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.

MSP-MVS		88.07 1	90.73 1	84.97 3	91.98 8	95.01 1	87.86 8	76.88 6	93.90 1	85.15 1	90.11 7	86.90 1	79.46 10	86.26 9	84.67 16	88.50 27	98.25 2

DVP-MVS		87.87 2	90.57 2	84.73 4	89.38 26	91.60 16	88.24 6	74.15 11	93.55 2	82.28 2	94.99 1	83.21 9	85.96 1	87.67 4	84.67 16	88.32 30	98.29 1

DPE-MVS		87.60 3	90.44 3	84.29 6	92.09 7	93.44 4	88.69 4	75.11 8	93.06 4	80.80 4	94.23 2	86.70 2	81.44 4	84.84 16	83.52 25	87.64 45	97.28 5

SF-MVS		87.30 4	88.71 4	85.64 1	94.57 1	94.55 2	91.01 1	79.94 1	89.15 10	79.85 5	92.37 3	83.29 8	79.75 6	83.52 24	82.72 30	88.75 19	95.37 23

APDe-MVS		86.37 5	88.41 6	84.00 8	91.43 13	91.83 14	88.34 5	74.67 9	91.19 5	81.76 3	91.13 5	81.94 16	80.07 5	83.38 26	82.58 33	87.69 43	96.78 10

CNVR-MVS		85.96 6	87.58 9	84.06 7	92.58 5	92.40 9	87.62 9	77.77 5	88.44 13	75.93 16	79.49 24	81.97 15	81.65 3	87.04 6	86.58 4	88.79 17	97.18 7

MCST-MVS		85.75 7	86.99 11	84.31 5	94.07 3	92.80 6	88.15 7	79.10 3	85.66 22	70.72 29	76.50 31	80.45 19	82.17 2	88.35 2	87.49 3	91.63 2	97.65 3

HPM-MVS++		85.64 8	88.43 5	82.39 11	92.65 4	90.24 25	85.83 15	74.21 10	90.68 7	75.63 17	86.77 12	84.15 6	78.68 14	86.33 7	85.26 9	87.32 52	95.60 18

DPM-MVS		85.41 9	86.72 14	83.89 9	91.66 11	91.92 13	90.49 3	78.09 4	86.90 17	73.95 19	74.52 33	82.01 14	79.29 11	90.24 1	90.65 1	89.86 6	90.78 70

SMA-MVS		85.24 10	88.27 7	81.72 14	91.74 10	90.71 19	86.71 11	73.16 18	90.56 8	74.33 18	83.07 17	85.88 3	77.16 18	86.28 8	85.58 6	87.23 56	95.77 14

APD-MVS		84.83 11	87.00 10	82.30 12	89.61 24	89.21 33	86.51 13	73.64 15	90.98 6	77.99 11	89.89 8	80.04 22	79.18 12	82.00 45	81.37 46	86.88 64	95.49 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		84.39 12	86.58 15	81.83 13	88.09 38	86.47 63	85.63 17	73.62 16	90.13 9	79.24 8	89.67 9	82.99 10	77.72 16	81.22 51	80.92 57	86.68 67	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
xxxxxxxxxxxxxcwj		84.33 13	83.20 25	85.64 1	94.57 1	94.55 2	91.01 1	79.94 1	89.15 10	79.85 5	92.37 3	44.71 139	79.75 6	83.52 24	82.72 30	88.75 19	95.37 23

SD-MVS		84.31 14	86.96 12	81.22 15	88.98 30	88.68 37	85.65 16	73.85 14	89.09 12	79.63 7	87.34 11	84.84 4	73.71 33	82.66 33	81.60 43	85.48 99	94.51 31
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
NCCC		84.16 15	85.46 19	82.64 10	92.34 6	90.57 22	86.57 12	76.51 7	86.85 19	72.91 22	77.20 30	78.69 25	79.09 13	84.64 18	84.88 14	88.44 28	95.41 21

ACMMP_NAP		83.54 16	86.37 16	80.25 20	89.57 25	90.10 27	85.27 19	71.66 22	87.38 14	73.08 21	84.23 16	80.16 20	75.31 24	84.85 15	83.64 22	86.57 68	94.21 37

train_agg		83.35 17	86.93 13	79.17 26	89.70 22	88.41 40	85.60 18	72.89 20	86.31 20	66.58 40	90.48 6	82.24 13	73.06 39	83.10 29	82.64 32	87.21 60	95.30 25

DeepPCF-MVS	76.94 1	83.08 18	87.77 8	77.60 34	90.11 18	90.96 18	78.48 53	72.63 21	93.10 3	65.84 41	80.67 22	81.55 17	74.80 28	85.94 11	85.39 8	83.75 136	96.77 11

CSCG		82.90 19	84.52 21	81.02 17	91.85 9	93.43 5	87.14 10	74.01 13	81.96 32	76.14 14	70.84 37	82.49 11	69.71 60	82.32 40	85.18 11	87.26 55	95.40 22

SteuartSystems-ACMMP		82.51 20	85.35 20	79.20 25	90.25 16	89.39 32	84.79 20	70.95 24	82.86 28	68.32 37	86.44 13	77.19 26	73.07 38	83.63 23	83.64 22	87.82 39	94.34 33
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		82.48 21	84.12 22	80.56 18	90.15 17	87.55 53	84.28 22	69.67 33	85.22 23	77.95 12	84.69 15	75.94 29	75.04 26	81.85 46	81.17 51	86.30 73	92.40 54

TSAR-MVS + GP.		82.27 22	85.98 17	77.94 32	80.72 70	88.25 43	81.12 42	67.71 44	87.10 15	73.31 20	85.23 14	83.68 7	76.64 20	80.43 59	81.47 45	88.15 36	95.66 17

DeepC-MVS_fast	75.41 2	81.69 23	82.10 32	81.20 16	91.04 15	87.81 50	83.42 26	74.04 12	83.77 26	71.09 27	66.88 46	72.44 37	79.48 9	85.08 13	84.97 13	88.12 38	93.78 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		81.65 24	83.10 26	79.97 22	88.14 37	87.62 52	83.96 25	69.90 30	86.92 16	77.67 13	72.47 35	78.74 24	74.13 32	81.59 49	81.15 52	86.01 81	93.19 47

TSAR-MVS + ACMM		81.59 25	85.84 18	76.63 38	89.82 21	86.53 62	86.32 14	66.72 51	85.96 21	65.43 42	88.98 10	82.29 12	67.57 77	82.06 44	81.33 47	83.93 134	93.75 42

MP-MVS		80.94 26	83.49 24	77.96 31	88.48 31	88.16 44	82.82 31	69.34 35	80.79 38	69.67 33	82.35 19	77.13 27	71.60 50	80.97 56	80.96 56	85.87 85	94.06 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		80.90 27	82.93 28	78.53 30	86.83 44	92.26 10	81.19 41	66.95 48	81.60 35	69.90 32	66.93 45	74.80 31	76.79 19	84.68 17	84.77 15	89.50 9	95.50 19

