The paper introduces GoMAvatar, a novel approach for real-time, memory-efficient, high-quality animatable human modeling from a single monocular video. The key contribution is the Gaussians-on-Mesh (GoM) representation, which combines the rendering quality and speed of Gaussian splatting with the geometry modeling and compatibility of deformable meshes.
The GoM representation attaches Gaussian splats to a deformable mesh, allowing for efficient rendering and articulation. The authors also propose a unique differentiable shading module that splits the final color into a pseudo albedo map from Gaussian splatting and a pseudo shading map derived from the normal map.
Extensive experiments on the ZJU-MoCap, PeopleSnapshot, and YouTube datasets show that GoMAvatar matches or surpasses the rendering quality of state-of-the-art monocular human modeling algorithms, while significantly outperforming them in computational efficiency (43 FPS) and memory efficiency (3.63 MB per subject).
إلى لغة أخرى
من محتوى المصدر
arxiv.org
الرؤى الأساسية المستخلصة من
by Jing Wen,Xia... في arxiv.org 04-12-2024
https://arxiv.org/pdf/2404.07991.pdfاستفسارات أعمق