Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM

TL;DR

This paper introduces a novel semantic SLAM framework that achieves illumination invariance through intrinsic appearance normalization and dynamic radiance balancing, significantly improving robustness and accuracy in challenging lighting conditions.

Contribution

It proposes a new SLAM system combining proactive and reactive illumination-invariance modules, enhancing robustness against extreme lighting variations.

Findings

State-of-the-art camera tracking accuracy

Improved map quality under extreme exposure

Enhanced semantic and geometric accuracy

Abstract

Extreme exposure degrades both the 3D map reconstruction and semantic segmentation accuracy, which is particularly detrimental to tightly-coupled systems. To achieve illumination invariance, we propose a novel semantic SLAM framework with two designs. First, the Intrinsic Appearance Normalization (IAN) module proactively disentangles the scene's intrinsic properties, such as albedo, from transient lighting. By learning a standardized, illumination-invariant appearance model, it assigns a stable and consistent color representation to each Gaussian primitive. Second, the Dynamic Radiance Balancing Loss (DRB-Loss) reactively handles frames with extreme exposure. It activates only when an image's exposure is poor, operating directly on the radiance field to guide targeted optimization. This prevents error accumulation from extreme lighting without compromising performance under normal conditions. The synergy between IAN's proactive invariance and DRB-Loss's reactive correction endows our system with unprecedented robustness. Evaluations on public datasets demonstrate state-of-the-art performance in camera tracking, map quality, and semantic and geometric accuracy.