ACMMPR		80.62 28	82.98 27	77.87 33	88.41 32	87.05 58	83.02 28	69.18 36	83.91 25	68.35 36	82.89 18	73.64 34	72.16 45	80.78 57	81.13 53	86.10 78	91.43 61

DeepC-MVS	74.46 3	80.30 29	81.05 35	79.42 23	87.42 40	88.50 39	83.23 27	73.27 17	82.78 29	71.01 28	62.86 56	69.93 50	74.80 28	84.30 19	84.20 19	86.79 66	94.77 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		79.49 30	79.84 40	79.08 27	88.26 36	92.49 7	84.12 24	70.63 26	65.27 79	69.60 35	61.29 61	66.50 59	72.75 41	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
CP-MVS		79.44 31	81.51 34	77.02 37	86.95 42	85.96 69	82.00 33	68.44 41	81.82 33	67.39 38	77.43 28	73.68 33	71.62 49	79.56 65	79.58 64	85.73 89	92.51 53

MVS_0304		79.43 32	82.20 30	76.20 41	84.22 52	91.79 15	81.82 36	63.81 69	76.83 50	61.71 54	66.37 48	75.52 30	76.38 22	85.54 12	85.03 12	89.28 11	94.32 34

PHI-MVS		79.43 32	84.06 23	74.04 55	86.15 47	91.57 17	80.85 45	68.90 39	82.22 31	51.81 88	78.10 26	74.28 32	70.39 57	84.01 22	84.00 20	86.14 77	94.24 35

PGM-MVS		79.42 34	81.84 33	76.60 39	88.38 34	86.69 60	82.97 30	65.75 57	80.39 39	64.94 43	81.95 21	72.11 42	71.41 51	80.45 58	80.55 61	86.18 75	90.76 72

CDPH-MVS		79.39 35	82.13 31	76.19 42	89.22 29	88.34 41	84.20 23	71.00 23	79.67 42	56.97 73	77.77 27	72.24 41	68.50 72	81.33 50	82.74 28	87.23 56	92.84 50

EPNet		79.28 36	82.25 29	75.83 44	88.31 35	90.14 26	79.43 51	68.07 42	81.76 34	61.26 56	77.26 29	70.08 49	70.06 58	82.43 38	82.00 37	87.82 39	92.09 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		78.57 37	77.33 50	80.02 21	88.39 33	84.79 75	84.62 21	66.17 55	75.96 52	78.40 9	61.59 59	71.47 44	73.54 36	78.43 73	78.88 70	88.97 14	90.18 78

3Dnovator	70.49 5	78.42 38	76.77 55	80.35 19	91.43 13	90.27 24	81.84 35	70.79 25	72.10 56	71.95 23	50.02 96	67.86 55	77.47 17	82.89 30	84.24 18	88.61 23	89.99 79

HQP-MVS		78.26 39	80.91 36	75.17 49	85.67 49	84.33 81	83.01 29	69.38 34	79.88 41	55.83 74	79.85 23	64.90 64	70.81 53	82.46 36	81.78 39	86.30 73	93.18 48

X-MVS		78.16 40	80.55 37	75.38 47	87.99 39	86.27 65	81.05 43	68.98 37	78.33 44	61.07 58	75.25 32	72.27 38	67.52 78	80.03 61	80.52 62	85.66 96	91.20 65

3Dnovator+	70.16 6	77.87 41	77.29 51	78.55 29	89.25 28	88.32 42	80.09 47	67.95 43	74.89 55	71.83 25	52.05 90	70.68 47	76.27 23	82.27 41	82.04 35	85.92 82	90.77 71

canonicalmvs		77.65 42	79.59 41	75.39 46	81.52 63	89.83 31	81.32 40	60.74 102	80.05 40	66.72 39	68.43 41	65.09 62	74.72 30	78.87 69	82.73 29	87.32 52	92.16 55

ACMMP		77.61 43	79.59 41	75.30 48	85.87 48	85.58 70	81.42 38	67.38 47	79.38 43	62.61 49	78.53 25	65.79 61	68.80 71	78.56 72	78.50 74	85.75 86	90.80 69
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
QAPM		77.50 44	77.43 49	77.59 35	91.52 12	92.00 12	81.41 39	70.63 26	66.22 72	58.05 68	54.70 78	71.79 43	74.49 31	82.46 36	82.04 35	89.46 10	92.79 52

MVS_111021_HR		77.42 45	78.40 46	76.28 40	86.95 42	90.68 20	77.41 62	70.56 29	66.21 73	62.48 51	66.17 49	63.98 66	72.08 46	82.87 31	83.15 26	88.24 33	95.71 16

CLD-MVS		77.36 46	77.29 51	77.45 36	82.21 59	88.11 45	81.92 34	68.96 38	77.97 46	69.62 34	62.08 57	59.44 88	73.57 35	81.75 47	81.27 49	88.41 29	90.39 75
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MAR-MVS		77.19 47	78.37 47	75.81 45	89.87 20	90.58 21	79.33 52	65.56 59	77.62 48	58.33 67	59.24 69	67.98 53	74.83 27	82.37 39	83.12 27	86.95 62	87.67 104
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
MVSTER		76.92 48	79.92 39	73.42 58	74.98 108	82.97 88	78.15 56	63.41 73	78.02 45	64.41 45	67.54 43	72.80 36	71.05 52	83.29 28	83.73 21	88.53 26	91.12 66

PVSNet_BlendedMVS		76.84 49	78.47 44	74.95 50	82.37 57	89.90 29	75.45 73	65.45 60	74.99 53	70.66 30	63.07 54	58.27 95	67.60 75	84.24 20	81.70 41	88.18 34	97.10 8

PVSNet_Blended		76.84 49	78.47 44	74.95 50	82.37 57	89.90 29	75.45 73	65.45 60	74.99 53	70.66 30	63.07 54	58.27 95	67.60 75	84.24 20	81.70 41	88.18 34	97.10 8

ETV-MVS		76.25 51	80.22 38	71.63 68	78.23 81	87.95 49	72.75 90	60.27 106	77.50 49	57.73 69	71.53 36	66.60 58	73.16 37	80.99 55	81.23 50	87.63 46	95.73 15

AdaColmap		76.23 52	73.55 70	79.35 24	89.38 26	85.00 74	79.99 49	73.04 19	76.60 51	71.17 26	55.18 77	57.99 97	77.87 15	76.82 86	76.82 87	84.67 121	86.45 111

PCF-MVS	70.85 4	75.73 53	76.55 58	74.78 53	83.67 53	88.04 48	81.47 37	70.62 28	69.24 67	57.52 71	60.59 65	69.18 51	70.65 55	77.11 83	77.65 81	84.75 119	94.01 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CPTT-MVS		75.43 54	77.13 53	73.44 57	81.43 64	82.55 92	80.96 44	64.35 65	77.95 47	61.39 55	69.20 40	70.94 46	69.38 67	73.89 115	73.32 129	83.14 146	92.06 57

