97.16 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NCCC		93.69 18	93.66 21	93.72 15	97.37 5	96.66 28	95.93 15	92.50 8	93.40 18	88.35 24	87.36 34	92.33 13	92.18 11	94.89 12	94.09 16	96.00 22	96.91 26

CNVR-MVS		94.37 10	94.65 10	94.04 10	97.29 6	97.11 9	96.00 9	92.43 9	93.45 15	89.85 18	90.92 24	93.04 7	92.59 8	95.77 3	94.82 4	96.11 20	97.42 15

HFP-MVS		94.02 13	94.22 16	93.78 13	97.25 7	96.85 19	95.81 19	90.94 22	94.12 9	90.29 15	94.09 13	89.98 30	92.52 9	93.94 31	93.49 32	95.87 28	97.10 23

APD-MVS		94.37 10	94.47 14	94.26 5	97.18 8	96.99 15	96.53 6	92.68 4	92.45 23	89.96 16	94.53 10	91.63 19	92.89 5	94.58 19	93.82 21	96.31 16	97.26 18
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	88.76 1	93.10 21	93.02 28	93.19 21	97.13 9	96.51 32	95.35 25	91.19 18	93.14 20	88.14 25	85.26 40	89.49 34	91.45 22	95.17 8	95.07 2	95.85 31	96.48 34
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		95.23 3	95.69 4	94.70 3	97.12 10	97.81 4	97.19 2	92.83 2	95.06 4	90.98 9	96.47 2	92.77 9	93.38 2	95.34 7	94.21 14	96.68 7	98.17 3

ACMMPR		93.72 17	93.94 18	93.48 17	97.07 11	96.93 16	95.78 20	90.66 25	93.88 13	89.24 20	93.53 15	89.08 37	92.24 10	93.89 33	93.50 30	95.88 26	96.73 31

mPP-MVS					97.06 12							88.08 44

ACMMP_NAP		93.94 14	94.49 13	93.30 19	97.03 13	97.31 8	95.96 11	91.30 17	93.41 17	88.55 23	93.00 18	90.33 27	91.43 25	95.53 5	94.41 12	95.53 51	97.47 14

PGM-MVS		92.76 25	93.03 27	92.45 27	97.03 13	96.67 27	95.73 22	87.92 41	90.15 42	86.53 35	92.97 19	88.33 43	91.69 20	93.62 36	93.03 38	95.83 32	96.41 37

SteuartSystems-ACMMP		94.06 12	94.65 10	93.38 18	96.97 15	97.36 7	96.12 8	91.78 13	92.05 27	87.34 29	94.42 11	90.87 23	91.87 18	95.47 6	94.59 9	96.21 18	97.77 10
Skip Steuart: Steuart Systems R&D Blog.
MSP-MVS		95.56 1	96.26 1	94.73 2	96.93 16	98.19 1	96.62 5	92.81 3	96.15 1	91.73 4	95.01 6	95.31 1	93.41 1	95.95 1	94.77 6	96.90 4	98.46 1

X-MVS		92.36 29	92.75 29	91.90 32	96.89 17	96.70 24	95.25 26	90.48 28	91.50 32	83.95 47	88.20 30	88.82 39	89.11 35	93.75 34	93.43 33	95.75 38	96.83 29

train_agg		92.87 24	93.53 23	92.09 29	96.88 18	95.38 48	95.94 13	90.59 27	90.65 37	83.65 50	94.31 12	91.87 18	90.30 30	93.38 38	92.42 45	95.17 68	96.73 31

CP-MVS		93.25 20	93.26 25	93.24 20	96.84 19	96.51 32	95.52 23	90.61 26	92.37 24	88.88 21	90.91 25	89.52 33	91.91 16	93.64 35	92.78 43	95.69 40	97.09 24

DVP-MVS		95.12 4	95.83 3	94.30 4	96.82 20	97.94 3	96.98 3	92.37 10	95.40 2	90.59 12	96.16 3	93.71 4	92.70 6	94.80 14	94.77 6	96.37 13	97.99 7

DPE-MVS		95.53 2	96.13 2	94.82 1	96.81 21	98.05 2	97.42 1	93.09 1	94.31 7	91.49 5	97.12 1	95.03 2	93.27 3	95.55 4	94.58 10	96.86 5	98.25 2

MCST-MVS		93.81 15	94.06 17	93.53 16	96.79 22	96.85 19	95.95 12	91.69 15	92.20 25	87.17 31	90.83 26	93.41 5	91.96 13	94.49 22	93.50 30	97.61 1	97.12 22

xxxxxxxxxxxxxcwj		92.95 23	91.88 32	94.20 7	96.75 23	97.07 10	95.82 17	92.60 5	93.98 11	91.09 7	95.89 4	71.01 123	91.93 14	94.40 24	93.56 27	97.04 2	97.27 16

SF-MVS		94.61 6	94.96 8	94.20 7	96.75 23	97.07 10	95.82 17	92.60 5	93.98 11	91.09 7	95.89 4	92.54 11	91.93 14	94.40 24	93.56 27	97.04 2	97.27 16

SR-MVS					96.58 25			90.99 21				92.40 12

EPNet		89.60 46	89.91 44	89.24 53	96.45 26	93.61 74	92.95 46	88.03 39	85.74 58	83.36 51	87.29 35	83.05 61	80.98 91	92.22 54	91.85 49	93.69 132	95.58 51
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CSCG		92.76 25	93.16 26	92.29 28	96.30 27	97.74 5	94.67 32	88.98 35	92.46 22	89.73 19	86.67 36	92.15 16	88.69 41	92.26 53	92.92 41	95.40 56	97.89 9

CDPH-MVS		91.14 38	92.01 31	90.11 42	96.18 28	96.18 38	94.89 30	88.80 37	88.76 47	77.88 82	89.18 29	87.71 46	87.29 59	93.13 41	93.31 35	95.62 45	95.84 45

DeepC-MVS	87.86 3	92.26 30	91.86 33	92.73 24	96.18 28	96.87 18	95.19 27	91.76 14	92.17 26	86.58 34	81.79 49	85.85 49	90.88 28	94.57 20	94.61 8	95.80 34	97.18 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		90.29 42	88.38 56	92.53 25	96.10 30	95.19 52	92.98 45	91.40 16	89.08 46	88.65 22	78.35 70	81.44 68	91.30 27	90.81 81	90.21 75	94.72 87	93.59 86

MSLP-MVS++		92.02 33	91.40 36	92.75 23	96.01 31	95.88 43	93.73 39	89.00 33	89.89 43	90.31 14	81.28 55	88.85 38	91.45 22	92.88 46	94.24 13	96.00 22	96.76 30

3Dnovator+	86.06 4	91.60 35	90.86 41	92.47 26	96.00 32	96.50 34	94.70 31	87.83 42	90.49 38	89.92 17	74.68 89	89.35 35	90.66 29	94.02 29	94.14 15	95.67 42	96.85 27

