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.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 5	76.83 7	94.16 1	86.57 1	90.85 6	87.07 1	86.18 1	86.36 7	85.08 12	88.67 21	98.21 3

DVP-MVS++		87.98 3	89.76 5	85.89 2	92.57 6	94.57 3	88.34 6	76.61 8	92.40 6	83.40 3	89.26 11	85.57 5	86.04 2	86.24 11	84.89 15	88.39 31	95.42 21

MSP-MVS		87.87 4	90.57 3	84.73 6	89.38 28	91.60 18	88.24 8	74.15 13	93.55 3	82.28 4	94.99 1	83.21 11	85.96 3	87.67 4	84.67 18	88.32 32	98.29 1
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
MCST-MVS		85.75 9	86.99 13	84.31 7	94.07 3	92.80 8	88.15 9	79.10 3	85.66 24	70.72 31	76.50 33	80.45 21	82.17 4	88.35 2	87.49 3	91.63 2	97.65 4

CNVR-MVS		85.96 8	87.58 11	84.06 9	92.58 5	92.40 11	87.62 11	77.77 5	88.44 15	75.93 18	79.49 26	81.97 17	81.65 5	87.04 6	86.58 4	88.79 17	97.18 7

DPE-MVS		87.60 5	90.44 4	84.29 8	92.09 9	93.44 6	88.69 4	75.11 10	93.06 5	80.80 6	94.23 2	86.70 3	81.44 6	84.84 18	83.52 27	87.64 48	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		86.37 7	88.41 8	84.00 10	91.43 15	91.83 16	88.34 6	74.67 11	91.19 7	81.76 5	91.13 5	81.94 18	80.07 7	83.38 28	82.58 35	87.69 46	96.78 10

xxxxxxxxxxxxxcwj		84.33 15	83.20 27	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	44.71 148	79.75 8	83.52 26	82.72 32	88.75 19	95.37 24

SF-MVS		87.30 6	88.71 6	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	83.29 10	79.75 8	83.52 26	82.72 32	88.75 19	95.37 24

ET-MVSNet_ETH3D		71.38 79	74.70 70	67.51 100	51.61 209	88.06 49	77.29 68	60.95 106	63.61 85	48.36 109	66.60 48	60.67 85	79.55 10	73.56 127	80.58 62	87.30 59	89.80 85

DeepC-MVS_fast	75.41 2	81.69 25	82.10 34	81.20 18	91.04 17	87.81 52	83.42 28	74.04 14	83.77 28	71.09 29	66.88 47	72.44 39	79.48 11	85.08 15	84.97 14	88.12 39	93.78 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS		88.07 2	90.73 2	84.97 5	91.98 10	95.01 2	87.86 10	76.88 6	93.90 2	85.15 2	90.11 8	86.90 2	79.46 12	86.26 10	84.67 18	88.50 28	98.25 2
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
DPM-MVS		85.41 11	86.72 16	83.89 11	91.66 13	91.92 15	90.49 3	78.09 4	86.90 19	73.95 21	74.52 35	82.01 16	79.29 13	90.24 1	90.65 1	89.86 6	90.78 74

APD-MVS		84.83 13	87.00 12	82.30 14	89.61 26	89.21 35	86.51 15	73.64 17	90.98 8	77.99 13	89.89 9	80.04 24	79.18 14	82.00 48	81.37 48	86.88 69	95.49 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		84.16 17	85.46 21	82.64 12	92.34 8	90.57 24	86.57 14	76.51 9	86.85 21	72.91 24	77.20 32	78.69 27	79.09 15	84.64 20	84.88 16	88.44 29	95.41 22

HPM-MVS++		85.64 10	88.43 7	82.39 13	92.65 4	90.24 27	85.83 17	74.21 12	90.68 9	75.63 19	86.77 14	84.15 8	78.68 16	86.33 8	85.26 9	87.32 57	95.60 18

AdaColmap		76.23 54	73.55 74	79.35 26	89.38 28	85.00 80	79.99 51	73.04 21	76.60 53	71.17 28	55.18 81	57.99 101	77.87 17	76.82 93	76.82 94	84.67 129	86.45 116

TSAR-MVS + MP.		84.39 14	86.58 17	81.83 15	88.09 40	86.47 66	85.63 19	73.62 18	90.13 11	79.24 10	89.67 10	82.99 12	77.72 18	81.22 54	80.92 58	86.68 73	94.66 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
3Dnovator	70.49 5	78.42 40	76.77 59	80.35 21	91.43 15	90.27 26	81.84 37	70.79 27	72.10 60	71.95 25	50.02 101	67.86 58	77.47 19	82.89 32	84.24 20	88.61 24	89.99 83

SMA-MVS		85.24 12	88.27 9	81.72 16	91.74 12	90.71 21	86.71 13	73.16 20	90.56 10	74.33 20	83.07 19	85.88 4	77.16 20	86.28 9	85.58 6	87.23 61	95.77 14
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
CANet		80.90 29	82.93 30	78.53 32	86.83 46	92.26 12	81.19 43	66.95 50	81.60 37	69.90 34	66.93 46	74.80 33	76.79 21	84.68 19	84.77 17	89.50 9	95.50 19

TSAR-MVS + GP.		82.27 24	85.98 19	77.94 34	80.72 72	88.25 45	81.12 44	67.71 46	87.10 17	73.31 22	85.23 16	83.68 9	76.64 22	80.43 62	81.47 47	88.15 38	95.66 17

abl_6				79.06 30	89.68 25	92.14 13	77.70 63	69.68 34	86.87 20	71.88 26	74.29 36	80.06 23	76.56 23			88.84 16	95.82 13

MVS_0304		79.43 34	82.20 32	76.20 43	84.22 54	91.79 17	81.82 38	63.81 71	76.83 52	61.71 57	66.37 49	75.52 32	76.38 24	85.54 14	85.03 13	89.28 11	94.32 36

3Dnovator+	70.16 6	77.87 43	77.29 54	78.55 31	89.25 30	88.32 44	80.09 49	67.95 45	74.89 58	71.83 27	52.05 94	70.68 49	76.27 25	82.27 42	82.04 37	85.92 90	90.77 75

ACMMP_NAP		83.54 18	86.37 18	80.25 22	89.57 27	90.10 29	85.27 21	71.66 24	87.38 16	73.08 23	84.23 18	80.16 22	75.31 26	84.85 17	83.64 24	86.57 74	94.21 39

MVS_Test		75.22 58	76.69 60	73.51 58	79.30 78	88.82 38	80.06 50	58.74 114	69.77 68	57.50 76	59.78 72	61.35 81	75.31 26	82.07 46	83.60 26	90.13 5	91.41 66

HFP-MVS		82.48 23	84.12 24	80.56 20	90.15 19	87.55 54	84.28 24	69.67 35	85.22 25	77.95 14	84.69 17	75.94 31	75.04 28	81.85 49	81.17 52	86.30 79	92.40 57

CS-MVS		73.80 66	77.47 51	69.53 83	74.86 118	85.07 78	69.93 122	56.91 138	72.12 59	54.28 87	64.82 53	66.85 60	74.88 29	79.25 73	79.64 69	86.30 79	94.52 31

