AI Paper Atlas

Research map / 3D vision / Gaussian splatting

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting

Zhenglin Zhou, Fan Ma, Hehe Fan, Zongxin Yang, Yi Yang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars · 49 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 HeadStudio instead of text-to-3D baselines for avatar textureHeadArtist · Static head avatarsCLIP-Score ViT-L/14: 0.272 -> 0.275Improved
use HeadStudio (3DGS) instead of TADA for renderingTADA · Dynamic head avatars, Kratosrendering speed (fps): 3 fps -> 52 fpsImproved
add super-dense Gaussian initialization (K=10 versus K=1)HeadStudio · head avatar generation (qualitative)avatar fidelityImproved
add FLAME-based control and landmark conditionHeadStudio · head avatar generation (qualitative)shape consistencyImproved
add denoised score distillationHeadStudio · head avatar generation (qualitative)texture qualityImproved
train with animation (pose and expression sampling)HeadStudio · head avatar generation (qualitative)deformation artifactsImproved
add adaptive geometry regularization with mesh-area scaleHeadStudio · head avatar generation (qualitative)alignment vs representationImproved
use Realistic Vision 5.1 instead of SD2.1 or SD1.5 as diffusion modelHeadStudio · head avatar generation (qualitative)visual appealImproved
increase geometry regularization weight too farHeadStudio · head avatar generation (qualitative)representation abilityHurt

Later papers that compared with this method

1 later accepted paper reports HeadStudio as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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