MorpheuS: Neural Dynamic 360{\deg} Surface Reconstruction from Monocular RGB-D Video

arXiv:2312.00778v2 Announce Type: replace
Abstract: Neural rendering has demonstrated remarkable success in dynamic scene reconstruction. Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the target object. Despite this, real-world video scenarios often feature large unobserved regions where neural representations struggle to achieve realistic completion. To tackle this challenge, we introduce MorpheuS, a framework for dynamic 360{\deg} surface reconstruction from a casually captured RGB-D video. Our approach models the target …

abstract arxiv cs.cv dynamic feature fidelity morpheus neural rendering object prior rendering rgb-d success surface type video world