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

2025-11-19

AI Summary

To address the rapid obsolescence of urban high-definition (HD) maps caused by dynamic environmental changes, this paper introduces UrbanMapUpdate—the first image-guided 3D point cloud map updating benchmark at city scale. Our method integrates calibrated RGB images with real-world LiDAR point clouds, leveraging Structure-from-Motion (SfM) reconstruction, synthetic change mask generation, and a scalable editing toolchain to construct a large-scale dataset covering 73 km of trajectories and containing over 23,000 synthetic change instances. UrbanMapUpdate enables, for the first time, end-to-end evaluation—from 2D image-based change detection to 3D incremental map updates. We publicly release both the benchmark dataset and an open-source toolchain, along with baseline methods, significantly enhancing reproducibility, traceability, and scalability in map updating research. This work provides critical infrastructure for maintaining dynamic HD maps in autonomous driving and smart city applications.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

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 However, these maps quickly become outdated as environments evolve, creating a need for robust methods that not only detect changes but also incorporate them into updated 3D representations.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 $ ext{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.

Problem

• Addressing the gap between 2D change detection and 3D map updating
• Providing city-scale benchmark for HD map maintenance through point cloud updates
• Solving outdated map issues for urban planning and autonomous navigation

Innovation

• Dataset for 3D HD map updating via change detection
• Baseline methods using image-based structure-from-motion pipeline
• Comprehensive toolkit supporting scalability and trackability