MAR-MVS		77.19 49	78.37 49	75.81 47	89.87 22	90.58 23	79.33 54	65.56 61	77.62 50	58.33 71	59.24 73	67.98 56	74.83 30	82.37 40	83.12 29	86.95 67	87.67 108
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
DeepPCF-MVS	76.94 1	83.08 20	87.77 10	77.60 36	90.11 20	90.96 20	78.48 55	72.63 23	93.10 4	65.84 43	80.67 24	81.55 19	74.80 31	85.94 13	85.39 8	83.75 144	96.77 11

DeepC-MVS	74.46 3	80.30 31	81.05 37	79.42 25	87.42 42	88.50 41	83.23 29	73.27 19	82.78 31	71.01 30	62.86 60	69.93 52	74.80 31	84.30 21	84.20 21	86.79 72	94.77 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
canonicalmvs		77.65 44	79.59 43	75.39 48	81.52 65	89.83 33	81.32 42	60.74 107	80.05 42	66.72 41	68.43 43	65.09 65	74.72 33	78.87 76	82.73 31	87.32 57	92.16 58

QAPM		77.50 46	77.43 52	77.59 37	91.52 14	92.00 14	81.41 41	70.63 28	66.22 76	58.05 72	54.70 82	71.79 45	74.49 34	82.46 37	82.04 37	89.46 10	92.79 55

zzz-MVS		81.65 26	83.10 28	79.97 24	88.14 39	87.62 53	83.96 27	69.90 32	86.92 18	77.67 15	72.47 37	78.74 26	74.13 35	81.59 52	81.15 53	86.01 89	93.19 50

CS-MVS-test		73.97 64	76.86 57	70.60 77	75.53 113	83.16 94	77.50 65	57.04 135	71.34 62	53.25 89	63.44 57	64.85 68	73.96 36	82.12 44	78.80 77	86.30 79	94.34 34

DROMVSNet		76.05 55	78.87 45	72.77 64	78.87 82	86.63 62	77.50 65	57.04 135	75.34 55	61.68 58	64.20 54	69.56 53	73.96 36	82.12 44	80.65 61	87.57 50	93.57 46

SD-MVS		84.31 16	86.96 14	81.22 17	88.98 32	88.68 39	85.65 18	73.85 16	89.09 14	79.63 9	87.34 13	84.84 6	73.71 38	82.66 35	81.60 45	85.48 107	94.51 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
casdiffmvs		75.20 59	75.69 66	74.63 56	79.26 79	89.07 36	78.47 56	63.59 74	67.05 74	63.79 48	55.72 79	60.32 87	73.58 39	82.16 43	81.78 41	89.08 13	93.72 45

CLD-MVS		77.36 48	77.29 54	77.45 38	82.21 61	88.11 47	81.92 36	68.96 40	77.97 48	69.62 36	62.08 61	59.44 92	73.57 40	81.75 50	81.27 50	88.41 30	90.39 79
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		78.57 39	77.33 53	80.02 23	88.39 35	84.79 81	84.62 23	66.17 57	75.96 54	78.40 11	61.59 63	71.47 46	73.54 41	78.43 80	78.88 76	88.97 14	90.18 82

ETV-MVS		76.25 53	80.22 40	71.63 71	78.23 86	87.95 51	72.75 94	60.27 111	77.50 51	57.73 73	71.53 38	66.60 61	73.16 42	80.99 58	81.23 51	87.63 49	95.73 15

SteuartSystems-ACMMP		82.51 22	85.35 22	79.20 27	90.25 18	89.39 34	84.79 22	70.95 26	82.86 30	68.32 39	86.44 15	77.19 28	73.07 43	83.63 25	83.64 24	87.82 42	94.34 34
Skip Steuart: Steuart Systems R&D Blog.
train_agg		83.35 19	86.93 15	79.17 28	89.70 24	88.41 42	85.60 20	72.89 22	86.31 22	66.58 42	90.48 7	82.24 15	73.06 44	83.10 31	82.64 34	87.21 65	95.30 26

DELS-MVS		79.49 32	79.84 42	79.08 29	88.26 38	92.49 9	84.12 26	70.63 28	65.27 83	69.60 37	61.29 65	66.50 62	72.75 45	88.07 3	88.03 2	89.13 12	97.22 6
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		71.37 80	70.27 95	72.66 66	80.79 71	81.33 110	71.07 115	65.75 59	82.36 32	64.80 46	42.46 136	56.49 106	72.70 46	73.00 134	70.52 169	80.84 178	85.76 126

CANet_DTU		72.84 70	76.63 61	68.43 94	76.81 101	86.62 64	75.54 77	54.71 163	72.06 61	43.54 129	67.11 45	58.46 96	72.40 47	81.13 57	80.82 60	87.57 50	90.21 81

DI_MVS_plusplus_trai		73.94 65	74.85 69	72.88 63	76.57 104	86.80 60	80.41 48	61.47 98	62.35 88	59.44 69	47.91 107	68.12 55	72.24 48	82.84 34	81.50 46	87.15 66	94.42 33

ACMMPR		80.62 30	82.98 29	77.87 35	88.41 34	87.05 59	83.02 30	69.18 38	83.91 27	68.35 38	82.89 20	73.64 36	72.16 49	80.78 60	81.13 54	86.10 86	91.43 64

MVS_111021_HR		77.42 47	78.40 48	76.28 42	86.95 44	90.68 22	77.41 67	70.56 31	66.21 77	62.48 53	66.17 50	63.98 70	72.08 50	82.87 33	83.15 28	88.24 35	95.71 16

diffmvs		74.32 61	75.42 67	73.04 62	75.60 112	87.27 56	78.20 57	62.96 80	68.66 73	61.89 55	59.79 71	59.84 90	71.80 51	78.30 83	79.87 66	87.80 44	94.23 38

OpenMVS	67.62 8	74.92 60	73.91 72	76.09 45	90.10 21	90.38 25	78.01 59	66.35 55	66.09 78	62.80 50	46.33 124	64.55 69	71.77 52	79.92 66	80.88 59	87.52 52	89.20 92

CP-MVS		79.44 33	81.51 36	77.02 39	86.95 44	85.96 74	82.00 35	68.44 43	81.82 35	67.39 40	77.43 30	73.68 35	71.62 53	79.56 71	79.58 70	85.73 97	92.51 56

MP-MVS		80.94 28	83.49 26	77.96 33	88.48 33	88.16 46	82.82 33	69.34 37	80.79 40	69.67 35	82.35 21	77.13 29	71.60 54	80.97 59	80.96 57	85.87 93	94.06 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		79.42 36	81.84 35	76.60 41	88.38 36	86.69 61	82.97 32	65.75 59	80.39 41	64.94 45	81.95 23	72.11 44	71.41 55	80.45 61	80.55 63	86.18 83	90.76 76

MVSTER		76.92 50	79.92 41	73.42 60	74.98 116	82.97 96	78.15 58	63.41 75	78.02 47	64.41 47	67.54 44	72.80 38	71.05 56	83.29 30	83.73 23	88.53 27	91.12 69

HQP-MVS		78.26 41	80.91 38	75.17 51	85.67 51	84.33 87	83.01 31	69.38 36	79.88 43	55.83 78	79.85 25	64.90 67	70.81 57	82.46 37	81.78 41	86.30 79	93.18 51

baseline		72.89 69	74.46 71	71.07 72	75.99 108	87.50 55	74.57 84	60.49 109	70.72 65	57.60 74	60.63 68	60.97 83	70.79 58	75.27 107	76.33 100	86.94 68	89.79 86

