AI Paper Atlas

Research map / 3D vision / Face and shape

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang

NeurIPS 2021 · 3D vision › Face and shape · approach: Clothed human modeling · 48 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
fine-tune MetaAvatar from 2.5D depth vs baselines trained on full meshesMetaAvatar · CAPE interpolation subj 00122/00215D_p (cm): 0.454 -> 0.450 vs LEAPImproved
MetaAvatar vs LEAP on subjects with unseen action trialsMetaAvatar · CAPE interpolation subj 00134/03375D_p (cm): 0.483 (LEAP) vs 0.518Hurt
add hypernetwork predicting SDF residuals over meta-SDF (vs plain MLP with pose input) (ablation)MetaAvatar · CAPE interpolation subj 00122/00215D_p (cm): 3.278 -> 0.461Improved
add positional encoding to MLP baseline (ablation)MLP · CAPE interpolation subj 00122/00215D_p (cm): 3.278 -> 1.806Improved
add hypernetwork (BoneEnc) over meta-learned SIREN conditioned on pose (ablation)MetaAvatar · CAPE interpolation subj 00122/00215D_p (cm): 0.472 -> 0.461Improved
hierarchical bone encoder instead of unit quaternions (ablation)MetaAvatar hypernetwork · CAPE interpolation subj 00122/00215D_p (cm): 0.460 -> 0.461No clear effect
hierarchical bone encoder instead of unit quaternions (ablation)MetaAvatar hypernetwork · CAPE interpolation subj 00134/03375D_p (cm): 0.526 -> 0.523Improved
reduce fine-tuning data from 50% to 10% (ablation)MetaAvatar · CAPE interpolation subj 00122/00215D_p (cm): 0.450 -> 0.512Hurt
reduce fine-tuning data to <1% (8-20 frames) (ablation)MetaAvatar · CAPE interpolation subj 00122/00215D_p (cm): 0.450 -> 0.592Hurt
reduce fine-tuning data to <1% on extrapolation perceptual score (ablation)MetaAvatar · CAPE extrapolationperceptual score: 0.5 -> 0.510 (00122/00215); 0.5 -> 0.387 (00134/03375)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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