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.

MCST-MVS		85.13 23	86.62 23	83.39 18	90.55 14	89.82 16	89.29 22	73.89 23	84.38 31	76.03 29	79.01 31	85.90 21	78.47 12	87.81 15	86.11 34	92.11 1	93.29 22

CSCG		85.28 22	87.68 18	82.49 25	89.95 24	91.99 4	88.82 25	71.20 38	86.41 22	79.63 17	79.26 29	88.36 9	73.94 39	86.64 32	86.67 25	91.40 2	94.41 7

xxxxxxxxxxxxxcwj		85.35 19	85.76 30	84.86 7	91.26 5	91.10 7	90.90 5	75.65 7	89.21 8	81.25 7	91.12 7	61.35 115	78.82 9	87.42 19	86.23 30	91.28 3	93.90 12

SF-MVS		87.47 7	89.70 7	84.86 7	91.26 5	91.10 7	90.90 5	75.65 7	89.21 8	81.25 7	91.12 7	88.93 6	78.82 9	87.42 19	86.23 30	91.28 3	93.90 12

SteuartSystems-ACMMP		85.99 15	88.31 15	83.27 21	90.73 10	89.84 14	90.27 14	74.31 15	84.56 30	75.88 30	87.32 14	85.04 24	77.31 24	89.01 6	88.46 3	91.14 5	93.96 11
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		88.00 5	90.50 5	85.08 4	90.95 7	91.58 6	92.03 1	75.53 12	91.15 4	80.10 15	92.27 4	88.34 10	80.80 4	88.00 13	86.99 18	91.09 6	95.16 5

DeepC-MVS	78.47 2	84.81 26	86.03 28	83.37 19	89.29 32	90.38 11	88.61 27	76.50 1	86.25 23	77.22 24	75.12 39	80.28 45	77.59 22	88.39 9	88.17 6	91.02 7	93.66 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SED-MVS		88.85 1	91.59 2	85.67 1	90.54 15	92.29 2	91.71 3	76.40 2	92.41 2	83.24 2	92.50 3	90.64 3	81.10 2	89.53 2	88.02 7	91.00 8	95.73 2

DPE-MVS		88.63 3	91.29 3	85.53 2	90.87 8	92.20 3	91.98 2	76.00 5	90.55 7	82.09 6	93.85 1	90.75 1	81.25 1	88.62 7	87.59 13	90.96 9	95.48 3

SMA-MVS		87.56 6	90.17 6	84.52 9	91.71 2	90.57 9	90.77 8	75.19 13	90.67 6	80.50 14	86.59 17	88.86 7	78.09 16	89.92 1	89.41 1	90.84 10	95.19 4
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
DVP-MVS		88.67 2	91.62 1	85.22 3	90.47 17	92.36 1	90.69 9	76.15 3	93.08 1	82.75 4	92.19 5	90.71 2	80.45 5	89.27 5	87.91 8	90.82 11	95.84 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
HFP-MVS		86.15 14	87.95 17	84.06 14	90.80 9	89.20 23	89.62 20	74.26 16	87.52 15	80.63 12	86.82 16	84.19 29	78.22 14	87.58 17	87.19 16	90.81 12	93.13 24

ACMMPR		85.52 17	87.53 19	83.17 22	90.13 20	89.27 20	89.30 21	73.97 21	86.89 20	77.14 25	86.09 18	83.18 32	77.74 20	87.42 19	87.20 15	90.77 13	92.63 25

ACMMP		83.42 31	85.27 32	81.26 31	88.47 37	88.49 34	88.31 31	72.09 33	83.42 35	72.77 41	82.65 24	78.22 49	75.18 33	86.24 38	85.76 36	90.74 14	92.13 31
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
PGM-MVS		84.42 28	86.29 27	82.23 26	90.04 22	88.82 27	89.23 23	71.74 36	82.82 37	74.61 33	84.41 23	82.09 35	77.03 28	87.13 25	86.73 24	90.73 15	92.06 32

DeepC-MVS_fast	78.24 3	84.27 29	85.50 31	82.85 23	90.46 18	89.24 21	87.83 33	74.24 17	84.88 26	76.23 28	75.26 38	81.05 43	77.62 21	88.02 12	87.62 12	90.69 16	92.41 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		86.96 9	89.45 8	84.05 15	90.13 20	89.23 22	89.77 18	74.59 14	89.17 10	80.70 11	89.93 11	89.67 4	78.47 12	87.57 18	86.79 22	90.67 17	93.76 16
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 + MP.		86.88 10	89.23 9	84.14 13	89.78 26	88.67 31	90.59 10	73.46 27	88.99 11	80.52 13	91.26 6	88.65 8	79.91 7	86.96 30	86.22 32	90.59 18	93.83 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MVS_0304		81.73 39	83.86 36	79.26 42	86.22 50	89.18 24	86.41 38	67.15 63	75.28 55	70.75 53	74.59 41	83.49 31	74.42 36	87.05 28	86.34 29	90.58 19	91.08 40

APD-MVS		86.84 11	88.91 13	84.41 10	90.66 11	90.10 12	90.78 7	75.64 9	87.38 17	78.72 19	90.68 10	86.82 16	80.15 6	87.13 25	86.45 28	90.51 20	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		84.74 27	86.43 26	82.77 24	89.48 30	88.13 39	88.64 26	73.93 22	84.92 25	76.77 26	81.94 26	83.50 30	77.29 26	86.92 31	86.49 27	90.49 21	93.14 23

XVS					86.63 46	88.68 28	85.00 47			71.81 46		81.92 37				90.47 22

X-MVStestdata					86.63 46	88.68 28	85.00 47			71.81 46		81.92 37				90.47 22

X-MVS		83.23 33	85.20 33	80.92 34	89.71 27	88.68 28	88.21 32	73.60 24	82.57 38	71.81 46	77.07 33	81.92 37	71.72 58	86.98 29	86.86 20	90.47 22	92.36 29

NCCC		85.34 20	86.59 24	83.88 16	91.48 3	88.88 25	89.79 17	75.54 11	86.67 21	77.94 23	76.55 35	84.99 25	78.07 17	88.04 11	87.68 11	90.46 25	93.31 21

CNVR-MVS		86.36 13	88.19 16	84.23 12	91.33 4	89.84 14	90.34 11	75.56 10	87.36 18	78.97 18	81.19 28	86.76 17	78.74 11	89.30 4	88.58 2	90.45 26	94.33 9

MP-MVS		85.50 18	87.40 20	83.28 20	90.65 12	89.51 19	89.16 24	74.11 19	83.70 34	78.06 22	85.54 20	84.89 27	77.31 24	87.40 22	87.14 17	90.41 27	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	75.73 4	82.40 35	82.76 40	81.97 29	88.02 38	89.67 17	86.60 37	71.48 37	81.28 43	78.18 21	64.78 83	77.96 51	77.13 27	87.32 23	86.83 21	90.41 27	91.48 36