MVS_Test		75.22 55	76.69 56	73.51 56	79.30 76	88.82 36	80.06 48	58.74 110	69.77 63	57.50 72	59.78 68	61.35 77	75.31 24	82.07 43	83.60 24	90.13 5	91.41 63

casdiffmvs		75.20 56	75.69 62	74.63 54	79.26 77	89.07 34	78.47 54	63.59 72	67.05 70	63.79 46	55.72 75	60.32 83	73.58 34	82.16 42	81.78 39	89.08 13	93.72 43

CS-MVS		75.18 57	78.59 43	71.20 69	77.74 85	87.69 51	73.93 87	58.81 109	69.17 68	55.73 75	67.86 42	66.89 56	72.87 40	82.50 34	81.29 48	88.15 36	94.71 29

OpenMVS	67.62 8	74.92 58	73.91 68	76.09 43	90.10 19	90.38 23	78.01 57	66.35 53	66.09 74	62.80 48	46.33 119	64.55 65	71.77 48	79.92 62	80.88 58	87.52 48	89.20 88

diffmvs		74.32 59	75.42 63	73.04 60	75.60 105	87.27 55	78.20 55	62.96 77	68.66 69	61.89 52	59.79 67	59.84 86	71.80 47	78.30 76	79.87 63	87.80 41	94.23 36

MVS_111021_LR		74.26 60	75.95 60	72.27 64	79.43 75	85.04 73	72.71 91	65.27 62	70.92 59	63.58 47	69.32 39	60.31 84	69.43 65	77.01 84	77.15 84	83.22 143	91.93 59

OMC-MVS		74.03 61	75.82 61	71.95 66	79.56 73	80.98 106	75.35 75	63.21 74	84.48 24	61.83 53	61.54 60	66.89 56	69.41 66	76.60 87	74.07 119	82.34 156	86.15 114

DI_MVS_plusplus_trai		73.94 62	74.85 65	72.88 61	76.57 97	86.80 59	80.41 46	61.47 93	62.35 84	59.44 65	47.91 102	68.12 52	72.24 44	82.84 32	81.50 44	87.15 61	94.42 32

EIA-MVS		73.48 63	76.05 59	70.47 75	78.12 82	87.21 56	71.78 96	60.63 103	69.66 64	55.56 78	64.86 51	60.69 80	69.53 63	77.35 82	78.59 71	87.22 58	94.01 39

TSAR-MVS + COLMAP		73.09 64	76.86 54	68.71 85	74.97 109	82.49 93	74.51 84	61.83 89	83.16 27	49.31 100	82.22 20	51.62 123	68.94 70	78.76 71	75.52 104	82.67 151	84.23 129

baseline		72.89 65	74.46 67	71.07 70	75.99 101	87.50 54	74.57 79	60.49 104	70.72 60	57.60 70	60.63 64	60.97 79	70.79 54	75.27 100	76.33 93	86.94 63	89.79 82

CANet_DTU		72.84 66	76.63 57	68.43 88	76.81 95	86.62 61	75.54 72	54.71 154	72.06 57	43.54 121	67.11 44	58.46 92	72.40 43	81.13 54	80.82 59	87.57 47	90.21 77

OPM-MVS		72.74 67	70.93 86	74.85 52	85.30 50	84.34 80	82.82 31	69.79 31	49.96 131	55.39 80	54.09 85	60.14 85	70.04 59	80.38 60	79.43 65	85.74 88	88.20 100

CHOSEN 1792x2688		72.55 68	71.98 77	73.22 59	86.57 45	92.41 8	75.63 69	66.77 50	62.08 85	52.32 85	30.27 184	50.74 126	66.14 81	86.22 10	85.41 7	91.90 1	96.75 12

CostFormer		72.18 69	73.90 69	70.18 77	79.47 74	86.19 68	76.94 65	48.62 172	66.07 75	60.40 63	54.14 84	65.82 60	67.98 73	75.84 95	76.41 92	87.67 44	92.83 51

ACMP	68.86 7	72.15 70	72.25 75	72.03 65	80.96 66	80.87 108	77.93 58	64.13 67	69.29 65	60.79 61	64.04 52	53.54 118	63.91 90	73.74 118	75.27 105	84.45 126	88.98 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		72.02 71	73.18 73	70.67 74	82.13 60	80.26 114	79.58 50	63.04 76	70.09 61	51.98 86	65.06 50	55.62 108	62.49 100	75.97 94	76.32 94	84.80 118	88.93 91

PVSNet_Blended_VisFu		71.76 72	73.54 71	69.69 78	79.01 78	87.16 57	72.05 93	61.80 90	56.46 105	59.66 64	53.88 86	62.48 69	59.08 122	81.17 52	78.90 69	86.53 70	94.74 28

baseline1		71.47 73	72.02 76	70.82 72	80.56 71	84.51 77	76.61 66	66.93 49	56.22 107	48.66 101	55.40 76	60.43 82	62.55 99	83.35 27	80.99 54	89.60 7	83.28 137

TAPA-MVS	67.10 9	71.45 74	73.47 72	69.10 83	77.04 93	80.78 109	73.81 88	62.10 85	80.80 37	51.28 89	60.91 62	63.80 68	67.98 73	74.59 106	72.42 141	82.37 155	80.97 151
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ET-MVSNet_ETH3D		71.38 75	74.70 66	67.51 94	51.61 199	88.06 47	77.29 63	60.95 101	63.61 81	48.36 103	66.60 47	60.67 81	79.55 8	73.56 119	80.58 60	87.30 54	89.80 81

CNLPA		71.37 76	70.27 90	72.66 63	80.79 69	81.33 102	71.07 108	65.75 57	82.36 30	64.80 44	42.46 130	56.49 102	72.70 42	73.00 126	70.52 160	80.84 168	85.76 119

baseline2		71.22 77	73.01 74	69.13 82	75.76 103	86.34 64	71.23 103	62.78 83	62.62 82	52.85 84	57.32 71	54.31 113	63.27 95	79.74 63	79.31 66	88.89 15	91.43 61

Effi-MVS+		70.42 78	71.23 83	69.47 79	78.04 83	85.24 72	75.57 71	58.88 108	59.56 93	48.47 102	52.73 89	54.94 111	69.69 61	78.34 75	77.06 85	86.18 75	90.73 73

ACMM	66.70 10	70.42 78	68.49 99	72.67 62	82.85 54	77.76 136	77.70 60	64.76 64	64.61 80	60.74 62	49.29 97	53.97 116	65.86 82	74.97 102	75.57 103	84.13 133	83.29 136
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet3		70.41 80	71.89 79	68.68 86	70.89 130	79.42 121	75.63 69	60.97 98	65.32 76	51.06 90	47.37 107	62.05 71	64.90 86	82.49 35	82.27 34	88.64 22	84.34 128

PMMVS		70.37 81	75.06 64	64.90 106	71.46 124	81.88 94	64.10 145	55.64 141	71.31 58	46.69 107	70.69 38	58.56 89	69.53 63	79.03 68	75.63 101	81.96 159	88.32 99