TSAR-MVS + ACMM		92.97 22	94.51 12	91.16 36	95.88 33	96.59 29	95.09 28	90.45 29	93.42 16	83.01 52	94.68 9	90.74 25	88.74 39	94.75 15	93.78 22	93.82 127	97.63 11

ACMMP		92.03 32	92.16 30	91.87 33	95.88 33	96.55 30	94.47 34	89.49 32	91.71 30	85.26 41	91.52 23	84.48 54	90.21 31	92.82 47	91.63 51	95.92 24	96.42 36
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
SD-MVS		94.53 8	95.22 6	93.73 14	95.69 35	97.03 13	95.77 21	91.95 11	94.41 6	91.35 6	94.97 7	93.34 6	91.80 19	94.72 17	93.99 18	95.82 33	98.07 6
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
DPM-MVS		91.72 34	91.48 34	92.00 30	95.53 36	95.75 44	95.94 13	91.07 20	91.20 33	85.58 40	81.63 53	90.74 25	88.40 44	93.40 37	93.75 23	95.45 55	93.85 80

TSAR-MVS + MP.		94.48 9	94.97 7	93.90 12	95.53 36	97.01 14	96.69 4	90.71 23	94.24 8	90.92 10	94.97 7	92.19 14	93.03 4	94.83 13	93.60 25	96.51 12	97.97 8
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CPTT-MVS		91.39 36	90.95 39	91.91 31	95.06 38	95.24 50	95.02 29	88.98 35	91.02 34	86.71 33	84.89 42	88.58 42	91.60 21	90.82 80	89.67 91	94.08 114	96.45 35

CANet		91.33 37	91.46 35	91.18 35	95.01 39	96.71 23	93.77 37	87.39 45	87.72 50	87.26 30	81.77 50	89.73 31	87.32 58	94.43 23	93.86 20	96.31 16	96.02 43

PHI-MVS		92.05 31	93.74 20	90.08 43	94.96 40	97.06 12	93.11 44	87.71 43	90.71 36	80.78 66	92.40 21	91.03 21	87.68 52	94.32 26	94.48 11	96.21 18	96.16 40

MAR-MVS		88.39 58	88.44 55	88.33 64	94.90 41	95.06 54	90.51 63	83.59 74	85.27 60	79.07 74	77.13 75	82.89 62	87.70 50	92.19 56	92.32 46	94.23 111	94.20 76
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
3Dnovator	85.17 5	90.48 41	89.90 45	91.16 36	94.88 42	95.74 45	93.82 36	85.36 56	89.28 44	87.81 27	74.34 91	87.40 47	88.56 42	93.07 42	93.74 24	96.53 11	95.71 47

DeepPCF-MVS	88.51 2	92.64 28	94.42 15	90.56 40	94.84 43	96.92 17	91.31 60	89.61 31	95.16 3	84.55 45	89.91 28	91.45 20	90.15 32	95.12 9	94.81 5	92.90 146	97.58 12

QAPM		89.49 47	89.58 48	89.38 51	94.73 44	95.94 41	92.35 48	85.00 59	85.69 59	80.03 70	76.97 77	87.81 45	87.87 49	92.18 57	92.10 47	96.33 14	96.40 38

MVS_111021_HR		90.56 40	91.29 38	89.70 48	94.71 45	95.63 46	91.81 56	86.38 50	87.53 51	81.29 60	87.96 31	85.43 51	87.69 51	93.90 32	92.93 40	96.33 14	95.69 48

abl_6				90.66 39	94.65 46	96.27 36	92.21 49	86.94 47	90.23 40	86.38 36	85.50 39	92.96 8	88.37 45			95.40 56	95.46 53

OpenMVS	82.53 11	87.71 64	86.84 71	88.73 56	94.42 47	95.06 54	91.02 62	83.49 77	82.50 74	82.24 57	67.62 127	85.48 50	85.56 69	91.19 68	91.30 54	95.67 42	94.75 64

PLC	83.76 9	88.61 55	86.83 72	90.70 38	94.22 48	92.63 90	91.50 58	87.19 46	89.16 45	86.87 32	75.51 84	80.87 70	89.98 33	90.01 91	89.20 100	94.41 106	90.45 140
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		85.96 76	84.37 91	87.81 66	94.13 49	93.27 79	90.26 67	89.00 33	84.91 64	72.84 103	71.74 103	72.47 117	87.45 56	89.53 99	89.09 102	93.20 142	89.60 143

EPNet_dtu		81.98 108	83.82 93	79.83 141	94.10 50	85.97 166	87.29 108	84.08 67	80.61 94	59.96 173	81.62 54	77.19 94	62.91 188	87.21 120	86.38 139	90.66 171	87.77 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_0304		90.88 39	91.35 37	90.34 41	93.91 51	96.79 22	94.49 33	86.54 49	86.57 54	82.85 53	81.68 52	89.70 32	87.57 54	94.64 18	93.93 19	96.67 9	96.15 41

OPM-MVS		87.56 66	85.80 82	89.62 49	93.90 52	94.09 68	94.12 35	88.18 38	75.40 125	77.30 85	76.41 78	77.93 90	88.79 38	92.20 55	90.82 62	95.40 56	93.72 84

DELS-MVS		89.71 45	89.68 47	89.74 46	93.75 53	96.22 37	93.76 38	85.84 52	82.53 72	85.05 43	78.96 67	84.24 55	84.25 74	94.91 11	94.91 3	95.78 37	96.02 43
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
CNLPA		88.40 56	87.00 70	90.03 44	93.73 54	94.28 64	89.56 77	85.81 53	91.87 28	87.55 28	69.53 117	81.49 67	89.23 34	89.45 100	88.59 110	94.31 110	93.82 81

HQP-MVS		89.13 50	89.58 48	88.60 59	93.53 55	93.67 72	93.29 42	87.58 44	88.53 48	75.50 86	87.60 33	80.32 73	87.07 60	90.66 86	89.95 83	94.62 93	96.35 39

OMC-MVS		90.23 43	90.40 42	90.03 44	93.45 56	95.29 49	91.89 55	86.34 51	93.25 19	84.94 44	81.72 51	86.65 48	88.90 36	91.69 61	90.27 74	94.65 91	93.95 78

ACMM	83.27 10	87.68 65	86.09 78	89.54 50	93.26 57	92.19 96	91.43 59	86.74 48	86.02 56	82.85 53	75.63 83	75.14 100	88.41 43	90.68 85	89.99 80	94.59 94	92.97 93
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS_111021_LR		90.14 44	90.89 40	89.26 52	93.23 58	94.05 69	90.43 64	84.65 61	90.16 41	84.52 46	90.14 27	83.80 58	87.99 48	92.50 51	90.92 60	94.74 85	94.70 66

