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.

SMA-MVS		77.32 6	82.51 6	71.26 7	75.43 14	80.19 8	82.22 7	58.26 3	84.83 6	64.36 8	78.19 15	83.46 5	63.61 7	81.00 1	80.28 1	83.66 4	89.62 5
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
SteuartSystems-ACMMP		75.23 12	79.60 14	70.13 13	76.81 7	78.92 12	81.74 8	57.99 5	75.30 30	59.83 26	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 9
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		75.62 11	79.91 13	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 17	63.04 14	70.69 24	81.15 15	62.99 10	80.23 4	79.54 3	83.11 9	89.16 7

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

HPM-MVS++		76.01 9	80.47 11	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 12	78.80 14	82.53 10	64.40 5	78.74 9	78.84 5	81.81 32	87.46 18

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

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 4	82.05 1	81.64 10	57.96 6	87.53 1	66.64 2	88.77 1	86.31 1	63.16 9	79.99 6	78.56 7	82.31 22	91.03 1

MSP-MVS		77.82 4	83.46 4	71.24 8	75.26 16	80.22 7	82.95 4	57.85 7	85.90 3	64.79 5	88.54 3	83.43 6	66.24 2	78.21 17	78.56 7	80.34 46	89.39 6

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

DeepC-MVS	66.32 2	73.85 23	78.10 22	68.90 23	67.92 50	79.31 11	78.16 29	59.28 1	78.24 22	61.13 20	67.36 36	76.10 33	63.40 8	79.11 8	78.41 10	83.52 5	88.16 12
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		74.31 18	78.87 17	68.99 22	73.49 23	78.56 15	79.25 23	56.51 17	75.33 28	60.69 23	75.30 19	79.12 23	61.81 21	77.78 21	77.93 11	82.18 28	88.06 13
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HFP-MVS		74.87 14	78.86 19	70.21 12	73.99 21	77.91 18	80.36 16	56.63 16	78.41 20	64.27 9	74.54 20	77.75 28	62.96 11	78.70 11	77.82 12	83.02 10	86.91 21

ACMMPR		73.79 24	78.41 20	68.40 25	72.35 28	77.79 19	79.32 21	56.38 19	77.67 24	58.30 32	74.16 21	76.66 29	61.40 23	78.32 13	77.80 13	82.68 16	86.51 22

zzz-MVS		74.25 20	77.97 23	69.91 15	73.43 24	74.06 44	79.69 19	56.44 18	80.74 14	64.98 4	68.72 30	79.98 20	62.92 12	78.24 16	77.77 14	81.99 30	86.30 23

DPE-MVS		78.11 3	83.84 3	71.42 5	77.82 6	81.32 3	82.92 6	57.81 8	84.04 7	63.19 13	88.63 2	86.00 3	64.52 4	78.71 10	77.63 15	82.26 23	90.57 3

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

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

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

CSCG		74.68 15	79.22 15	69.40 18	75.69 12	80.01 9	79.12 24	52.83 42	79.34 18	63.99 10	70.49 25	82.02 11	60.35 31	77.48 24	77.22 19	84.38 1	87.97 14

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

DeepC-MVS_fast	65.08 3	72.00 30	76.11 29	67.21 29	68.93 46	77.46 21	76.54 35	54.35 32	74.92 32	58.64 31	65.18 38	74.04 43	62.62 15	77.92 19	77.02 21	82.16 29	86.21 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		77.58 5	82.93 5	71.35 6	77.86 5	80.55 6	83.38 1	57.61 9	85.57 4	61.11 21	86.10 6	82.98 7	64.76 3	78.29 14	76.78 22	83.40 6	90.20 4

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

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

OPM-MVS		69.33 38	71.05 46	67.32 28	72.34 29	75.70 33	79.57 20	56.34 20	55.21 70	53.81 54	59.51 61	68.96 54	59.67 33	77.61 23	76.44 25	82.19 27	83.88 40

ACMMP		71.57 31	75.84 31	66.59 31	70.30 40	76.85 29	78.46 28	53.95 35	73.52 36	55.56 39	70.13 26	71.36 48	58.55 38	77.00 28	76.23 26	82.71 15	85.81 28
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
APD-MVS		75.80 10	80.90 10	69.86 16	75.42 15	78.48 16	81.43 13	57.44 12	80.45 15	59.32 27	85.28 7	80.82 17	63.96 6	76.89 29	76.08 27	81.58 38	88.30 11
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		73.89 22	78.25 21	68.80 24	75.25 17	72.27 52	79.75 18	56.05 21	74.87 33	58.97 28	81.83 11	79.76 21	61.05 26	77.39 25	76.01 28	81.71 35	85.61 30

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

TSAR-MVS + MP.		75.22 13	80.06 12	69.56 17	74.61 18	72.74 50	80.59 14	55.70 24	80.80 13	62.65 16	86.25 5	82.92 8	62.07 20	76.89 29	75.66 30	81.77 34	85.19 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
xxxxxxxxxxxxxcwj		74.63 16	77.07 27	71.79 2	79.32 1	80.76 4	82.96 2	57.49 10	82.82 8	64.79 5	83.69 9	52.03 117	62.83 13	77.13 26	75.21 31	83.35 7	87.85 15

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

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

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

ACMM	60.30 7	67.58 48	68.82 57	66.13 34	70.59 37	72.01 54	76.54 35	54.26 33	65.64 54	54.78 47	50.35 102	61.72 77	58.74 36	75.79 39	75.03 34	81.88 31	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 39	72.89 37	54.88 45	70.03 27	70.48 50	57.26 47	76.02 36	75.01 36	81.78 33	86.21 24

CLD-MVS		67.02 50	71.57 43	61.71 52	71.01 35	74.81 38	71.62 53	38.91 154	71.86 41	60.70 22	64.97 39	67.88 61	51.88 88	76.77 32	74.98 37	76.11 92	69.75 120
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_111021_HR		67.62 47	70.39 50	64.39 44	69.77 42	70.45 58	71.44 55	51.72 48	60.77 64	55.06 43	62.14 53	66.40 63	58.13 41	76.13 35	74.79 38	80.19 48	82.04 49

MAR-MVS		68.04 45	70.74 48	64.90 42	71.68 32	76.33 31	74.63 44	50.48 56	63.81 56	55.52 40	54.88 81	69.90 52	57.39 45	75.42 42	74.79 38	79.71 51	80.03 56
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
LGP-MVS_train		68.87 40	72.03 42	65.18 40	69.33 44	74.03 45	76.67 34	53.88 36	68.46 49	52.05 59	63.21 45	63.89 67	56.31 55	75.99 37	74.43 40	82.83 14	84.18 36

