Human Pose Estimation in Extremely Low-Light Conditions
- Title
- Human Pose Estimation in Extremely Low-Light Conditions
- Authors
- 이소현; 임재성; 정보승; Kim, Geonu; Woo, Byungju; Lee, Haechan; 조성현; 곽수하
- Date Issued
- 2023-06-21
- Publisher
- IEEE Computer Society
- Abstract
- We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality significantly. To address the first issue, we develop a ded-icated camera system and build a new dataset of real low-light images with accurate pose labels. Thanks to our camera system, each low-light image in our dataset is coupled with an aligned well-lit image, which enables accurate pose labeling and is used as privileged information during training. We also propose a new model and a new training strategy that fully exploit the privileged information to learn representation insensitive to lighting conditions. Our method demonstrates outstanding performance on real extremely low-light images, and extensive analyses validate that both of our model and dataset contribute to the success.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/122807
- Article Type
- Conference
- Citation
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, page. 704 - 714, 2023-06-21
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.