AI Paper Atlas

Research map / 3D vision / 3D generation

Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement

Xingqun Qi, Chen Liu, Muyi Sun, Lincheng Li, Changjie Fan, Xin Yu

CVPR 2023 · 3D vision › 3D generation · approach: Hand-object interaction generation · 21 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 bilateral hand disentanglement with the complete stage-one method3D hand prediction from body dynamics · B2H and TED HandsFHD: 0.973 -> 0.471; 0.877 -> 0.258Improved
Apply PSS diversificationOurs (stage one) · B2HDiversity: 1.001$^{\pm 0.061}$ -> 1.324$^{\pm 0.066}$Improved
Apply PSS diversificationOurs (stage one) · TED HandsDiversity: 4.018$^{\pm 0.190}$ -> 6.426$^{\pm 0.300}$Improved
Add the disentanglement loss (ablation)Bilateral hand prediction model · B2H and TED HandsFHD: 0.773 -> 0.682; 0.731 -> 0.595Improved
Add the perceptual loss (ablation)Bilateral hand prediction model · B2H and TED HandsFHD: 0.773 -> 0.657; 0.731 -> 0.699Improved
Add both disentanglement and perceptual losses (ablation)Bilateral hand prediction model · B2H and TED HandsFHD: 0.773 -> 0.640; 0.731 -> 0.495Improved
Add SRM (ablation)Bilateral hand prediction model with both losses · B2H and TED HandsFHD: 0.640 -> 0.580; 0.495 -> 0.393Improved
Add TMM after SRM (ablation)Bilateral hand prediction model with both losses · B2H and TED HandsFHD: 0.580 -> 0.471; 0.393 -> 0.258Improved
Place TMM before SRM rather than after it (ablation)Bilateral hand prediction model · B2H and TED HandsFHD: 0.471 -> 0.614; 0.258 -> 0.463Hurt
Share weights between the two hand transformers (ablation)Bilateral hand prediction model · B2H and TED HandsFHD: 0.471 -> 0.598; 0.258 -> 0.380Hurt

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