ACMMP_NAP		86.52 12	89.01 10	83.62 17	90.28 19	90.09 13	90.32 13	74.05 20	88.32 14	79.74 16	87.04 15	85.59 23	76.97 29	89.35 3	88.44 4	90.35 29	94.27 10

zzz-MVS		85.71 16	86.88 22	84.34 11	90.54 15	87.11 44	89.77 18	74.17 18	88.54 13	83.08 3	78.60 32	86.10 19	78.11 15	87.80 16	87.46 14	90.35 29	92.56 26

CS-MVS		76.92 62	78.01 62	75.64 60	81.47 73	83.59 71	80.68 64	62.47 111	68.39 73	65.83 68	67.84 72	70.74 76	73.07 45	85.31 45	82.79 56	90.33 31	87.42 65

CDPH-MVS		82.64 34	85.03 34	79.86 39	89.41 31	88.31 36	88.32 30	71.84 35	80.11 45	67.47 62	82.09 25	81.44 41	71.85 56	85.89 40	86.15 33	90.24 32	91.25 38

LGP-MVS_train		79.83 44	81.22 47	78.22 50	86.28 49	85.36 58	86.76 36	69.59 47	77.34 50	65.14 71	75.68 37	70.79 75	71.37 62	84.60 48	84.01 47	90.18 33	90.74 42

HPM-MVS++		87.09 8	88.92 12	84.95 5	92.61 1	87.91 40	90.23 15	76.06 4	88.85 12	81.20 10	87.33 13	87.93 11	79.47 8	88.59 8	88.23 5	90.15 34	93.60 20

3Dnovator	73.76 5	79.75 46	80.52 51	78.84 45	84.94 60	87.35 41	84.43 52	65.54 74	78.29 49	73.97 35	63.00 91	75.62 57	74.07 38	85.00 47	85.34 40	90.11 35	89.04 53

DPM-MVS		83.30 32	84.33 35	82.11 27	89.56 28	88.49 34	90.33 12	73.24 28	83.85 33	76.46 27	72.43 48	82.65 33	73.02 47	86.37 36	86.91 19	90.03 36	89.62 51

ETV-MVS		77.32 60	78.81 58	75.58 61	82.24 70	83.64 70	79.98 68	64.02 86	69.64 71	63.90 76	70.89 56	69.94 82	73.41 42	85.39 44	83.91 49	89.92 37	88.31 58

ACMP	73.23 7	79.79 45	80.53 50	78.94 44	85.61 53	85.68 53	85.61 43	69.59 47	77.33 51	71.00 52	74.45 42	69.16 88	71.88 54	83.15 61	83.37 53	89.92 37	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
train_agg		84.86 25	87.21 21	82.11 27	90.59 13	85.47 55	89.81 16	73.55 26	83.95 32	73.30 38	89.84 12	87.23 14	75.61 32	86.47 34	85.46 39	89.78 39	92.06 32

TSAR-MVS + GP.		83.69 30	86.58 25	80.32 36	85.14 55	86.96 45	84.91 50	70.25 42	84.71 29	73.91 36	85.16 21	85.63 22	77.92 18	85.44 41	85.71 37	89.77 40	92.45 27

ACMM	72.26 8	78.86 55	78.13 61	79.71 40	86.89 45	83.40 73	86.02 40	70.50 40	75.28 55	71.49 50	63.01 90	69.26 87	73.57 41	84.11 52	83.98 48	89.76 41	87.84 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		79.68 48	79.28 57	80.15 38	87.99 39	86.77 47	88.52 29	72.72 30	64.55 92	67.65 61	67.87 71	74.33 61	74.31 37	86.37 36	85.25 41	89.73 42	89.81 49

MSP-MVS		88.09 4	90.84 4	84.88 6	90.00 23	91.80 5	91.63 4	75.80 6	91.99 3	81.23 9	92.54 2	89.18 5	80.89 3	87.99 14	87.91 8	89.70 43	94.51 6
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
CANet		81.62 40	83.41 37	79.53 41	87.06 43	88.59 32	85.47 45	67.96 59	76.59 53	74.05 34	74.69 40	81.98 36	72.98 48	86.14 39	85.47 38	89.68 44	90.42 46

abl_6				79.05 43	87.27 42	88.85 26	83.62 56	68.25 55	81.68 41	72.94 40	73.79 45	84.45 28	72.55 50			89.66 45	90.64 43

MVS_111021_HR		80.13 43	81.46 45	78.58 47	85.77 52	85.17 59	83.45 57	69.28 50	74.08 61	70.31 54	74.31 43	75.26 58	73.13 44	86.46 35	85.15 42	89.53 46	89.81 49

IS_MVSNet		73.33 79	77.34 71	68.65 109	81.29 74	83.47 72	74.45 118	63.58 89	65.75 84	48.49 145	67.11 76	70.61 77	54.63 161	84.51 49	83.58 52	89.48 47	86.34 75

DELS-MVS		79.15 53	81.07 48	76.91 55	83.54 62	87.31 42	84.45 51	64.92 79	69.98 67	69.34 55	71.62 52	76.26 54	69.84 67	86.57 33	85.90 35	89.39 48	89.88 48
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
UniMVSNet_NR-MVSNet		70.59 98	72.19 97	68.72 107	77.72 104	80.72 96	73.81 133	69.65 46	61.99 112	43.23 170	60.54 98	57.50 132	58.57 131	79.56 107	81.07 70	89.34 49	83.97 102

EIA-MVS		75.64 69	76.60 76	74.53 71	82.43 68	83.84 66	78.32 87	62.28 115	65.96 82	63.28 79	68.95 63	67.54 97	71.61 60	82.55 66	81.63 64	89.24 50	85.72 79

PHI-MVS		82.36 36	85.89 29	78.24 49	86.40 48	89.52 18	85.52 44	69.52 49	82.38 40	65.67 69	81.35 27	82.36 34	73.07 45	87.31 24	86.76 23	89.24 50	91.56 35

canonicalmvs		79.16 52	82.37 43	75.41 62	82.33 69	86.38 51	80.80 63	63.18 92	82.90 36	67.34 63	72.79 47	76.07 55	69.62 68	83.46 60	84.41 46	89.20 52	90.60 44

MSLP-MVS++		82.09 37	82.66 41	81.42 30	87.03 44	87.22 43	85.82 42	70.04 43	80.30 44	78.66 20	68.67 67	81.04 44	77.81 19	85.19 46	84.88 44	89.19 53	91.31 37

HQP-MVS		81.19 41	83.27 38	78.76 46	87.40 41	85.45 56	86.95 35	70.47 41	81.31 42	66.91 65	79.24 30	76.63 53	71.67 59	84.43 50	83.78 50	89.19 53	92.05 34

EPP-MVSNet		74.00 77	77.41 69	70.02 95	80.53 82	83.91 65	74.99 114	62.68 106	65.06 87	49.77 141	68.68 66	72.09 69	63.06 103	82.49 68	80.73 75	89.12 55	88.91 54

NR-MVSNet		68.79 119	70.56 107	66.71 138	77.48 107	79.54 105	73.52 137	69.20 51	61.20 120	39.76 177	58.52 109	50.11 183	51.37 170	80.26 99	80.71 80	88.97 56	83.59 108

