DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters

TL;DR

DRiVE introduces a diffusion-based framework utilizing 3D Gaussian representations for generating and rigging complex 3D characters, significantly improving animation quality and versatility over existing methods.

Contribution

The paper presents DRiVE, a novel rigging framework that leverages 3D Gaussian diffusion for detailed character animation, along with the AnimeRig dataset for training and evaluation.

Findings

DRiVE achieves more accurate rigging results.

It enables realistic clothing and hair dynamics.

Outperforms previous methods in quality and versatility.

Abstract

Recent advances in generative models have enabled high-quality 3D character reconstruction from multi-modal. However, animating these generated characters remains a challenging task, especially for complex elements like garments and hair, due to the lack of large-scale datasets and effective rigging methods. To address this gap, we curate AnimeRig, a large-scale dataset with detailed skeleton and skinning annotations. Building upon this, we propose DRiVE, a novel framework for generating and rigging 3D human characters with intricate structures. Unlike existing methods, DRiVE utilizes a 3D Gaussian representation, facilitating efficient animation and high-quality rendering. We further introduce GSDiff, a 3D Gaussian-based diffusion module that predicts joint positions as spatial distributions, overcoming the limitations of regression-based approaches. Extensive experiments demonstrate that DRiVE achieves precise rigging results, enabling realistic dynamics for clothing and hair, and surpassing previous methods in both quality and versatility. The code and dataset will be made public for academic use upon acceptance.