PCF-MVS	70.85 4	75.73 56	76.55 62	74.78 55	83.67 55	88.04 50	81.47 39	70.62 30	69.24 72	57.52 75	60.59 69	69.18 54	70.65 59	77.11 90	77.65 88	84.75 127	94.01 41
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PLC	64.00 12	68.54 94	66.66 118	70.74 75	80.28 74	74.88 166	72.64 96	63.70 73	69.26 71	55.71 79	47.24 115	55.31 114	70.42 60	72.05 146	70.67 167	81.66 172	77.19 170
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PHI-MVS		79.43 34	84.06 25	74.04 57	86.15 49	91.57 19	80.85 47	68.90 41	82.22 33	51.81 94	78.10 28	74.28 34	70.39 61	84.01 24	84.00 22	86.14 85	94.24 37

EPNet		79.28 38	82.25 31	75.83 46	88.31 37	90.14 28	79.43 53	68.07 44	81.76 36	61.26 60	77.26 31	70.08 51	70.06 62	82.43 39	82.00 39	87.82 42	92.09 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		72.74 71	70.93 90	74.85 54	85.30 52	84.34 86	82.82 33	69.79 33	49.96 139	55.39 83	54.09 89	60.14 89	70.04 63	80.38 63	79.43 71	85.74 96	88.20 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CSCG		82.90 21	84.52 23	81.02 19	91.85 11	93.43 7	87.14 12	74.01 15	81.96 34	76.14 16	70.84 39	82.49 13	69.71 64	82.32 41	85.18 11	87.26 60	95.40 23

Effi-MVS+		70.42 82	71.23 87	69.47 84	78.04 88	85.24 77	75.57 76	58.88 113	59.56 98	48.47 108	52.73 93	54.94 115	69.69 65	78.34 82	77.06 92	86.18 83	90.73 77

Anonymous202405211			66.35 122		78.00 89	84.41 85	74.85 82	63.18 77	51.00 135		31.37 191	53.73 124	69.67 66	76.28 96	76.84 93	83.21 153	90.85 72

EIA-MVS		73.48 67	76.05 63	70.47 78	78.12 87	87.21 57	71.78 102	60.63 108	69.66 69	55.56 81	64.86 52	60.69 84	69.53 67	77.35 89	78.59 78	87.22 63	94.01 41

PMMVS		70.37 85	75.06 68	64.90 115	71.46 133	81.88 102	64.10 154	55.64 150	71.31 63	46.69 113	70.69 40	58.56 93	69.53 67	79.03 75	75.63 108	81.96 169	88.32 103

MVS_111021_LR		74.26 62	75.95 64	72.27 67	79.43 77	85.04 79	72.71 95	65.27 64	70.92 64	63.58 49	69.32 41	60.31 88	69.43 69	77.01 91	77.15 91	83.22 151	91.93 62

OMC-MVS		74.03 63	75.82 65	71.95 69	79.56 75	80.98 114	75.35 80	63.21 76	84.48 26	61.83 56	61.54 64	66.89 59	69.41 70	76.60 94	74.07 128	82.34 165	86.15 120

CPTT-MVS		75.43 57	77.13 56	73.44 59	81.43 66	82.55 100	80.96 46	64.35 67	77.95 49	61.39 59	69.20 42	70.94 48	69.38 71	73.89 123	73.32 138	83.14 154	92.06 60

Anonymous20231211		68.44 95	66.37 121	70.86 73	77.58 93	83.49 92	75.15 81	61.89 93	52.54 132	58.50 70	28.89 196	56.78 105	69.29 72	74.96 111	76.61 95	82.73 157	91.36 67

Fast-Effi-MVS+		67.59 102	67.56 113	67.62 99	73.67 122	81.14 113	71.12 113	54.79 162	58.88 100	50.61 101	46.70 122	47.05 142	69.12 73	76.06 100	76.44 98	86.43 77	86.65 114

TSAR-MVS + COLMAP		73.09 68	76.86 57	68.71 90	74.97 117	82.49 101	74.51 89	61.83 94	83.16 29	49.31 106	82.22 22	51.62 130	68.94 74	78.76 78	75.52 112	82.67 159	84.23 137

ACMMP		77.61 45	79.59 43	75.30 50	85.87 50	85.58 75	81.42 40	67.38 49	79.38 45	62.61 51	78.53 27	65.79 64	68.80 75	78.56 79	78.50 81	85.75 94	90.80 73
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
CDPH-MVS		79.39 37	82.13 33	76.19 44	89.22 31	88.34 43	84.20 25	71.00 25	79.67 44	56.97 77	77.77 29	72.24 43	68.50 76	81.33 53	82.74 30	87.23 61	92.84 53

CostFormer		72.18 73	73.90 73	70.18 80	79.47 76	86.19 73	76.94 70	48.62 182	66.07 79	60.40 67	54.14 88	65.82 63	67.98 77	75.84 102	76.41 99	87.67 47	92.83 54

TAPA-MVS	67.10 9	71.45 78	73.47 76	69.10 88	77.04 99	80.78 117	73.81 92	62.10 90	80.80 39	51.28 95	60.91 66	63.80 72	67.98 77	74.59 113	72.42 150	82.37 164	80.97 159
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		76.84 51	78.47 46	74.95 52	82.37 59	89.90 31	75.45 78	65.45 62	74.99 56	70.66 32	63.07 58	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

PVSNet_Blended		76.84 51	78.47 46	74.95 52	82.37 59	89.90 31	75.45 78	65.45 62	74.99 56	70.66 32	63.07 58	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

TSAR-MVS + ACMM		81.59 27	85.84 20	76.63 40	89.82 23	86.53 65	86.32 16	66.72 53	85.96 23	65.43 44	88.98 12	82.29 14	67.57 81	82.06 47	81.33 49	83.93 142	93.75 44

X-MVS		78.16 42	80.55 39	75.38 49	87.99 41	86.27 70	81.05 45	68.98 39	78.33 46	61.07 62	75.25 34	72.27 40	67.52 82	80.03 64	80.52 64	85.66 104	91.20 68

FC-MVSNet-train		68.83 93	68.29 107	69.47 84	78.35 85	79.94 123	64.72 151	66.38 54	54.96 123	54.51 86	56.75 76	47.91 140	66.91 83	75.57 106	75.75 106	85.92 90	87.12 110

DCV-MVSNet		69.13 90	69.07 100	69.21 86	77.65 92	77.52 147	74.68 83	57.85 124	54.92 124	55.34 84	55.74 78	55.56 113	66.35 84	75.05 108	76.56 97	83.35 148	88.13 105

CHOSEN 1792x2688		72.55 72	71.98 81	73.22 61	86.57 47	92.41 10	75.63 74	66.77 52	62.08 89	52.32 91	30.27 194	50.74 133	66.14 85	86.22 12	85.41 7	91.90 1	96.75 12

ACMM	66.70 10	70.42 82	68.49 105	72.67 65	82.85 56	77.76 145	77.70 63	64.76 66	64.61 84	60.74 66	49.29 102	53.97 122	65.86 86	74.97 109	75.57 110	84.13 141	83.29 144
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		67.15 108	68.12 110	66.03 108	76.21 106	80.98 114	71.27 109	45.05 193	60.69 94	50.63 100	46.95 120	54.15 121	65.30 87	71.80 148	71.77 154	87.72 45	90.48 78

