AI Paper Atlas

Research map / 3D vision / Human pose estimation

Human Pose Estimation in Extremely Low-Light Conditions

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

CVPR 2023 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use LSBN and neural-style LUPI with paired well-lit imagesCPN, ResNet-50 · ExLPose LL-AAP@0.5:0.95: 25.4 -> 32.7Improved
Add LSBN to pose-only Baseline-all (ablation)CPN, ResNet-50 · ExLPose LL-AAP@0.5:0.95: 25.4 -> 30.1Improved
Add LUPI to LSBN (ablation)CPN, ResNet-50 · ExLPose LL-AAP@0.5:0.95: 30.1 -> 32.7Improved
Use LUPI without LSBN (ablation)CPN, ResNet-50 · ExLPose LL-AAP@0.5:0.95: 25.4 -> 24.0Hurt
Use aligned low-light and well-lit pairs for training (ablation)LSBN + LUPI · ExLPose LL-AAP@0.5:0.95: 30.2 -> 32.7Improved
Use accurate low-light pose labels instead of unlabeled low-light data (ablation)LSBN + LUPI · ExLPose LL-AAP@0.5:0.95: 4.6 -> 32.7Improved
Match teacher neural styles rather than feature maps directly (ablation)LSBN + LUPI · ExLPose LL-AAP@0.5:0.95: 30.4 -> 32.7Improved
Apply LUPI from C1 through R4 rather than only C1 (ablation)LSBN + LUPI · ExLPose LL-AAP@0.5:0.95: 29.7 -> 32.7Improved
Send LUPI gradients only from teacher to student (ablation)LSBN + LUPI · ExLPose LL-AAP@0.5:0.95: 31.6 -> 32.7; 29.5 -> 32.7Improved
Scale low-light inputs to average channel intensity 0.4 (ablation)Ours · ExLPose LL-AAP@0.5:0.95: 14.5 -> 32.7Improved
Use image enhancement before pose estimationBaseline-all · ExLPose LL-EAP@0.5:0.95: 14.3 -> 8.3 (LLFlow); 14.3 -> 12.5 (LIME)Hurt
Use image enhancement before pose estimationBaseline-all · ExLPose LL-NAP@0.5:0.95: 33.8 -> 35.2 (LLFlow); 33.8 -> 38.3 (LIME)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy