ProDyGS: Dynamic Gaussian Splatting from a Single Static Monocular Camera

arXiv:2609.32711 · cs.CV · Submitted 2026-09-26 · Read on arXiv

cs.CV

Submitted: 2026-09-26

Updated: 2026-09-26

Project page: https://prodygs.github.io

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: We present ProDyGS, a novel dynamic 3D Gaussian Splatting framework for high-quality novel view synthesis from videos captured by a single static camera.

Terminology

Abstract

We present ProDyGS, a novel dynamic 3D Gaussian Splatting framework for high-quality novel view synthesis from videos captured by a single static camera. While existing methods rely on multi-view setups or significant camera motion for geometric constraints, our approach addresses the challenging scenario where multi-view supervision is completely absent. We overcome this limitation by generating synthetic multi-view supervision through depth-guided proxy image synthesis. Specifically, we estimate temporally consistent depth maps using foundational monocular depth networks, then construct 3D Gaussian representations that generate proxy images from arbitrary viewpoints. A deformation network learns temporal dynamics by warping canonical Gaussians using this augmented supervision. Experiments on the DyNeRF dataset demonstrate that our method achieves state-of-the-art performance while requiring only monocular depth estimation as external supervision, outperforming approaches that rely on stronger priors such as scene flow.

Sources

Related papers