LS3D		64.54 126	62.14 150	67.34 103	80.85 69	75.79 160	69.99 120	65.87 58	60.77 93	44.35 125	42.43 137	45.95 145	65.01 88	69.88 166	68.69 176	77.97 193	71.43 191

HyFIR lowres test		68.39 96	68.28 108	68.52 93	80.85 69	88.11 47	71.08 114	58.09 119	54.87 126	47.80 112	27.55 200	55.80 110	64.97 89	79.11 74	79.14 74	88.31 33	93.35 47

FMVSNet3		70.41 84	71.89 83	68.68 91	70.89 139	79.42 129	75.63 74	60.97 103	65.32 80	51.06 96	47.37 112	62.05 75	64.90 90	82.49 36	82.27 36	88.64 23	84.34 136

PatchMatch-RL		62.22 146	60.69 160	64.01 123	68.74 149	75.75 161	59.27 178	60.35 110	56.09 115	53.80 88	47.06 118	36.45 179	64.80 91	68.22 173	67.22 180	77.10 195	74.02 179

tpm cat1		67.47 105	67.05 116	67.98 96	76.63 102	81.51 108	74.49 90	47.65 187	61.18 91	61.12 61	42.51 135	53.02 128	64.74 92	70.11 165	71.50 156	83.22 151	89.49 88

GeoE		68.96 92	69.32 98	68.54 92	76.61 103	83.12 95	71.78 102	56.87 139	60.21 96	54.86 85	45.95 125	54.79 118	64.27 93	74.59 113	75.54 111	86.84 71	91.01 71

dps		64.08 128	63.22 138	65.08 113	75.27 115	79.65 126	66.68 145	46.63 191	56.94 108	55.67 80	43.96 127	43.63 151	64.00 94	69.50 170	69.82 171	82.25 166	79.02 166

ACMP	68.86 7	72.15 74	72.25 79	72.03 68	80.96 68	80.87 116	77.93 60	64.13 69	69.29 70	60.79 65	64.04 55	53.54 125	63.91 95	73.74 126	75.27 113	84.45 134	88.98 94
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Effi-MVS+-dtu		64.58 124	64.08 133	65.16 112	73.04 126	75.17 165	70.68 119	56.23 144	54.12 129	44.71 124	47.42 111	51.10 131	63.82 96	68.08 174	66.32 185	82.47 163	86.38 117

GBi-Net		69.21 88	70.40 93	67.81 97	69.49 144	78.65 134	74.54 85	60.97 103	65.32 80	51.06 96	47.37 112	62.05 75	63.43 97	77.49 85	78.22 83	87.37 54	83.73 139

test1		69.21 88	70.40 93	67.81 97	69.49 144	78.65 134	74.54 85	60.97 103	65.32 80	51.06 96	47.37 112	62.05 75	63.43 97	77.49 85	78.22 83	87.37 54	83.73 139

FMVSNet2		68.06 99	68.57 104	67.45 102	69.49 144	78.65 134	74.54 85	60.23 112	56.29 113	49.64 105	42.13 139	57.08 104	63.43 97	81.15 56	80.99 55	87.37 54	83.73 139

baseline2		71.22 81	73.01 78	69.13 87	75.76 110	86.34 69	71.23 110	62.78 86	62.62 86	52.85 90	57.32 75	54.31 119	63.27 100	79.74 69	79.31 72	88.89 15	91.43 64

EPMVS		66.21 112	67.49 114	64.73 116	75.81 109	84.20 89	68.94 129	44.37 197	61.55 90	48.07 111	49.21 104	54.87 117	62.88 101	71.82 147	71.40 160	88.28 34	79.37 165

CHOSEN 280x420		62.23 145	66.57 119	57.17 171	59.88 193	68.92 190	61.20 173	42.28 204	54.17 128	39.57 148	47.78 109	64.97 66	62.68 102	73.85 124	69.52 174	77.43 194	86.75 113

thres100view900		67.14 109	66.09 124	68.38 95	77.70 90	83.84 91	74.52 88	66.33 56	49.16 143	43.40 131	43.24 128	41.34 154	62.59 103	79.31 72	75.92 105	85.73 97	89.81 84

baseline1		71.47 77	72.02 80	70.82 74	80.56 73	84.51 83	76.61 71	66.93 51	56.22 114	48.66 107	55.40 80	60.43 86	62.55 104	83.35 29	80.99 55	89.60 7	83.28 145

LGP-MVS_train		72.02 75	73.18 77	70.67 76	82.13 62	80.26 122	79.58 52	63.04 78	70.09 66	51.98 92	65.06 51	55.62 112	62.49 105	75.97 101	76.32 101	84.80 126	88.93 95

MSDG		65.57 117	61.57 154	70.24 79	82.02 63	76.47 154	74.46 91	68.73 42	56.52 111	50.33 102	38.47 158	41.10 158	62.42 106	72.12 144	72.94 145	83.47 147	73.37 184

test_part1		66.32 111	63.35 137	69.77 81	77.40 97	78.35 138	77.85 61	56.25 143	44.52 162	62.15 54	33.05 185	53.91 123	62.38 107	72.19 143	74.65 118	82.59 160	86.81 112

IterMVS-LS		66.08 114	66.56 120	65.51 109	73.67 122	74.88 166	70.89 117	53.55 169	50.42 137	48.32 110	50.59 99	55.66 111	61.83 108	73.93 122	74.42 124	84.82 125	86.01 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MS-PatchMatch		70.34 86	69.00 101	71.91 70	85.20 53	85.35 76	77.84 62	61.77 96	58.01 106	55.40 82	41.26 143	58.34 98	61.69 109	81.70 51	78.29 82	89.56 8	80.02 162

v2v482		63.68 132	62.85 144	64.65 117	68.01 153	80.46 120	71.90 100	57.60 127	44.26 163	42.82 136	39.80 154	38.62 170	61.56 110	73.06 132	74.86 116	86.03 88	88.90 97

tfpn200view9		65.90 115	64.96 128	67.00 105	77.70 90	81.58 106	71.71 105	62.94 83	49.16 143	43.40 131	43.24 128	41.34 154	61.42 111	76.24 97	74.63 120	84.84 122	88.52 101

Fast-Effi-MVS+-dtu		63.05 136	64.72 131	61.11 145	71.21 137	76.81 153	70.72 118	43.13 202	52.51 133	35.34 173	46.55 123	46.36 143	61.40 112	71.57 151	71.44 158	84.84 122	87.79 107