PVSNet_Blended_VisFu		76.57 64	77.90 63	75.02 65	80.56 81	86.58 49	79.24 77	66.18 68	64.81 89	68.18 59	65.61 77	71.45 70	67.05 78	84.16 51	81.80 62	88.90 57	90.92 41

TranMVSNet+NR-MVSNet		69.25 114	70.81 106	67.43 122	77.23 109	79.46 107	73.48 138	69.66 45	60.43 126	39.56 178	58.82 108	53.48 159	55.74 155	79.59 105	81.21 68	88.89 58	82.70 112

QAPM		78.47 56	80.22 54	76.43 57	85.03 57	86.75 48	80.62 66	66.00 71	73.77 62	65.35 70	65.54 79	78.02 50	72.69 49	83.71 55	83.36 54	88.87 59	90.41 47

casdiffmvs		76.76 63	78.46 60	74.77 68	80.32 84	83.73 69	80.65 65	63.24 91	73.58 63	66.11 67	69.39 62	74.09 62	69.49 70	82.52 67	79.35 103	88.84 60	86.52 73

CPTT-MVS		81.77 38	83.10 39	80.21 37	85.93 51	86.45 50	87.72 34	70.98 39	82.54 39	71.53 49	74.23 44	81.49 40	76.31 31	82.85 64	81.87 61	88.79 61	92.26 30

Effi-MVS+		75.28 71	76.20 77	74.20 73	81.15 75	83.24 74	81.11 61	63.13 94	66.37 78	60.27 85	64.30 87	68.88 92	70.93 65	81.56 73	81.69 63	88.61 62	87.35 66

UniMVSNet (Re)		69.53 110	71.90 100	66.76 136	76.42 113	80.93 92	72.59 143	68.03 58	61.75 115	41.68 175	58.34 115	57.23 134	53.27 166	79.53 108	80.62 84	88.57 63	84.90 94

PCF-MVS	73.28 6	79.42 49	80.41 52	78.26 48	84.88 61	88.17 37	86.08 39	69.85 44	75.23 57	68.43 57	68.03 70	78.38 48	71.76 57	81.26 82	80.65 83	88.56 64	91.18 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_part1		74.24 75	73.44 87	75.18 64	82.02 72	82.34 81	83.88 54	62.40 113	60.93 122	68.68 56	49.25 174	69.71 84	65.73 93	81.26 82	81.98 60	88.35 65	88.60 57

MAR-MVS		79.21 51	80.32 53	77.92 51	87.46 40	88.15 38	83.95 53	67.48 62	74.28 59	68.25 58	64.70 84	77.04 52	72.17 52	85.42 42	85.00 43	88.22 66	87.62 64
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
Fast-Effi-MVS+		73.11 81	73.66 85	72.48 78	77.72 104	80.88 95	78.55 84	58.83 152	65.19 86	60.36 84	59.98 102	62.42 113	71.22 63	81.66 70	80.61 85	88.20 67	84.88 95

ET-MVSNet_ETH3D		72.46 85	74.19 83	70.44 90	62.50 193	81.17 90	79.90 71	62.46 112	64.52 93	57.52 98	71.49 54	59.15 125	72.08 53	78.61 119	81.11 69	88.16 68	83.29 110

OMC-MVS		80.26 42	82.59 42	77.54 52	83.04 63	85.54 54	83.25 58	65.05 78	87.32 19	72.42 42	72.04 50	78.97 47	73.30 43	83.86 53	81.60 65	88.15 69	88.83 55

AdaColmap		79.74 47	78.62 59	81.05 33	89.23 33	86.06 52	84.95 49	71.96 34	79.39 48	75.51 31	63.16 89	68.84 93	76.51 30	83.55 57	82.85 55	88.13 70	86.46 74

OpenMVS	70.44 10	76.15 67	76.82 75	75.37 63	85.01 58	84.79 61	78.99 81	62.07 116	71.27 66	67.88 60	57.91 117	72.36 68	70.15 66	82.23 69	81.41 66	88.12 71	87.78 63

UA-Net		74.47 74	77.80 64	70.59 89	85.33 54	85.40 57	73.54 136	65.98 72	60.65 124	56.00 106	72.11 49	79.15 46	54.63 161	83.13 62	82.25 58	88.04 72	81.92 122

DU-MVS		69.63 109	70.91 105	68.13 113	75.99 115	79.54 105	73.81 133	69.20 51	61.20 120	43.23 170	58.52 109	53.50 157	58.57 131	79.22 111	80.45 86	87.97 73	83.97 102

FC-MVSNet-train		72.60 84	75.07 81	69.71 98	81.10 77	78.79 115	73.74 135	65.23 77	66.10 81	53.34 121	70.36 58	63.40 110	56.92 146	81.44 75	80.96 72	87.93 74	84.46 100

IB-MVS	66.94 12	71.21 94	71.66 102	70.68 86	79.18 92	82.83 78	72.61 142	61.77 120	59.66 129	63.44 78	53.26 146	59.65 123	59.16 130	76.78 139	82.11 59	87.90 75	87.33 67
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
PVSNet_BlendedMVS		76.21 65	77.52 67	74.69 69	79.46 90	83.79 67	77.50 94	64.34 84	69.88 68	71.88 44	68.54 68	70.42 78	67.05 78	83.48 58	79.63 95	87.89 76	86.87 70

PVSNet_Blended		76.21 65	77.52 67	74.69 69	79.46 90	83.79 67	77.50 94	64.34 84	69.88 68	71.88 44	68.54 68	70.42 78	67.05 78	83.48 58	79.63 95	87.89 76	86.87 70

DeepPCF-MVS	79.04 1	85.30 21	88.93 11	81.06 32	88.77 36	90.48 10	85.46 46	73.08 29	90.97 5	73.77 37	84.81 22	85.95 20	77.43 23	88.22 10	87.73 10	87.85 78	94.34 8

thisisatest0530		71.48 91	73.01 91	69.70 99	73.83 139	78.62 117	74.53 117	59.12 146	64.13 95	58.63 91	64.60 85	58.63 127	64.27 96	80.28 98	80.17 91	87.82 79	84.64 98

TAPA-MVS	71.42 9	77.69 59	80.05 55	74.94 66	80.68 80	84.52 62	81.36 60	63.14 93	84.77 27	64.82 73	68.72 65	75.91 56	71.86 55	81.62 71	79.55 99	87.80 80	85.24 88
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tttt0517		71.41 92	72.95 92	69.60 100	73.70 141	78.70 116	74.42 121	59.12 146	63.89 99	58.35 94	64.56 86	58.39 129	64.27 96	80.29 97	80.17 91	87.74 81	84.69 97

MVS_Test		75.37 70	77.13 73	73.31 76	79.07 93	81.32 88	79.98 68	60.12 137	69.72 70	64.11 75	70.53 57	73.22 64	68.90 72	80.14 101	79.48 101	87.67 82	85.50 83

DI_MVS_plusplus_trai		75.13 72	76.12 78	73.96 74	78.18 98	81.55 84	80.97 62	62.54 108	68.59 72	65.13 72	61.43 93	74.81 59	69.32 71	81.01 88	79.59 97	87.64 83	85.89 77

