SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection

TL;DR

SceneEdited introduces a comprehensive city-scale dataset and toolkit for research on updating 3D HD maps using image-guided change detection, addressing the gap between change detection and map updating.

Contribution

It provides the first large-scale dataset with synthesized urban changes and baseline methods for 3D map updating from images, facilitating future research.

Findings

Over 23,000 synthesized object changes in 800+ scenes

Baseline methods demonstrate feasibility of image-based 3D map updating

Dataset and toolkit are publicly available for benchmarking

Abstract

Accurate, up-to-date High-Definition (HD) maps are critical for urban planning, infrastructure monitoring, and autonomous navigation. However, these maps quickly become outdated as environments evolve, creating a need for robust methods that not only detect changes but also incorporate them into updated 3D representations. While change detection techniques have advanced significantly, there remains a clear gap between detecting changes and actually updating 3D maps, particularly when relying on 2D image-based change detection. To address this gap, we introduce SceneEdited, the first city-scale dataset explicitly designed to support research on HD map maintenance through 3D point cloud updating. SceneEdited contains over 800 up-to-date scenes covering 73 km of driving and approximate 3 $\text{km}^2$ of urban area, with more than 23,000 synthesized object changes created both manually and automatically across 2000+ out-of-date versions, simulating realistic urban modifications such as missing roadside infrastructure, buildings, overpasses, and utility poles. Each scene includes calibrated RGB images, LiDAR scans, and detailed change masks for training and evaluation. We also provide baseline methods using a foundational image-based structure-from-motion pipeline for updating outdated scenes, as well as a comprehensive toolkit supporting scalability, trackability, and portability for future dataset expansion and unification of out-of-date object annotations. Both the dataset and the toolkit are publicly available at https://github.com/ChadLin9596/ScenePoint-ETK, establising a standardized benchmark for 3D map updating research.