XVS					93.11 59	96.70 24	91.91 53			83.95 47		88.82 39				95.79 35

X-MVStestdata					93.11 59	96.70 24	91.91 53			83.95 47		88.82 39				95.79 35

PCF-MVS	84.60 6	88.66 53	87.75 66	89.73 47	93.06 61	96.02 39	93.22 43	90.00 30	82.44 75	80.02 71	77.96 73	85.16 52	87.36 57	88.54 108	88.54 111	94.72 87	95.61 50
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TAPA-MVS	84.37 7	88.91 52	88.93 52	88.89 54	93.00 62	94.85 58	92.00 52	84.84 60	91.68 31	80.05 69	79.77 62	84.56 53	88.17 47	90.11 90	89.00 106	95.30 63	92.57 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_Blended_VisFu		87.40 68	87.80 63	86.92 72	92.86 63	95.40 47	88.56 95	83.45 81	79.55 102	82.26 56	74.49 90	84.03 56	79.24 121	92.97 45	91.53 53	95.15 70	96.65 33

UA-Net		86.07 74	87.78 64	84.06 95	92.85 64	95.11 53	87.73 101	84.38 62	73.22 145	73.18 99	79.99 61	89.22 36	71.47 165	93.22 40	93.03 38	94.76 84	90.69 135

LGP-MVS_train		88.25 60	88.55 53	87.89 65	92.84 65	93.66 73	93.35 41	85.22 58	85.77 57	74.03 95	86.60 37	76.29 97	86.62 64	91.20 67	90.58 70	95.29 64	95.75 46

TSAR-MVS + COLMAP		88.40 56	89.09 51	87.60 69	92.72 66	93.92 71	92.21 49	85.57 55	91.73 29	73.72 96	91.75 22	73.22 115	87.64 53	91.49 63	89.71 90	93.73 130	91.82 121

PVSNet_BlendedMVS		88.19 61	88.00 61	88.42 61	92.71 67	94.82 59	89.08 84	83.81 69	84.91 64	86.38 36	79.14 64	78.11 88	82.66 80	93.05 43	91.10 55	95.86 29	94.86 62

PVSNet_Blended		88.19 61	88.00 61	88.42 61	92.71 67	94.82 59	89.08 84	83.81 69	84.91 64	86.38 36	79.14 64	78.11 88	82.66 80	93.05 43	91.10 55	95.86 29	94.86 62

ACMP	83.90 8	88.32 59	88.06 59	88.62 58	92.18 69	93.98 70	91.28 61	85.24 57	86.69 53	81.23 61	85.62 38	75.13 101	87.01 62	89.83 93	89.77 88	94.79 81	95.43 54
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MSDG		83.87 92	81.02 114	87.19 71	92.17 70	89.80 125	89.15 82	85.72 54	80.61 94	79.24 73	66.66 130	68.75 133	82.69 79	87.95 115	87.44 120	94.19 112	85.92 172

TSAR-MVS + GP.		92.71 27	93.91 19	91.30 34	91.96 71	96.00 40	93.43 40	87.94 40	92.53 21	86.27 39	93.57 14	91.94 17	91.44 24	93.29 39	92.89 42	96.78 6	97.15 21

ETV-MVS		89.22 49	89.76 46	88.60 59	91.60 72	94.61 62	89.48 79	83.46 80	85.20 61	81.58 58	82.75 45	82.59 63	88.80 37	94.57 20	93.28 36	96.68 7	95.31 55

EIA-MVS		87.94 63	88.05 60	87.81 66	91.46 73	95.00 56	88.67 91	82.81 85	82.53 72	80.81 65	80.04 60	80.20 74	87.48 55	92.58 50	91.61 52	95.63 44	94.36 70

CS-MVS		88.97 51	89.44 50	88.41 63	91.45 74	95.24 50	90.03 68	82.43 95	84.08 67	81.16 62	81.02 57	83.83 57	88.74 39	94.25 27	92.73 44	96.67 9	94.95 59

canonicalmvs		89.36 48	89.92 43	88.70 57	91.38 75	95.92 42	91.81 56	82.61 93	90.37 39	82.73 55	82.09 47	79.28 83	88.30 46	91.17 69	93.59 26	95.36 59	97.04 25

CLD-MVS		88.66 53	88.52 54	88.82 55	91.37 76	94.22 65	92.82 47	82.08 97	88.27 49	85.14 42	81.86 48	78.53 87	85.93 68	91.17 69	90.61 68	95.55 50	95.00 57
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CHOSEN 1792x2688		82.16 106	80.91 117	83.61 100	91.14 77	92.01 97	89.55 78	79.15 129	79.87 98	70.29 109	52.51 190	72.56 116	81.39 87	88.87 106	88.17 114	90.15 175	92.37 115

IB-MVS	79.09 12	82.60 103	82.19 102	83.07 106	91.08 78	93.55 75	80.90 171	81.35 102	76.56 117	80.87 64	64.81 144	69.97 127	68.87 172	85.64 146	90.06 79	95.36 59	94.74 65
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
IS_MVSNet		86.18 73	88.18 58	83.85 98	91.02 79	94.72 61	87.48 104	82.46 94	81.05 89	70.28 110	76.98 76	82.20 66	76.65 137	93.97 30	93.38 34	95.18 67	94.97 58

HyFIR lowres test		81.62 116	79.45 136	84.14 94	91.00 80	93.38 78	88.27 96	78.19 137	76.28 119	70.18 111	48.78 194	73.69 110	83.52 76	87.05 123	87.83 118	93.68 133	89.15 146

COLMAP_ROB	76.78 15	80.50 122	78.49 141	82.85 107	90.96 81	89.65 131	86.20 125	83.40 82	77.15 115	66.54 128	62.27 152	65.62 142	77.89 129	85.23 153	84.70 160	92.11 153	84.83 176
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CANet_DTU		85.43 79	87.72 67	82.76 109	90.95 82	93.01 84	89.99 69	75.46 160	82.67 71	64.91 140	83.14 44	80.09 75	80.68 95	92.03 59	91.03 57	94.57 96	92.08 116

FC-MVSNet-train		85.18 81	85.31 85	85.03 81	90.67 83	91.62 100	87.66 102	83.61 72	79.75 100	74.37 93	78.69 68	71.21 121	78.91 122	91.23 65	89.96 82	94.96 76	94.69 67

baseline1		84.54 86	84.43 90	84.67 83	90.62 84	91.16 103	88.63 93	83.75 71	79.78 99	71.16 106	75.14 86	74.10 105	77.84 130	91.56 62	90.67 67	96.04 21	88.58 149

thres600view7		82.53 105	81.02 114	84.28 90	90.61 85	93.05 82	88.57 94	82.67 89	74.12 136	68.56 121	65.09 141	62.13 160	80.40 101	91.15 71	89.02 105	94.88 78	92.59 106

thres400		82.68 102	81.15 112	84.47 86	90.52 86	92.89 86	88.95 89	82.71 87	74.33 133	69.22 118	65.31 138	62.61 155	80.63 97	90.96 78	89.50 95	94.79 81	92.45 114

