Chamelion🦎

Reliable Change Detection for Long-Term LiDAR Mapping in Transient Environments

Seoyeon Jang1, Alex Junho Lee2, I Made Aswin Nahrendra3, Hyun Myung1,
1KAIST, 2Sookmyung Women's Univ. 3KRAFTON
Paper arXiv Code
Overview

Chamelion is a novel approach for online change detection and long-term 3D map management, leveraging a dual-head network and composition-based augmentation for robust generalization across sensors and environments.

Chamelion is a novel approach for online change detection and long-term 3D map management, leveraging a dual-head network and composition-based augmentation for robust generalization across sensors and environments.

Composition-based Data Augmentation for Single-Session Pseudo-Label Generation

Training change detection requires multi-session data, which is costly and impractical to collect. To address this, we propose a single-session augmentation method that synthetically generates change pseudo-labels using only a single traversal of the environment.

Dual-head Structure for Change Classification and Cross-visibility Confidence Estimation

We introduce a dual-head structure designed to jointly handle change classification and cross-visibility confidence estimation.

xvisibility

The class head predicts whether each point is a change or static, while the confidence head estimates the probability that the point is visible in both the map and scan.

Experimental results

We qualitatively evaluated the generalization performance across various environments.

Code and Datasets

We will release the code and datasets. stay tuned!