AI Paper Atlas

Research map / 3D vision / Face and shape

STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction

Jiankuo Zhao, Xiangyu Zhu, Zidu Wang, Zhen Lei

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 3 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 UV-Adaptive Soft Binding (ablation)STAvatar · INSTAPSNR: 29.66 -> 30.63Improved
add adaptive density control (ablation)STAvatar · INSTALPIPS: 0.0505 -> 0.0304Improved
add adaptive density control (ablation)STAvatar · INSTAPSNR: 30.31 -> 30.63Improved
replace positional gradient with FPE-AP (ablation)STAvatar · INSTALPIPS: 0.0321 -> 0.0304Improved
add FLAME-conditioned temporal clustering (ablation)STAvatar · INSTALPIPS: 0.0310 -> 0.0304Improved
add local decoder branch (ablation)STAvatar · INSTAPSNR: 30.36 -> 30.63Improved
add VGG perceptual loss (ablation)STAvatar · INSTALPIPS: 0.0426 -> 0.0304Improved
add VGG perceptual loss (ablation)STAvatar · INSTASSIM: 0.9592 -> 0.9587Hurt
apply FTC for densification (ablation)STAvatar · INSTA mouth-interior Gaussian countGaussian count: 2337 -> 2751Improved
use STAvatar instead of prior Gaussian avatar methodsGaussian head avatars · PointAvatar / HDTFPSNR: 28.25 vs 28.36 (Fate); 27.99 vs 28.36Mixed

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