ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion

TL;DR

ActionMesh is a novel generative model that creates high-quality, animated 3D meshes efficiently by incorporating temporal diffusion and autoencoding, enabling rapid, topology-consistent animations from various inputs.

Contribution

The paper introduces ActionMesh, a fast, rig-free 3D animation generation framework using temporal 3D diffusion and autoencoding, improving quality and speed over prior methods.

Findings

Achieves state-of-the-art geometric accuracy and temporal consistency.

Generates animated 3D meshes from videos, text, or static meshes.

Produces results with rapid inference and topology preservation.

Abstract

Generating animated 3D objects is at the heart of many applications, yet most advanced works are typically difficult to apply in practice because of their limited setup, their long runtime, or their limited quality. We introduce ActionMesh, a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. Drawing inspiration from early video models, our key insight is to modify existing 3D diffusion models to include a temporal axis, resulting in a framework we dubbed "temporal 3D diffusion". Specifically, we first adapt the 3D diffusion stage to generate a sequence of synchronized latents representing time-varying and independent 3D shapes. Second, we design a temporal 3D autoencoder that translates a sequence of independent shapes into the corresponding deformations of a pre-defined reference shape, allowing us to build an animation. Combining these two components, ActionMesh generates animated 3D meshes from different inputs like a monocular video, a text description, or even a 3D mesh with a text prompt describing its animation. Besides, compared to previous approaches, our method is fast and produces results that are rig-free and topology consistent, hence enabling rapid iteration and seamless applications like texturing and retargeting. We evaluate our model on standard video-to-4D benchmarks (Consistent4D, Objaverse) and report state-of-the-art performances on both geometric accuracy and temporal consistency, demonstrating that our model can deliver animated 3D meshes with unprecedented speed and quality.