MVSTER		72.06 86	74.24 82	69.51 101	70.39 169	75.97 145	76.91 100	57.36 159	64.64 91	61.39 83	68.86 64	63.76 108	63.46 100	81.44 75	79.70 94	87.56 84	85.31 87

TSAR-MVS + ACMM		85.10 24	88.81 14	80.77 35	89.55 29	88.53 33	88.59 28	72.55 31	87.39 16	71.90 43	90.95 9	87.55 12	74.57 34	87.08 27	86.54 26	87.47 85	93.67 17

CLD-MVS		79.35 50	81.23 46	77.16 54	85.01 58	86.92 46	85.87 41	60.89 126	80.07 47	75.35 32	72.96 46	73.21 65	68.43 76	85.41 43	84.63 45	87.41 86	85.44 85
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Effi-MVS+-dtu		71.82 88	71.86 101	71.78 80	78.77 94	80.47 98	78.55 84	61.67 123	60.68 123	55.49 107	58.48 111	65.48 103	68.85 73	76.92 136	75.55 148	87.35 87	85.46 84

WR-MVS		63.03 159	67.40 144	57.92 178	75.14 124	77.60 132	60.56 191	66.10 69	54.11 168	23.88 200	53.94 140	53.58 155	34.50 196	73.93 155	77.71 121	87.35 87	80.94 129

v144192		69.34 113	68.68 131	70.12 93	74.06 135	80.54 97	78.08 90	60.54 130	54.99 161	54.13 114	52.92 153	52.80 168	66.73 85	77.13 134	76.72 137	87.15 89	85.63 80

EPNet		79.08 54	80.62 49	77.28 53	88.90 35	83.17 76	83.65 55	72.41 32	74.41 58	67.15 64	76.78 34	74.37 60	64.43 95	83.70 56	83.69 51	87.15 89	88.19 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		67.24 140	66.94 147	67.60 120	78.73 95	81.35 87	73.28 140	59.49 142	46.89 193	51.42 133	43.65 186	53.49 158	55.50 158	81.38 77	80.66 82	87.15 89	81.17 128

v1144		69.93 107	69.36 121	70.61 88	74.89 127	80.93 92	79.11 79	60.64 128	55.97 153	55.31 109	53.85 141	54.14 150	66.54 87	78.10 124	77.44 127	87.14 92	85.09 90

anonymousdsp		65.28 149	67.98 138	62.13 159	58.73 201	73.98 159	67.10 165	50.69 185	48.41 189	47.66 153	54.27 135	52.75 169	61.45 121	76.71 140	80.20 89	87.13 93	89.53 52

PLC	68.99 11	75.68 68	75.31 80	76.12 59	82.94 64	81.26 89	79.94 70	66.10 69	77.15 52	66.86 66	59.13 107	68.53 94	73.73 40	80.38 95	79.04 104	87.13 93	81.68 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v10		70.22 103	69.76 116	70.74 84	74.79 128	80.30 102	79.22 78	59.81 140	57.71 140	56.58 104	54.22 139	55.31 143	66.95 81	78.28 122	77.47 126	87.12 95	85.07 91

v1192		69.50 111	68.83 127	70.29 92	74.49 131	80.92 94	78.55 84	60.54 130	55.04 159	54.21 112	52.79 155	52.33 170	66.92 82	77.88 126	77.35 130	87.04 96	85.51 82

v1921920		69.03 116	68.32 135	69.86 96	74.03 136	80.37 99	77.55 92	60.25 134	54.62 163	53.59 120	52.36 159	51.50 176	66.75 84	77.17 133	76.69 139	86.96 97	85.56 81

v2v482		70.05 106	69.46 120	70.74 84	74.62 130	80.32 101	79.00 80	60.62 129	57.41 142	56.89 101	55.43 130	55.14 145	66.39 89	77.25 132	77.14 132	86.90 98	83.57 109

Vis-MVSNet		72.77 83	77.20 72	67.59 121	74.19 134	84.01 64	76.61 104	61.69 121	60.62 125	50.61 137	70.25 59	71.31 73	55.57 157	83.85 54	82.28 57	86.90 98	88.08 60
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PEN-MVS		62.96 160	65.77 154	59.70 171	73.98 137	75.45 149	63.39 184	67.61 61	52.49 174	25.49 199	53.39 143	49.12 186	40.85 189	71.94 167	77.26 131	86.86 100	80.72 131

v8		70.23 102	69.86 114	70.67 87	74.69 129	79.82 104	78.79 82	59.18 145	58.80 133	58.20 95	55.00 131	57.33 133	66.31 90	77.51 129	76.71 138	86.82 101	83.88 105

ACMH+	66.54 13	71.36 93	70.09 111	72.85 77	82.59 66	81.13 91	78.56 83	68.04 57	61.55 116	52.52 128	51.50 163	54.14 150	68.56 75	78.85 116	79.50 100	86.82 101	83.94 104

v1240		68.64 121	67.89 140	69.51 101	73.89 138	80.26 103	76.73 102	59.97 139	53.43 171	53.08 123	51.82 162	50.84 179	66.62 86	76.79 138	76.77 136	86.78 103	85.34 86

DCV-MVSNet		73.65 78	75.78 79	71.16 83	80.19 85	79.27 109	77.45 96	61.68 122	66.73 77	58.72 90	65.31 80	69.96 81	62.19 108	81.29 81	80.97 71	86.74 104	86.91 69

GBi-Net		70.78 95	73.37 89	67.76 114	72.95 146	78.00 122	75.15 109	62.72 101	64.13 95	51.44 130	58.37 112	69.02 89	57.59 138	81.33 78	80.72 76	86.70 105	82.02 116

test1		70.78 95	73.37 89	67.76 114	72.95 146	78.00 122	75.15 109	62.72 101	64.13 95	51.44 130	58.37 112	69.02 89	57.59 138	81.33 78	80.72 76	86.70 105	82.02 116

FMVSNet2		70.39 101	72.67 95	67.72 117	72.95 146	78.00 122	75.15 109	62.69 105	63.29 103	51.25 134	55.64 126	68.49 95	57.59 138	80.91 89	80.35 88	86.70 105	82.02 116

v7n		67.05 142	66.94 147	67.17 128	72.35 151	78.97 110	73.26 141	58.88 151	51.16 182	50.90 135	48.21 177	50.11 183	60.96 122	77.70 127	77.38 128	86.68 108	85.05 92

WR-MVS_H		61.83 174	65.87 153	57.12 181	71.72 156	76.87 136	61.45 189	66.19 67	51.97 179	22.92 204	53.13 150	52.30 172	33.80 197	71.03 174	75.00 151	86.65 109	80.78 130

MSDG		71.52 90	69.87 113	73.44 75	82.21 71	79.35 108	79.52 74	64.59 81	66.15 80	61.87 80	53.21 148	56.09 140	65.85 92	78.94 115	78.50 111	86.60 110	76.85 158

FMVSNet3		70.49 99	72.90 93	67.67 119	72.88 149	77.98 125	74.96 115	62.72 101	64.13 95	51.44 130	58.37 112	69.02 89	57.43 141	79.43 109	79.57 98	86.59 111	81.81 123