PHI-MVS		69.27 39	74.84 35	62.76 51	66.83 54	74.83 37	73.88 47	49.32 61	70.61 45	50.93 60	69.62 28	74.84 36	57.25 48	75.53 40	74.32 41	78.35 65	84.17 37

ACMP	61.42 5	68.72 43	71.37 44	65.64 38	69.06 45	74.45 42	75.88 38	53.30 38	68.10 50	55.74 38	61.53 56	62.29 73	56.97 50	74.70 45	74.23 42	82.88 13	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TSAR-MVS + GP.		69.71 35	73.92 37	64.80 43	68.27 48	70.56 57	71.90 51	50.75 52	71.38 42	57.46 36	68.68 31	75.42 34	60.10 32	73.47 51	73.99 43	80.32 47	83.97 38

SD-MVS		74.43 17	78.87 17	69.26 20	74.39 19	73.70 46	79.06 25	55.24 26	81.04 12	62.71 15	80.18 12	82.61 9	61.70 22	75.43 41	73.92 44	82.44 21	85.22 32
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + ACMM		72.56 29	79.07 16	64.96 41	73.24 25	73.16 49	78.50 27	48.80 65	79.34 18	55.32 41	85.04 8	81.49 14	58.57 37	75.06 44	73.75 45	75.35 102	85.61 30

AdaColmap		67.89 46	68.85 56	66.77 30	73.73 22	74.30 43	75.28 40	53.58 37	70.24 46	57.59 35	51.19 99	59.19 89	60.74 28	75.33 43	73.72 46	79.69 54	77.96 67

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

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

DELS-MVS		65.87 52	70.30 52	60.71 54	64.05 72	72.68 51	70.90 56	45.43 79	57.49 67	49.05 69	64.43 40	68.66 55	55.11 63	74.31 46	73.02 49	79.70 52	81.51 50
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
EPNet		65.14 56	69.54 54	60.00 58	66.61 56	67.67 75	67.53 63	55.32 25	62.67 60	46.22 78	67.74 33	65.93 64	48.07 107	72.17 56	72.12 50	76.28 88	78.47 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		68.76 42	73.01 38	63.81 48	65.42 62	73.66 47	76.39 37	52.08 44	72.61 39	50.33 62	60.73 57	72.65 46	59.43 35	73.32 52	72.12 50	79.19 58	85.99 26

Effi-MVS+		63.28 60	65.96 66	60.17 57	64.26 68	68.06 69	68.78 58	45.71 77	54.08 73	46.64 75	55.92 76	63.13 71	55.94 59	70.38 71	71.43 52	79.68 55	78.70 62

QAPM		65.27 54	69.49 55	60.35 56	65.43 61	72.20 53	65.69 83	47.23 68	63.46 57	49.14 67	53.56 87	71.04 49	57.01 49	72.60 55	71.41 53	77.62 69	82.14 48

ETV-MVS		63.23 61	66.08 65	59.91 59	63.13 76	68.13 68	67.62 62	44.62 89	53.39 78	46.23 77	58.74 63	58.19 92	57.45 44	73.60 49	71.38 54	80.39 45	79.13 59

canonicalmvs		65.62 53	72.06 41	58.11 67	63.94 73	71.05 55	64.49 92	43.18 122	74.08 34	47.35 71	64.17 42	71.97 47	51.17 91	71.87 57	70.74 55	78.51 63	80.56 54

test_part1		63.06 62	65.27 71	60.47 55	66.24 60	70.17 59	71.86 52	45.36 81	53.75 75	49.61 65	44.85 144	65.53 65	48.93 98	71.39 60	70.65 56	80.82 43	80.59 53

EG-PatchMatch MVS		56.98 103	58.24 124	55.50 89	64.66 65	68.62 64	61.48 103	43.63 109	38.44 185	41.44 100	38.05 175	46.18 154	43.95 125	71.71 58	70.61 57	77.87 66	74.08 100

MSLP-MVS++		68.17 44	70.72 49	65.19 39	69.41 43	70.64 56	74.99 41	45.76 75	70.20 47	60.17 24	56.42 73	73.01 44	61.14 24	72.80 54	70.54 58	79.70 52	81.42 51

IB-MVS	54.11 11	58.36 92	60.70 92	55.62 88	58.67 95	68.02 70	61.56 101	43.15 123	46.09 133	44.06 88	44.24 147	50.99 123	48.71 101	66.70 121	70.33 59	77.60 70	78.50 63
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
anonymousdsp		52.84 132	57.78 128	47.06 151	40.24 195	58.95 144	53.70 153	33.54 186	36.51 192	32.69 139	43.88 149	45.40 158	47.97 108	67.17 113	70.28 60	74.22 110	82.29 47

ACMH	52.42 13	58.24 94	59.56 111	56.70 83	66.34 58	69.59 60	66.71 71	49.12 62	46.08 134	28.90 157	42.67 164	41.20 181	52.60 81	71.39 60	70.28 60	76.51 84	75.72 88
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IS_MVSNet		57.95 97	64.26 78	50.60 117	61.62 81	65.25 100	57.18 126	45.42 80	50.79 92	26.49 168	57.81 68	60.05 86	34.51 168	71.24 64	70.20 62	78.36 64	74.44 96

CS-MVS		63.45 59	65.72 68	60.80 53	64.20 69	67.86 71	68.46 60	43.50 114	53.86 74	49.90 64	56.44 72	60.45 84	57.27 46	73.56 50	70.13 63	81.45 40	77.73 69

PVSNet_Blended_VisFu		63.65 58	66.92 59	59.83 60	60.03 89	73.44 48	66.33 74	48.95 63	52.20 88	50.81 61	56.07 74	60.25 85	53.56 70	73.23 53	70.01 64	79.30 56	83.24 44

Vis-MVSNet		58.48 88	65.70 69	50.06 122	53.40 140	67.20 81	60.24 112	43.32 119	48.83 110	30.23 150	62.38 52	61.61 78	40.35 143	71.03 65	69.77 65	72.82 129	79.11 60
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		60.36 74	63.35 81	56.87 81	58.70 94	65.86 93	65.08 88	37.11 167	53.00 83	45.36 82	52.12 94	56.07 104	56.27 56	71.28 63	69.42 66	78.71 59	75.69 89

PCF-MVS	59.98 8	67.32 49	71.04 47	62.97 50	64.77 64	74.49 40	74.78 43	49.54 59	67.44 51	54.39 52	58.35 66	72.81 45	55.79 61	71.54 59	69.24 67	78.57 60	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EIA-MVS		61.53 72	63.79 80	58.89 64	63.82 74	67.61 76	65.35 86	42.15 132	49.98 96	45.66 80	57.47 70	56.62 99	56.59 54	70.91 66	69.15 68	79.78 50	74.80 94

