AI Paper Atlas

Research map / 3D vision / Face and shape

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

Zhe Li, Zerong Zheng, Hongwen Zhang, Chaonan Ji, Yebin Liu

ECCV 2022 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 34 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
decompose avatar into pose-agnostic template plus pose-dependent warping field (ablation)GeoTexAvatar · Avatar animationanimation detail (qualitative)Improved
use SMPL positional map instead of local pose vector as warping-field pose encoding (ablation)GeoTexAvatar · Avatar animationanimation quality (qualitative)Improved
add texture template supervision to warping field (ablation)GeoTexAvatar · Avatar animation correspondenceswarping correspondence (qualitative)Improved
increase training scans from 20 to 80 (ablation)GeoTexAvatar · SHORT_SLEEVE_1Chamfer and scan-to-mesh distanceNo clear effect
replace direct covering with canonical normal fusion (ablation)AvatarCap · Reconstruction vs ground-truth scanspoint-to-surface error (qualitative)Improved
use avatar prior with normal fusion instead of PIFuHDAvatarCap · Monocular capture test setChamfer distance: 3.400 -> 1.097Improved
use avatar prior instead of NormalGAN back-view inferenceAvatarCap · Monocular capture test setChamfer distance: 2.852 -> 1.097Improved
use GeoTexAvatar instead of SCANimateavatar · HOODY_1Chamfer distance: 7.38 -> 6.29Improved
use GeoTexAvatar instead of POPavatar · SHIRT_1Chamfer distance: 3.08 -> 2.80Improved

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