MVS_111021_LR		78.13 58	79.85 56	76.13 58	81.12 76	81.50 86	80.28 67	65.25 76	76.09 54	71.32 51	76.49 36	72.87 67	72.21 51	82.79 65	81.29 67	86.59 111	87.91 61

DTE-MVSNet		61.85 172	64.96 163	58.22 177	74.32 133	74.39 158	61.01 190	67.85 60	51.76 181	21.91 207	53.28 145	48.17 187	37.74 193	72.22 164	76.44 141	86.52 113	78.49 147

baseline2		69.69 108	70.27 110	69.01 105	75.72 119	77.13 135	73.82 132	58.94 150	61.35 118	57.09 100	61.68 92	57.17 135	61.99 112	78.10 124	76.58 140	86.48 114	79.85 138

thisisatest0515		67.40 138	68.78 128	65.80 141	70.02 171	75.24 152	69.36 155	57.37 158	54.94 162	53.67 119	55.53 129	54.85 146	58.00 136	78.19 123	78.91 107	86.39 115	83.78 106

FMVSNet1		68.84 118	70.47 109	66.94 133	71.35 163	77.68 130	74.71 116	62.35 114	56.93 144	49.94 140	50.01 169	64.59 105	57.07 143	81.33 78	80.72 76	86.25 116	82.00 119

UGNet		72.78 82	77.67 65	67.07 131	71.65 158	83.24 74	75.20 108	63.62 88	64.93 88	56.72 102	71.82 51	73.30 63	49.02 174	81.02 87	80.70 81	86.22 117	88.67 56
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		71.90 87	72.48 96	71.21 82	80.14 86	81.53 85	76.92 99	62.89 97	64.46 94	58.94 87	43.80 185	70.98 74	62.22 107	80.70 90	80.19 90	86.18 118	85.73 78

tfpn200view9		68.11 124	68.72 130	67.40 123	77.83 102	78.93 111	74.28 123	62.81 98	56.64 146	46.82 155	52.65 156	53.47 160	56.59 147	80.41 92	78.43 112	86.11 119	80.52 133

CANet_DTU		73.29 80	76.96 74	69.00 106	77.04 110	82.06 82	79.49 75	56.30 162	67.85 75	53.29 122	71.12 55	70.37 80	61.81 117	81.59 72	80.96 72	86.09 120	84.73 96

CP-MVSNet		62.68 162	65.49 157	59.40 174	71.84 154	75.34 150	62.87 186	67.04 64	52.64 173	27.19 197	53.38 144	48.15 188	41.40 187	71.26 170	75.68 146	86.07 121	82.00 119

ACMH	65.37 14	70.71 97	70.00 112	71.54 81	82.51 67	82.47 80	77.78 91	68.13 56	56.19 151	46.06 161	54.30 134	51.20 177	68.68 74	80.66 91	80.72 76	86.07 121	84.45 101
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres600view7		67.68 132	68.43 134	66.80 135	77.90 99	78.86 113	73.84 131	62.75 99	56.07 152	44.70 168	52.85 154	52.81 167	55.58 156	80.41 92	77.77 120	86.05 123	80.28 135

thres200		67.98 126	68.55 133	67.30 126	77.89 101	78.86 113	74.18 127	62.75 99	56.35 149	46.48 158	52.98 152	53.54 156	56.46 148	80.41 92	77.97 118	86.05 123	79.78 140

CNLPA		77.20 61	77.54 66	76.80 56	82.63 65	84.31 63	79.77 72	64.64 80	85.17 24	73.18 39	56.37 124	69.81 83	74.53 35	81.12 86	78.69 109	86.04 125	87.29 68

TSAR-MVS + COLMAP		78.34 57	81.64 44	74.48 72	80.13 87	85.01 60	81.73 59	65.93 73	84.75 28	61.68 81	85.79 19	66.27 101	71.39 61	82.91 63	80.78 74	86.01 126	85.98 76

LS3D		74.08 76	73.39 88	74.88 67	85.05 56	82.62 79	79.71 73	68.66 53	72.82 64	58.80 89	57.61 118	61.31 116	71.07 64	80.32 96	78.87 108	86.00 127	80.18 136

Anonymous202405211			72.16 99		80.85 79	81.85 83	76.88 101	65.40 75	62.89 107		46.35 181	67.99 96	62.05 110	81.15 85	80.38 87	85.97 128	84.50 99

PS-CasMVS		62.38 168	65.06 160	59.25 175	71.73 155	75.21 154	62.77 187	66.99 65	51.94 180	26.96 198	52.00 161	47.52 191	41.06 188	71.16 173	75.60 147	85.97 128	81.97 121

thres400		67.95 127	68.62 132	67.17 128	77.90 99	78.59 118	74.27 124	62.72 101	56.34 150	45.77 163	53.00 151	53.35 163	56.46 148	80.21 100	78.43 112	85.91 130	80.43 134

thres100view900		67.60 136	68.02 137	67.12 130	77.83 102	77.75 129	73.90 130	62.52 109	56.64 146	46.82 155	52.65 156	53.47 160	55.92 152	78.77 117	77.62 123	85.72 131	79.23 143

Vis-MVSNet (Re-imp)		67.83 130	73.52 86	61.19 163	78.37 97	76.72 139	66.80 168	62.96 95	65.50 85	34.17 189	67.19 75	69.68 85	39.20 192	79.39 110	79.44 102	85.68 132	76.73 159

baseline1		70.10 105	72.17 98	67.69 118	79.74 88	76.80 137	73.91 129	64.38 83	62.74 108	48.30 147	64.94 81	64.08 107	54.17 163	81.46 74	78.92 106	85.66 133	76.22 160

V42		68.76 120	69.63 117	67.74 116	64.93 189	78.01 121	78.30 88	56.48 161	58.65 134	56.30 105	54.26 137	57.03 136	64.85 94	77.47 130	77.01 134	85.60 134	84.96 93

TransMVSNet (Re)		64.74 152	65.66 155	63.66 154	77.40 108	75.33 151	69.86 151	62.67 107	47.63 191	41.21 176	50.01 169	52.33 170	45.31 180	79.57 106	77.69 122	85.49 135	77.07 157

IterMVS-LS		71.69 89	72.82 94	70.37 91	77.54 106	76.34 142	75.13 112	60.46 132	61.53 117	57.57 97	64.89 82	67.33 98	66.04 91	77.09 135	77.37 129	85.48 136	85.18 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_ETH3D		67.18 141	67.03 146	67.36 124	74.44 132	78.12 120	74.07 128	66.38 66	52.22 176	46.87 154	48.64 175	51.84 174	56.96 144	77.29 131	78.53 110	85.42 137	82.59 113

Baseline_NR-MVSNet		67.53 137	68.77 129	66.09 140	75.99 115	74.75 156	72.43 144	68.41 54	61.33 119	38.33 182	51.31 164	54.13 152	56.03 151	79.22 111	78.19 115	85.37 138	82.45 114