EPP-MVSNet		59.39 78	65.45 70	52.32 112	60.96 84	67.70 74	58.42 120	44.75 87	49.71 98	27.23 165	59.03 62	62.20 74	43.34 129	70.71 67	69.13 69	79.25 57	79.63 58

TranMVSNet+NR-MVSNet		55.87 112	60.14 102	50.88 116	59.46 93	63.82 108	57.93 122	52.98 40	48.94 108	20.52 181	52.87 89	47.33 141	36.81 161	69.12 80	69.03 70	77.56 72	69.89 119

ACMH+	53.71 12	59.26 79	60.28 97	58.06 68	64.17 71	68.46 65	67.51 64	50.93 51	52.46 87	35.83 129	40.83 169	45.12 163	52.32 84	69.88 74	69.00 71	77.59 71	76.21 85

UniMVSNet_NR-MVSNet		56.94 105	61.14 88	52.05 114	60.02 90	65.21 101	57.44 124	52.93 41	49.37 102	24.31 175	54.62 85	50.54 124	39.04 147	68.69 82	68.84 72	78.53 62	70.72 113

OMC-MVS		65.16 55	71.35 45	57.94 71	52.95 143	68.82 63	69.00 57	38.28 161	79.89 16	55.20 42	62.76 49	68.31 57	56.14 58	71.30 62	68.70 73	76.06 94	79.67 57

NR-MVSNet		55.35 118	59.46 112	50.56 118	61.33 82	62.97 112	57.91 123	51.80 46	48.62 116	20.59 180	51.99 95	44.73 169	34.10 171	68.58 85	68.64 74	77.66 68	70.67 117

OpenMVS	57.13 9	62.81 64	65.75 67	59.39 61	66.47 57	69.52 61	64.26 94	43.07 124	61.34 63	50.19 63	47.29 119	64.41 66	54.60 64	70.18 73	68.62 75	77.73 67	78.89 61

ET-MVSNet_ETH3D		58.38 91	61.57 86	54.67 93	42.15 192	65.26 98	65.70 81	43.82 102	48.84 109	42.34 96	59.76 60	47.76 135	56.68 53	67.02 118	68.60 76	77.33 75	73.73 103

FC-MVSNet-train		58.40 90	63.15 82	52.85 108	64.29 67	61.84 118	55.98 138	46.47 71	53.06 81	34.96 132	61.95 55	56.37 102	39.49 145	68.67 83	68.36 77	75.92 96	71.81 108

MVS_111021_LR		63.05 63	66.43 62	59.10 63	61.33 82	63.77 109	65.87 80	43.58 110	60.20 65	53.70 55	62.09 54	62.38 72	55.84 60	70.24 72	68.08 78	74.30 109	78.28 66

HyFIR lowres test		56.87 106	58.60 121	54.84 91	56.62 120	69.27 62	64.77 90	42.21 130	45.66 137	37.50 124	33.08 186	57.47 97	53.33 76	65.46 138	67.94 79	74.60 106	71.35 110

UniMVSNet (Re)		55.15 122	60.39 96	49.03 131	55.31 125	64.59 105	55.77 139	50.63 53	48.66 115	20.95 179	51.47 97	50.40 125	34.41 170	67.81 102	67.89 80	77.11 79	71.88 107

thisisatest0530		56.68 107	59.68 106	53.19 104	52.97 142	60.96 128	59.41 115	40.51 144	48.26 119	41.06 105	52.67 90	46.30 151	49.78 93	67.66 106	67.83 81	75.39 100	74.07 101

tttt0517		56.53 109	59.59 108	52.95 107	52.66 145	60.99 127	59.21 117	40.51 144	47.89 122	40.40 108	52.50 93	46.04 155	49.78 93	67.75 104	67.83 81	75.15 103	74.17 98

MSDG		58.46 89	58.97 117	57.85 75	66.27 59	66.23 91	67.72 61	42.33 128	53.43 77	43.68 89	43.39 155	45.35 159	49.75 95	68.66 84	67.77 83	77.38 73	67.96 135

DU-MVS		55.41 117	59.59 108	50.54 119	54.60 131	62.97 112	57.44 124	51.80 46	48.62 116	24.31 175	51.99 95	47.00 144	39.04 147	68.11 95	67.75 84	76.03 95	70.72 113

Anonymous202405211			60.60 93		63.44 75	66.71 88	61.00 108	47.23 68	50.62 94		36.85 178	60.63 83	43.03 133	69.17 78	67.72 85	75.41 99	72.54 105

DCV-MVSNet		59.49 77	64.00 79	54.23 94	61.81 78	64.33 106	61.42 104	43.77 103	52.85 84	38.94 117	55.62 78	62.15 75	43.24 132	69.39 77	67.66 86	76.22 90	75.97 86

UGNet		57.03 102	65.25 72	47.44 150	46.54 179	66.73 85	56.30 133	43.28 120	50.06 95	32.99 136	62.57 51	63.26 70	33.31 173	68.25 90	67.58 87	72.20 141	78.29 65
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
CHOSEN 1792x2688		55.85 113	58.01 125	53.33 101	57.26 114	62.82 114	63.29 100	41.55 135	46.65 129	38.34 118	34.55 184	53.50 110	52.43 83	67.10 116	67.56 88	67.13 163	73.92 102

CANet_DTU		58.88 82	64.68 76	52.12 113	55.77 123	66.75 84	63.92 95	37.04 168	53.32 79	37.45 125	59.81 59	61.81 76	44.43 124	68.25 90	67.47 89	74.12 111	75.33 92

UA-Net		58.50 87	64.68 76	51.30 115	66.97 53	67.13 82	53.68 154	45.65 78	49.51 101	31.58 144	62.91 47	68.47 56	35.85 164	68.20 93	67.28 90	74.03 112	69.24 130

Effi-MVS+-dtu		60.34 75	62.32 84	58.03 70	64.31 66	67.44 79	65.99 78	42.26 129	49.55 99	42.00 99	48.92 109	59.79 87	56.27 56	68.07 97	67.03 91	77.35 74	75.45 91

GBi-Net		55.20 119	60.25 98	49.31 125	52.42 146	61.44 120	57.03 127	44.04 97	49.18 105	30.47 146	48.28 111	58.19 92	38.22 150	68.05 98	66.96 92	73.69 116	69.65 121

test1		55.20 119	60.25 98	49.31 125	52.42 146	61.44 120	57.03 127	44.04 97	49.18 105	30.47 146	48.28 111	58.19 92	38.22 150	68.05 98	66.96 92	73.69 116	69.65 121

