AI Paper Atlas

Research map / 3D vision / Human pose estimation

Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions

Yihao Ai, Yifei Qi, Bo Wang, Yu Cheng, Xinchao Wang, Robby T. Tan

ECCV 2024 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 9 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
add Extreme Low-Light Augmentation (ELLA) fake low-light images (ablation)DEKR-W32 pre-training · ExLPose-test LL-AAP@0.5:0.95: 0.8 -> 15.8Improved
add Person-specific Degradation Augmentation (PDA) in stage 2 (ablation)Single-teacher student · ExLPose-test LL-AAP@0.5:0.95: 16.8 -> 19.0Improved
add PDA in stage 2 (ablation)Single-teacher student · ExLPose-test WL (well-lit)AP@0.5:0.95: 60.5 -> 59.4Hurt
add complementary keypoint-based teacher to the main teacher (ablation)Dual-teacher framework with PDA · ExLPose-test LL-AAP@0.5:0.95: 19.0 -> 21.1Improved
add complementary teacher (ablation)Dual-teacher framework · ExLPose-test WLAP@0.5:0.95: 59.4 -> 61.6Improved
use complementary teacher to add pseudo labels beyond main teacher (ablation)Pseudo-labeling on ExLPose training set · ExLPose training setvalid pseudo labels: 5056 -> +2136 at OKS 0.5 (+49.8%)Improved
train with well-lit labels only plus dual-teacher low-light adaptation versus LSBN+LUPI trained with paired low-light labelsBottom-up DEKR framework · ExLPose-OCN (avg)AP@0.5:0.95: 35.2 -> 37.6Improved
apply low-light image enhancement before pose estimation (RFormer, LLFlow)Base-well DEKR · ExLPose-OCN (avg)AP@0.5:0.95: 6.3 -> 18.3 (RFormer), 21.4 (LLFlow)Improved
use generic domain adaptation (UDA-HE) instead of low-light specific augmentationBase-well DEKR · ExLPose-OCN (avg)AP@0.5:0.95: 6.3 -> 6.9No clear effect
compare bottom-up ours against top-down LIME trained with low-light labelsOurs versus LIME on ExLPose-test · ExLPose-testAP@0.5:0.95: LL-A 21.1 vs 21.1; LL-E 5.0 vs 7.6Mixed

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