AI Paper Atlas

Research map / 3D vision / Face and shape

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

Shenhan Qian, Jiale Xu, Ziwei Liu, Liqian Ma, Shenghua Gao

ECCV 2022 · 3D vision › Face and shape · approach: Clothed human modeling · 18 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
add adjacent part seaming (APS) (ablation)UNIF · unseen pose, qualitativevisual qualityImproved
add bone limit loss (ablation)UNIF · partition at early training, qualitativepart divisionImproved
add section normal loss (ablation)UNIF · partition at early training, qualitativepart divisionImproved
add minimal perimeter loss (ablation)UNIF · partition at early training, qualitativeextra surfacesImproved
UNIF instead of SNARFclothed human reconstruction · CAPE extrapolation testChamfer distance (CD): 29.34 -> 6.64Improved
UNIF instead of NASApart-based reconstruction · CAPE extrapolation testChamfer distance (CD): 98.23 -> 8.06Improved
UNIF instead of SCANimate/SNARFClothSeq interpolation · ClothSeq interpolation testChamfer distance (CD): 8.81 -> 8.89 (JS)Mixed
use Fourier featuresUNIF · training initializationinitialization / extra surfacesHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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