MS-PatchMatch		70.34 82	69.00 95	71.91 67	85.20 51	85.35 71	77.84 59	61.77 91	58.01 99	55.40 79	41.26 137	58.34 94	61.69 103	81.70 48	78.29 75	89.56 8	80.02 154

GBi-Net		69.21 83	70.40 88	67.81 91	69.49 135	78.65 126	74.54 80	60.97 98	65.32 76	51.06 90	47.37 107	62.05 71	63.43 92	77.49 78	78.22 76	87.37 49	83.73 131

test1		69.21 83	70.40 88	67.81 91	69.49 135	78.65 126	74.54 80	60.97 98	65.32 76	51.06 90	47.37 107	62.05 71	63.43 92	77.49 78	78.22 76	87.37 49	83.73 131

DCV-MVSNet		69.13 85	69.07 94	69.21 81	77.65 88	77.52 138	74.68 78	57.85 120	54.92 116	55.34 81	55.74 74	55.56 109	66.35 80	75.05 101	76.56 90	83.35 140	88.13 101

IB-MVS	64.48 11	69.02 86	68.97 96	69.09 84	81.75 62	89.01 35	64.50 143	64.91 63	56.65 103	62.59 50	47.89 103	45.23 137	51.99 147	69.18 162	81.88 38	88.77 18	92.93 49
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
FC-MVSNet-train		68.83 87	68.29 100	69.47 79	78.35 80	79.94 115	64.72 142	66.38 52	54.96 115	54.51 82	56.75 72	47.91 132	66.91 79	75.57 99	75.75 99	85.92 82	87.12 106

PLC	64.00 12	68.54 88	66.66 110	70.74 73	80.28 72	74.88 157	72.64 92	63.70 71	69.26 66	55.71 76	47.24 110	55.31 110	70.42 56	72.05 137	70.67 158	81.66 162	77.19 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Anonymous20231211		68.44 89	66.37 113	70.86 71	77.58 89	83.49 86	75.15 76	61.89 88	52.54 124	58.50 66	28.89 186	56.78 101	69.29 68	74.96 104	76.61 88	82.73 149	91.36 64

HyFIR lowres test		68.39 90	68.28 101	68.52 87	80.85 67	88.11 45	71.08 107	58.09 115	54.87 118	47.80 106	27.55 190	55.80 106	64.97 85	79.11 67	79.14 68	88.31 31	93.35 44

thisisatest0530		68.38 91	70.98 85	65.35 102	72.61 118	84.42 78	68.21 124	57.98 116	59.77 92	50.80 93	54.63 79	58.48 91	57.92 128	76.99 85	77.47 82	84.60 122	85.07 122

test-LLR		68.23 92	71.61 81	64.28 113	71.37 125	81.32 103	63.98 148	61.03 96	58.62 96	42.96 126	52.74 87	61.65 75	57.74 131	75.64 97	78.09 79	88.61 23	93.21 45

FMVSNet2		68.06 93	68.57 98	67.45 95	69.49 135	78.65 126	74.54 80	60.23 107	56.29 106	49.64 99	42.13 133	57.08 100	63.43 92	81.15 53	80.99 54	87.37 49	83.73 131

tttt0517		67.99 94	70.61 87	64.94 105	71.94 123	83.96 84	67.62 128	57.98 116	59.30 94	49.90 98	54.50 82	57.98 98	57.92 128	76.48 88	77.47 82	84.24 129	84.58 125

Fast-Effi-MVS+		67.59 95	67.56 105	67.62 93	73.67 113	81.14 105	71.12 106	54.79 153	58.88 95	50.61 95	46.70 117	47.05 133	69.12 69	76.06 93	76.44 91	86.43 71	86.65 109

EPP-MVSNet		67.58 96	71.10 84	63.48 119	75.71 104	83.35 87	66.85 134	57.83 121	53.02 123	41.15 135	55.82 73	67.89 54	56.01 137	74.40 108	72.92 137	83.33 141	90.30 76

UGNet		67.57 97	71.69 80	62.76 126	69.88 133	82.58 91	66.43 138	58.64 111	54.71 119	51.87 87	61.74 58	62.01 74	45.46 170	74.78 105	74.99 106	84.24 129	91.02 67
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
tpm cat1		67.47 98	67.05 108	67.98 90	76.63 96	81.51 100	74.49 85	47.65 177	61.18 87	61.12 57	42.51 129	53.02 121	64.74 88	70.11 156	71.50 147	83.22 143	89.49 84

TESTMET0.1,1		67.38 99	71.61 81	62.45 129	66.05 158	81.32 103	63.98 148	55.36 146	58.62 96	42.96 126	52.74 87	61.65 75	57.74 131	75.64 97	78.09 79	88.61 23	93.21 45

IS_MVSNet		67.29 100	71.98 77	61.82 133	76.92 94	84.32 82	65.90 141	58.22 113	55.75 111	39.22 143	54.51 81	62.47 70	45.99 168	78.83 70	78.52 73	84.70 120	89.47 85

tpmrst		67.15 101	68.12 103	66.03 100	76.21 99	80.98 106	71.27 102	45.05 183	60.69 90	50.63 94	46.95 115	54.15 115	65.30 83	71.80 139	71.77 145	87.72 42	90.48 74

thres100view900		67.14 102	66.09 116	68.38 89	77.70 86	83.84 85	74.52 83	66.33 54	49.16 135	43.40 123	43.24 122	41.34 145	62.59 98	79.31 66	75.92 98	85.73 89	89.81 80

EPMVS		66.21 103	67.49 106	64.73 107	75.81 102	84.20 83	68.94 120	44.37 187	61.55 86	48.07 105	49.21 99	54.87 112	62.88 96	71.82 138	71.40 151	88.28 32	79.37 157

EPNet_dtu		66.17 104	70.13 91	61.54 135	81.04 65	77.39 140	68.87 121	62.50 84	69.78 62	33.51 170	63.77 53	56.22 103	37.65 183	72.20 134	72.18 144	85.69 92	79.38 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-LS		66.08 105	66.56 112	65.51 101	73.67 113	74.88 157	70.89 110	53.55 159	50.42 129	48.32 104	50.59 94	55.66 107	61.83 102	73.93 114	74.42 115	84.82 117	86.01 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		65.90 106	64.96 120	67.00 97	77.70 86	81.58 98	71.71 98	62.94 80	49.16 135	43.40 123	43.24 122	41.34 145	61.42 105	76.24 90	74.63 111	84.84 114	88.52 97

thres200		65.58 107	64.74 122	66.56 98	77.52 91	81.61 96	73.44 89	62.95 78	46.23 147	42.45 130	42.76 124	41.18 147	58.12 126	76.24 90	75.59 102	84.89 112	89.58 83

MSDG		65.57 108	61.57 145	70.24 76	82.02 61	76.47 145	74.46 86	68.73 40	56.52 104	50.33 96	38.47 150	41.10 149	62.42 101	72.12 135	72.94 136	83.47 139	73.37 176

