AI Paper Atlas

Research map / 3D vision / Face and shape

HHAvatar: Gaussian Head Avatar with Dynamic Hairs

Zhanfeng Liao, Yuelang Xu, Zhe Li, Qijing Li, Boyao Zhou, Ruifeng Bai, Di Xu, Hongwen Zhang, Yebin Liu

TPAMI 2025 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 43 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 super resolution network (ablation)HHAvatar · Self reenactment (2K)LPIPS (2K): 0.202 -> 0.098Improved
add super resolution network (ablation)HHAvatar · Self reenactment (2K)FID (2K): 45.50 -> 18.50Improved
add super resolution network (ablation)HHAvatar · Self reenactmentPSNR: 27.82 -> 27.70Mixed
use geometry-guided initialization instead of FLAME initialization (ablation)HHAvatar · Self reenactmentLPIPS: 0.123 -> 0.108Improved
use geometry-guided initialization instead of FLAME initialization (ablation)HHAvatar · Self reenactmentPSNR: 28.73 -> 28.94Improved
use fully learned deformation instead of mesh LBS deformation (ablation)HHAvatar · Self reenactmentLPIPS: 0.116 -> 0.108Improved
use fully learned deformation instead of mesh LBS deformation (ablation)HHAvatar · Self reenactmentPSNR: 28.83 -> 28.94Improved
add separate dynamic hair module (ablation)HHAvatar · Self reenactment with hairPSNR: 26.23 -> 27.02Improved
add separate dynamic hair module (ablation)HHAvatar · Self reenactment with hairSSIM: 0.825 -> 0.876Improved
add occlusion perception module (ablation)HHAvatar · Self reenactment with hairLPIPS: 0.116 -> 0.108Improved
add occlusion perception module (ablation)HHAvatar · Self reenactment with hairPSNR: 26.83 -> 27.02Improved

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