Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction

arXiv:2312.01196v2 Announce Type: replace
Abstract: Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, high-quality novel views from camera positions that are significantly different from the training views. In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we …

abstract arxiv consistent cs.cv dynamic however nature novel object objects parametric quality solution type videos work