单图生成带衣服的4D人体，衣服和身体分离建模更精细。
Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
- 用高斯点云分离人体与衣物建模，提升细节与灵活性。
- 结合扩散模型生成遮挡部位，支持动态4D动画。
- 每件衣物独立编码，可提取复用，适合影视动画应用。
我们提出Disco4D，一种基于高斯溅射的4D人体生成与动画新框架，仅需单张图像即可完成。不同于现有方法，Disco4D将衣物（用高斯模型）与人体（用SMPL-X模型）进行解耦，显著提升生成细节与灵活性。技术上：1）高效拟合衣物高斯点云到SMPL-X高斯点云；2）引入扩散模型增强3D生成，如重建输入图像中不可见的遮挡区域；3）为每个衣物高斯学习身份编码，便于衣物资产的分离与提取。该方法天然支持生动的4D人体动画。大量实验表明其在4D人体生成与动画任务中表现优越。可视化结果见：https://disco-4d.github.io/。
原文摘要 · Abstract (English)
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/}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。