Vis-MVSNet		65.53 109	69.83 92	60.52 139	70.80 131	84.59 76	66.37 140	55.47 145	48.40 138	40.62 139	57.67 70	58.43 93	45.37 171	77.49 78	76.24 95	84.47 125	85.99 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchmatchNet		65.43 110	67.71 104	62.78 125	73.49 115	82.83 89	66.42 139	45.40 182	60.40 91	45.27 112	49.22 98	57.60 99	60.01 114	70.61 148	71.38 152	86.08 79	81.91 148
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		65.21 111	67.28 107	62.79 124	70.91 129	81.72 95	69.28 119	49.50 171	58.08 98	43.94 120	50.50 95	56.02 104	58.86 123	70.72 147	73.37 127	84.24 129	80.52 153

thres400		65.18 112	64.44 124	66.04 99	76.40 98	82.63 90	71.52 100	64.27 66	44.93 153	40.69 138	41.86 134	40.79 151	58.12 126	77.67 77	74.64 110	85.26 102	88.56 96

tpm		64.85 113	66.02 117	63.48 119	74.52 110	78.38 129	70.98 109	44.99 185	51.61 126	43.28 125	47.66 105	53.18 119	60.57 109	70.58 150	71.30 154	86.54 69	89.45 86

UA-Net		64.62 114	68.23 102	60.42 140	77.53 90	81.38 101	60.08 167	57.47 126	47.01 142	44.75 116	60.68 63	71.32 45	41.84 178	73.27 121	72.25 143	80.83 169	71.68 181

Effi-MVS+-dtu		64.58 115	64.08 125	65.16 103	73.04 117	75.17 156	70.68 112	56.23 135	54.12 121	44.71 117	47.42 106	51.10 124	63.82 91	68.08 165	66.32 176	82.47 154	86.38 112

GA-MVS		64.55 116	65.76 119	63.12 121	69.68 134	81.56 99	69.59 116	58.16 114	45.23 152	35.58 163	47.01 114	41.82 144	59.41 118	79.62 64	78.54 72	86.32 72	86.56 110

LS3D		64.54 117	62.14 141	67.34 96	80.85 67	75.79 151	69.99 113	65.87 56	60.77 89	44.35 118	42.43 131	45.95 136	65.01 84	69.88 157	68.69 167	77.97 183	71.43 183

CDS-MVSNet		64.22 118	65.89 118	62.28 131	70.05 132	80.59 110	69.91 115	57.98 116	43.53 157	46.58 108	48.22 101	50.76 125	46.45 165	75.68 96	76.08 96	82.70 150	86.34 113
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
dps		64.08 119	63.22 129	65.08 104	75.27 107	79.65 118	66.68 136	46.63 181	56.94 101	55.67 77	43.96 121	43.63 142	64.00 89	69.50 161	69.82 162	82.25 157	79.02 158

test-mter		64.06 120	69.24 93	58.01 154	59.07 186	77.40 139	59.13 170	48.11 175	55.64 112	39.18 144	51.56 92	58.54 90	55.38 139	73.52 120	76.00 97	87.22 58	92.05 58

SCA		63.90 121	66.67 109	60.66 138	73.75 111	71.78 172	59.87 168	43.66 188	61.13 88	45.03 114	51.64 91	59.45 87	57.92 128	70.96 145	70.80 156	83.71 137	80.92 152

thres600view7		63.77 122	63.14 130	64.51 109	75.49 106	81.61 96	69.59 116	62.95 78	43.96 156	38.90 145	41.09 138	40.24 156	55.25 140	76.24 90	71.54 146	84.89 112	87.30 105

v2v482		63.68 123	62.85 135	64.65 108	68.01 144	80.46 112	71.90 94	57.60 123	44.26 154	42.82 128	39.80 146	38.62 161	61.56 104	73.06 124	74.86 108	86.03 80	88.90 93

FMVSNet1		63.48 124	63.07 131	63.97 115	65.31 163	76.37 147	71.77 97	57.90 119	43.32 158	45.66 110	35.06 173	49.43 128	58.57 124	77.49 78	78.22 76	84.59 123	81.60 150

v8		63.44 125	62.58 137	64.43 110	68.28 143	78.07 131	71.82 95	54.85 151	46.70 145	45.20 113	39.40 147	40.91 150	60.54 110	72.85 128	74.39 116	85.92 82	85.76 119

pmmvs4		63.14 126	62.46 138	63.94 116	66.03 159	76.40 146	66.82 135	57.60 123	56.74 102	50.26 97	40.81 141	37.51 164	59.26 120	71.75 140	71.48 148	83.68 138	82.53 142

Fast-Effi-MVS+-dtu		63.05 127	64.72 123	61.11 136	71.21 128	76.81 144	70.72 111	43.13 192	52.51 125	35.34 164	46.55 118	46.36 134	61.40 106	71.57 142	71.44 149	84.84 114	87.79 103

v1144		63.00 128	62.39 139	63.70 118	67.72 147	80.27 113	71.23 103	56.40 132	42.51 159	40.81 137	38.12 154	37.73 162	60.42 112	74.46 107	74.55 113	85.64 97	89.12 89

v10		63.00 128	62.22 140	63.90 117	67.88 146	77.78 135	71.59 99	54.34 155	45.37 151	42.76 129	38.53 149	38.93 159	61.05 108	74.39 109	74.52 114	85.75 86	86.04 115

V42		62.86 130	62.97 132	62.74 127	60.84 180	78.99 124	71.46 101	57.13 130	46.85 143	44.28 119	38.87 148	40.73 153	57.63 133	72.60 132	74.14 117	85.09 107	88.63 95

gg-mvs-nofinetune		62.34 131	66.19 115	57.86 156	76.15 100	88.61 38	71.18 105	41.24 200	25.74 202	13.16 203	22.91 197	63.97 67	54.52 142	85.06 14	85.25 10	90.92 3	91.78 60

CR-MVSNet		62.31 132	64.75 121	59.47 146	68.63 141	71.29 174	67.53 129	43.18 190	55.83 109	41.40 132	41.04 139	55.85 105	57.29 134	72.76 129	73.27 131	78.77 180	83.23 138

UniMVSNet_NR-MVSNet		62.30 133	63.51 128	60.89 137	69.48 138	77.83 134	64.07 146	63.94 68	50.03 130	31.17 174	44.82 120	41.12 148	51.37 150	71.02 144	74.81 109	85.30 101	84.95 123

v1192		62.25 134	61.64 144	62.96 122	66.88 152	79.72 117	69.96 114	55.77 139	41.58 164	39.42 141	37.05 159	35.96 175	60.50 111	74.30 112	74.09 118	85.24 103	88.76 94

Vis-MVSNet (Re-imp)		62.25 134	68.74 97	54.68 171	73.70 112	78.74 125	56.51 176	57.49 125	55.22 113	26.86 182	54.56 80	61.35 77	31.06 185	73.10 123	74.90 107	82.49 153	83.31 135

