KeypointNet: A large-scale 3D keypoint dataset aggregated from numerous human annotations

Yang You; Yujing Lou; Chengkun Li; Zhoujun Cheng; Liangwei Li; Lizhuang Ma; Cewu Lu; Weiming Wang

doi:10.1109/CVPR42600.2020.01366

KeypointNet: A large-scale 3D keypoint dataset aggregated from numerous human annotations

Yang You
, Yujing Lou
, Chengkun Li
, Zhoujun Cheng
, Liangwei Li
, Lizhuang Ma
, Cewu Lu
, Weiming Wang^*

^*Corresponding author for this work

Shanghai Jiao Tong University

Research output: Contribution to journal › Conference article › peer-review

68 Scopus citations

Abstract

Detecting 3D objects keypoints is ofgreat interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 83,231 keypoints and 8,329 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset.

Original language	English
Article number	9157559
Pages (from-to)	13644-13653
Number of pages	10
Journal	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs	https://doi.org/10.1109/CVPR42600.2020.01366
State	Published - 2020
Externally published	Yes
Event	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States Duration: 14 Jun 2020 → 19 Jun 2020

Access to Document

10.1109/CVPR42600.2020.01366

Cite this

@article{e9049dc9afbc46b68a262dad09542986,

title = "KeypointNet: A large-scale 3D keypoint dataset aggregated from numerous human annotations",

abstract = "Detecting 3D objects keypoints is ofgreat interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 83,231 keypoints and 8,329 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset.",

author = "Yang You and Yujing Lou and Chengkun Li and Zhoujun Cheng and Liangwei Li and Lizhuang Ma and Cewu Lu and Weiming Wang",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 ; Conference date: 14-06-2020 Through 19-06-2020",

year = "2020",

doi = "10.1109/CVPR42600.2020.01366",

language = "英语",

pages = "13644--13653",

journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

issn = "1063-6919",

publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - KeypointNet

T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020

AU - You, Yang

AU - Lou, Yujing

AU - Li, Chengkun

AU - Cheng, Zhoujun

AU - Li, Liangwei

AU - Ma, Lizhuang

AU - Lu, Cewu

AU - Wang, Weiming

PY - 2020

Y1 - 2020

N2 - Detecting 3D objects keypoints is ofgreat interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 83,231 keypoints and 8,329 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset.

AB - Detecting 3D objects keypoints is ofgreat interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 83,231 keypoints and 8,329 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset.

UR - https://www.scopus.com/pages/publications/85094847351

U2 - 10.1109/CVPR42600.2020.01366

DO - 10.1109/CVPR42600.2020.01366

M3 - 会议文章

AN - SCOPUS:85094847351

SN - 1063-6919

SP - 13644

EP - 13653

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

M1 - 9157559

Y2 - 14 June 2020 through 19 June 2020

ER -

KeypointNet: A large-scale 3D keypoint dataset aggregated from numerous human annotations

Abstract

Access to Document

Other files and links

Fingerprint

Cite this