AI Paper Atlas

Research map / 3D vision / Face and shape

UIKA: Fast Universal Head Avatar from Pose-Free Images

Zijian Wu, Boyao Zhou, Liangxiao Hu, Hongyu Liu, Yuan Sun, Xuan Wang, Xun Cao, Yujun Shen, Hao Zhu

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 5 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
train with synthetic multi-view head dataset (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)PSNR: 21.86 -> 22.61Improved
add UV attention branch (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)PSNR: 22.21 -> 22.61Improved
add aggregated UV color and confidence map with self-adaptive fusion (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)PSNR: 22.39 -> 22.61Improved
add UV attention branch (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)LPIPS: 0.091 -> 0.082Improved
add UV attention branch (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)AKD: 3.086 -> 3.037No clear effect
add synthetic dataset (ablation)UIKA · Monocular self reenactment (NeRSemble-v2)AED: 0.060 -> 0.055No clear effect
increase number of input images from 1 to 16UIKA · VFHQ and NeRSemble-v2 qualitative3D consistency and detailsImproved
use UIKA with UV-guided correspondence instead of GPAvatar/InvertAvatar multi-view aggregationmulti-view avatar reconstruction · Multi-view self reenactment (NeRSemble-v2)PSNR: 17.11 -> 22.50 vs GPAvatarImproved
use UIKA instead of GAGAvatar in monocular cross reenactmentmonocular avatar reconstruction · Monocular cross reenactment (VFHQ + NeRSemble-v2)CSIM: 0.678 -> 0.649Hurt
use UIKA instead of GAGAvatar in monocular self reenactmentmonocular avatar reconstruction · Monocular self reenactment (VFHQ + NeRSemble-v2)PSNR: 20.34 -> 21.69Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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