EPP-MVSNet		86.55 70	87.76 65	85.15 80	90.52 86	94.41 63	87.24 110	82.32 96	81.79 81	73.60 97	78.57 69	82.41 64	82.07 85	91.23 65	90.39 72	95.14 71	95.48 52

ACMH	78.52 14	81.86 110	80.45 121	83.51 104	90.51 88	91.22 102	85.62 132	84.23 64	70.29 160	62.21 156	69.04 121	64.05 147	84.48 73	87.57 118	88.45 113	94.01 118	92.54 110
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet (Re-imp)		83.65 95	86.81 73	79.96 139	90.46 89	92.71 87	84.84 140	82.00 98	80.93 91	62.44 155	76.29 79	82.32 65	65.54 185	92.29 52	91.66 50	94.49 101	91.47 130

thres200		82.77 101	81.25 111	84.54 84	90.38 90	93.05 82	89.13 83	82.67 89	74.40 132	69.53 115	65.69 136	63.03 152	80.63 97	91.15 71	89.42 96	94.88 78	92.04 118

MS-PatchMatch		81.79 112	81.44 108	82.19 116	90.35 91	89.29 137	88.08 99	75.36 161	77.60 113	69.00 119	64.37 147	78.87 86	77.14 136	88.03 114	85.70 150	93.19 143	86.24 169

PatchMatch-RL		83.34 97	81.36 109	85.65 77	90.33 92	89.52 133	84.36 144	81.82 99	80.87 93	79.29 72	74.04 92	62.85 154	86.05 67	88.40 111	87.04 127	92.04 154	86.77 165

thres100view900		82.55 104	81.01 116	84.34 87	90.30 93	92.27 94	89.04 87	82.77 86	75.14 126	69.56 113	65.72 134	63.13 149	79.62 116	89.97 92	89.26 99	94.73 86	91.61 128

tfpn200view9		82.86 99	81.46 107	84.48 85	90.30 93	93.09 81	89.05 86	82.71 87	75.14 126	69.56 113	65.72 134	63.13 149	80.38 102	91.15 71	89.51 94	94.91 77	92.50 112

casdiffmvs		87.45 67	87.15 69	87.79 68	90.15 95	94.22 65	89.96 70	83.93 68	85.08 62	80.91 63	75.81 82	77.88 91	86.08 66	91.86 60	90.86 61	95.74 39	94.37 69

MVS_Test		86.93 69	87.24 68	86.56 73	90.10 96	93.47 76	90.31 65	80.12 115	83.55 69	78.12 78	79.58 63	79.80 78	85.45 70	90.17 89	90.59 69	95.29 64	93.53 87

ACMH+	79.08 13	81.84 111	80.06 126	83.91 97	89.92 97	90.62 107	86.21 124	83.48 79	73.88 138	65.75 133	66.38 131	65.30 143	84.63 72	85.90 143	87.25 123	93.45 138	91.13 133

Effi-MVS+		85.33 80	85.08 86	85.63 78	89.69 98	93.42 77	89.90 71	80.31 113	79.32 103	72.48 105	73.52 97	74.03 106	86.55 65	90.99 76	89.98 81	94.83 80	94.27 75

Anonymous202405211			82.75 100		89.58 99	92.97 85	89.04 87	84.13 66	78.72 107		57.18 178	76.64 96	83.13 78	89.55 98	89.92 84	93.38 140	94.28 74

tttt0517		85.11 83	85.81 81	84.30 89	89.24 100	92.68 89	87.12 115	80.11 116	81.98 79	74.31 94	78.08 72	73.57 111	79.90 109	91.01 75	89.58 92	95.11 74	93.77 82

DI_MVS_plusplus_trai		86.41 72	85.54 84	87.42 70	89.24 100	93.13 80	92.16 51	82.65 91	82.30 76	80.75 67	68.30 124	80.41 72	85.01 71	90.56 87	90.07 78	94.70 89	94.01 77

thisisatest0530		85.15 82	85.86 80	84.33 88	89.19 102	92.57 93	87.22 111	80.11 116	82.15 78	74.41 92	78.15 71	73.80 109	79.90 109	90.99 76	89.58 92	95.13 72	93.75 83

DCV-MVSNet		85.88 78	86.17 76	85.54 79	89.10 103	89.85 123	89.34 80	80.70 106	83.04 70	78.08 80	76.19 80	79.00 84	82.42 83	89.67 96	90.30 73	93.63 135	95.12 56

UGNet		85.90 77	88.23 57	83.18 105	88.96 104	94.10 67	87.52 103	83.60 73	81.66 82	77.90 81	80.76 58	83.19 60	66.70 182	91.13 74	90.71 66	94.39 107	96.06 42
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
Anonymous20231211		84.42 90	83.02 96	86.05 75	88.85 105	92.70 88	88.92 90	83.40 82	79.99 97	78.31 77	55.83 182	78.92 85	83.33 77	89.06 103	89.76 89	93.50 137	94.90 60

MVSTER		86.03 75	86.12 77	85.93 76	88.62 106	89.93 121	89.33 81	79.91 120	81.87 80	81.35 59	81.07 56	74.91 102	80.66 96	92.13 58	90.10 77	95.68 41	92.80 98

TDRefinement		79.05 140	77.05 159	81.39 123	88.45 107	89.00 144	86.92 116	82.65 91	74.21 135	64.41 141	59.17 170	59.16 176	74.52 151	85.23 153	85.09 155	91.37 163	87.51 161

IterMVS-LS		83.28 98	82.95 98	83.65 99	88.39 108	88.63 148	86.80 119	78.64 134	76.56 117	73.43 98	72.52 102	75.35 99	80.81 93	86.43 138	88.51 112	93.84 126	92.66 103
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		86.52 71	86.76 74	86.23 74	88.31 109	92.63 90	89.58 76	81.61 101	86.14 55	80.26 68	79.00 66	77.27 93	83.58 75	88.94 104	89.06 103	94.05 116	94.29 71

Fast-Effi-MVS+		83.77 94	82.98 97	84.69 82	87.98 110	91.87 98	88.10 98	77.70 143	78.10 111	73.04 101	69.13 119	68.51 134	86.66 63	90.49 88	89.85 86	94.67 90	92.88 95

gg-mvs-nofinetune		75.64 177	77.26 156	73.76 182	87.92 111	92.20 95	87.32 107	64.67 199	51.92 204	35.35 207	46.44 197	77.05 95	71.97 162	92.64 49	91.02 58	95.34 61	89.53 144

RPSCF		83.46 96	83.36 95	83.59 101	87.75 112	87.35 157	84.82 141	79.46 125	83.84 68	78.12 78	82.69 46	79.87 76	82.60 82	82.47 177	81.13 180	88.78 182	86.13 170

