GauHuman：来自单目人体视频的铰接式高斯泼溅
GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
AI总结：
本文提出 GauHuman，通过标准空间高斯泼溅、LBS姿态变换、KL散度引导及高斯合并等策略，从单目视频快速重建可实时渲染的高质量三维人体。
摘要：
我们提出了 GauHuman，这是一种采用 Gaussian Splatting（高斯泼溅）的三维人体模型，兼具快速训练（1至2分钟）和实时渲染（最高189 FPS）能力；相比之下，现有基于 NeRF 的隐式表示建模框架需要数小时训练，且每帧渲染需要数秒。具体而言，GauHuman 在标准空间中编码 Gaussian Splatting，并使用线性混合蒙皮（LBS）将三维高斯从标准空间变换到姿态空间；其中设计了有效的姿态和 LBS 细化模块，以可忽略的计算成本学习三维人体的精细细节。此外，为实现 GauHuman 的快速优化，我们利用三维人体先验初始化并剪枝三维高斯，同时通过 KL 散度引导进行分裂/克隆，并采用一种新颖的合并操作进一步加速。在 ZJU_Mocap 和 MonoCap 数据集上的大量实验表明，GauHuman 在定量和定性方面均达到最先进性能，并具有快速训练和实时渲染速度。值得注意的是，在不牺牲渲染质量的情况下，GauHuman 能够使用约13k个三维高斯快速建模三维人体表演者。
英文摘要：
We present, GauHuman, a 3D human model with Gaussian Splatting for both fast training (1 ~ 2 minutes) and real-time rendering (up to 189 FPS), compared with existing NeRF-based implicit representation modelling frameworks demanding hours of training and seconds of rendering per frame. Specifically, GauHuman encodes Gaussian Splatting in the canonical space and transforms 3D Gaussians from canonical space to posed space with linear blend skinning (LBS), in which effective pose and LBS refinement modules are designed to learn fine details of 3D humans under negligible computational cost. Moreover, to enable fast optimization of GauHuman, we initialize and prune 3D Gaussians with 3D human prior, while splitting/cloning via KL divergence guidance, along with a novel merge operation for further speeding up. Extensive experiments on ZJU_Mocap and MonoCap datasets demonstrate that GauHuman achieves state-of-the-art performance quantitatively and qualitatively with fast training and real-time rendering speed. Notably, without sacrificing rendering quality, GauHuman can fast model the 3D human performer with ~13k 3D Gaussians.
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。
