Learning Topology Uniformed Face Mesh by Volume Rendering for Multi-view Reconstruction

arXiv:2404.05606v1 Announce Type: new
Abstract: Face meshes in consistent topology serve as the foundation for many face-related applications, such as 3DMM constrained face reconstruction and expression retargeting. Traditional methods commonly acquire topology uniformed face meshes by two separate steps: multi-view stereo (MVS) to reconstruct shapes followed by non-rigid registration to align topology, but struggles with handling noise and non-lambertian surfaces. Recently neural volume rendering techniques have been rapidly evolved and shown great advantages in 3D reconstruction or novel view synthesis. …

abstract applications arxiv consistent cs.cv face foundation mesh meshes registration rendering serve topology type view