AI Paper Atlas

Research map / 3D vision / Human pose estimation

AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation

Weiting Huang, Pengfei Ren, Jingyu Wang, Qi Qi, Haifeng Sun

AAAI 2020 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 83 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 adaptive aggregation with joint-coordinate supervision to dense supervision (ablation)AWR with 3D offsets · NYUMean Error (mm): 7.87 -> 7.48Improved
Use adaptive aggregation and joint supervision instead of direct coordinate regressionNYU ResNet50 · NYUMean Error (mm): 8.82 -> 7.75Improved
Use 3D offsets instead of 2D offsets with depth offset maps (ablation)AWR with joint and dense supervision · NYUMean Error (mm): 7.58 -> 7.48Improved
Use depth offset maps rather than absolute depth maps (ablation)AWR with 2D offsets · NYUMean Error (mm): 7.86 -> 7.58Improved
Increase backbone depth from ResNet50 to ResNet101 (ablation)AWR · NYUMean Error (mm): 7.48 -> 7.37Improved
Replace ResNet50 with a two-stage Hourglass (ablation)AWR · NYUMean Error (mm): 7.48 -> 7.43Improved
Add joint-coordinate supervision to dense-only training (ablation)AWR with depth-image input · NYUMean Error (mm): 7.87 -> 7.48Improved
Add joint-coordinate supervision to dense-only training (ablation)AWR with voxel input · NYUMean Error (mm): 11.40 -> 8.60Improved
Add joint-coordinate supervision to dense-only training (ablation)AWR with point-cloud input · NYUMean Error (mm): 10.6 -> 10.52Improved
Increase the 3D-offset kernel size (ablation)AWR with both supervisions · NYUMean Error (mm): 7.49mm; 7.48mm; 7.46mm; 7.45mmNo clear effect
Increase ResNet backbone depth from ResNet18 to ResNet50 (ablation)Ours · HANDS 2017AVG mean error (mm): 7.84 -> 7.48Improved

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