Fast-Effi-MVS+-dtu		68.34 122	69.47 119	67.01 132	75.15 123	77.97 127	77.12 98	55.40 164	57.87 135	46.68 157	56.17 125	60.39 117	62.36 106	76.32 143	76.25 144	85.35 139	81.34 126

diffmvs		74.86 73	77.37 70	71.93 79	75.62 120	80.35 100	79.42 76	60.15 136	72.81 65	64.63 74	71.51 53	73.11 66	66.53 88	79.02 114	77.98 117	85.25 140	86.83 72

GA-MVS		68.14 123	69.17 124	66.93 134	73.77 140	78.50 119	74.45 118	58.28 154	55.11 158	48.44 146	60.08 100	53.99 153	61.50 119	78.43 121	77.57 124	85.13 141	80.54 132

v148		67.85 129	67.53 141	68.23 111	73.25 144	77.57 133	74.26 125	57.36 159	55.70 154	57.45 99	53.53 142	55.42 142	61.96 113	75.23 147	73.92 156	85.08 142	81.32 127

HyFIR lowres test		69.47 112	68.94 126	70.09 94	76.77 112	82.93 77	76.63 103	60.17 135	59.00 132	54.03 115	40.54 194	65.23 104	67.89 77	76.54 142	78.30 114	85.03 143	80.07 137

gg-mvs-nofinetune		62.55 163	65.05 161	59.62 172	78.72 96	77.61 131	70.83 150	53.63 165	39.71 205	22.04 206	36.36 198	64.32 106	47.53 176	81.16 84	79.03 105	85.00 144	77.17 155

COLMAP_ROB	62.73 15	67.66 133	66.76 149	68.70 108	80.49 83	77.98 125	75.29 107	62.95 96	63.62 101	49.96 139	47.32 180	50.72 180	58.57 131	76.87 137	75.50 149	84.94 145	75.33 169
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpnnormal		64.27 155	63.64 171	65.02 144	75.84 118	75.61 148	71.24 149	62.52 109	47.79 190	42.97 172	42.65 188	44.49 198	52.66 168	78.77 117	76.86 135	84.88 146	79.29 142

pm-mvs1		65.62 146	67.42 143	63.53 155	73.66 142	76.39 141	69.66 152	60.87 127	49.73 186	43.97 169	51.24 165	57.00 137	48.16 175	79.89 102	77.84 119	84.85 147	79.82 139

gm-plane-assit		57.00 187	57.62 194	56.28 184	76.10 114	62.43 200	47.62 208	46.57 199	33.84 208	23.24 202	37.52 195	40.19 205	59.61 129	79.81 103	77.55 125	84.55 148	72.03 179

USDC		67.36 139	67.90 139	66.74 137	71.72 156	75.23 153	71.58 146	60.28 133	67.45 76	50.54 138	60.93 94	45.20 197	62.08 109	76.56 141	74.50 154	84.25 149	75.38 168

MS-PatchMatch		70.17 104	70.49 108	69.79 97	80.98 78	77.97 127	77.51 93	58.95 149	62.33 110	55.22 110	53.14 149	65.90 102	62.03 111	79.08 113	77.11 133	84.08 150	77.91 150

TDRefinement		66.09 145	65.03 162	67.31 125	69.73 173	76.75 138	75.33 105	64.55 82	60.28 127	49.72 142	45.63 183	42.83 200	60.46 127	75.75 144	75.95 145	84.08 150	78.04 149

pmmvs4		67.89 128	67.39 145	68.48 110	71.60 160	73.57 160	74.45 118	60.98 125	64.65 90	57.97 96	54.95 132	51.73 175	61.88 114	73.78 156	75.11 150	83.99 152	77.91 150

pmmvs5		62.37 169	64.04 168	60.42 166	65.03 187	71.67 167	67.17 164	52.70 175	50.30 183	44.80 166	54.23 138	51.19 178	49.37 173	72.88 159	73.48 160	83.45 153	74.55 172

pmmvs-eth3d		63.52 158	62.44 180	64.77 146	66.82 184	70.12 172	69.41 154	59.48 143	54.34 167	52.71 124	46.24 182	44.35 199	56.93 145	72.37 160	73.77 158	83.30 154	75.91 162

pmmvs6		62.41 166	62.88 174	61.87 160	71.38 162	75.18 155	67.76 161	59.45 144	41.64 201	42.52 174	37.33 196	52.91 166	46.87 177	77.67 128	76.26 143	83.23 155	79.18 144

CDS-MVSNet		67.65 134	69.83 115	65.09 143	75.39 122	76.55 140	74.42 121	63.75 87	53.55 169	49.37 143	59.41 105	62.45 112	44.44 181	79.71 104	79.82 93	83.17 156	77.36 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PMMVS		65.06 150	69.17 124	60.26 168	55.25 207	63.43 194	66.71 169	43.01 203	62.41 109	50.64 136	69.44 61	67.04 99	63.29 101	74.36 153	73.54 159	82.68 157	73.99 176

SixPastTwentyTwo		61.84 173	62.45 179	61.12 164	69.20 177	72.20 164	62.03 188	57.40 157	46.54 194	38.03 184	57.14 122	41.72 202	58.12 135	69.67 184	71.58 167	81.94 158	78.30 148

IterMVS		66.36 144	68.30 136	64.10 150	69.48 176	74.61 157	73.41 139	50.79 184	57.30 143	48.28 148	60.64 97	59.92 122	60.85 126	74.14 154	72.66 163	81.80 159	78.82 146
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchMatch-RL		67.78 131	66.65 150	69.10 104	73.01 145	72.69 163	68.49 158	61.85 119	62.93 106	60.20 86	56.83 123	50.42 181	69.52 69	75.62 145	74.46 155	81.51 160	73.62 177

TinyColmap		62.84 161	61.03 186	64.96 145	69.61 174	71.69 166	68.48 159	59.76 141	55.41 155	47.69 152	47.33 179	34.20 208	62.76 105	74.52 151	72.59 164	81.44 161	71.47 180

EPNet_dtu		68.08 125	71.00 104	64.67 147	79.64 89	68.62 178	75.05 113	63.30 90	66.36 79	45.27 165	67.40 74	66.84 100	43.64 183	75.37 146	74.98 152	81.15 162	77.44 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		64.83 151	65.54 156	64.01 152	70.64 168	69.41 173	65.97 173	52.74 173	57.81 137	52.65 125	54.27 135	56.31 139	60.92 123	72.20 165	73.09 161	81.12 163	75.69 165

RPMNet		61.71 176	62.88 174	60.34 167	69.51 175	69.41 173	63.48 183	49.23 189	57.81 137	45.64 164	50.51 167	50.12 182	53.13 167	68.17 191	68.49 182	81.07 164	75.62 167

test-mter		60.84 178	64.62 165	56.42 183	55.99 205	64.18 189	65.39 175	34.23 208	54.39 166	46.21 160	57.40 121	59.49 124	55.86 153	71.02 175	69.65 173	80.87 165	76.20 161

test-LLR		64.42 153	64.36 166	64.49 148	75.02 125	63.93 191	66.61 170	61.96 117	54.41 164	47.77 150	57.46 119	60.25 118	55.20 159	70.80 176	69.33 174	80.40 166	74.38 173