CHOSEN 280x420		62.23 136	66.57 111	57.17 162	59.88 183	68.92 180	61.20 164	42.28 194	54.17 120	39.57 140	47.78 104	64.97 63	62.68 97	73.85 116	69.52 165	77.43 184	86.75 108

PatchMatch-RL		62.22 137	60.69 151	64.01 114	68.74 140	75.75 152	59.27 169	60.35 105	56.09 108	53.80 83	47.06 113	36.45 170	64.80 87	68.22 164	67.22 171	77.10 185	74.02 171

v144192		62.05 138	61.46 146	62.73 128	66.59 156	79.87 116	69.30 118	55.88 137	41.50 166	39.41 142	37.23 157	36.45 170	59.62 116	72.69 131	73.51 124	85.61 98	88.93 91

v148		62.00 139	61.19 148	62.96 122	67.46 150	79.49 120	67.87 125	57.66 122	42.30 160	45.02 115	38.20 153	38.89 160	54.77 141	69.83 158	72.60 140	84.96 108	87.01 107

IterMVS		61.87 140	63.55 127	59.90 142	67.29 151	72.20 169	67.34 132	48.56 173	47.48 141	37.86 152	47.07 112	48.27 129	54.08 143	72.12 135	73.71 122	84.30 128	83.99 130
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		61.66 141	61.10 149	62.31 130	66.32 157	79.57 119	68.41 123	55.49 144	41.03 167	38.69 146	36.64 165	35.27 178	59.60 117	73.23 122	73.41 126	85.37 100	88.51 98

ACMH	59.42 14	61.59 142	59.22 161	64.36 112	78.92 79	78.26 130	67.65 127	67.48 46	39.81 171	30.98 176	38.25 152	34.59 181	61.37 107	70.55 151	73.47 125	79.74 175	79.59 155
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	60.36 13	61.16 143	58.38 163	64.42 111	77.37 92	74.35 162	68.45 122	62.81 82	45.86 149	38.48 147	35.71 168	37.35 165	59.81 115	67.24 167	69.80 164	79.58 176	78.32 160

v1240		61.09 144	60.55 153	61.72 134	65.92 161	79.28 122	67.16 133	54.91 150	39.79 172	38.10 149	36.08 167	34.64 180	59.15 121	72.86 127	73.36 128	85.10 105	87.84 102

NR-MVSNet		61.08 145	62.09 142	59.90 142	71.96 122	75.87 149	63.60 152	61.96 86	49.31 133	27.95 179	42.76 124	33.85 185	48.82 157	74.35 110	74.05 120	85.13 104	84.45 126

DU-MVS		60.87 146	61.82 143	59.76 144	66.69 153	75.87 149	64.07 146	61.96 86	49.31 133	31.17 174	42.76 124	36.95 167	51.37 150	69.67 159	73.20 134	83.30 142	84.95 123

UniMVSNet (Re)		60.62 147	62.93 134	57.92 155	67.64 148	77.90 133	61.75 161	61.24 95	49.83 132	29.80 178	42.57 127	40.62 154	43.36 174	70.49 152	73.27 131	83.76 135	85.81 118

PatchT		60.46 148	63.85 126	56.51 165	65.95 160	75.68 153	47.34 189	41.39 197	53.89 122	41.40 132	37.84 155	50.30 127	57.29 134	72.76 129	73.27 131	85.67 93	83.23 138

TranMVSNet+NR-MVSNet		60.38 149	61.30 147	59.30 148	68.34 142	75.57 155	63.38 155	63.78 70	46.74 144	27.73 180	42.56 128	36.84 168	47.66 160	70.36 153	74.59 112	84.91 111	82.46 143

IterMVS-SCA-FT		60.21 150	62.97 132	57.00 163	66.64 155	71.84 170	67.53 129	46.93 180	47.56 140	36.77 157	46.85 116	48.21 130	52.51 146	70.36 153	72.40 142	71.63 198	83.53 134

pmmvs5		59.72 151	60.24 155	59.11 150	62.77 175	77.33 141	63.17 156	54.00 156	40.21 170	37.23 153	40.41 142	35.99 174	51.75 148	72.55 133	72.74 139	85.72 91	82.45 144

USDC		59.69 152	60.03 157	59.28 149	64.04 168	71.84 170	63.15 157	55.36 146	54.90 117	35.02 165	48.34 100	29.79 195	58.16 125	70.60 149	71.33 153	79.99 173	73.42 175

Baseline_NR-MVSNet		59.47 153	60.28 154	58.54 153	66.69 153	73.90 163	61.63 162	62.90 81	49.15 137	26.87 181	35.18 172	37.62 163	48.20 158	69.67 159	73.61 123	84.92 109	82.82 141

thisisatest0515		59.37 154	60.68 152	57.84 157	64.39 167	75.65 154	58.56 172	53.86 157	41.55 165	42.12 131	40.40 143	39.59 157	47.09 163	71.69 141	73.79 121	81.02 167	82.08 147

pm-mvs1		59.21 155	59.58 160	58.77 152	67.97 145	77.07 143	64.12 144	57.20 128	34.73 187	36.86 154	35.34 170	40.54 155	43.34 175	74.32 111	73.30 130	83.13 147	81.77 149

tfpnnormal		58.97 156	56.48 171	61.89 132	71.27 127	76.21 148	66.65 137	61.76 92	32.90 190	36.41 158	27.83 189	29.14 196	50.64 154	73.06 124	73.05 135	84.58 124	83.15 140

FMVSNet5		58.86 157	60.24 155	57.25 161	52.66 198	66.25 186	63.77 151	52.86 164	57.85 100	37.92 151	36.12 166	52.22 122	51.37 150	70.88 146	71.43 150	84.92 109	66.91 190

TAMVS		58.86 157	60.91 150	56.47 166	62.38 177	77.57 137	58.97 171	52.98 162	38.76 175	36.17 159	42.26 132	47.94 131	46.45 165	70.23 155	70.79 157	81.86 160	78.82 159

EG-PatchMatch MVS		58.73 159	58.03 166	59.55 145	72.32 119	80.49 111	63.44 154	55.55 143	32.49 191	38.31 148	28.87 187	37.22 166	42.84 176	74.30 112	75.70 100	84.84 114	77.14 163

RPMNet		58.63 160	62.80 136	53.76 175	67.59 149	71.29 174	54.60 179	38.13 202	55.83 109	35.70 162	41.58 136	53.04 120	47.89 159	66.10 169	67.38 169	78.65 182	84.40 127

ADS-MVSNet		58.40 161	59.16 162	57.52 159	65.80 162	74.57 161	60.26 165	40.17 201	50.51 128	38.01 150	40.11 145	44.72 138	59.36 119	64.91 174	66.55 174	81.53 163	72.72 179

UniMVSNet_ETH3D		57.83 162	56.46 172	59.43 147	63.24 172	73.22 166	67.70 126	55.58 142	36.17 182	36.84 155	32.64 176	35.14 179	51.50 149	65.81 170	69.81 163	81.73 161	82.44 145

