AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Hand Articulations by Hallucinating Heat Distribution

Chiho Choi, Sangpil Kim, Karthik Ramani

ICCV 2017 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 39 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 multi-task per-finger branches instead of a single holistic network (ablation)Depth network · Synthetic hand datasetmean joint angle errorImproved
group fingers anatomically (T-IMR-L) instead of dividing into six sub-tasks (ablation)Depth network · Synthetic hand datasetmean joint angle errorImproved
weight thumb loss 3 times larger (alpha = 3) (ablation)Depth network · Synthetic hand datasetmean joint angle errorImproved
add hallucinated heat distribution features and refinement network (ablation)Depth-alone baseline · Synthetic hand datasetmean joint angle errorImproved
add hallucinated heat distribution features and refinement network (ablation)Depth-alone baseline · NYUfraction of frames within distance thresholdImproved
use hallucinated features instead of ideal heat distribution network features (ablation)Refinement network · Synthetic hand datasetmean joint angle errorNo clear effect
concatenate depth features after conv6 and heat features after conv5 versus other layer combinations (ablation)Refinement network · Synthetic hand datasetmean angle errorImproved
use unpooling versus deconvolution for segmentation upsampling (ablation)Localization network · HandNetsegmentation accuracy and timeNo clear effect
use different set of heat source vertices J (ablation)Heat distribution descriptor · Synthetic hand datasetregression accuracyNo clear effect
proposed method versus generative method [23]Ours · MSRA14mean distance error (mm): 9.2 -> 20.0Hurt
proposed method versus discriminative method [7]Ours · MSRA14mean distance error (mm): 22.7 -> 20.0Improved

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