Human Pose Estimation in Extremely Low-Light Conditions

Sohyun Lee · Jaesung Rim · Boseung Jeong · Geonu Kim · Byungju Woo · Haechan Lee · Sunghyun Cho · Suha Kwak

West Building Exhibit Halls ABC 067
[ Abstract ] [ Project Page ]
Tue 20 Jun 10:30 a.m. PDT — noon PDT


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 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.

Chat is not available.