Fast-SNARF: A Fast Deformer for Articulated Neural Fields

Xu Chen, Tianjian Jiang, Jie Song, Max Rietmann, Andreas Geiger, Michael J. Black, Otmar Hilliges

Abstract: Neural fields have revolutionized the area of 3D reconstruction and novel view synthesis of <i>rigid</i> scenes. A key challenge in making such methods applicable to <i>articulated</i> objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space. We propose a new articulation module for neural fields, Fast-SNARF, which finds accurate correspondences between canonical space and posed space via iterative root finding. Fast-SNARF is a drop-in replacement in functionality to our previous work, SNARF, while significantly improving its computational efficiency. We contribute several algorithmic and implementation improvements over SNARF, yielding a speed-up of <inline-formula><tex-math notation="LaTeX">$150\times$</tex-math></inline-formula> . These improvements include voxel-based correspondence search, pre-computing the linear blend skinning function, and an efficient software implementation with CUDA kernels. Fast-SNARF enables efficient and simultaneous optimization of shape and skinning weights given deformed observations without correspondences (e.g. 3D meshes). Because learning of deformation maps is a crucial component in many 3D human avatar methods and since Fast-SNARF provides a computationally efficient solution, we believe that this work represents a significant step towards the practical creation of 3D virtual humans.