FMVSNet1		54.08 127	58.68 119	48.71 135	50.90 162	61.35 123	56.73 131	43.94 101	45.91 135	29.32 156	42.72 163	56.26 103	37.70 155	68.05 98	66.96 92	73.69 116	69.50 125

thisisatest0515		53.85 128	56.84 135	50.37 120	50.25 166	58.17 153	55.99 137	39.90 151	41.88 166	38.16 120	45.91 133	45.30 160	44.58 123	66.15 130	66.89 95	73.36 122	73.57 104

CDS-MVSNet		52.42 135	57.06 134	47.02 152	53.92 138	58.30 151	55.50 142	46.47 71	42.52 163	29.38 155	49.50 105	52.85 114	28.49 183	66.70 121	66.89 95	68.34 158	62.63 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVSTER		57.19 101	61.11 89	52.62 110	50.82 163	58.79 145	61.55 102	37.86 164	48.81 111	41.31 102	57.43 71	52.10 116	48.60 102	68.19 94	66.75 97	75.56 98	75.68 90

MS-PatchMatch		58.19 96	60.20 100	55.85 87	65.17 63	64.16 107	64.82 89	41.48 136	50.95 91	42.17 98	45.38 139	56.42 100	48.08 106	68.30 89	66.70 98	73.39 120	69.46 128

DI_MVS_plusplus_trai		61.88 68	65.17 73	58.06 68	60.05 88	65.26 98	66.03 77	44.22 93	55.75 69	46.73 73	54.64 84	68.12 59	54.13 67	69.13 79	66.66 99	77.18 76	76.61 78

TSAR-MVS + COLMAP		62.65 66	69.90 53	54.19 95	46.31 180	66.73 85	65.49 85	41.36 137	76.57 25	46.31 76	76.80 17	56.68 98	53.27 78	69.50 76	66.65 100	72.40 138	76.36 84

Anonymous20231211		57.71 99	60.79 91	54.13 96	61.68 80	65.81 94	60.81 109	43.70 107	51.97 89	39.67 112	34.82 183	63.59 68	43.31 130	68.55 87	66.63 101	75.59 97	74.13 99

v1144		58.88 82	60.16 101	57.39 77	58.03 99	67.26 80	67.14 67	44.46 91	45.17 139	44.33 87	47.81 116	49.92 128	53.20 79	67.77 103	66.62 102	77.15 77	76.58 79

v10		59.17 81	60.60 93	57.50 76	57.95 100	66.73 85	67.09 69	44.11 94	46.85 127	45.42 81	48.18 115	51.07 120	53.63 69	67.84 101	66.59 103	76.79 80	76.92 75

v1192		58.51 86	59.66 107	57.17 78	57.82 101	67.72 73	66.21 76	44.83 86	44.15 147	43.49 90	46.68 121	47.94 132	53.55 71	67.39 110	66.51 104	77.13 78	77.20 73

LS3D		60.20 76	61.70 85	58.45 66	64.18 70	67.77 72	67.19 65	48.84 64	61.67 62	41.27 103	45.89 134	51.81 118	54.18 66	68.78 81	66.50 105	75.03 104	69.48 126

Fast-Effi-MVS+-dtu		56.30 110	59.29 114	52.82 109	58.64 96	64.89 102	65.56 84	32.89 189	45.80 136	35.04 131	45.89 134	54.14 109	49.41 96	67.16 114	66.45 106	75.37 101	70.69 115

MVS_Test		62.40 67	66.23 64	57.94 71	59.77 92	64.77 104	66.50 73	41.76 133	57.26 68	49.33 66	62.68 50	67.47 62	53.50 73	68.57 86	66.25 107	76.77 81	76.58 79

v7n		55.67 114	57.46 132	53.59 100	56.06 121	65.29 97	61.06 107	43.26 121	40.17 176	37.99 121	40.79 170	45.27 162	47.09 111	67.67 105	66.21 108	76.08 93	76.82 76

FMVSNet2		55.04 123	59.95 105	49.31 125	52.42 146	61.44 120	57.03 127	44.08 96	49.55 99	30.40 149	46.89 120	58.84 90	38.22 150	67.07 117	66.21 108	73.69 116	69.65 121

casdiffmvs		64.09 57	68.13 58	59.37 62	61.81 78	68.32 67	68.48 59	44.45 92	61.95 61	49.12 68	63.04 46	69.67 53	53.83 68	70.46 68	66.06 110	78.55 61	77.43 70

v2v482		58.69 85	60.12 104	57.03 79	57.16 117	66.05 92	67.17 66	43.52 112	46.33 131	45.19 83	49.46 106	51.02 121	52.51 82	67.30 111	66.03 111	76.61 82	74.62 95

Baseline_NR-MVSNet		53.50 129	57.89 126	48.37 141	54.60 131	59.25 142	56.10 134	51.84 45	49.32 103	17.92 188	45.38 139	47.68 136	36.93 160	68.11 95	65.95 112	72.84 128	69.57 124

V42		56.97 104	60.14 102	53.28 102	48.16 172	62.78 115	66.30 75	37.93 163	47.44 124	42.68 94	48.19 114	52.59 115	51.90 87	67.46 109	65.94 113	72.72 131	76.55 81

v144192		58.23 95	59.40 113	56.87 81	57.56 102	66.89 83	65.70 81	45.01 84	44.06 148	42.88 92	46.61 123	48.09 131	53.49 74	66.94 119	65.90 114	76.61 82	77.29 71

v1240		57.55 100	58.63 120	56.29 85	57.30 113	66.48 90	63.77 96	44.56 90	42.77 161	42.48 95	45.64 137	46.28 152	53.46 75	66.32 126	65.80 115	76.16 91	77.13 74

v1921920		57.89 98	59.02 116	56.58 84	57.55 103	66.66 89	64.72 91	44.70 88	43.55 151	42.73 93	46.17 131	46.93 145	53.51 72	66.78 120	65.75 116	76.29 87	77.28 72

v8		58.88 82	60.57 95	56.92 80	57.35 110	65.69 95	66.69 72	42.64 126	47.89 122	45.77 79	49.04 107	52.98 113	52.77 80	67.51 108	65.57 117	76.26 89	75.30 93

diffmvs		61.64 69	66.55 61	55.90 86	56.63 119	63.71 110	67.13 68	41.27 138	59.49 66	46.70 74	63.93 44	68.01 60	50.46 92	67.30 111	65.51 118	73.24 126	77.87 68

