Animus3D: Text-driven 3D Animation via Motion Score Distillation

TL;DR

Animus3D introduces a novel text-driven 3D animation framework that uses Motion Score Distillation with a LoRA-enhanced diffusion model and regularization techniques to produce detailed, high-fidelity animations from static 3D assets and text prompts.

Contribution

The paper proposes a new SDS alternative called Motion Score Distillation, incorporating LoRA-enhanced diffusion, regularization, and a motion refinement module for improved 3D animation quality.

Findings

Outperforms state-of-the-art baselines in motion richness and detail.

Effectively preserves appearance while animating from text prompts.

Generates high-quality, temporally consistent 3D animations.

Abstract

We present Animus3D, a text-driven 3D animation framework that generates motion field given a static 3D asset and text prompt. Previous methods mostly leverage the vanilla Score Distillation Sampling (SDS) objective to distill motion from pretrained text-to-video diffusion, leading to animations with minimal movement or noticeable jitter. To address this, our approach introduces a novel SDS alternative, Motion Score Distillation (MSD). Specifically, we introduce a LoRA-enhanced video diffusion model that defines a static source distribution rather than pure noise as in SDS, while another inversion-based noise estimation technique ensures appearance preservation when guiding motion. To further improve motion fidelity, we incorporate explicit temporal and spatial regularization terms that mitigate geometric distortions across time and space. Additionally, we propose a motion refinement module to upscale the temporal resolution and enhance fine-grained details, overcoming the fixed-resolution constraints of the underlying video model. Extensive experiments demonstrate that Animus3D successfully animates static 3D assets from diverse text prompts, generating significantly more substantial and detailed motion than state-of-the-art baselines while maintaining high visual integrity. Code will be released at https://qiisun.github.io/animus3d_page.