STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting

TL;DR

STAR introduces a skeleton-aware, end-to-end method for generating animated 4D avatars from text, effectively addressing pose and motion mismatches with in-network retargeting and multi-view supervision.

Contribution

It proposes a novel skeleton-aware framework that corrects motion mismatches and integrates skeleton-conditioned priors for high-quality, text-driven 4D avatar synthesis.

Findings

Produces high-quality, vivid 4D avatars aligned with text descriptions.

Effectively corrects motion and pose mismatches using in-network retargeting.

Achieves coherent multi-view and frame-consistent supervision.

Abstract

The creation of 4D avatars (i.e., animated 3D avatars) from text description typically uses text-to-image (T2I) diffusion models to synthesize 3D avatars in the canonical space and subsequently applies animation with target motions. However, such an optimization-by-animation paradigm has several drawbacks. (1) For pose-agnostic optimization, the rendered images in canonical pose for naive Score Distillation Sampling (SDS) exhibit domain gap and cannot preserve view-consistency using only T2I priors, and (2) For post hoc animation, simply applying the source motions to target 3D avatars yields translation artifacts and misalignment. To address these issues, we propose Skeleton-aware Text-based 4D Avatar generation with in-network motion Retargeting (STAR). STAR considers the geometry and skeleton differences between the template mesh and target avatar, and corrects the mismatched source motion by resorting to the pretrained motion retargeting techniques. With the informatively retargeted and occlusion-aware skeleton, we embrace the skeleton-conditioned T2I and text-to-video (T2V) priors, and propose a hybrid SDS module to coherently provide multi-view and frame-consistent supervision signals. Hence, STAR can progressively optimize the geometry, texture, and motion in an end-to-end manner. The quantitative and qualitative experiments demonstrate our proposed STAR can synthesize high-quality 4D avatars with vivid animations that align well with the text description. Additional ablation studies shows the contributions of each component in STAR. The source code and demos are available at: \href{https://star-avatar.github.io}{https://star-avatar.github.io}.