ACMH	59.42 14	61.59 151	59.22 170	64.36 121	78.92 81	78.26 139	67.65 136	67.48 48	39.81 181	30.98 187	38.25 160	34.59 190	61.37 113	70.55 160	73.47 134	79.74 185	79.59 163
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v10		63.00 137	62.22 149	63.90 126	67.88 155	77.78 144	71.59 106	54.34 164	45.37 159	42.76 137	38.53 157	38.93 168	61.05 114	74.39 117	74.52 123	85.75 94	86.04 121

tpm		64.85 122	66.02 125	63.48 128	74.52 119	78.38 137	70.98 116	44.99 195	51.61 134	43.28 133	47.66 110	53.18 126	60.57 115	70.58 159	71.30 163	86.54 75	89.45 90

v8		63.44 134	62.58 146	64.43 119	68.28 152	78.07 140	71.82 101	54.85 160	46.70 153	45.20 120	39.40 155	40.91 159	60.54 116	72.85 136	74.39 125	85.92 90	85.76 126

v1192		62.25 143	61.64 153	62.96 131	66.88 161	79.72 125	69.96 121	55.77 148	41.58 173	39.42 150	37.05 167	35.96 184	60.50 117	74.30 120	74.09 127	85.24 111	88.76 98

v1144		63.00 137	62.39 148	63.70 127	67.72 156	80.27 121	71.23 110	56.40 140	42.51 168	40.81 145	38.12 162	37.73 171	60.42 118	74.46 115	74.55 122	85.64 105	89.12 93

gm-plane-assit		54.99 180	57.99 176	51.49 189	69.27 148	54.42 213	32.32 216	42.59 203	21.18 217	13.71 213	23.61 204	43.84 150	60.21 119	87.09 5	86.55 5	90.81 4	89.28 91

PatchmatchNet		65.43 119	67.71 112	62.78 134	73.49 124	82.83 97	66.42 148	45.40 192	60.40 95	45.27 118	49.22 103	57.60 103	60.01 120	70.61 157	71.38 161	86.08 87	81.91 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH+	60.36 13	61.16 152	58.38 172	64.42 120	77.37 98	74.35 171	68.45 131	62.81 85	45.86 157	38.48 156	35.71 176	37.35 174	59.81 121	67.24 176	69.80 173	79.58 186	78.32 168

v144192		62.05 147	61.46 155	62.73 137	66.59 165	79.87 124	69.30 127	55.88 146	41.50 175	39.41 151	37.23 165	36.45 179	59.62 122	72.69 139	73.51 133	85.61 106	88.93 95

v1921920		61.66 150	61.10 158	62.31 139	66.32 166	79.57 127	68.41 132	55.49 153	41.03 176	38.69 155	36.64 173	35.27 187	59.60 123	73.23 130	73.41 135	85.37 108	88.51 102

GA-MVS		64.55 125	65.76 127	63.12 130	69.68 143	81.56 107	69.59 125	58.16 118	45.23 160	35.58 172	47.01 119	41.82 153	59.41 124	79.62 70	78.54 79	86.32 78	86.56 115

ADS-MVSNet		58.40 170	59.16 171	57.52 168	65.80 171	74.57 170	60.26 174	40.17 211	50.51 136	38.01 159	40.11 153	44.72 147	59.36 125	64.91 183	66.55 183	81.53 173	72.72 187

pmmvs4		63.14 135	62.46 147	63.94 125	66.03 168	76.40 155	66.82 144	57.60 127	56.74 109	50.26 103	40.81 148	37.51 173	59.26 126	71.75 149	71.48 157	83.68 146	82.53 150

v1240		61.09 153	60.55 162	61.72 143	65.92 170	79.28 130	67.16 142	54.91 159	39.79 182	38.10 158	36.08 175	34.64 189	59.15 127	72.86 135	73.36 137	85.10 113	87.84 106

PVSNet_Blended_VisFu		71.76 76	73.54 75	69.69 82	79.01 80	87.16 58	72.05 99	61.80 95	56.46 112	59.66 68	53.88 90	62.48 73	59.08 128	81.17 55	78.90 75	86.53 76	94.74 29

MDTV_nov1_ep13		65.21 120	67.28 115	62.79 133	70.91 138	81.72 103	69.28 128	49.50 181	58.08 103	43.94 128	50.50 100	56.02 108	58.86 129	70.72 156	73.37 136	84.24 137	80.52 161

FMVSNet1		63.48 133	63.07 140	63.97 124	65.31 172	76.37 156	71.77 104	57.90 123	43.32 167	45.66 116	35.06 181	49.43 135	58.57 130	77.49 85	78.22 83	84.59 131	81.60 158

USDC		59.69 161	60.03 166	59.28 158	64.04 177	71.84 179	63.15 166	55.36 155	54.90 125	35.02 174	48.34 105	29.79 206	58.16 131	70.60 158	71.33 162	79.99 183	73.42 183

thres400		65.18 121	64.44 132	66.04 107	76.40 105	82.63 98	71.52 107	64.27 68	44.93 161	40.69 146	41.86 140	40.79 160	58.12 132	77.67 84	74.64 119	85.26 110	88.56 100

thres200		65.58 116	64.74 130	66.56 106	77.52 95	81.61 104	73.44 93	62.95 81	46.23 155	42.45 138	42.76 130	41.18 156	58.12 132	76.24 97	75.59 109	84.89 120	89.58 87

test2506		69.26 87	70.79 91	67.48 101	78.64 83	86.40 67	72.22 97	62.75 87	58.05 104	45.24 119	50.76 97	54.93 116	58.05 134	79.82 67	79.70 67	87.96 40	85.90 124

ECVR-MVS		67.93 101	68.49 105	67.28 104	78.64 83	86.40 67	72.22 97	62.75 87	58.05 104	44.06 127	40.92 147	48.20 138	58.05 134	79.82 67	79.70 67	87.96 40	86.32 119

thisisatest0530		68.38 97	70.98 89	65.35 111	72.61 127	84.42 84	68.21 133	57.98 120	59.77 97	50.80 99	54.63 83	58.48 95	57.92 136	76.99 92	77.47 89	84.60 130	85.07 130

tttt0517		67.99 100	70.61 92	64.94 114	71.94 132	83.96 90	67.62 137	57.98 120	59.30 99	49.90 104	54.50 86	57.98 102	57.92 136	76.48 95	77.47 89	84.24 137	84.58 133

SCA		63.90 130	66.67 117	60.66 147	73.75 120	71.78 181	59.87 177	43.66 198	61.13 92	45.03 121	51.64 95	59.45 91	57.92 136	70.96 154	70.80 165	83.71 145	80.92 160

test-LLR		68.23 98	71.61 85	64.28 122	71.37 134	81.32 111	63.98 157	61.03 101	58.62 101	42.96 134	52.74 91	61.65 79	57.74 139	75.64 104	78.09 86	88.61 24	93.21 48

TESTMET0.1,1		67.38 106	71.61 85	62.45 138	66.05 167	81.32 111	63.98 157	55.36 155	58.62 101	42.96 134	52.74 91	61.65 79	57.74 139	75.64 104	78.09 86	88.61 24	93.21 48

V42		62.86 139	62.97 141	62.74 136	60.84 190	78.99 132	71.46 108	57.13 134	46.85 151	44.28 126	38.87 156	40.73 162	57.63 141	72.60 140	74.14 126	85.09 115	88.63 99

CR-MVSNet		62.31 141	64.75 129	59.47 155	68.63 150	71.29 184	67.53 138	43.18 200	55.83 116	41.40 140	41.04 145	55.85 109	57.29 142	72.76 137	73.27 140	78.77 190	83.23 146

PatchT		60.46 157	63.85 134	56.51 174	65.95 169	75.68 162	47.34 199	41.39 207	53.89 130	41.40 140	37.84 163	50.30 134	57.29 142	72.76 137	73.27 140	85.67 101	83.23 146

TinyColmap		52.66 189	50.09 200	55.65 176	59.72 194	64.02 204	57.15 184	52.96 173	40.28 179	32.51 182	32.42 187	20.97 217	56.65 144	63.95 189	65.15 190	74.91 201	63.87 205

