AI Paper Atlas

Research map / 3D vision / Face and shape

InteractAvatar: Modeling Hand-Face Interaction in Photorealistic Avatars with Deformable Gaussians

Kefan Chen, Sreyas Mohan, Justin Theiss, Sergiu Oprea, Srinath Sridhar, Aayush Prakash

ICCV 2025 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 2 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 PointNet++ geometric feature (ablation)InteractAvatar · DECAF novel view (subject 4)PSNR: 28.93 -> 29.85Improved
add PointNet++ geometric feature (ablation)InteractAvatar · DECAF novel view (subject 4)LPIPS: 0.0370 -> 0.0338Improved
add dynamic hand MLPs H (ablation)InteractAvatar · DECAF novel view (subject 4)PSNR: 26.97 -> 29.85Improved
add dynamic hand MLPs H (ablation)InteractAvatar · DECAF novel view (subject 4)LPIPS: 0.0574 -> 0.0338Improved
add dynamic hand MLPs H (ablation)InteractAvatar · DECAF novel view (subject 4)SSIM: 0.9359 -> 0.9335Hurt
add hand-face interaction MLPs I (ablation)InteractAvatar · DECAF novel view (subject 4)PSNR: 28.23 -> 29.85Improved
add hand-face interaction MLPs I (ablation)InteractAvatar · DECAF novel view (subject 4)LPIPS: 0.0467 -> 0.0338Improved
add hand-face interaction MLPs I (ablation)InteractAvatar · DECAF novel view (subject 4)SSIM: 0.9389 -> 0.9335Hurt
use InteractAvatar instead of GaussianAvatarGaussianAvatar · DECAF novel viewPSNR: 26.71 -> 29.85Improved
use InteractAvatar instead of GaussianAvatarGaussianAvatar · DECAF self-enactmentSSIM: 0.9393 -> 0.9356Hurt
use InteractAvatar instead of GaussianAvatarGaussianAvatar · DECAF self-enactmentLPIPS: 0.0578 -> 0.0396Improved
add patch perceptual loss Lpatch (ablation)InteractAvatar · DECAF (qualitative)visual detailImproved

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