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

TL;DR

MorpheuS is a novel framework that reconstructs 360-degree dynamic surfaces from monocular RGB-D videos by modeling scene geometry and appearance, and completing unobserved regions using a diffusion prior.

Contribution

It introduces a canonical and deformation field approach combined with a view-dependent diffusion prior for realistic scene completion.

Findings

High-fidelity 360° surface reconstruction achieved.

Effective completion of unobserved regions in real-world scenes.

Applicable to both real-world and synthetic datasets.

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 scene as a canonical field that encodes its geometry and appearance, in conjunction with a deformation field that warps points from the current frame to the canonical space. We leverage a view-dependent diffusion prior and distill knowledge from it to achieve realistic completion of unobserved regions. Experimental results on various real-world and synthetic datasets show that our method can achieve high-fidelity 360{\deg} surface reconstruction of a deformable object from a monocular RGB-D video.