AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation

TL;DR

AnimateAnyMesh introduces a novel feed-forward framework for efficient, text-driven animation of 3D meshes, utilizing a new architecture and a large dataset to produce high-quality animations quickly.

Contribution

It presents the first feed-forward method for 4D mesh animation driven by text, with a new architecture and a large annotated dataset, advancing 4D content creation.

Findings

Generates semantically accurate, temporally coherent animations in seconds

Outperforms existing methods in quality and efficiency

Introduces DyMeshVAE architecture and DyMesh Dataset with 4M sequences

Abstract

Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training data. In this paper, we present AnimateAnyMesh, the first feed-forward framework that enables efficient text-driven animation of arbitrary 3D meshes. Our approach leverages a novel DyMeshVAE architecture that effectively compresses and reconstructs dynamic mesh sequences by disentangling spatial and temporal features while preserving local topological structures. To enable high-quality text-conditional generation, we employ a Rectified Flow-based training strategy in the compressed latent space. Additionally, we contribute the DyMesh Dataset, containing over 4M diverse dynamic mesh sequences with text annotations. Experimental results demonstrate that our method generates semantically accurate and temporally coherent mesh animations in a few seconds, significantly outperforming existing approaches in both quality and efficiency. Our work marks a substantial step forward in making 4D content creation more accessible and practical. All the data, code, and models will be open-released.