TransMVSNet (Re)		57.83 162	56.90 169	58.91 151	72.26 120	74.69 160	63.57 153	61.42 94	32.30 192	32.65 171	33.97 174	35.96 175	39.17 181	73.84 117	72.84 138	84.37 127	74.69 169

MIMVSNet		57.78 164	59.71 159	55.53 168	54.79 194	77.10 142	63.89 150	45.02 184	46.59 146	36.79 156	28.36 188	40.77 152	45.84 169	74.97 102	76.58 89	86.87 65	73.60 174

CMPMVS	43.63 17	57.67 165	55.43 173	60.28 141	72.01 121	79.00 123	62.77 158	53.23 161	41.77 163	45.42 111	30.74 183	39.03 158	53.01 145	64.81 176	64.65 182	75.26 190	68.03 188
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		57.35 166	59.89 158	54.38 173	71.37 125	73.45 165	52.71 181	61.03 96	46.11 148	26.33 183	41.73 135	44.08 140	29.72 187	71.43 143	70.90 155	85.10 105	71.56 182

v7n		57.04 167	56.64 170	57.52 159	62.85 174	74.75 159	61.76 160	51.80 167	35.58 186	36.02 161	32.33 178	33.61 186	50.16 155	67.73 166	70.34 161	82.51 152	82.12 146

pmmvs-eth3d		55.20 168	53.95 177	56.65 164	57.34 192	67.77 182	57.54 174	53.74 158	40.93 168	41.09 136	31.19 182	29.10 197	49.07 156	65.54 171	67.28 170	81.14 165	75.81 164

COLMAP_ROB	51.17 15	55.13 169	52.90 181	57.73 158	73.47 116	67.21 184	62.13 159	55.82 138	47.83 139	34.39 166	31.60 180	34.24 182	44.90 172	63.88 181	62.52 188	75.67 188	63.02 197
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPSCF		55.07 170	58.06 165	51.57 177	48.87 202	58.95 199	53.68 180	41.26 199	62.42 83	45.88 109	54.38 83	54.26 114	53.75 144	57.15 190	53.53 200	66.01 200	65.75 192

gm-plane-assit		54.99 171	57.99 167	51.49 179	69.27 139	54.42 203	32.32 206	42.59 193	21.18 206	13.71 201	23.61 194	43.84 141	60.21 113	87.09 5	86.55 5	90.81 4	89.28 87

anonymousdsp		54.99 171	57.24 168	52.36 176	53.82 196	71.75 173	51.49 182	48.14 174	33.74 188	33.66 169	38.34 151	36.13 173	47.54 161	64.53 178	70.60 159	79.53 177	85.59 121

CVMVSNet		54.92 173	58.16 164	51.13 180	62.61 176	68.44 181	55.45 178	52.38 165	42.28 161	21.45 190	47.10 111	46.10 135	37.96 182	64.42 179	63.81 183	76.92 186	75.01 168

GG-mvs-BLEND		54.54 174	77.58 48	27.67 202	0.03 215	90.09 28	77.20 64	0.02 212	66.83 71	0.05 215	59.90 66	73.33 35	0.04 211	78.40 74	79.30 67	88.65 21	95.20 26

MDTV_nov1_ep13_2view		54.47 175	54.61 174	54.30 174	60.50 181	73.82 164	57.92 173	43.38 189	39.43 174	32.51 172	33.23 175	34.05 183	47.26 162	62.36 182	66.21 177	84.24 129	73.19 177

pmmvs6		54.20 176	53.54 178	54.97 169	63.22 173	72.98 167	60.17 166	52.32 166	26.77 201	34.30 167	23.29 196	36.23 172	40.33 180	68.77 163	68.76 166	79.47 178	78.00 161

MVS-HIRNet		53.86 177	53.02 179	54.85 170	60.30 182	72.36 168	44.63 197	42.20 195	39.45 173	43.47 122	21.66 200	34.00 184	55.47 138	65.42 172	67.16 172	83.02 148	71.08 184

TDRefinement		52.70 178	51.02 187	54.66 172	57.41 191	65.06 190	61.47 163	54.94 148	44.03 155	33.93 168	30.13 185	27.57 198	46.17 167	61.86 183	62.48 189	74.01 194	66.06 191

TinyColmap		52.66 179	50.09 190	55.65 167	59.72 184	64.02 194	57.15 175	52.96 163	40.28 169	32.51 172	32.42 177	20.97 206	56.65 136	63.95 180	65.15 181	74.91 191	63.87 195

Anonymous20231206		52.23 180	52.80 182	51.56 178	64.70 166	69.41 178	51.01 183	58.60 112	36.63 179	22.44 189	21.80 199	31.42 191	30.52 186	66.79 168	67.83 168	82.10 158	75.73 165

PEN-MVS		51.04 181	52.94 180	48.82 183	61.45 179	66.00 187	48.68 186	57.20 128	36.87 178	15.36 197	36.98 160	32.72 187	28.77 191	57.63 189	66.37 175	81.44 164	74.00 172

WR-MVS		51.02 182	54.56 175	46.90 189	63.84 169	69.23 179	44.78 196	56.38 133	38.19 176	14.19 199	37.38 156	36.82 169	22.39 196	60.14 185	66.20 178	79.81 174	73.95 173

CP-MVSNet		50.57 183	52.60 184	48.21 186	58.77 188	65.82 188	48.17 187	56.29 134	37.41 177	16.59 194	37.14 158	31.95 189	29.21 188	56.60 192	63.71 184	80.22 171	75.56 166

PS-CasMVS		50.17 184	52.02 185	48.02 187	58.60 189	65.54 189	48.04 188	56.19 136	36.42 181	16.42 196	35.68 169	31.33 192	28.85 190	56.42 194	63.54 185	80.01 172	75.18 167

PM-MVS		50.11 185	50.38 189	49.80 181	47.23 204	62.08 197	50.91 184	44.84 186	41.90 162	36.10 160	35.22 171	26.05 202	46.83 164	57.64 188	55.42 199	72.90 195	74.32 170

DTE-MVSNet		49.82 186	51.92 186	47.37 188	61.75 178	64.38 192	45.89 195	57.33 127	36.11 183	12.79 204	36.87 161	31.93 190	25.73 194	58.01 187	65.22 180	80.75 170	70.93 185

WR-MVS_H		49.62 187	52.63 183	46.11 192	58.80 187	67.58 183	46.14 194	54.94 148	36.51 180	13.63 202	36.75 163	35.67 177	22.10 197	56.43 193	62.76 187	81.06 166	72.73 178

LTVRE_ROB	47.26 16	49.41 188	49.91 191	48.82 183	64.76 165	69.79 177	49.05 185	47.12 179	20.36 208	16.52 195	36.65 164	26.96 199	50.76 153	60.47 184	63.16 186	64.73 201	72.00 180
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
SixPastTwentyTwo		49.11 189	49.22 192	48.99 182	58.54 190	64.14 193	47.18 190	47.75 176	31.15 194	24.42 185	41.01 140	26.55 200	44.04 173	54.76 197	58.70 194	71.99 197	68.21 186

testgi		48.51 190	50.53 188	46.16 191	64.78 164	67.15 185	41.54 199	54.81 152	29.12 197	17.03 193	32.07 179	31.98 188	20.15 200	65.26 173	67.00 173	78.67 181	61.10 201