GA-MVS		55.67 114	58.33 122	52.58 111	55.23 128	63.09 111	61.08 106	40.15 150	42.95 156	37.02 127	52.61 91	47.68 136	47.51 109	65.92 132	65.35 119	74.49 108	70.68 116

IterMVS-LS		58.30 93	61.39 87	54.71 92	59.92 91	58.40 149	59.42 114	43.64 108	48.71 113	40.25 110	57.53 69	58.55 91	52.15 86	65.42 139	65.34 120	72.85 127	75.77 87
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	52.09 14	59.21 80	62.47 83	55.41 90	53.24 141	64.84 103	64.47 93	40.41 148	65.92 53	44.53 86	46.19 130	55.69 105	55.33 62	68.24 92	65.30 121	74.50 107	71.09 111
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		62.78 65	66.31 63	58.65 65	58.47 97	68.41 66	65.98 79	41.22 139	78.02 23	56.04 37	46.65 122	59.50 88	57.50 43	69.67 75	65.27 122	72.70 133	76.67 77

TransMVSNet (Re)		51.92 142	55.38 141	47.88 147	60.95 85	59.90 136	53.95 151	45.14 83	39.47 179	24.85 172	43.87 150	46.51 150	29.15 180	67.55 107	65.23 123	73.26 125	65.16 156

PVSNet_BlendedMVS		61.63 70	64.82 74	57.91 73	57.21 115	67.55 77	63.47 98	46.08 73	54.72 71	52.46 57	58.59 64	60.73 80	51.82 89	70.46 68	65.20 124	76.44 85	76.50 82

PVSNet_Blended		61.63 70	64.82 74	57.91 73	57.21 115	67.55 77	63.47 98	46.08 73	54.72 71	52.46 57	58.59 64	60.73 80	51.82 89	70.46 68	65.20 124	76.44 85	76.50 82

FMVSNet3		54.78 124	59.58 110	49.17 128	52.37 149	61.31 124	56.72 132	44.04 97	49.18 105	30.47 146	48.28 111	58.19 92	38.09 153	65.48 137	65.20 124	73.31 123	69.45 129

UniMVSNet_ETH3D		52.62 133	55.98 137	48.70 136	51.04 160	60.71 130	56.87 130	46.74 70	42.52 163	26.96 166	42.50 165	45.95 156	37.87 154	66.22 128	65.15 127	72.74 130	68.78 133

TAPA-MVS	54.74 10	60.85 73	66.61 60	54.12 97	47.38 176	65.33 96	65.35 86	36.51 170	75.16 31	48.82 70	54.70 83	63.51 69	53.31 77	68.36 88	64.97 128	73.37 121	74.27 97
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
WR-MVS		48.78 162	55.06 144	41.45 177	55.50 124	60.40 131	43.77 192	49.99 58	41.92 165	8.10 206	45.24 142	45.56 157	17.47 196	61.57 155	64.60 129	73.85 113	66.14 148

tfpn200view9		52.53 134	55.51 139	49.06 130	57.31 111	60.24 132	55.42 144	43.77 103	42.85 159	27.81 161	43.00 161	45.06 165	37.32 157	66.38 123	64.54 130	72.71 132	66.54 141

thres400		52.38 137	55.51 139	48.74 134	57.49 106	60.10 135	55.45 143	43.54 111	42.90 158	26.72 167	43.34 157	45.03 167	36.61 162	66.20 129	64.53 131	72.66 134	66.43 142

gg-mvs-nofinetune		49.07 160	52.56 160	45.00 161	61.99 77	59.78 137	53.55 156	41.63 134	31.62 201	12.08 196	29.56 195	53.28 112	29.57 179	66.27 127	64.49 132	71.19 149	62.92 165

baseline2		55.89 111	57.82 127	53.64 98	57.36 109	61.09 126	59.75 113	40.45 146	47.38 125	41.26 104	51.23 98	46.90 146	48.11 105	65.63 136	64.38 133	74.90 105	68.16 134

baseline1		54.48 126	58.69 118	49.57 123	60.63 87	58.29 152	55.70 140	44.95 85	49.20 104	29.62 153	54.77 82	54.75 107	35.29 165	67.15 115	64.08 134	71.21 148	62.58 169

PEN-MVS		49.21 158	54.32 148	43.24 171	54.33 134	59.26 141	47.04 178	51.37 50	41.67 167	9.97 201	46.22 129	41.80 180	22.97 192	60.52 158	64.03 135	73.73 115	66.75 140

pm-mvs1		51.02 146	55.55 138	45.73 156	54.16 135	58.52 147	50.92 161	42.56 127	40.32 175	25.67 170	43.66 152	50.34 126	30.06 178	65.85 133	63.97 136	70.99 150	66.21 145

thres200		52.39 136	55.37 142	48.90 132	57.39 108	60.18 133	55.60 141	43.73 105	42.93 157	27.41 163	43.35 156	45.09 164	36.61 162	66.36 124	63.92 137	72.66 134	65.78 151

pmmvs4		54.66 125	56.07 136	53.00 106	54.63 130	57.08 160	60.43 111	44.10 95	51.69 90	40.55 107	46.55 126	44.79 168	45.95 117	62.54 149	63.66 138	72.36 139	66.20 146

thres100view900		52.04 140	54.81 146	48.80 133	57.31 111	59.33 140	55.30 145	42.92 125	42.85 159	27.81 161	43.00 161	45.06 165	36.99 159	64.74 142	63.51 139	72.47 137	65.21 155

tfpnnormal		50.16 152	52.19 164	47.78 149	56.86 118	58.37 150	54.15 150	44.01 100	38.35 187	25.94 169	36.10 179	37.89 194	34.50 169	65.93 131	63.42 140	71.26 147	65.28 154

Vis-MVSNet (Re-imp)		50.37 150	57.73 130	41.80 176	57.53 104	54.35 166	45.70 184	45.24 82	49.80 97	13.43 194	58.23 67	56.42 100	20.11 195	62.96 147	63.36 141	68.76 157	58.96 181

thres600view7		51.91 143	55.14 143	48.14 143	57.43 107	60.18 133	54.60 149	43.73 105	42.61 162	25.20 171	43.10 160	44.47 172	35.19 166	66.36 124	63.28 142	72.66 134	66.01 149

pmmvs6		48.35 164	51.64 166	44.51 164	51.92 152	57.94 156	49.44 167	42.17 131	34.45 194	24.62 174	28.87 197	46.90 146	29.07 182	64.60 143	63.08 143	69.83 154	65.68 152