Effi-MVS+-dtu		82.05 107	81.76 104	82.38 113	87.72 113	90.56 108	86.90 118	78.05 139	73.85 139	66.85 127	71.29 105	71.90 119	82.00 86	86.64 133	85.48 152	92.76 148	92.58 107

CostFormer		80.94 119	80.21 123	81.79 118	87.69 114	88.58 149	87.47 105	70.66 175	80.02 96	77.88 82	73.03 98	71.40 120	78.24 126	79.96 186	79.63 182	88.82 181	88.84 147

baseline2		82.80 100	82.86 99	82.73 110	87.68 115	90.50 109	84.92 139	78.93 130	78.07 112	73.06 100	75.08 87	69.77 128	77.31 133	88.90 105	86.94 128	94.50 99	90.74 134

Vis-MVSNet		84.38 91	86.68 75	81.70 119	87.65 116	94.89 57	88.14 97	80.90 105	74.48 131	68.23 122	77.53 74	80.72 71	69.98 169	92.68 48	91.90 48	95.33 62	94.58 68
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test-LLR		79.47 135	79.84 130	79.03 145	87.47 117	82.40 191	81.24 168	78.05 139	73.72 140	62.69 152	73.76 94	74.42 103	73.49 156	84.61 162	82.99 172	91.25 165	87.01 163

test0.0.03 1		76.03 171	78.51 140	73.12 186	87.47 117	85.13 177	76.32 189	78.05 139	73.19 147	50.98 193	70.64 107	69.28 131	55.53 192	85.33 151	84.38 164	90.39 173	81.63 188

tpmrst		76.55 164	75.99 171	77.20 159	87.32 119	83.05 184	82.86 154	65.62 194	78.61 109	67.22 126	69.19 118	65.71 141	75.87 141	76.75 195	75.33 195	84.31 199	83.28 182

baseline		84.89 84	86.06 79	83.52 103	87.25 120	89.67 130	87.76 100	75.68 159	84.92 63	78.40 76	80.10 59	80.98 69	80.20 105	86.69 132	87.05 126	91.86 157	92.99 92

CDS-MVSNet		81.63 115	82.09 103	81.09 128	87.21 121	90.28 112	87.46 106	80.33 112	69.06 164	70.66 107	71.30 104	73.87 107	67.99 175	89.58 97	89.87 85	92.87 147	90.69 135
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tpm cat1		77.78 153	75.28 179	80.70 131	87.14 122	85.84 168	85.81 128	70.40 176	77.44 114	78.80 75	63.72 148	64.01 148	76.55 138	75.60 197	75.21 196	85.51 197	85.12 174

tpm		76.30 170	76.05 170	76.59 165	86.97 123	83.01 185	83.83 148	67.06 190	71.83 150	63.87 146	69.56 116	62.88 153	73.41 158	79.79 187	78.59 186	84.41 198	86.68 166

EPMVS		77.53 155	78.07 148	76.90 163	86.89 124	84.91 178	82.18 163	66.64 192	81.00 90	64.11 144	72.75 101	69.68 129	74.42 153	79.36 189	78.13 188	87.14 190	80.68 192

PatchmatchNet		78.67 145	78.85 139	78.46 153	86.85 125	86.03 165	83.77 149	68.11 187	80.88 92	66.19 130	72.90 100	73.40 113	78.06 127	79.25 190	77.71 190	87.75 187	81.75 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		79.51 134	80.15 125	78.75 148	86.58 126	87.70 154	83.07 153	68.53 184	81.31 84	66.40 129	73.83 93	75.38 98	79.30 120	80.49 184	79.39 185	88.63 184	82.96 184

USDC		80.69 120	79.89 129	81.62 121	86.48 127	89.11 142	86.53 121	78.86 131	81.15 88	63.48 148	72.98 99	59.12 178	81.16 89	87.10 121	85.01 156	93.23 141	84.77 177

Fast-Effi-MVS+-dtu		79.95 126	80.69 118	79.08 144	86.36 128	89.14 141	85.85 127	72.28 169	72.85 148	59.32 176	70.43 111	68.42 135	77.57 131	86.14 140	86.44 138	93.11 144	91.39 131

tfpnnormal		77.46 156	74.86 181	80.49 135	86.34 129	88.92 145	84.33 145	81.26 103	61.39 192	61.70 163	51.99 191	53.66 196	74.84 148	88.63 107	87.38 122	94.50 99	92.08 116

dps		78.02 150	75.94 172	80.44 136	86.06 130	86.62 163	82.58 155	69.98 179	75.14 126	77.76 84	69.08 120	59.93 169	78.47 124	79.47 188	77.96 189	87.78 186	83.40 181

IterMVS-SCA-FT		79.41 136	80.20 124	78.49 152	85.88 131	86.26 164	83.95 147	71.94 170	73.55 143	61.94 159	70.48 110	70.50 124	75.23 143	85.81 145	84.61 162	91.99 156	90.18 141

LTVRE_ROB	74.41 16	75.78 176	74.72 182	77.02 162	85.88 131	89.22 138	82.44 158	77.17 146	50.57 205	45.45 199	65.44 137	52.29 198	81.25 88	85.50 149	87.42 121	89.94 177	92.62 104
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
EG-PatchMatch MVS		76.40 168	75.47 177	77.48 158	85.86 133	90.22 114	82.45 157	73.96 166	59.64 196	59.60 175	52.75 189	62.20 159	68.44 174	88.23 112	87.50 119	94.55 97	87.78 159

CR-MVSNet		78.71 144	78.86 138	78.55 151	85.85 134	85.15 175	82.30 160	68.23 185	74.71 129	65.37 136	64.39 146	69.59 130	77.18 134	85.10 158	84.87 157	92.34 152	88.21 153

GA-MVS		79.52 133	79.71 133	79.30 143	85.68 135	90.36 111	84.55 142	78.44 135	70.47 159	57.87 181	68.52 123	61.38 161	76.21 139	89.40 101	87.89 115	93.04 145	89.96 142

UniMVSNet_ETH3D		79.24 138	76.47 164	82.48 112	85.66 136	90.97 104	86.08 126	81.63 100	64.48 184	68.94 120	54.47 184	57.65 181	78.83 123	85.20 156	88.91 107	93.72 131	93.60 85

TransMVSNet (Re)		76.57 163	75.16 180	78.22 155	85.60 137	87.24 158	82.46 156	81.23 104	59.80 195	59.05 179	57.07 179	59.14 177	66.60 183	88.09 113	86.82 129	94.37 108	87.95 158

RPMNet		77.07 158	77.63 154	76.42 166	85.56 138	85.15 175	81.37 165	65.27 196	74.71 129	60.29 172	63.71 149	66.59 139	73.64 155	82.71 175	82.12 177	92.38 151	88.39 151

MDTV_nov1_ep13		79.14 139	79.49 135	78.74 149	85.40 139	86.89 161	84.32 146	70.29 177	78.85 106	69.42 116	75.37 85	73.29 114	75.64 142	80.61 183	79.48 184	87.36 188	81.91 186