N_pmnet		47.67 191	47.00 195	48.45 185	54.72 195	62.78 195	46.95 191	51.25 168	36.01 184	26.09 184	26.59 192	25.93 203	35.50 184	55.67 196	59.01 192	76.22 187	63.04 196

FC-MVSNet-test		47.24 192	54.37 176	38.93 198	59.49 185	58.25 201	34.48 205	53.36 160	45.66 150	6.66 209	50.62 93	42.02 143	16.62 204	58.39 186	61.21 190	62.99 202	64.40 194

test20.03		47.23 193	48.69 193	45.53 193	63.28 171	64.39 191	41.01 200	56.93 131	29.16 196	15.21 198	23.90 193	30.76 194	17.51 203	64.63 177	65.26 179	79.21 179	62.71 198

EU-MVSNet		44.84 194	47.85 194	41.32 197	49.26 201	56.59 202	43.07 198	47.64 178	33.03 189	13.82 200	36.78 162	30.99 193	24.37 195	53.80 198	55.57 198	69.78 199	68.21 186

MDA-MVSNet-bldmvs		44.15 195	42.27 200	46.34 190	38.34 206	62.31 196	46.28 192	55.74 140	29.83 195	20.98 191	27.11 191	16.45 211	41.98 177	41.11 204	57.47 195	74.72 192	61.65 200

new-patchmatchnet		42.21 196	42.97 197	41.33 196	53.05 197	59.89 198	39.38 201	49.61 170	28.26 199	12.10 205	22.17 198	21.54 205	19.22 201	50.96 199	56.04 197	74.61 193	61.92 199

pmmvs3		41.86 197	42.29 199	41.36 195	39.80 205	52.66 204	38.93 203	35.85 206	23.40 205	20.22 192	19.30 201	20.84 207	40.56 179	55.98 195	58.79 193	72.80 196	65.03 193

MIMVSNet1		40.84 198	43.46 196	37.79 199	32.14 207	58.92 200	39.24 202	50.83 169	27.00 200	11.29 206	16.76 206	26.53 201	17.75 202	57.14 191	61.12 191	75.46 189	56.78 202

FPMVS		39.11 199	36.39 201	42.28 194	55.97 193	45.94 206	46.23 193	41.57 196	35.73 185	22.61 187	23.46 195	19.82 208	28.32 192	43.57 201	40.67 203	58.96 204	45.54 204

new_pmnet		33.19 200	35.52 202	30.47 201	27.55 211	45.31 207	29.29 207	30.92 207	29.00 198	9.88 208	18.77 202	17.64 210	26.77 193	44.07 200	45.98 202	58.41 205	47.87 203

PMVS	27.44 18	32.08 201	29.07 203	35.60 200	48.33 203	24.79 209	26.97 208	41.34 198	20.45 207	22.50 188	17.11 205	18.64 209	20.44 199	41.99 203	38.06 204	54.02 206	42.44 205
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		24.91 202	24.61 204	25.26 203	31.47 208	21.59 210	18.06 209	37.53 203	25.43 203	10.03 207	4.18 211	4.25 215	14.85 205	43.20 202	47.03 201	39.62 208	26.55 209
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		20.45 203	22.31 205	18.27 206	20.52 212	26.73 208	14.85 211	28.43 209	13.69 209	0.79 214	10.35 207	9.10 212	3.83 210	27.64 206	32.87 205	41.17 207	35.81 206

E-PMN		15.08 204	11.65 207	19.08 204	28.73 209	12.31 213	6.95 214	36.87 205	10.71 211	3.63 212	5.13 208	2.22 218	13.81 207	11.34 209	18.50 208	24.49 210	21.32 210

EMVS		14.40 205	10.71 208	18.70 205	28.15 210	12.09 214	7.06 213	36.89 204	11.00 210	3.56 213	4.95 209	2.27 217	13.91 206	10.13 210	16.06 209	22.63 211	18.51 211

MVE	15.98 19	14.37 206	16.36 206	12.04 208	7.72 214	20.24 211	5.90 215	29.05 208	8.28 212	3.92 211	4.72 210	2.42 216	9.57 208	18.89 208	31.46 206	16.07 213	28.53 208
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		0.05 207	0.08 209	0.01 209	0.00 216	0.01 216	0.03 217	0.01 213	0.05 213	0.00 216	0.14 213	0.01 219	0.03 213	0.05 211	0.05 210	0.01 214	0.24 213

test123		0.05 207	0.08 209	0.01 209	0.00 216	0.01 216	0.01 218	0.00 214	0.05 213	0.00 216	0.16 212	0.00 220	0.04 211	0.02 212	0.05 210	0.00 215	0.26 212

uanet_test		0.00 209	0.00 211	0.00 211	0.00 216	0.00 218	0.00 219	0.00 214	0.00 215	0.00 216	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 215	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 211	0.00 216	0.00 218	0.00 219	0.00 214	0.00 215	0.00 216	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 215	0.00 214

sosnet		0.00 209	0.00 211	0.00 211	0.00 216	0.00 218	0.00 219	0.00 214	0.00 215	0.00 216	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 215	0.00 214

9.14												84.47 5

SR-MVS					86.33 46			67.54 45				80.78 18

Anonymous202405211			66.35 114		78.00 84	84.41 79	74.85 77	63.18 75	51.00 127		31.37 181	53.73 117	69.67 62	76.28 89	76.84 86	83.21 145	90.85 68

our_test_3					63.32 170	71.07 176	55.90 177

test_part1																	97.29 4

ambc			42.30 198		50.36 200	49.51 205	35.47 204		32.04 193	23.53 186	17.36 203	8.95 213	29.06 189	64.88 175	56.26 196	61.29 203	67.12 189

MTAPA										78.32 10		79.42 23

MTMP										76.04 15		76.65 28

Patchmatch-RL test							2.17 216

tmp_tt				16.09 207	13.07 213	8.12 215	13.61 212	2.08 211	55.09 114	30.10 177	40.26 144	22.83 204	5.35 209	29.91 205	25.25 207	32.33 209

XVS					82.43 55	86.27 65	75.70 67			61.07 58		72.27 38				85.67 93

X-MVStestdata					82.43 55	86.27 65	75.70 67			61.07 58		72.27 38				85.67 93

abl_6				79.06 28	89.68 23	92.14 11	77.70 60	69.68 32	86.87 18	71.88 24	74.29 34	80.06 21	76.56 21			88.84 16	95.82 13

mPP-MVS					86.96 41							70.61 48

NP-MVS									81.60 35

Patchmtry						78.06 132	67.53 129	43.18 190		41.40 132

DeepMVS_CX						19.81 212	17.01 210	10.02 210	23.61 204	5.85 210	17.21 204	8.03 214	21.13 198	22.60 207		21.42 212	30.01 207

High-resolution multi-view benchmark