EPP-MVSNet		67.58 103	71.10 88	63.48 128	75.71 111	83.35 93	66.85 143	57.83 125	53.02 131	41.15 143	55.82 77	67.89 57	56.01 145	74.40 116	72.92 146	83.33 149	90.30 80

test1111		66.72 110	67.80 111	65.45 110	77.42 96	86.63 62	69.69 124	62.98 79	55.29 120	39.47 149	40.12 152	47.11 141	55.70 146	79.96 65	80.00 65	87.47 53	85.49 129

MVS-HIRNet		53.86 187	53.02 189	54.85 179	60.30 192	72.36 177	44.63 207	42.20 205	39.45 183	43.47 130	21.66 210	34.00 193	55.47 147	65.42 181	67.16 181	83.02 156	71.08 193

test-mter		64.06 129	69.24 99	58.01 163	59.07 196	77.40 148	59.13 179	48.11 185	55.64 119	39.18 153	51.56 96	58.54 94	55.38 148	73.52 128	76.00 104	87.22 63	92.05 61

thres600view7		63.77 131	63.14 139	64.51 118	75.49 114	81.61 104	69.59 125	62.95 81	43.96 165	38.90 154	41.09 144	40.24 165	55.25 149	76.24 97	71.54 155	84.89 120	87.30 109

v148		62.00 148	61.19 157	62.96 131	67.46 159	79.49 128	67.87 134	57.66 126	42.30 169	45.02 122	38.20 161	38.89 169	54.77 150	69.83 167	72.60 149	84.96 116	87.01 111

gg-mvs-nofinetune		62.34 140	66.19 123	57.86 165	76.15 107	88.61 40	71.18 112	41.24 210	25.74 213	13.16 215	22.91 207	63.97 71	54.52 151	85.06 16	85.25 10	90.92 3	91.78 63

IterMVS		61.87 149	63.55 135	59.90 151	67.29 160	72.20 178	67.34 141	48.56 183	47.48 149	37.86 161	47.07 117	48.27 136	54.08 152	72.12 144	73.71 131	84.30 136	83.99 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPSCF		55.07 179	58.06 174	51.57 187	48.87 212	58.95 209	53.68 190	41.26 209	62.42 87	45.88 115	54.38 87	54.26 120	53.75 153	57.15 200	53.53 210	66.01 210	65.75 202

CMPMVS	43.63 17	57.67 174	55.43 182	60.28 150	72.01 130	79.00 131	62.77 167	53.23 171	41.77 172	45.42 117	30.74 193	39.03 167	53.01 154	64.81 185	64.65 191	75.26 200	68.03 198
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
IterMVS-SCA-FT		60.21 159	62.97 141	57.00 172	66.64 164	71.84 179	67.53 138	46.93 190	47.56 148	36.77 166	46.85 121	48.21 137	52.51 155	70.36 162	72.40 151	71.63 208	83.53 142

IB-MVS	64.48 11	69.02 91	68.97 102	69.09 89	81.75 64	89.01 37	64.50 152	64.91 65	56.65 110	62.59 52	47.89 108	45.23 146	51.99 156	69.18 171	81.88 40	88.77 18	92.93 52
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
pmmvs5		59.72 160	60.24 164	59.11 159	62.77 184	77.33 150	63.17 165	54.00 166	40.21 180	37.23 162	40.41 149	35.99 183	51.75 157	72.55 141	72.74 148	85.72 99	82.45 152

UniMVSNet_ETH3D		57.83 171	56.46 181	59.43 156	63.24 181	73.22 175	67.70 135	55.58 151	36.17 193	36.84 164	32.64 186	35.14 188	51.50 158	65.81 179	69.81 172	81.73 171	82.44 153

UniMVSNet_NR-MVSNet		62.30 142	63.51 136	60.89 146	69.48 147	77.83 143	64.07 155	63.94 70	50.03 138	31.17 185	44.82 126	41.12 157	51.37 159	71.02 153	74.81 117	85.30 109	84.95 131

DU-MVS		60.87 155	61.82 152	59.76 153	66.69 162	75.87 158	64.07 155	61.96 91	49.31 141	31.17 185	42.76 130	36.95 176	51.37 159	69.67 168	73.20 143	83.30 150	84.95 131

FMVSNet5		58.86 166	60.24 164	57.25 170	52.66 208	66.25 196	63.77 160	52.86 174	57.85 107	37.92 160	36.12 174	52.22 129	51.37 159	70.88 155	71.43 159	84.92 117	66.91 200

LTVRE_ROB	47.26 16	49.41 198	49.91 201	48.82 193	64.76 174	69.79 187	49.05 195	47.12 189	20.36 219	16.52 207	36.65 172	26.96 210	50.76 162	60.47 194	63.16 196	64.73 211	72.00 188
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
tfpnnormal		58.97 165	56.48 180	61.89 141	71.27 136	76.21 157	66.65 146	61.76 97	32.90 201	36.41 167	27.83 199	29.14 207	50.64 163	73.06 132	73.05 144	84.58 132	83.15 148

v7n		57.04 176	56.64 179	57.52 168	62.85 183	74.75 168	61.76 169	51.80 177	35.58 197	36.02 170	32.33 188	33.61 195	50.16 164	67.73 175	70.34 170	82.51 161	82.12 154

pmmvs-eth3d		55.20 177	53.95 186	56.65 173	57.34 202	67.77 192	57.54 183	53.74 168	40.93 177	41.09 144	31.19 192	29.10 208	49.07 165	65.54 180	67.28 179	81.14 175	75.81 172

NR-MVSNet		61.08 154	62.09 151	59.90 151	71.96 131	75.87 158	63.60 161	61.96 91	49.31 141	27.95 190	42.76 130	33.85 194	48.82 166	74.35 118	74.05 129	85.13 112	84.45 134

Baseline_NR-MVSNet		59.47 162	60.28 163	58.54 162	66.69 162	73.90 172	61.63 171	62.90 84	49.15 145	26.87 192	35.18 180	37.62 172	48.20 167	69.67 168	73.61 132	84.92 117	82.82 149

RPMNet		58.63 169	62.80 145	53.76 185	67.59 158	71.29 184	54.60 188	38.13 212	55.83 116	35.70 171	41.58 142	53.04 127	47.89 168	66.10 178	67.38 178	78.65 192	84.40 135

TranMVSNet+NR-MVSNet		60.38 158	61.30 156	59.30 157	68.34 151	75.57 164	63.38 164	63.78 72	46.74 152	27.73 191	42.56 134	36.84 177	47.66 169	70.36 162	74.59 121	84.91 119	82.46 151

anonymousdsp		54.99 180	57.24 177	52.36 186	53.82 206	71.75 182	51.49 192	48.14 184	33.74 199	33.66 179	38.34 159	36.13 182	47.54 170	64.53 187	70.60 168	79.53 187	85.59 128

MDTV_nov1_ep13_2view		54.47 184	54.61 183	54.30 184	60.50 191	73.82 173	57.92 182	43.38 199	39.43 184	32.51 182	33.23 184	34.05 192	47.26 171	62.36 191	66.21 186	84.24 137	73.19 185

thisisatest0515		59.37 163	60.68 161	57.84 166	64.39 176	75.65 163	58.56 181	53.86 167	41.55 174	42.12 139	40.40 150	39.59 166	47.09 172	71.69 150	73.79 130	81.02 177	82.08 155

