AnimaMimic: Imitating 3D Animation from Video Priors

TL;DR

AnimaMimic introduces a novel framework that leverages video diffusion models to animate static 3D meshes, combining data-driven motion priors with physical simulation for realistic, controllable 3D animation.

Contribution

The paper presents a new method that automatically generates 3D animations from videos, integrating motion priors, skeleton construction, and physical refinement for improved realism and control.

Findings

Produces physically plausible, temporally coherent animations

Automatically constructs skeletons and refines joint parameters

Integrates seamlessly into standard animation pipelines

Abstract

Creating realistic 3D animation remains a time-consuming and expertise-dependent process, requiring manual rigging, keyframing, and fine-tuning of complex motions. Meanwhile, video diffusion models have recently demonstrated remarkable motion imagination in 2D, generating dynamic and visually coherent motion from text or image prompts. However, their results lack explicit 3D structure and cannot be directly used for animation or simulation. We present AnimaMimic, a framework that animates static 3D meshes using motion priors learned from video diffusion models. Starting from an input mesh, AnimaMimic synthesizes a monocular animation video, automatically constructs a skeleton with skinning weights, and refines joint parameters through differentiable rendering and video-based supervision. To further enhance realism, we integrate a differentiable simulation module that refines mesh deformation through physically grounded soft-tissue dynamics. Our method bridges the creativity of video diffusion and the structural control of 3D rigged animation, producing physically plausible, temporally coherent, and artist-editable motion sequences that integrate seamlessly into standard animation pipelines. Our project page is at: https://xpandora.github.io/AnimaMimic/