HumanSplat：具备结构先验的可泛化单图像人体高斯泼溅重建
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
AI总结：
针对现有高保真人体重建依赖多视角图像或逐实例优化的局限，提出带结构先验的可泛化单图人体三维高斯泼溅方法HumanSplat，通过多视图扩散模型、结构先验Transformer及分层损失实现更优的照片级新视角合成。
摘要：
尽管高保真人体重建技术近期取得进展，但对密集采集图像或耗时的逐实例优化的需求，极大限制了其在更广泛场景中的应用。为解决这些问题，我们提出HumanSplat，该方法以可泛化的方式从单张输入图像预测任意人体的3D Gaussian Splatting（三维高斯泼溅）属性。具体而言，HumanSplat包含一个2D多视图扩散模型和一个带有人体结构先验的隐空间重建Transformer，可在统一框架中巧妙整合几何先验与语义特征。我们进一步设计了融入人体语义信息的分层损失，以实现高保真纹理建模，并更好地约束估计得到的多视图结果。在标准基准和真实场景图像上的综合实验表明，HumanSplat在实现照片级真实感新视角合成方面超越了现有最先进方法。
英文摘要：
Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