PM-MVS		50.11 195	50.38 199	49.80 191	47.23 214	62.08 207	50.91 194	44.84 196	41.90 171	36.10 169	35.22 179	26.05 213	46.83 173	57.64 198	55.42 209	72.90 205	74.32 178

CDS-MVSNet		64.22 127	65.89 126	62.28 140	70.05 141	80.59 118	69.91 123	57.98 120	43.53 166	46.58 114	48.22 106	50.76 132	46.45 174	75.68 103	76.08 103	82.70 158	86.34 118
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		58.86 166	60.91 159	56.47 175	62.38 186	77.57 146	58.97 180	52.98 172	38.76 185	36.17 168	42.26 138	47.94 139	46.45 174	70.23 164	70.79 166	81.86 170	78.82 167

TDRefinement		52.70 188	51.02 197	54.66 181	57.41 201	65.06 200	61.47 172	54.94 157	44.03 164	33.93 178	30.13 195	27.57 209	46.17 176	61.86 192	62.48 199	74.01 204	66.06 201

IS_MVSNet		67.29 107	71.98 81	61.82 142	76.92 100	84.32 88	65.90 150	58.22 117	55.75 118	39.22 152	54.51 85	62.47 74	45.99 177	78.83 77	78.52 80	84.70 128	89.47 89

MIMVSNet		57.78 173	59.71 168	55.53 177	54.79 204	77.10 151	63.89 159	45.02 194	46.59 154	36.79 165	28.36 198	40.77 161	45.84 178	74.97 109	76.58 96	86.87 70	73.60 182

UGNet		67.57 104	71.69 84	62.76 135	69.88 142	82.58 99	66.43 147	58.64 115	54.71 127	51.87 93	61.74 62	62.01 78	45.46 179	74.78 112	74.99 114	84.24 137	91.02 70
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
Vis-MVSNet		65.53 118	69.83 97	60.52 148	70.80 140	84.59 82	66.37 149	55.47 154	48.40 146	40.62 147	57.67 74	58.43 97	45.37 180	77.49 85	76.24 102	84.47 133	85.99 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
COLMAP_ROB	51.17 15	55.13 178	52.90 191	57.73 167	73.47 125	67.21 194	62.13 168	55.82 147	47.83 147	34.39 176	31.60 190	34.24 191	44.90 181	63.88 190	62.52 198	75.67 198	63.02 207
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SixPastTwentyTwo		49.11 199	49.22 202	48.99 192	58.54 200	64.14 203	47.18 200	47.75 186	31.15 205	24.42 196	41.01 146	26.55 211	44.04 182	54.76 207	58.70 204	71.99 207	68.21 196

UniMVSNet (Re)		60.62 156	62.93 143	57.92 164	67.64 157	77.90 142	61.75 170	61.24 100	49.83 140	29.80 189	42.57 133	40.62 163	43.36 183	70.49 161	73.27 140	83.76 143	85.81 125

pm-mvs1		59.21 164	59.58 169	58.77 161	67.97 154	77.07 152	64.12 153	57.20 132	34.73 198	36.86 163	35.34 178	40.54 164	43.34 184	74.32 119	73.30 139	83.13 155	81.77 157

EG-PatchMatch MVS		58.73 168	58.03 175	59.55 154	72.32 128	80.49 119	63.44 163	55.55 152	32.49 202	38.31 157	28.87 197	37.22 175	42.84 185	74.30 120	75.70 107	84.84 122	77.14 171

MDA-MVSNet-bldmvs		44.15 205	42.27 210	46.34 200	38.34 216	62.31 206	46.28 202	55.74 149	29.83 206	20.98 202	27.11 201	16.45 222	41.98 186	41.11 214	57.47 205	74.72 202	61.65 210

UA-Net		64.62 123	68.23 109	60.42 149	77.53 94	81.38 109	60.08 176	57.47 130	47.01 150	44.75 123	60.68 67	71.32 47	41.84 187	73.27 129	72.25 152	80.83 179	71.68 189

pmmvs3		41.86 207	42.29 209	41.36 205	39.80 215	52.66 214	38.93 213	35.85 216	23.40 216	20.22 203	19.30 211	20.84 218	40.56 188	55.98 205	58.79 203	72.80 206	65.03 203

pmnet_mix02		53.92 186	53.30 188	54.65 182	61.89 187	71.33 183	54.54 189	54.17 165	40.38 178	34.65 175	34.76 182	30.68 205	40.44 189	60.97 193	63.71 193	82.19 167	71.24 192

pmmvs6		54.20 185	53.54 187	54.97 178	63.22 182	72.98 176	60.17 175	52.32 176	26.77 212	34.30 177	23.29 206	36.23 181	40.33 190	68.77 172	68.76 175	79.47 188	78.00 169

TransMVSNet (Re)		57.83 171	56.90 178	58.91 160	72.26 129	74.69 169	63.57 162	61.42 99	32.30 203	32.65 181	33.97 183	35.96 184	39.17 191	73.84 125	72.84 147	84.37 135	74.69 177

CVMVSNet		54.92 182	58.16 173	51.13 190	62.61 185	68.44 191	55.45 187	52.38 175	42.28 170	21.45 201	47.10 116	46.10 144	37.96 192	64.42 188	63.81 192	76.92 196	75.01 176

EPNet_dtu		66.17 113	70.13 96	61.54 144	81.04 67	77.39 149	68.87 130	62.50 89	69.78 67	33.51 180	63.77 56	56.22 107	37.65 193	72.20 142	72.18 153	85.69 100	79.38 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
N_pmnet		47.67 201	47.00 205	48.45 195	54.72 205	62.78 205	46.95 201	51.25 178	36.01 195	26.09 195	26.59 202	25.93 214	35.50 194	55.67 206	59.01 202	76.22 197	63.04 206

Vis-MVSNet (Re-imp)		62.25 143	68.74 103	54.68 180	73.70 121	78.74 133	56.51 185	57.49 129	55.22 121	26.86 193	54.56 84	61.35 81	31.06 195	73.10 131	74.90 115	82.49 162	83.31 143

Anonymous20231206		52.23 190	52.80 192	51.56 188	64.70 175	69.41 188	51.01 193	58.60 116	36.63 190	22.44 200	21.80 209	31.42 201	30.52 196	66.79 177	67.83 177	82.10 168	75.73 173

test0.0.03 1		57.35 175	59.89 167	54.38 183	71.37 134	73.45 174	52.71 191	61.03 101	46.11 156	26.33 194	41.73 141	44.08 149	29.72 197	71.43 152	70.90 164	85.10 113	71.56 190

CP-MVSNet		50.57 193	52.60 194	48.21 196	58.77 198	65.82 198	48.17 197	56.29 142	37.41 187	16.59 206	37.14 166	31.95 198	29.21 198	56.60 202	63.71 193	80.22 181	75.56 174

ambc			42.30 208		50.36 210	49.51 215	35.47 214		32.04 204	23.53 197	17.36 213	8.95 224	29.06 199	64.88 184	56.26 206	61.29 213	67.12 199

PS-CasMVS		50.17 194	52.02 195	48.02 197	58.60 199	65.54 199	48.04 198	56.19 145	36.42 192	16.42 208	35.68 177	31.33 202	28.85 200	56.42 204	63.54 195	80.01 182	75.18 175

