AI Paper Atlas

Research map / 3D vision / Human pose estimation

Depth-Based Hand Pose Estimation: Methods, Data, and Challenges

James Steven Supančič, Grégory Rogez, Yi Yang, Jamie Shotton, Deva Ramanan

IJCV 2018 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 103 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
Train the NN baseline on NYU real auto-annotated data instead of the libhand synthetic set (ablation)1-NN volumetric exemplars · New testsetpose accuracyImproved
Enlarge the synthetic libhand training set (ablation)1-NN volumetric exemplars · New testsetpose accuracyImproved
Train NN on other datasets with larger pose variation than ICL, instead of ICL-Train (ablation)1-NN volumetric exemplars · ICL testsetpose accuracy (50mm)Hurt
Use deep models (DeepJoint, DeepPrior) instead of 1-NNhand pose estimators · ICL and NYU testsetspose accuracyImproved
Use scanning-window methods such as NN instead of multistage detect-then-estimate pipelineshand pose estimators · New testset (cluttered, distant hands)pose accuracyImproved

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