Human Pose Estimation in the Dark

Sohyun Lee, Jaesung Rim, Boseung Jeong, Geonu Kim, ByungJu Woo, Haechan Lee, Sunghyun Cho, Suha Kwak

Keywords: Low-light image understanding, Robustness, Learning using privileged information, Human pose estimation

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 dedicated 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 a near-perfectly aligned well-lit image, which enables accurate pose labeling and is used as privileged information during training. We also propose a new model that fully exploits the privileged information to learn representation insensitive to lighting conditions. Our model demonstrates outstanding performance on real extremely low-light images, and extensive analyses validate that both of our dataset and model contribute to the success.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

TL;DR: We for the first time tackle human pose estimation under extremely low-light conditions, and introduce a new training strategy and new datasets for the challenging task.