AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Compositional Representation for 4D Captures With Neural ODE

Boyan Jiang, Yinda Zhang, Xingkui Wei, Xiangyang Xue, Yanwei Fu

CVPR 2021 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 23 citations (OpenAlex)

Check 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 the compositional latent ODE method rather than OFlow4D reconstruction · D-FAUST seen individualsIoU: 79.9% -> 81.8%Improved
Use the compositional latent ODE method rather than OFlow4D reconstruction · D-FAUST unseen individualIoU: 69.6% -> 68.2%Hurt
Use the compositional latent ODE method rather than OFlow4D reconstruction · Warping CarsIoU: 70.0% -> 70.9%Improved
Use the compositional representation for motion transferD-FAUST motion transfer · D-FAUSTIoU: 26.7% -> 85.0%Improved
Use the compositional method rather than OFlowD-FAUST completion · D-FAUST temporal completionIoU: 85.1% -> 86.4%Improved
Use the compositional method rather than OFlowD-FAUST completion · D-FAUST spatial completionIoU: 86.0% -> 87.2%Improved
Use the compositional method rather than OFlowD-FAUST future prediction · D-FAUSTIoU: 75.5% -> 80.8%Improved
Replace the conditional latent ODE with an MLP pose predictor (ablation)Proposed 4D reconstruction method · D-FAUSTIoU: 81.8% -> 80.4%Hurt
Replace the conditional latent ODE with an MLP pose predictor (ablation)Proposed 4D reconstruction method · D-FAUSTChamfer Distance: 0.068 -> 0.073Hurt
Add identity exchange training at 50% rather than no exchange (ablation)Proposed method · D-FAUST motion transferIoU: 65.3% -> 85.0%Improved
Add identity exchange training at 50% rather than no exchange (ablation)Proposed method · D-FAUST 4D reconstructionIoU: 83.3% -> 81.8%Hurt
Vary the identity exchange rate from 25% to 50% (ablation)Proposed method · D-FAUST motion transferIoU: 84.1% -> 85.0%Improved

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