AI Paper Atlas

Research map / 3D vision / Face and shape

GaussianSpeech: Audio-Driven Personalized 3D Gaussian Avatars

Shivangi Aneja, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai, Matthias Nießner

ICCV 2025 · 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
use the proposed avatar initialization instead of GaussianAvatars3DGS head avatar · Avatar reconstruction (Subject 4)PSNR / # Gaussians: 26.53 -> 29.90 PSNR; 98083 -> 32379 GaussiansImproved
add perceptual losses (ArcFace global + VGG patch) (ablation)avatar initialization · Avatar reconstruction (Subject 4)PSNR: 27.03 -> 29.90Improved
add wrinkle regularization (ablation)avatar initialization · Avatar reconstruction (Subject 4)PSNR: 28.10 -> 29.90Improved
add mouth region subdivision (ablation)avatar initialization · Avatar reconstruction (Subject 4)PSNR: 28.35 -> 29.90Improved
add expression-dependent color MLP (ablation)avatar initialization · Avatar reconstruction (Subject 4)PSNR: 28.93 -> 29.90Improved
add alignment mask in audio cross-attention (ablation)GaussianSpeech sequence model · Audio-driven animation (Subject 4)LSE-D: 12.66 -> 11.15Improved
personalize lip encoder via audio fine-tuning (ablation)GaussianSpeech sequence model · Audio-driven animation (Subject 4)LSE-D: 11.78 -> 11.15Improved
add wrinkle features for expression prediction (ablation)GaussianSpeech sequence model · Audio-driven animation (Subject 4)PSNR: 23.14 -> 24.97Improved
fine-tune color MLP and Gaussian latents with predicted expressions (ablation)GaussianSpeech · Audio-driven animation (Subject 4)PSNR: 23.96 -> 24.97Improved
GaussianSpeech vs best mesh-based baseline combined with GaussianAvatarsGaussianSpeech · Audio-driven animation (frontal camera)LSE-D: 11.61 -> 11.25Improved

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