COLMAP_ROB	46.52 15	51.99 141	54.86 145	48.63 137	49.13 170	61.73 119	60.53 110	36.57 169	53.14 80	32.95 137	37.10 176	38.68 192	40.49 142	65.72 134	63.08 143	72.11 142	64.60 159
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
gm-plane-assit		44.74 180	45.95 188	43.33 169	60.88 86	46.79 194	36.97 202	32.24 192	24.15 207	11.79 197	29.26 196	32.97 202	46.64 112	65.09 141	62.95 145	71.45 146	60.42 176

DTE-MVSNet		48.03 168	53.28 155	41.91 175	54.64 129	57.50 158	44.63 191	51.66 49	41.02 171	7.97 207	46.26 128	40.90 182	20.24 194	60.45 159	62.89 146	72.33 140	63.97 161

pmmvs-eth3d		51.33 144	52.25 163	50.26 121	50.82 163	54.65 165	56.03 136	43.45 118	43.51 152	37.20 126	39.20 173	39.04 191	42.28 135	61.85 154	62.78 147	71.78 144	64.72 158

LTVRE_ROB	44.17 16	47.06 174	50.15 177	43.44 168	51.39 155	58.42 148	42.90 194	43.51 113	22.27 208	14.85 192	41.94 168	34.57 199	45.43 118	62.28 152	62.77 148	62.56 180	68.83 132
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
EPNet_dtu		52.05 139	58.26 123	44.81 162	54.10 136	50.09 181	52.01 159	40.82 142	53.03 82	27.41 163	54.90 80	57.96 96	26.72 185	62.97 146	62.70 149	67.78 161	66.19 147
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v148		55.58 116	57.61 131	53.20 103	54.59 133	61.86 117	61.18 105	38.70 159	44.30 146	42.25 97	47.53 117	50.24 127	48.73 100	65.15 140	62.61 150	73.79 114	71.61 109

TDRefinement		49.31 155	52.44 161	45.67 158	30.44 205	59.42 139	59.24 116	39.78 152	48.76 112	31.20 145	35.73 180	29.90 205	42.81 134	64.24 144	62.59 151	70.55 151	66.43 142

CP-MVSNet		48.37 163	53.53 152	42.34 173	51.35 156	58.01 155	46.56 179	50.54 54	41.62 168	10.61 198	46.53 127	40.68 185	23.18 190	58.71 168	61.83 152	71.81 143	67.36 139

PS-CasMVS		48.18 165	53.25 156	42.27 174	51.26 157	57.94 156	46.51 180	50.52 55	41.30 169	10.56 199	45.35 141	40.34 187	23.04 191	58.66 169	61.79 153	71.74 145	67.38 138

IterMVS-SCA-FT		52.18 138	57.75 129	45.68 157	51.01 161	62.06 116	55.10 147	34.75 176	44.85 140	32.86 138	51.13 100	51.22 119	48.74 99	62.47 150	61.51 154	51.61 202	71.02 112

WR-MVS_H		47.65 169	53.67 151	40.63 180	51.45 154	59.74 138	44.71 190	49.37 60	40.69 173	7.61 208	46.04 132	44.34 174	17.32 197	57.79 174	61.18 155	73.30 124	65.86 150

USDC		51.11 145	53.71 150	48.08 145	44.76 184	55.99 163	53.01 158	40.90 140	52.49 86	36.14 128	44.67 145	33.66 201	43.27 131	63.23 145	61.10 156	70.39 153	64.82 157

SixPastTwentyTwo		47.55 171	50.25 176	44.41 165	47.30 177	54.31 167	47.81 173	40.36 149	33.76 195	19.93 183	43.75 151	32.77 203	42.07 136	59.82 161	60.94 157	68.98 155	66.37 144

IterMVS		53.45 130	57.12 133	49.17 128	49.23 169	60.93 129	59.05 118	34.63 178	44.53 142	33.22 134	51.09 101	51.01 122	48.38 103	62.43 151	60.79 158	70.54 152	69.05 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
baseline		55.19 121	60.88 90	48.55 138	49.87 167	58.10 154	58.70 119	34.75 176	52.82 85	39.48 116	60.18 58	60.86 79	45.41 119	61.05 156	60.74 159	63.10 176	72.41 106

CR-MVSNet		50.47 148	52.61 159	47.98 146	49.03 171	52.94 170	48.27 170	38.86 156	44.41 143	39.59 113	44.34 146	44.65 171	46.63 113	58.97 165	60.31 160	65.48 168	62.66 166

PatchT		48.08 166	51.03 171	44.64 163	42.96 189	50.12 180	40.36 198	35.09 174	43.17 154	39.59 113	42.00 167	39.96 188	46.63 113	58.97 165	60.31 160	63.21 175	62.66 166

CMPMVS	37.70 17	49.24 157	52.71 158	45.19 159	45.97 182	51.23 177	47.44 176	29.31 194	43.04 155	44.69 84	34.45 185	48.35 130	43.64 126	62.59 148	59.82 162	60.08 184	69.48 126
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchMatch-RL		50.11 153	51.56 167	48.43 139	46.23 181	51.94 174	50.21 164	38.62 160	46.62 130	37.51 123	42.43 166	39.38 189	52.24 85	60.98 157	59.56 163	65.76 167	60.01 179

TinyColmap		47.08 172	47.56 186	46.52 153	42.35 191	53.44 169	51.77 160	40.70 143	43.44 153	31.92 142	29.78 194	23.72 210	45.04 122	61.99 153	59.54 164	67.35 162	61.03 173

PMMVS		49.20 159	54.28 149	43.28 170	34.13 200	45.70 196	48.98 168	26.09 202	46.31 132	34.92 133	55.22 79	53.47 111	47.48 110	59.43 162	59.04 165	68.05 160	60.77 174

pmmvs5		47.07 173	51.02 172	42.46 172	45.18 183	51.47 176	48.23 172	33.09 188	38.17 188	28.62 159	46.60 124	43.48 176	30.74 176	58.28 171	58.63 166	68.92 156	60.48 175

CostFormer		56.57 108	59.13 115	53.60 99	57.52 105	61.12 125	66.94 70	35.95 172	53.44 76	44.68 85	55.87 77	54.44 108	48.21 104	60.37 160	58.33 167	68.27 159	70.33 118

ambc			45.54 192		50.66 165	52.63 173	40.99 197		38.36 186	24.67 173	22.62 204	13.94 213	29.14 181	65.71 135	58.06 168	58.60 188	67.43 137

