RMAvatar：基于校正的网格嵌入高斯的单目视频照片级真实感人形化身重建
RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians
AI总结：
本研究提出RMAvatar，一种将高斯溅射嵌入网格的人形化身表示方法，通过网格控制高斯运动并设计姿态相关校正模块学习精细非刚性形变，从单目视频重建的带服饰化身在渲染质量与定量评估上达SOTA。
摘要：
我们提出了RMAvatar，这是一种新型的人形化身表示方法，采用嵌入在网格上的高斯溅射技术，可从单目视频中学习带服饰的化身。我们利用显式网格几何表示虚拟人的运动与形状，并通过高斯溅射实现隐式外观渲染。该方法包含两个核心模块：高斯初始化模块与高斯校正模块。我们将高斯嵌入三角形面片内，通过网格控制其运动，以此保证化身的低频运动与表面形变。由于线性混合蒙皮（LBS）公式的局限性，人体骨骼难以控制复杂的非刚性变换，因此我们设计了与姿态相关的高斯校正模块，用于学习精细的非刚性形变，进一步提升化身的真实感与表现力。我们在公开数据集上开展了大量实验，RMAvatar在渲染质量与定量评估两方面均达到了当前最优性能。项目主页见https://rm-avatar.github.io。
英文摘要：
We introduce RMAvatar, a novel human avatar representation with Gaussian splatting embedded on mesh to learn clothed avatar from a monocular video. We utilize the explicit mesh geometry to represent motion and shape of a virtual human and implicit appearance rendering with Gaussian Splatting. Our method consists of two main modules: Gaussian initialization module and Gaussian rectification module. We embed Gaussians into triangular faces and control their motion through the mesh, which ensures low-frequency motion and surface deformation of the avatar. Due to the limitations of LBS formula, the human skeleton is hard to control complex non-rigid transformations. We then design a pose-related Gaussian rectification module to learn fine-detailed non-rigid deformations, further improving the realism and expressiveness of the avatar. We conduct extensive experiments on public datasets, RMAvatar shows state-of-the-art performance on both rendering quality and quantitative evaluations. Please see our project page at https://rm-avatar.github.io.
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。
