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

arXiv: https://arxiv.org/abs/2602.08189 · HTML: https://mlsanity.com/paper/2602.08189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data](https://mlsanity.com/paper/2105.08971/) (2021)
- [Weakly Supervised Silhouette-based Semantic Scene Change Detection](https://mlsanity.com/paper/1811.11985/) (2018)
- [Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency](https://mlsanity.com/paper/2109.10165/) (2021)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection](https://mlsanity.com/paper/2103.00879/) (2021)
- [ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building](https://mlsanity.com/paper/2103.04316/) (2021)
- [ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments](https://mlsanity.com/paper/2103.05368/) (2021)
- [Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation](https://mlsanity.com/paper/2307.08314/) (2023)
- [TRAVEL: Traversable Ground and Above-Ground Object Segmentation Using Graph Representation of 3D LiDAR Scans](https://mlsanity.com/paper/2206.03190/) (2022)
- [LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping](https://mlsanity.com/paper/2107.07712/) (2021)
- [LiSTA: Geometric Object-Based Change Detection in Cluttered Environments](https://mlsanity.com/paper/2403.02175/) (2024)
- [TOSS: Real-time Tracking and Moving Object Segmentation for Static Scene Mapping](https://mlsanity.com/paper/2408.05453/) (2024)
- [LTS-NET: End-to-end Unsupervised Learning of Long-Term 3D Stable objects](https://mlsanity.com/paper/2301.03426/) (2023)

## Abstract (arXiv)

Online change detection is crucial for mobile robots to efficiently navigate through dynamic environments. Detecting changes in transient settings, such as active construction sites or frequently reconfigured indoor spaces, is particularly challenging due to frequent occlusions and spatiotemporal variations. Existing approaches often struggle to detect changes and fail to update the map across different observations. To address these limitations, we propose a dual-head network designed for online change detection and long-term map maintenance. A key difficulty in this task is the collection and alignment of real-world data, as manually registering structural differences over time is both labor-intensive and often impractical. To overcome this, we develop a data augmentation strategy that synthesizes structural changes by importing elements from different scenes, enabling effective model training without the need for extensive ground-truth annotations. Experiments conducted at real-world construction sites and in indoor office environments demonstrate that our approach generalizes well across diverse scenarios, achieving efficient and accurate map updates.resubmitOur source code and additional material are available at: https://chamelion-pages.github.io/.