TAMVS		44.02 183	49.18 180	37.99 188	47.03 178	45.97 195	45.04 187	28.47 197	39.11 182	20.23 182	43.22 159	48.52 129	28.49 183	58.15 172	57.95 169	58.71 186	51.36 192

SCA		50.99 147	53.22 157	48.40 140	51.07 159	56.78 161	50.25 163	39.05 153	48.31 118	41.38 101	49.54 104	46.70 149	46.00 116	58.31 170	56.28 170	62.65 178	56.60 186

dps		50.42 149	51.20 170	49.51 124	55.88 122	56.07 162	53.73 152	38.89 155	43.66 149	40.36 109	45.66 136	37.63 196	45.23 120	59.05 163	56.18 171	62.94 177	60.16 177

MDA-MVSNet-bldmvs		41.36 188	43.15 197	39.27 184	28.74 207	52.68 172	44.95 189	40.84 141	32.89 197	18.13 187	31.61 189	22.09 211	38.97 149	50.45 199	56.11 172	64.01 173	56.23 187

MIMVSNet		43.79 184	48.53 182	38.27 186	41.46 193	48.97 184	50.81 162	32.88 190	44.55 141	22.07 177	32.05 187	47.15 142	24.76 188	58.73 167	56.09 173	57.63 191	52.14 190

test-mter		45.30 179	50.37 173	39.38 183	33.65 202	46.99 191	47.59 174	18.59 208	38.75 183	28.00 160	43.28 158	46.82 148	41.50 139	57.28 176	55.78 174	66.93 166	63.70 163

CVMVSNet		46.38 177	52.01 165	39.81 182	42.40 190	50.26 179	46.15 181	37.68 165	40.03 177	15.09 191	46.56 125	47.56 138	33.72 172	56.50 182	55.65 175	63.80 174	67.53 136

MDTV_nov1_ep13_2view		47.62 170	49.72 179	45.18 160	48.05 173	53.70 168	54.90 148	33.80 184	39.90 178	29.79 152	38.85 174	41.89 179	39.17 146	58.99 164	55.55 176	65.34 170	59.17 180

test-LLR		49.28 156	50.29 174	48.10 144	55.26 126	47.16 189	49.52 165	43.48 116	39.22 180	31.98 140	43.65 153	47.93 133	41.29 140	56.80 178	55.36 177	67.08 164	61.94 170

TESTMET0.1,1		46.09 178	50.29 174	41.18 178	36.91 198	47.16 189	49.52 165	20.32 207	39.22 180	31.98 140	43.65 153	47.93 133	41.29 140	56.80 178	55.36 177	67.08 164	61.94 170

MDTV_nov1_ep13		50.32 151	52.43 162	47.86 148	49.87 167	54.70 164	58.10 121	34.29 180	45.59 138	37.71 122	47.44 118	47.42 140	41.86 137	58.07 173	55.21 179	65.34 170	58.56 182

FMVSNet5		40.96 189	45.81 190	35.29 194	34.30 199	44.55 199	47.28 177	28.84 196	40.76 172	21.62 178	29.85 193	42.44 177	24.77 187	57.53 175	55.00 180	54.93 194	50.56 195

FC-MVSNet-test		39.65 194	48.35 183	29.49 199	44.43 185	39.28 205	30.23 208	40.44 147	43.59 150	3.12 214	53.00 88	42.03 178	10.02 210	55.09 189	54.77 181	48.66 203	50.71 194

test20.03		40.38 193	44.20 194	35.92 192	53.73 139	49.05 182	38.54 200	43.49 115	32.55 198	9.54 202	27.88 198	39.12 190	12.24 203	56.28 183	54.69 182	57.96 190	49.83 199

Anonymous20231206		42.28 186	45.89 189	38.07 187	51.96 151	48.98 183	43.66 193	38.81 158	38.74 184	14.32 193	26.74 199	40.90 182	20.94 193	56.64 181	54.67 183	58.71 186	54.59 188

CHOSEN 280x420		40.80 190	45.05 193	35.84 193	32.95 203	29.57 208	44.98 188	23.71 205	37.54 190	18.42 186	31.36 190	47.07 143	46.41 115	56.71 180	54.65 184	48.55 204	58.47 183

test0.0.03 1		43.15 185	46.95 187	38.72 185	55.26 126	50.56 178	42.48 195	43.48 116	38.16 189	15.11 190	35.07 182	44.69 170	16.47 198	55.95 186	54.34 185	59.54 185	49.87 198

tpm cat1		53.30 131	53.41 153	53.17 105	58.16 98	59.15 143	63.73 97	38.27 162	50.73 93	46.98 72	45.57 138	44.00 175	49.20 97	55.90 187	54.02 186	62.65 178	64.50 160

RPMNet		46.41 175	48.72 181	43.72 166	47.77 175	52.94 170	46.02 183	33.92 182	44.41 143	31.82 143	36.89 177	37.42 197	37.41 156	53.88 193	54.02 186	65.37 169	61.47 172

MIMVSNet1		35.51 198	41.41 198	28.63 200	27.53 209	43.36 200	38.09 201	33.82 183	32.01 199	6.77 209	21.63 205	35.43 198	11.97 205	55.05 190	53.99 188	53.59 199	48.36 201

PatchmatchNet		49.92 154	51.29 168	48.32 142	51.83 153	51.86 175	53.38 157	37.63 166	47.90 121	40.83 106	48.54 110	45.30 160	45.19 121	56.86 177	53.99 188	61.08 183	54.57 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		44.55 182	48.13 184	40.37 181	32.85 204	46.82 193	46.11 182	29.28 195	40.48 174	29.99 151	39.98 172	34.39 200	41.80 138	56.08 185	53.88 190	62.19 181	65.31 153

testgi		38.71 195	43.64 195	32.95 196	52.30 150	48.63 185	35.59 205	35.05 175	31.58 202	9.03 205	30.29 191	40.75 184	11.19 208	55.30 188	53.47 191	54.53 197	45.48 202

RPSCF		46.41 175	54.42 147	37.06 190	25.70 212	45.14 197	45.39 186	20.81 206	62.79 59	35.10 130	44.92 143	55.60 106	43.56 127	56.12 184	52.45 192	51.80 201	63.91 162

pmmvs3		35.10 199	38.47 201	31.17 198	26.37 211	40.47 202	34.51 206	18.09 209	24.75 206	16.88 189	23.05 203	26.69 207	32.69 174	50.73 198	51.60 193	58.46 189	51.98 191

