MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

TL;DR

MoDGS introduces a novel pipeline that leverages depth priors and a 3D-aware initialization to enable high-quality novel view synthesis of dynamic scenes from casually captured monocular videos, overcoming previous camera motion limitations.

Contribution

The paper presents MoDGS, a new method that effectively reconstructs dynamic scenes from static or slowly moving camera videos using depth guidance and innovative initialization techniques.

Findings

Outperforms state-of-the-art methods significantly.

Capable of rendering high-quality views from casual monocular videos.

Effective in handling static or slow camera movements.

Abstract

In this paper, we propose MoDGS, a new pipeline to render novel views of dy namic scenes from a casually captured monocular video. Previous monocular dynamic NeRF or Gaussian Splatting methods strongly rely on the rapid move ment of input cameras to construct multiview consistency but struggle to recon struct dynamic scenes on casually captured input videos whose cameras are either static or move slowly. To address this challenging task, MoDGS adopts recent single-view depth estimation methods to guide the learning of the dynamic scene. Then, a novel 3D-aware initialization method is proposed to learn a reasonable deformation field and a new robust depth loss is proposed to guide the learning of dynamic scene geometry. Comprehensive experiments demonstrate that MoDGS is able to render high-quality novel view images of dynamic scenes from just a casually captured monocular video, which outperforms state-of-the-art meth ods by a significant margin. The code will be publicly available.