Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)
-
Updated
Oct 7, 2025 - Python
Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)
Official Repo of NeurIPS '21: "Trust, but Verify: Cross-Modality Fusion for HD Map Change Detection"
Leveraging HD Maps for 3d object detection
Detecting street poles in HD map point cloud data.
🛣️ Live on-device top-down lane mapping from a dash-mounted phone. ARCore + LiteRT lane detection, lane vectorization, and HD-map exports (GeoJSON, OpenDRIVE, Lanelet2, KML) plus ML dataset export. 100% offline. Kotlin/Android.
Core pipeline for the detection of road lines and their representation in world coordinates. Base for several autonomous vehicles works.
Dynamic-scene-robust HD-map localization for cheap vision sensors: ONNX masking + 2D ICP + gated EKF, on ROS2 with an AWS map/model pipeline.
Production-grade Python engineering playbooks for HD vehicle mapping & autonomous-vehicle spatial data — HD map architecture, lane geometry, and sensor fusion.
An India-native, self-improving data engine for autonomous driving. Auto-labeling with a calibrated confidence gate, active learning, HD maps, per-object dynamics, and a governed closed loop.
Turn any Android phone into an HD mapping device for self-driving cars. On-device camera+GNSS+IMU to lane-level HD maps with OpenDRIVE/Lanelet2/GeoJSON export. By Sherin Joseph Roy / blurabbit.com
Add a description, image, and links to the hd-maps topic page so that developers can more easily learn about it.
To associate your repository with the hd-maps topic, visit your repo's landing page and select "manage topics."