Ani3DHuman：基于自引导随机采样的逼真三维人体动画
Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling
提出自引导随机采样策略，解决扩散模型在分布外输入（如粗糙渲染）下的采样失败问题，可迁移到其他需要高质量恢复或超分的视觉任务；同时分层运动表示将刚性运动与非刚性残差解耦，为动态人体建模提供可复用思路。
原文依据 self-guided stochastic sampling, which effectively solves the out-of-distribution problem by combining stochastic sampling (for photorealistic quality) with self-guidance (for identity fidelity)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前的三维人体动画方法无法实现逼真效果：基于运动学的方法缺乏衣物等非刚性动态，而从生成视频重建的方法则受低质量伪影和身份丢失困扰。为克服这些局限，我们提出 Ani3DHuman，一个将基于运动学的动画与视频扩散先验相结合的框架。我们首先引入一种分层运动表示，将刚性运动与残差非刚性运动解耦。然后，我们使用预训练视频扩散模型对来自网格绑定动画的粗糙渲染进行恢复，为运动场提供监督。然而，这种基于扩散采样的恢复任务极具挑战性，因为初始渲染是分布外的，导致标准确定性 ODE 采样器失败。因此，我们的核心技术贡献是自引导随机采样，它通过结合随机采样（实现逼真质量）与自引导（保持身份保真度）有效解决了分布外问题。这些恢复的视频提供了高质量监督，使得能够优化逼真的四维运动场。Ani3DHuman 取得了最优结果，消融实验验证了采样器的两个组件对于高保真恢复都是必不可少的。
英文原文摘要 1332 字符
Current 3D human animation methods fail at photorealism: kinematics-based approaches lack non-rigid dynamics like clothing, while methods reconstructing from generated videos suffer from low-quality artifacts and identity loss. To overcome these limitations, we present Ani3DHuman, a framework that marries kinematics-based animation with video diffusion priors. We first introduce a layered motion representation that disentangles rigid motion and residual non-rigid motion. Then, we use a pretrained video diffusion model to restore a coarse rendering from the mesh-rigged animation, which provides supervision for the motion field. However, this restoration task, based on diffusion sampling, is highly challenging, as the initial renderings are out-of-distribution, causing standard deterministic ODE samplers to fail. Therefore, our core technical contribution is self-guided stochastic sampling, which effectively solves the out-of-distribution problem by combining stochastic sampling (for photorealistic quality) with self-guidance (for identity fidelity). These restored videos provide high-quality supervision, enabling the optimization of a realistic 4D motion field. Ani3DHuman achieves state-of-the-art results, and our ablations validate that both components of our sampler are essential for high-fidelity restoration.