TESTMET0.1,1		61.10 177	64.36 166	57.29 180	57.53 202	63.93 191	66.61 170	36.22 207	54.41 164	47.77 150	57.46 119	60.25 118	55.20 159	70.80 176	69.33 174	80.40 166	74.38 173

CostFormer		68.92 117	69.58 118	68.15 112	75.98 117	76.17 144	78.22 89	51.86 178	65.80 83	61.56 82	63.57 88	62.83 111	61.85 115	70.40 182	68.67 179	79.42 168	79.62 141

CVMVSNet		62.55 163	65.89 152	58.64 176	66.95 182	69.15 175	66.49 172	56.29 163	52.46 175	32.70 190	59.27 106	58.21 131	50.09 172	71.77 168	71.39 168	79.31 169	78.99 145

CHOSEN 1792x2688		69.20 115	69.26 122	69.13 103	76.86 111	78.93 111	77.27 97	60.12 137	61.86 114	54.42 111	42.54 189	61.61 114	66.91 83	78.55 120	78.14 116	79.23 170	83.23 111

PM-MVS		60.48 179	60.94 187	59.94 169	58.85 200	66.83 184	64.27 181	51.39 181	55.03 160	48.03 149	50.00 171	40.79 204	58.26 134	69.20 187	67.13 189	78.84 171	77.60 152

baseline		70.45 100	74.09 84	66.20 139	70.95 166	75.67 146	74.26 125	53.57 166	68.33 74	58.42 92	69.87 60	71.45 70	61.55 118	74.84 150	74.76 153	78.42 172	83.72 107

PatchT		61.97 171	64.04 168	59.55 173	60.49 197	67.40 181	56.54 198	48.65 193	56.69 145	52.65 125	51.10 166	52.14 173	60.92 123	72.20 165	73.09 161	78.03 173	75.69 165

RPSCF		67.64 135	71.25 103	63.43 156	61.86 195	70.73 170	67.26 163	50.86 183	74.20 60	58.91 88	67.49 73	69.33 86	64.10 98	71.41 169	68.45 183	77.61 174	77.17 155

MDTV_nov1_ep13_2view		60.16 180	60.51 188	59.75 170	65.39 186	69.05 176	68.00 160	48.29 195	51.99 177	45.95 162	48.01 178	49.64 185	53.39 165	68.83 188	66.52 190	77.47 175	69.55 186

MDTV_nov1_ep13		64.37 154	65.24 158	63.37 157	68.94 178	70.81 169	72.40 145	50.29 187	60.10 128	53.91 117	60.07 101	59.15 125	57.21 142	69.43 186	67.30 186	77.47 175	69.78 185

LTVRE_ROB	59.44 16	61.82 175	62.64 177	60.87 165	72.83 150	77.19 134	64.37 180	58.97 148	33.56 209	28.00 196	52.59 158	42.21 201	63.93 99	74.52 151	76.28 142	77.15 177	82.13 115
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
IterMVS-SCA-FT		66.89 143	69.22 123	64.17 149	71.30 164	75.64 147	71.33 147	53.17 170	57.63 141	49.08 144	60.72 96	60.05 121	63.09 102	74.99 149	73.92 156	77.07 178	81.57 125

SCA		65.40 148	66.58 151	64.02 151	70.65 167	73.37 161	67.35 162	53.46 168	63.66 100	54.14 113	60.84 95	60.20 120	61.50 119	69.96 183	68.14 184	77.01 179	69.91 183

MDA-MVSNet-bldmvs		53.37 196	53.01 199	53.79 192	43.67 211	67.95 180	59.69 194	57.92 155	43.69 197	32.41 191	41.47 190	27.89 213	52.38 169	56.97 206	65.99 192	76.68 180	67.13 190

MVS-HIRNet		54.41 193	52.10 200	57.11 182	58.99 199	56.10 206	49.68 206	49.10 190	46.18 195	52.15 129	33.18 202	46.11 194	56.10 150	63.19 199	59.70 202	76.64 181	60.25 202

dps		64.00 157	62.99 173	65.18 142	73.29 143	72.07 165	68.98 157	53.07 171	57.74 139	58.41 93	55.55 128	47.74 190	60.89 125	69.53 185	67.14 188	76.44 182	71.19 181

test0.0.03 1		58.80 183	61.58 184	55.56 186	75.02 125	68.45 179	59.58 195	61.96 117	52.74 172	29.57 193	49.75 172	54.56 148	31.46 199	71.19 171	69.77 172	75.75 183	64.57 194

EU-MVSNet		54.63 192	58.69 190	49.90 197	56.99 203	62.70 199	56.41 199	50.64 186	45.95 196	23.14 203	50.42 168	46.51 193	36.63 194	65.51 194	64.85 193	75.57 184	74.91 170

PatchmatchNet		64.21 156	64.65 164	63.69 153	71.29 165	68.66 177	69.63 153	51.70 180	63.04 104	53.77 118	59.83 104	58.34 130	60.23 128	68.54 189	66.06 191	75.56 185	68.08 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous20231206		56.36 189	57.80 193	54.67 189	70.08 170	66.39 185	60.46 192	57.54 156	49.50 188	29.30 194	33.86 201	46.64 192	35.18 195	70.44 180	68.88 178	75.47 186	68.88 188

CMPMVS	47.78 17	62.49 165	62.52 178	62.46 158	70.01 172	70.66 171	62.97 185	51.84 179	51.98 178	56.71 103	42.87 187	53.62 154	57.80 137	72.23 163	70.37 171	75.45 187	75.91 162
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet		58.52 185	61.34 185	55.22 187	60.76 196	67.01 183	66.81 167	49.02 191	56.43 148	38.90 180	40.59 193	54.54 149	40.57 190	73.16 158	71.65 166	75.30 188	66.00 192

TAMVS		59.58 182	62.81 176	55.81 185	66.03 185	65.64 188	63.86 182	48.74 192	49.95 185	37.07 186	54.77 133	58.54 128	44.44 181	72.29 162	71.79 165	74.70 189	66.66 191

tpm cat1		65.41 147	63.81 170	67.28 127	75.61 121	72.88 162	75.32 106	52.85 172	62.97 105	63.66 77	53.24 147	53.29 165	61.83 116	65.54 193	64.14 195	74.43 190	74.60 171

test20.03		53.93 195	56.28 196	51.19 195	72.19 153	65.83 186	53.20 202	61.08 124	42.74 199	22.08 205	37.07 197	45.76 196	24.29 207	70.44 180	69.04 176	74.31 191	63.05 198

FMVSNet5		57.24 186	60.02 189	53.99 191	56.45 204	62.74 198	65.27 176	47.03 198	55.14 157	39.55 179	40.88 191	53.42 162	41.83 184	72.35 161	71.10 170	73.79 192	64.50 195

testgi		54.39 194	57.86 192	50.35 196	71.59 161	67.24 182	54.95 200	53.25 169	43.36 198	23.78 201	44.64 184	47.87 189	24.96 204	70.45 179	68.66 180	73.60 193	62.78 199