GG-mvs-BLEND		36.62 197	53.39 154	17.06 206	0.01 217	58.61 146	48.63 169	0.01 214	47.13 126	0.02 218	43.98 148	60.64 82	0.03 213	54.92 191	51.47 194	53.64 198	56.99 185

tpm		48.82 161	51.27 169	45.96 155	54.10 136	47.35 188	56.05 135	30.23 193	46.70 128	43.21 91	52.54 92	47.55 139	37.28 158	54.11 192	50.50 195	54.90 195	60.12 178

EU-MVSNet		40.63 192	45.65 191	34.78 195	39.11 196	46.94 192	40.02 199	34.03 181	33.50 196	10.37 200	35.57 181	37.80 195	23.65 189	51.90 194	50.21 196	61.49 182	63.62 164

tpmrst		48.08 166	49.88 178	45.98 154	52.71 144	48.11 186	53.62 155	33.70 185	48.70 114	39.74 111	48.96 108	46.23 153	40.29 144	50.14 200	49.28 197	55.80 192	57.71 184

Gipuma		25.87 203	26.91 206	24.66 203	28.98 206	20.17 211	20.46 210	34.62 179	29.55 203	9.10 203	4.91 213	5.31 217	15.76 200	49.37 203	49.10 198	39.03 207	29.95 207
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EPMVS		44.66 181	47.86 185	40.92 179	47.97 174	44.70 198	47.58 175	33.27 187	48.11 120	29.58 154	49.65 103	44.38 173	34.65 167	51.71 195	47.90 199	52.49 200	48.57 200

PMVS	27.84 18	33.81 200	35.28 204	32.09 197	34.13 200	24.81 210	32.51 207	26.48 201	26.41 205	19.37 184	23.76 202	24.02 209	25.18 186	50.78 196	47.24 200	54.89 196	49.95 197
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		42.24 187	41.15 199	43.51 167	44.06 188	40.74 201	35.77 204	35.35 173	35.38 193	38.34 118	25.63 201	38.55 193	43.48 128	50.77 197	47.03 201	64.07 172	49.98 196

FPMVS		38.36 196	40.41 200	35.97 191	38.92 197	39.85 203	45.50 185	25.79 203	41.13 170	18.70 185	30.10 192	24.56 208	31.86 175	49.42 202	46.80 202	55.04 193	51.03 193

ADS-MVSNet		40.67 191	43.38 196	37.50 189	44.36 186	39.79 204	42.09 196	32.67 191	44.34 145	28.87 158	40.76 171	40.37 186	30.22 177	48.34 204	45.87 203	46.81 205	44.21 204

N_pmnet		32.67 202	36.85 203	27.79 202	40.55 194	32.13 207	35.80 203	26.79 200	37.24 191	9.10 203	32.02 188	30.94 204	16.30 199	47.22 205	41.21 204	38.21 208	37.21 205

new-patchmatchnet		33.24 201	37.20 202	28.62 201	44.32 187	38.26 206	29.68 209	36.05 171	31.97 200	6.33 210	26.59 200	27.33 206	11.12 209	50.08 201	41.05 205	44.23 206	45.15 203

new_pmnet		23.19 204	28.17 205	17.37 204	17.03 213	24.92 209	19.66 211	16.16 211	27.05 204	4.42 211	20.77 206	19.20 212	12.19 204	37.71 206	36.38 206	34.77 209	31.17 206

MVE	12.28 19	13.53 208	15.72 208	10.96 209	7.39 215	15.71 213	6.05 215	23.73 204	10.29 214	3.01 215	5.77 212	3.41 218	11.91 206	20.11 208	29.79 207	13.67 213	24.98 208
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		15.84 205	19.68 207	11.35 208	15.74 214	16.95 212	13.31 212	17.64 210	16.08 210	0.36 217	13.12 207	11.47 214	1.69 212	28.82 207	27.24 208	19.38 212	24.09 209

E-PMN		15.09 206	13.19 209	17.30 205	27.80 208	12.62 214	7.81 214	27.54 198	14.62 212	3.19 212	6.89 210	2.52 220	15.09 201	15.93 209	20.22 209	22.38 210	19.53 210

EMVS		14.49 207	12.45 210	16.87 207	27.02 210	12.56 215	8.13 213	27.19 199	15.05 211	3.14 213	6.69 211	2.67 219	15.08 202	14.60 211	18.05 210	20.67 211	17.56 212

tmp_tt				5.40 210	3.97 216	2.35 217	3.26 217	0.44 213	17.56 209	12.09 195	11.48 209	7.14 215	1.98 211	15.68 210	15.49 211	10.69 214

testmvs		0.01 209	0.02 211	0.00 211	0.00 218	0.00 218	0.01 219	0.00 215	0.01 215	0.00 219	0.03 215	0.00 221	0.01 214	0.01 213	0.01 212	0.00 216	0.06 214

test123		0.01 209	0.02 211	0.00 211	0.00 218	0.00 218	0.00 220	0.00 215	0.01 215	0.00 219	0.04 214	0.00 221	0.01 214	0.00 214	0.01 212	0.00 216	0.07 213

uanet_test		0.00 211	0.00 213	0.00 211	0.00 218	0.00 218	0.00 220	0.00 215	0.00 217	0.00 219	0.00 216	0.00 221	0.00 216	0.00 214	0.00 214	0.00 216	0.00 215

sosnet-low-res		0.00 211	0.00 213	0.00 211	0.00 218	0.00 218	0.00 220	0.00 215	0.00 217	0.00 219	0.00 216	0.00 221	0.00 216	0.00 214	0.00 214	0.00 216	0.00 215

sosnet		0.00 211	0.00 213	0.00 211	0.00 218	0.00 218	0.00 220	0.00 215	0.00 217	0.00 219	0.00 216	0.00 221	0.00 216	0.00 214	0.00 214	0.00 216	0.00 215

RE-MVS-def										33.01 135

9.14												81.81 12

SR-MVS					71.46 34			54.67 29				81.54 13

our_test_3					51.15 158	57.31 159	55.12 146

MTAPA										65.14 3		80.20 19

MTMP										62.63 17		78.04 26

Patchmatch-RL test							1.04 218

XVS					70.49 38	76.96 26	74.36 45			54.48 49		74.47 38				82.24 24

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

abl_6				64.36 45	70.08 41	77.45 22	72.88 50	50.15 57	71.31 43	54.77 48	62.79 48	77.99 27	56.80 52			81.50 39	83.91 39

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 40

Patchmtry						47.61 187	48.27 170	38.86 156		39.59 113

DeepMVS_CX						6.95 216	5.98 216	2.25 212	11.73 213	2.07 216	11.85 208	5.43 216	11.75 207	11.40 212		8.10 215	18.38 211

High-resolution multi-view benchmark