PEN-MVS		51.04 191	52.94 190	48.82 193	61.45 189	66.00 197	48.68 196	57.20 132	36.87 188	15.36 209	36.98 168	32.72 196	28.77 201	57.63 199	66.37 184	81.44 174	74.00 180

FPMVS		39.11 209	36.39 211	42.28 204	55.97 203	45.94 216	46.23 203	41.57 206	35.73 196	22.61 198	23.46 205	19.82 219	28.32 202	43.57 211	40.67 213	58.96 214	45.54 214

new_pmnet		33.19 210	35.52 212	30.47 211	27.55 221	45.31 217	29.29 217	30.92 217	29.00 209	9.88 220	18.77 212	17.64 221	26.77 203	44.07 210	45.98 212	58.41 215	47.87 213

DTE-MVSNet		49.82 196	51.92 196	47.37 198	61.75 188	64.38 202	45.89 205	57.33 131	36.11 194	12.79 216	36.87 169	31.93 199	25.73 204	58.01 197	65.22 189	80.75 180	70.93 194

EU-MVSNet		44.84 204	47.85 204	41.32 207	49.26 211	56.59 212	43.07 208	47.64 188	33.03 200	13.82 212	36.78 170	30.99 203	24.37 205	53.80 208	55.57 208	69.78 209	68.21 196

test_method		28.15 212	34.48 213	20.76 214	6.76 225	21.18 221	21.03 219	18.41 220	36.77 189	17.52 204	15.67 217	31.63 200	24.05 206	41.03 215	26.69 217	36.82 219	68.38 195

WR-MVS		51.02 192	54.56 184	46.90 199	63.84 178	69.23 189	44.78 206	56.38 141	38.19 186	14.19 211	37.38 164	36.82 178	22.39 207	60.14 195	66.20 187	79.81 184	73.95 181

WR-MVS_H		49.62 197	52.63 193	46.11 202	58.80 197	67.58 193	46.14 204	54.94 157	36.51 191	13.63 214	36.75 171	35.67 186	22.10 208	56.43 203	62.76 197	81.06 176	72.73 186

DeepMVS_CX						19.81 223	17.01 221	10.02 221	23.61 215	5.85 222	17.21 214	8.03 225	21.13 209	22.60 218		21.42 223	30.01 217

PMVS	27.44 18	32.08 211	29.07 214	35.60 210	48.33 213	24.79 219	26.97 218	41.34 208	20.45 218	22.50 199	17.11 215	18.64 220	20.44 210	41.99 213	38.06 214	54.02 216	42.44 215
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testgi		48.51 200	50.53 198	46.16 201	64.78 173	67.15 195	41.54 209	54.81 161	29.12 208	17.03 205	32.07 189	31.98 197	20.15 211	65.26 182	67.00 182	78.67 191	61.10 211

new-patchmatchnet		42.21 206	42.97 207	41.33 206	53.05 207	59.89 208	39.38 211	49.61 180	28.26 210	12.10 217	22.17 208	21.54 216	19.22 212	50.96 209	56.04 207	74.61 203	61.92 209

MIMVSNet1		40.84 208	43.46 206	37.79 209	32.14 217	58.92 210	39.24 212	50.83 179	27.00 211	11.29 218	16.76 216	26.53 212	17.75 213	57.14 201	61.12 201	75.46 199	56.78 212

test20.03		47.23 203	48.69 203	45.53 203	63.28 180	64.39 201	41.01 210	56.93 137	29.16 207	15.21 210	23.90 203	30.76 204	17.51 214	64.63 186	65.26 188	79.21 189	62.71 208

FC-MVSNet-test		47.24 202	54.37 185	38.93 208	59.49 195	58.25 211	34.48 215	53.36 170	45.66 158	6.66 221	50.62 98	42.02 152	16.62 215	58.39 196	61.21 200	62.99 212	64.40 204

Gipuma		24.91 213	24.61 215	25.26 213	31.47 218	21.59 220	18.06 220	37.53 213	25.43 214	10.03 219	4.18 222	4.25 226	14.85 216	43.20 212	47.03 211	39.62 218	26.55 219
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		14.40 216	10.71 219	18.70 216	28.15 220	12.09 225	7.06 224	36.89 214	11.00 221	3.56 225	4.95 220	2.27 228	13.91 217	10.13 221	16.06 220	22.63 222	18.51 221

E-PMN		15.08 215	11.65 218	19.08 215	28.73 219	12.31 224	6.95 225	36.87 215	10.71 222	3.63 224	5.13 219	2.22 229	13.81 218	11.34 220	18.50 219	24.49 221	21.32 220

MVE	15.98 19	14.37 217	16.36 217	12.04 219	7.72 224	20.24 222	5.90 226	29.05 218	8.28 223	3.92 223	4.72 221	2.42 227	9.57 219	18.89 219	31.46 216	16.07 224	28.53 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				16.09 218	13.07 223	8.12 226	13.61 223	2.08 222	55.09 122	30.10 188	40.26 151	22.83 215	5.35 220	29.91 216	25.25 218	32.33 220

PMMVS2		20.45 214	22.31 216	18.27 217	20.52 222	26.73 218	14.85 222	28.43 219	13.69 220	0.79 226	10.35 218	9.10 223	3.83 221	27.64 217	32.87 215	41.17 217	35.81 216

GG-mvs-BLEND		54.54 183	77.58 50	27.67 212	0.03 226	90.09 30	77.20 69	0.02 223	66.83 75	0.05 227	59.90 70	73.33 37	0.04 222	78.40 81	79.30 73	88.65 22	95.20 27

test123		0.05 218	0.08 220	0.01 220	0.00 227	0.01 227	0.01 229	0.00 225	0.05 224	0.00 228	0.16 223	0.00 231	0.04 222	0.02 223	0.05 221	0.00 226	0.26 222

testmvs		0.05 218	0.08 220	0.01 220	0.00 227	0.01 227	0.03 228	0.01 224	0.05 224	0.00 228	0.14 224	0.01 230	0.03 224	0.05 222	0.05 221	0.01 225	0.24 223

uanet_test		0.00 220	0.00 222	0.00 222	0.00 227	0.00 229	0.00 230	0.00 225	0.00 226	0.00 228	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 226	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 222	0.00 227	0.00 229	0.00 230	0.00 225	0.00 226	0.00 228	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 226	0.00 224

sosnet		0.00 220	0.00 222	0.00 222	0.00 227	0.00 229	0.00 230	0.00 225	0.00 226	0.00 228	0.00 225	0.00 231	0.00 225	0.00 224	0.00 223	0.00 226	0.00 224

RE-MVS-def										31.47 184

9.14												84.47 7

SR-MVS					86.33 48			67.54 47				80.78 20

our_test_3					63.32 179	71.07 186	55.90 186

MTAPA										78.32 12		79.42 25

MTMP										76.04 17		76.65 30

Patchmatch-RL test							2.17 227

XVS					82.43 57	86.27 70	75.70 72			61.07 62		72.27 40				85.67 101

X-MVStestdata					82.43 57	86.27 70	75.70 72			61.07 62		72.27 40				85.67 101

mPP-MVS					86.96 43							70.61 50

NP-MVS									81.60 37

Patchmtry						78.06 141	67.53 138	43.18 200		41.40 140

High-resolution multi-view benchmark