UniMVSNet (Re)		81.22 117	81.08 113	81.39 123	85.35 140	91.76 99	84.93 138	82.88 84	76.13 120	65.02 139	64.94 142	63.09 151	75.17 145	87.71 117	89.04 104	94.97 75	94.88 61

UniMVSNet_NR-MVSNet		81.87 109	81.33 110	82.50 111	85.31 141	91.30 101	85.70 129	84.25 63	75.89 121	64.21 142	66.95 129	64.65 145	80.22 103	87.07 122	89.18 101	95.27 66	94.29 71

IterMVS		78.79 143	79.71 133	77.71 156	85.26 142	85.91 167	84.54 143	69.84 181	73.38 144	61.25 167	70.53 109	70.35 125	74.43 152	85.21 155	83.80 167	90.95 169	88.77 148
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NR-MVSNet		80.25 124	79.98 128	80.56 134	85.20 143	90.94 105	85.65 131	83.58 75	75.74 122	61.36 166	65.30 139	56.75 185	72.38 161	88.46 110	88.80 108	95.16 69	93.87 79

CMPMVS	56.49 17	73.84 185	71.73 190	76.31 169	85.20 143	85.67 170	75.80 190	73.23 167	62.26 189	65.40 135	53.40 188	59.70 171	71.77 164	80.25 185	79.56 183	86.45 193	81.28 189
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TinyColmap		76.73 160	73.95 184	79.96 139	85.16 145	85.64 171	82.34 159	78.19 137	70.63 157	62.06 158	60.69 162	49.61 201	80.81 93	85.12 157	83.69 168	91.22 167	82.27 185

gm-plane-assit		70.29 189	70.65 191	69.88 190	85.03 146	78.50 200	58.41 207	65.47 195	50.39 206	40.88 204	49.60 193	50.11 200	75.14 146	91.43 64	89.78 87	94.32 109	84.73 178

FC-MVSNet-test		76.53 165	81.62 106	70.58 189	84.99 147	85.73 169	74.81 192	78.85 132	77.00 116	39.13 206	75.90 81	73.50 112	54.08 196	86.54 135	85.99 147	91.65 159	86.68 166

DU-MVS		81.20 118	80.30 122	82.25 114	84.98 148	90.94 105	85.70 129	83.58 75	75.74 122	64.21 142	65.30 139	59.60 173	80.22 103	86.89 125	89.31 97	94.77 83	94.29 71

Baseline_NR-MVSNet		79.84 128	78.37 145	81.55 122	84.98 148	86.66 162	85.06 136	83.49 77	75.57 124	63.31 149	58.22 177	60.97 163	78.00 128	86.89 125	87.13 124	94.47 102	93.15 90

TranMVSNet+NR-MVSNet		80.52 121	79.84 130	81.33 125	84.92 150	90.39 110	85.53 134	84.22 65	74.27 134	60.68 171	64.93 143	59.96 168	77.48 132	86.75 130	89.28 98	95.12 73	93.29 88

pm-mvs1		78.51 148	77.75 153	79.40 142	84.83 151	89.30 136	83.55 151	79.38 126	62.64 188	63.68 147	58.73 175	64.68 144	70.78 168	89.79 94	87.84 116	94.17 113	91.28 132

testgi		71.92 187	74.20 183	69.27 191	84.58 152	83.06 183	73.40 194	74.39 163	64.04 186	46.17 198	68.90 122	57.15 183	48.89 200	84.07 167	83.08 171	88.18 185	79.09 196

thisisatest0515		79.76 130	80.59 120	78.80 147	84.40 153	88.91 146	79.48 177	76.94 149	72.29 149	67.33 125	67.82 126	65.99 140	70.80 167	88.50 109	87.84 116	93.86 125	92.75 101

FMVSNet3		84.44 89	84.64 89	84.21 91	84.32 154	90.13 116	89.85 72	80.37 109	81.17 85	75.50 86	69.63 113	79.69 80	79.62 116	89.72 95	90.52 71	95.59 48	91.58 129

GBi-Net		84.51 87	84.80 87	84.17 92	84.20 155	89.95 118	89.70 73	80.37 109	81.17 85	75.50 86	69.63 113	79.69 80	79.75 113	90.73 82	90.72 63	95.52 52	91.71 123

test1		84.51 87	84.80 87	84.17 92	84.20 155	89.95 118	89.70 73	80.37 109	81.17 85	75.50 86	69.63 113	79.69 80	79.75 113	90.73 82	90.72 63	95.52 52	91.71 123

FMVSNet2		83.87 92	83.73 94	84.05 96	84.20 155	89.95 118	89.70 73	80.21 114	79.17 105	74.89 90	65.91 132	77.49 92	79.75 113	90.87 79	91.00 59	95.52 52	91.71 123

WR-MVS		76.63 162	78.02 150	75.02 176	84.14 158	89.76 127	78.34 184	80.64 107	69.56 161	52.32 188	61.26 155	61.24 162	60.66 189	84.45 164	87.07 125	93.99 119	92.77 99

v8		79.90 127	78.39 144	81.66 120	83.97 159	89.81 124	87.16 113	77.40 145	71.49 151	67.71 123	61.24 156	62.49 156	79.83 112	85.48 150	86.17 142	93.89 123	92.02 120

v2v482		79.84 128	78.07 148	81.90 117	83.75 160	90.21 115	87.17 112	79.85 121	70.65 156	65.93 132	61.93 153	60.07 167	80.82 92	85.25 152	86.71 131	93.88 124	91.70 126

v10		79.62 131	78.19 146	81.28 126	83.73 161	89.69 129	87.27 109	76.86 150	70.50 158	65.46 134	60.58 163	60.47 165	80.44 100	86.91 124	86.63 134	93.93 120	92.55 109

v1144		79.38 137	77.83 151	81.18 127	83.62 162	90.23 113	87.15 114	78.35 136	69.13 163	64.02 145	60.20 165	59.41 174	80.14 107	86.78 128	86.57 135	93.81 128	92.53 111

v148		78.59 146	76.84 162	80.62 133	83.61 163	89.16 140	83.65 150	79.24 128	69.38 162	69.34 117	59.88 167	60.41 166	75.19 144	83.81 168	84.63 161	92.70 149	90.63 137

SixPastTwentyTwo		76.02 172	75.72 174	76.36 167	83.38 164	87.54 155	75.50 191	76.22 154	65.50 181	57.05 182	70.64 107	53.97 195	74.54 150	80.96 182	82.12 177	91.44 161	89.35 145

CVMVSNet		76.70 161	78.46 142	74.64 180	83.34 165	84.48 179	81.83 164	74.58 162	68.88 165	51.23 192	69.77 112	70.05 126	67.49 178	84.27 165	83.81 166	89.38 179	87.96 157

v1192		78.94 141	77.33 155	80.82 130	83.25 166	89.90 122	86.91 117	77.72 142	68.63 167	62.61 154	59.17 170	57.53 182	80.62 99	86.89 125	86.47 137	93.79 129	92.75 101

