PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments

TL;DR

PG-SLAM introduces a photo-realistic, geometry-aware RGB-D SLAM approach that effectively handles dynamic environments by modeling both static and moving objects, improving localization and scene reconstruction accuracy.

Contribution

The paper presents a novel SLAM method extending Gaussian splatting to jointly map dynamic foregrounds and static backgrounds, enhancing scene completeness and localization in dynamic scenes.

Findings

Outperforms state-of-the-art in camera localization accuracy.

Provides photo-realistic scene reconstruction in dynamic environments.

Effectively models non-rigid and rigid moving objects.

Abstract

Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in incomplete scene reconstruction and limited accuracy of camera localization. The other works express dynamic objects by point clouds, sparse joints, or coarse meshes, which fails to provide a photo-realistic representation. To overcome the above limitations, we propose a photo-realistic and geometry-aware RGB-D SLAM method by extending Gaussian splatting. Our method is composed of three main modules to 1) map the dynamic foreground including non-rigid humans and rigid items, 2) reconstruct the static background, and 3) localize the camera. To map the foreground, we focus on modeling the deformations and/or motions. We consider the shape priors of humans and exploit geometric and appearance constraints of humans and items. For background mapping, we design an optimization strategy between neighboring local maps by integrating appearance constraint into geometric alignment. As to camera localization, we leverage both static background and dynamic foreground to increase the observations for noise compensation. We explore the geometric and appearance constraints by associating 3D Gaussians with 2D optical flows and pixel patches. Experiments on various real-world datasets demonstrate that our method outperforms state-of-the-art approaches in terms of camera localization and scene representation. Source codes will be publicly available upon paper acceptance.