AI Paper Atlas

Research map / 3D vision / Face and shape

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

Byungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon, Jason Saragih, Hanbyul Joo, Junxuan Li

ICCV 2025 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 6 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
compositional face/hair prior fine-tuned per subject versus DELTAHairCUP · Personalization on 8 unseen identitiesPSNR: 23.775 -> 27.040Improved
compositional face/hair prior versus DELTAHairCUP · Personalization on 8 unseen identitiesLPIPS: 0.0241 -> 0.0131Improved
compositional face/hair prior versus DELTAHairCUP · Personalization on 8 unseen identitiesL1: 0.0344 -> 0.0223Improved
compositional face/hair prior versus DELTAHairCUP · Personalization on 8 unseen identitiesSSIM: 0.790 -> 0.817Improved
anchor hair Gaussians to bald mesh instead of haired mesh (ablation)HairCUP · hairstyle transfer (qualitative)transfer naturalnessImproved
add boundary-free segmentation loss (disable near face-hair boundary) (ablation)HairCUP · hairstyle transfer (qualitative)boundary smoothnessImproved

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