DTE-MVSNet		75.14 179	75.44 178	74.80 178	83.18 167	87.19 159	78.25 186	80.11 116	66.05 176	48.31 195	60.88 160	54.67 192	64.54 186	82.57 176	86.17 142	94.43 105	90.53 139

PEN-MVS		76.02 172	76.07 168	75.95 171	83.17 168	87.97 152	79.65 175	80.07 119	66.57 174	51.45 190	60.94 159	55.47 190	66.81 181	82.72 174	86.80 130	94.59 94	92.03 119

TAMVS		76.42 166	77.16 158	75.56 172	83.05 169	85.55 172	80.58 173	71.43 172	65.40 183	61.04 170	67.27 128	69.22 132	67.99 175	84.88 160	84.78 159	89.28 180	83.01 183

pmmvs4		79.99 125	78.08 147	82.22 115	83.04 170	87.16 160	84.95 137	78.80 133	78.64 108	74.53 91	64.61 145	59.41 174	79.45 118	84.13 166	84.54 163	92.53 150	88.08 155

v144192		78.81 142	77.22 157	80.67 132	82.95 171	89.79 126	86.40 122	77.42 144	68.26 169	63.13 150	59.50 168	58.13 179	80.08 108	85.93 142	86.08 144	94.06 115	92.83 97

v1921920		78.57 147	76.99 160	80.41 137	82.93 172	89.63 132	86.38 123	77.14 147	68.31 168	61.80 162	58.89 174	56.79 184	80.19 106	86.50 137	86.05 146	94.02 117	92.76 100

CHOSEN 280x420		80.28 123	81.66 105	78.67 150	82.92 173	79.24 199	85.36 135	66.79 191	78.11 110	70.32 108	75.03 88	79.87 76	81.09 90	89.07 102	83.16 170	85.54 196	87.17 162

WR-MVS_H		75.84 175	76.93 161	74.57 181	82.86 174	89.50 134	78.34 184	79.36 127	66.90 172	52.51 187	60.20 165	59.71 170	59.73 190	83.61 169	85.77 149	94.65 91	92.84 96

v1240		78.15 149	76.53 163	80.04 138	82.85 175	89.48 135	85.61 133	76.77 151	67.05 171	61.18 169	58.37 176	56.16 188	79.89 111	86.11 141	86.08 144	93.92 121	92.47 113

V42		79.59 132	78.43 143	80.94 129	82.79 176	89.71 128	86.66 120	76.73 152	71.38 152	67.42 124	61.01 158	62.30 158	78.39 125	85.56 148	86.48 136	93.65 134	92.60 105

CP-MVSNet		76.36 169	76.41 165	76.32 168	82.73 177	88.64 147	79.39 178	79.62 122	67.21 170	53.70 184	60.72 161	55.22 191	67.91 177	83.52 170	86.34 140	94.55 97	93.19 89

PS-CasMVS		75.90 174	75.86 173	75.96 170	82.59 178	88.46 150	79.23 181	79.56 124	66.00 177	52.77 186	59.48 169	54.35 194	67.14 180	83.37 171	86.23 141	94.47 102	93.10 91

test20.03		68.31 192	70.05 193	66.28 196	82.41 179	80.84 195	67.35 201	76.11 156	58.44 198	40.80 205	53.77 187	54.54 193	42.28 203	83.07 172	81.96 179	88.73 183	77.76 198

FMVSNet1		81.64 114	80.61 119	82.84 108	82.36 180	89.20 139	88.67 91	79.58 123	70.79 155	72.63 104	58.95 173	72.26 118	79.34 119	90.73 82	90.72 63	94.47 102	91.62 127

pmmvs6		74.83 180	72.89 187	77.09 160	82.11 181	87.50 156	80.88 172	76.97 148	52.79 203	61.91 161	46.66 196	60.49 164	69.28 171	86.74 131	85.46 153	91.39 162	90.56 138

pmmvs5		76.93 159	76.33 166	77.62 157	81.97 182	88.40 151	81.32 167	74.35 164	65.42 182	61.42 165	63.07 150	57.95 180	73.23 159	85.60 147	85.35 154	93.41 139	88.55 150

v7n		77.22 157	76.23 167	78.38 154	81.89 183	89.10 143	82.24 162	76.36 153	65.96 178	61.21 168	56.56 180	55.79 189	75.07 147	86.55 134	86.68 132	93.52 136	92.95 94

our_test_3					81.81 184	83.96 182	76.61 188

Anonymous20231206		70.80 188	70.59 192	71.04 188	81.60 185	82.49 190	74.64 193	75.87 158	64.17 185	49.27 194	44.85 200	53.59 197	54.68 195	83.07 172	82.34 176	90.17 174	83.65 180

ADS-MVSNet		74.53 182	75.69 175	73.17 185	81.57 186	80.71 196	79.27 180	63.03 201	79.27 104	59.94 174	67.86 125	68.32 137	71.08 166	77.33 194	76.83 192	84.12 201	79.53 193

test-mter		77.79 152	80.02 127	75.18 175	81.18 187	82.85 186	80.52 174	62.03 203	73.62 142	62.16 157	73.55 96	73.83 108	73.81 154	84.67 161	83.34 169	91.37 163	88.31 152

TESTMET0.1,1		77.78 153	79.84 130	75.38 174	80.86 188	82.40 191	81.24 168	62.72 202	73.72 140	62.69 152	73.76 94	74.42 103	73.49 156	84.61 162	82.99 172	91.25 165	87.01 163

MDTV_nov1_ep13_2view		73.21 186	72.91 186	73.56 184	80.01 189	84.28 181	78.62 182	66.43 193	68.64 166	59.12 177	60.39 164	59.69 172	69.81 170	78.82 192	77.43 191	87.36 188	81.11 191

FPMVS		63.63 197	60.08 202	67.78 193	80.01 189	71.50 205	72.88 196	69.41 183	61.82 191	53.11 185	45.12 199	42.11 208	50.86 198	66.69 202	63.84 203	80.41 203	69.46 204

anonymousdsp		77.94 151	79.00 137	76.71 164	79.03 191	87.83 153	79.58 176	72.87 168	65.80 179	58.86 180	65.82 133	62.48 157	75.99 140	86.77 129	88.66 109	93.92 121	95.68 49

N_pmnet		66.85 193	66.63 194	67.11 195	78.73 192	74.66 203	70.53 198	71.07 173	66.46 175	46.54 197	51.68 192	51.91 199	55.48 193	74.68 198	72.38 199	80.29 204	74.65 201

PMMVS		81.65 113	84.05 92	78.86 146	78.56 193	82.63 188	83.10 152	67.22 189	81.39 83	70.11 112	84.91 41	79.74 79	82.12 84	87.31 119	85.70 150	92.03 155	86.67 168

