用自回归方法从一张照片生成可动的4D高斯角色，精度高且能自动调节复杂度。
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
- 自回归Transformer逐点生成3D高斯点云，动态调整点密度和数量。
- 生成时同步预测绑定信息，实现真实动画效果，渲染质量显著提升。
- 适合做高质量虚拟角色生成的研究者与开发者，代码将开源。
我们提出AvatarPointillist，一种从单张肖像图生成动态4D高斯角色的新框架。核心是一个仅解码器的Transformer，自回归地生成3D高斯溅射的点云。该序列化方法允许精确、自适应的构建过程，根据主体复杂度动态调整点密度和总点数。生成过程中，自回归模型同时预测每个点的绑定信息，支持真实感动画。生成后，专用高斯解码器将点转换为完整可渲染的高斯属性。实验表明，将解码器条件化在自回归生成器的潜在特征上，能有效促进阶段间交互，显著提升保真度。大量实验证明，AvatarPointillist可生成高质量、逼真且可控的虚拟角色。我们认为这种自回归范式代表了角色生成的新方向，代码将开源以激励后续研究。
原文摘要 · Abstract (English)
We introduce AvatarPointillist, a novel framework for generating dynamic 4D Gaussian avatars from a single portrait image. At the core of our method is a decoder-only Transformer that autoregressively generates a point cloud for 3D Gaussian Splatting. This sequential approach allows for precise, adaptive construction, dynamically adjusting point density and the total number of points based on the subject's complexity. During point generation, the AR model also jointly predicts per-point binding information, enabling realistic animation. After generation, a dedicated Gaussian decoder converts the points into complete, renderable Gaussian attributes. We demonstrate that conditioning the decoder on the latent features from the AR generator enables effective interaction between stages and markedly improves fidelity. Extensive experiments validate that AvatarPointillist produces high-quality, photorealistic, and controllable avatars. We believe this autoregressive formulation represents a new paradigm for avatar generation, and we will release our code inspire future research.
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。