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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Shouhe, Ren, Dayong, Song, Sensen, Qian, Yurong, Jia, Zhenhong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912735190581248
author Zhang, Shouhe
Ren, Dayong
Song, Sensen
Qian, Yurong
Jia, Zhenhong
author_facet Zhang, Shouhe
Ren, Dayong
Song, Sensen
Qian, Yurong
Jia, Zhenhong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM
Zhang, Shouhe
Ren, Dayong
Song, Sensen
Qian, Yurong
Jia, Zhenhong
Computer Vision and Pattern Recognition
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.
title Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22968