PatchT		76.42 166	77.81 152	74.80 178	78.46 194	84.30 180	71.82 197	65.03 198	73.89 137	65.37 136	61.58 154	66.70 138	77.18 134	85.10 158	84.87 157	90.94 170	88.21 153

MVS-HIRNet		68.83 191	66.39 195	71.68 187	77.58 195	75.52 202	66.45 202	65.05 197	62.16 190	62.84 151	44.76 201	56.60 187	71.96 163	78.04 193	75.06 197	86.18 195	72.56 202

pmmvs-eth3d		74.32 183	71.96 189	77.08 161	77.33 196	82.71 187	78.41 183	76.02 157	66.65 173	65.98 131	54.23 186	49.02 203	73.14 160	82.37 178	82.69 174	91.61 160	86.05 171

new-patchmatchnet		63.80 196	63.31 198	64.37 197	76.49 197	75.99 201	63.73 204	70.99 174	57.27 199	43.08 201	45.86 198	43.80 205	45.13 202	73.20 199	70.68 202	86.80 192	76.34 200

FMVSNet5		75.50 178	76.07 168	74.83 177	76.16 198	81.19 194	81.34 166	70.21 178	73.20 146	61.59 164	58.97 172	68.33 136	68.50 173	85.87 144	85.85 148	91.18 168	79.11 195

PM-MVS		74.17 184	73.10 185	75.41 173	76.07 199	82.53 189	77.56 187	71.69 171	71.04 153	61.92 160	61.23 157	47.30 204	74.82 149	81.78 180	79.80 181	90.42 172	88.05 156

MIMVSNet		74.69 181	75.60 176	73.62 183	76.02 200	85.31 174	81.21 170	67.43 188	71.02 154	59.07 178	54.48 183	64.07 146	66.14 184	86.52 136	86.64 133	91.83 158	81.17 190

EU-MVSNet		69.98 190	72.30 188	67.28 194	75.67 201	79.39 198	73.12 195	69.94 180	63.59 187	42.80 202	62.93 151	56.71 186	55.07 194	79.13 191	78.55 187	87.06 191	85.82 173

ET-MVSNet_ETH3D		84.65 85	85.58 83	83.56 102	74.99 202	92.62 92	90.29 66	80.38 108	82.16 77	73.01 102	83.41 43	71.10 122	87.05 61	87.77 116	90.17 76	95.62 45	91.82 121

PMVS	50.48 18	55.81 201	51.93 203	60.33 200	72.90 203	49.34 209	48.78 208	69.51 182	43.49 208	54.25 183	36.26 206	41.04 210	39.71 205	65.07 203	60.70 204	76.85 206	67.58 205
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ambc			61.92 199		70.98 204	73.54 204	63.64 205		60.06 194	52.23 189	38.44 204	19.17 214	57.12 191	82.33 179	75.03 198	83.21 202	84.89 175

pmmvs3		61.89 198	61.74 200	62.06 199	64.30 205	70.83 206	64.22 203	52.14 207	48.78 207	44.47 200	41.67 203	41.70 209	63.03 187	76.06 196	76.02 193	84.18 200	77.14 199

MDA-MVSNet-bldmvs		66.22 194	64.49 197	68.24 192	61.67 206	82.11 193	70.07 199	76.16 155	59.14 197	47.94 196	54.35 185	35.82 211	67.33 179	64.94 204	75.68 194	86.30 194	79.36 194

new_pmnet		59.28 199	61.47 201	56.73 201	61.66 207	68.29 207	59.57 206	54.91 204	60.83 193	34.38 208	44.66 202	43.65 206	49.90 199	71.66 200	71.56 201	79.94 205	69.67 203

Gipuma		49.17 202	47.05 204	51.65 202	59.67 208	48.39 210	41.98 210	63.47 200	55.64 202	33.33 209	14.90 208	13.78 215	41.34 204	69.31 201	72.30 200	70.11 207	55.00 208
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MIMVSNet1		65.00 195	66.24 196	63.55 198	58.41 209	80.01 197	69.00 200	74.03 165	55.81 201	41.88 203	36.81 205	49.48 202	47.89 201	81.32 181	82.40 175	90.08 176	77.88 197

EMVS		30.49 206	25.44 208	36.39 205	51.47 210	29.89 214	20.17 214	54.00 206	26.49 210	12.02 213	13.94 211	8.84 216	34.37 206	25.04 210	34.37 209	46.29 212	39.53 211

E-PMN		31.40 204	26.80 207	36.78 204	51.39 211	29.96 213	20.20 213	54.17 205	25.93 211	12.75 212	14.73 209	8.58 217	34.10 207	27.36 209	37.83 208	48.07 211	43.18 210

PMMVS2		41.68 203	44.74 205	38.10 203	46.97 212	52.32 208	40.63 211	48.08 208	35.51 209	7.36 214	26.86 207	24.64 213	16.72 209	55.24 206	59.03 205	68.85 208	59.59 207

tmp_tt				32.73 206	43.96 213	21.15 215	26.71 212	8.99 211	65.67 180	51.39 191	56.01 181	42.64 207	11.76 210	56.60 205	50.81 207	53.55 210

MVE	30.17 19	30.88 205	33.52 206	27.80 208	23.78 214	39.16 212	18.69 215	46.90 209	21.88 212	15.39 211	14.37 210	7.31 218	24.41 208	41.63 208	56.22 206	37.64 213	54.07 209
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND		57.56 200	82.61 101	28.34 207	0.22 215	90.10 117	79.37 179	0.14 213	79.56 101	0.40 215	71.25 106	83.40 59	0.30 213	86.27 139	83.87 165	89.59 178	83.83 179

testmvs		1.03 207	1.63 209	0.34 209	0.09 216	0.35 216	0.61 217	0.16 212	1.49 213	0.10 216	3.15 212	0.15 219	0.86 212	1.32 211	1.18 210	0.20 214	3.76 213

test123		0.87 208	1.40 210	0.25 210	0.03 217	0.25 217	0.35 218	0.08 214	1.21 214	0.05 217	2.84 213	0.03 220	0.89 211	0.43 212	1.16 211	0.13 215	3.87 212

uanet_test		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet		0.00 209	0.00 211	0.00 211	0.00 218	0.00 218	0.00 219	0.00 215	0.00 215	0.00 218	0.00 214	0.00 221	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

9.14												92.16 15

test_part1																	98.10 4

MTAPA										92.97 2		91.03 21

MTMP										93.14 1		90.21 29

Patchmatch-RL test							8.55 216

NP-MVS									87.47 52

Patchmtry						85.54 173	82.30 160	68.23 185		65.37 136

DeepMVS_CX						48.31 211	48.03 209	26.08 210	56.42 200	25.77 210	47.51 195	31.31 212	51.30 197	48.49 207		53.61 209	61.52 206

High-resolution multi-view benchmark