Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
This addresses the challenge of realistic 4D human creation for applications like virtual reality and animation, representing a novel method for a known bottleneck.
The paper tackles the problem of generating and animating 4D humans from a single image by introducing Disco4D, a framework that disentangles clothing from the body using Gaussian Splatting and diffusion models, resulting in enhanced details and flexibility as demonstrated in extensive experiments.
We present \textbf{Disco4D}, a novel Gaussian Splatting framework for 4D human generation and animation from a single image. Different from existing methods, Disco4D distinctively disentangles clothings (with Gaussian models) from the human body (with SMPL-X model), significantly enhancing the generation details and flexibility. It has the following technical innovations. \textbf{1)} Disco4D learns to efficiently fit the clothing Gaussians over the SMPL-X Gaussians. \textbf{2)} It adopts diffusion models to enhance the 3D generation process, \textit{e.g.}, modeling occluded parts not visible in the input image. \textbf{3)} It learns an identity encoding for each clothing Gaussian to facilitate the separation and extraction of clothing assets. Furthermore, Disco4D naturally supports 4D human animation with vivid dynamics. Extensive experiments demonstrate the superiority of Disco4D on 4D human generation and animation tasks. Our visualizations can be found in \url{https://disco-4d.github.io/}.