点彩派头像：自回归四维高斯化身生成

摘要

我们提出了AvatarPointillist——一个从单张肖像图像生成动态4D高斯化身的创新框架。该方法的核心是仅含解码器的Transformer模型，它通过自回归方式为3D高斯泼溅生成点云。这种序列化方法实现了精准的自适应构建，能根据主体复杂度动态调整点密度与总点数。在点生成过程中，自回归模型还联合预测各点的绑定信息，从而实现逼真的动画效果。生成后，专用高斯解码器将点云转换为完整可渲染的高斯属性。我们证明，通过将解码器条件化于自回归生成器的潜在特征，可实现阶段间的有效交互并显著提升保真度。大量实验验证了AvatarPointillist能生成高质量、照片级真实感且可控的虚拟化身。我们相信这种自回归范式为化身生成开辟了新范式，代码开源将助力未来研究。

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.

点彩派头像：自回归四维高斯化身生成

AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

摘要

Support