Suha Kwak, Sohyun Lee, Sunghyun Cho, Geonu Kim, Boseung Jeong, Jaesung Rim, Haechan Lee, Byungju Woo
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 lowlight 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15410")
get_code_for_paper("2303.15410")
have("2303.15410")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.15410.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.15410)
Connect an agent — have() is free.