AI Paper Atlas

Research map / 3D vision / Face and shape

NPMs: Neural Parametric Models for 3D Deformable Shapes

Pablo Palafox, Aljaž Božič, Justus Thies, Matthias Nießner, Angela Dai

ICCV 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 100 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
initialize pose code with the pose encoder (ablation)NPMs · CAPEEPE: 3.61 -> 0.74Improved
initialize shape code with the shape encoder (ablation)NPMs · CAPEEPE: 0.77 -> 0.74No clear effect
initialize both codes with encoders (ablation)NPMs · CAPEIoU: 0.77 -> 0.83Improved
add positional encoding to shape and pose MLPs (ablation)NPMs · CAPEChamfer-l2: 0.142 -> 0.022Improved
use smaller latent code size 128 (ablation)NPMs · CAPEChamfer-l2: 0.052 -> 0.022Hurt
use larger latent code size 384 (ablation)NPMs · CAPEChamfer-l2: 0.076 -> 0.022Hurt
add temporal consistency on flow predictions (ablation)NPMs · CAPEChamfer-l2: 0.037 -> 0.022Improved
enforce temporal consistency on flow instead of on pose codes (ablation)NPMs · CAPEChamfer-l2: 0.034 -> 0.022Improved
add ICP loss at the start of optimization (ablation)NPMs · CAPEChamfer-l2: 0.031 -> 0.022Improved
add ICP loss at the start of optimization (ablation)NPMs · CAPEEPE: 0.79 -> 0.74Improved

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