Gassidy: Gaussian Splatting SLAM in Dynamic Environments

TL;DR

Gassidy introduces a dynamic environment-aware Gaussian Splatting SLAM method that effectively filters environmental disturbances, significantly improving camera tracking accuracy and map quality in dynamic scenes.

Contribution

It develops a novel dynamic filtering approach within Gaussian Splatting SLAM to handle environmental disturbances from moving objects.

Findings

Camera tracking precision improved by up to 97.9%.

Map quality enhanced by up to 6%.

Effective disturbance filtering in dynamic environments.

Abstract

3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dynamic objects with irregular movement, leading to degradation in both camera tracking accuracy and map reconstruction quality. To address this challenge, we develop an RGB-D dense SLAM which is called Gaussian Splatting SLAM in Dynamic Environments (Gassidy). This approach calculates Gaussians to generate rendering loss flows for each environmental component based on a designed photometric-geometric loss function. To distinguish and filter environmental disturbances, we iteratively analyze rendering loss flows to detect features characterized by changes in loss values between dynamic objects and static components. This process ensures a clean environment for accurate scene reconstruction. Compared to state-of-the-art SLAM methods, experimental results on open datasets show that Gassidy improves camera tracking precision by up to 97.9% and enhances map quality by up to 6%.