MIMVSNet1		49.27 198	53.25 198	44.62 201	44.61 209	61.52 201	53.61 201	52.18 176	41.62 202	18.68 209	28.14 207	41.58 203	25.50 202	68.46 190	69.04 176	73.15 194	62.37 200

pmmvs3		47.65 199	49.08 204	45.99 200	44.61 209	54.79 207	50.04 204	31.95 211	33.91 207	29.90 192	30.37 203	33.53 209	46.31 178	63.50 197	63.67 196	73.14 195	63.77 197

FC-MVSNet-test		56.90 188	65.20 159	47.21 199	66.98 181	63.20 196	49.11 207	58.60 153	59.38 131	11.50 213	65.60 78	56.68 138	24.66 206	71.17 172	71.36 169	72.38 196	69.02 187

GG-mvs-BLEND		46.86 202	67.51 142	22.75 208	0.05 218	76.21 143	64.69 178	0.04 215	61.90 113	0.09 219	55.57 127	71.32 72	0.08 214	70.54 178	67.19 187	71.58 197	69.86 184

ambc			53.42 197		64.99 188	63.36 195	49.96 205		47.07 192	37.12 185	28.97 205	16.36 216	41.82 185	75.10 148	67.34 185	71.55 198	75.72 164

tpmrst		62.00 170	62.35 181	61.58 161	71.62 159	64.14 190	69.07 156	48.22 197	62.21 111	53.93 116	58.26 116	55.30 144	55.81 154	63.22 198	62.62 197	70.85 199	70.70 182

tpm		62.41 166	63.15 172	61.55 162	72.24 152	63.79 193	71.31 148	46.12 201	57.82 136	55.33 108	59.90 103	54.74 147	53.63 164	67.24 192	64.29 194	70.65 200	74.25 175

FPMVS		51.87 197	50.00 202	54.07 190	66.83 183	57.25 204	60.25 193	50.91 182	50.25 184	34.36 188	36.04 199	32.02 210	41.49 186	58.98 204	56.07 203	70.56 201	59.36 204

EPMVS		60.00 181	61.97 182	57.71 179	68.46 179	63.17 197	64.54 179	48.23 196	63.30 102	44.72 167	60.19 99	56.05 141	50.85 171	65.27 196	62.02 198	69.44 202	63.81 196

PMVS	39.38 18	46.06 203	43.30 205	49.28 198	62.93 191	38.75 211	41.88 210	53.50 167	33.33 210	35.46 187	28.90 206	31.01 211	33.04 198	58.61 205	54.63 206	68.86 203	57.88 205
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmnet_mix02		55.30 191	57.01 195	53.30 194	64.14 190	59.09 202	58.39 197	50.24 188	53.47 170	38.68 181	49.75 172	45.86 195	40.14 191	65.38 195	60.22 200	68.19 204	65.33 193

CHOSEN 280x420		58.70 184	61.88 183	54.98 188	55.45 206	50.55 209	64.92 177	40.36 204	55.21 156	38.13 183	48.31 176	63.76 108	63.03 104	73.73 157	68.58 181	68.00 205	73.04 178

new-patchmatchnet		46.97 201	49.47 203	44.05 203	62.82 192	56.55 205	45.35 209	52.01 177	42.47 200	17.04 211	35.73 200	35.21 207	21.84 210	61.27 201	54.83 205	65.26 206	60.26 201

ADS-MVSNet		55.94 190	58.01 191	53.54 193	62.48 194	58.48 203	59.12 196	46.20 200	59.65 130	42.88 173	52.34 160	53.31 164	46.31 178	62.00 200	60.02 201	64.23 207	60.24 203

N_pmnet		47.35 200	50.13 201	44.11 202	59.98 198	51.64 208	51.86 203	44.80 202	49.58 187	20.76 208	40.65 192	40.05 206	29.64 200	59.84 202	55.15 204	57.63 208	54.00 206

new_pmnet		38.40 204	42.64 206	33.44 205	37.54 214	45.00 210	36.60 211	32.72 210	40.27 203	12.72 212	29.89 204	28.90 212	24.78 205	53.17 207	52.90 207	56.31 209	48.34 207

Gipuma		36.38 205	35.80 207	37.07 204	45.76 208	33.90 212	29.81 212	48.47 194	39.91 204	18.02 210	8.00 214	8.14 218	25.14 203	59.29 203	61.02 199	55.19 210	40.31 208
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		25.60 206	29.75 208	20.76 209	28.00 215	30.93 213	23.10 213	29.18 212	23.14 212	1.46 218	18.23 210	16.54 215	5.08 212	40.22 208	41.40 209	37.76 211	37.79 210

E-PMN		21.77 207	18.24 210	25.89 206	40.22 212	19.58 215	12.46 216	39.87 205	18.68 214	6.71 215	9.57 211	4.31 221	22.36 209	19.89 212	27.28 211	33.73 212	28.34 212

EMVS		20.98 208	17.15 211	25.44 207	39.51 213	19.37 216	12.66 215	39.59 206	19.10 213	6.62 216	9.27 212	4.40 220	22.43 208	17.99 213	24.40 212	31.81 213	25.53 213

tmp_tt				14.50 211	14.68 216	7.17 218	10.46 218	2.21 214	37.73 206	28.71 195	25.26 208	16.98 214	4.37 213	31.49 209	29.77 210	26.56 214

MVE	19.12 19	20.47 209	23.27 209	17.20 210	12.66 217	25.41 214	10.52 217	34.14 209	14.79 215	6.53 217	8.79 213	4.68 219	16.64 211	29.49 210	41.63 208	22.73 215	38.11 209
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						18.74 217	18.55 214	8.02 213	26.96 211	7.33 214	23.81 209	13.05 217	25.99 201	25.17 211		22.45 216	36.25 211

testmvs		0.09 210	0.15 212	0.02 212	0.01 219	0.02 219	0.05 220	0.01 216	0.11 216	0.01 220	0.26 216	0.01 222	0.06 216	0.10 214	0.10 213	0.01 217	0.43 215

test123		0.09 210	0.14 213	0.02 212	0.00 220	0.02 219	0.02 221	0.01 216	0.09 217	0.00 221	0.30 215	0.00 223	0.08 214	0.03 215	0.09 214	0.01 217	0.45 214

uanet_test		0.00 212	0.00 214	0.00 214	0.00 220	0.00 221	0.00 222	0.00 218	0.00 218	0.00 221	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet-low-res		0.00 212	0.00 214	0.00 214	0.00 220	0.00 221	0.00 222	0.00 218	0.00 218	0.00 221	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet		0.00 212	0.00 214	0.00 214	0.00 220	0.00 221	0.00 222	0.00 218	0.00 218	0.00 221	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

RE-MVS-def										46.24 159

9.14												86.88 15

SR-MVS					88.99 34			73.57 25				87.54 13

our_test_3					67.93 180	70.99 168	66.89 166

MTAPA										83.48 1		86.45 18

MTMP										82.66 5		84.91 26

Patchmatch-RL test							2.85 219

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 46

Patchmtry						65.80 187	65.97 173	52.74 173		52.65 125

High-resolution multi-view benchmark