Popular GitHub Repositories for Urban Mobility

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image and UAV image segmentation.

A data standard to enable right-of-way regulation, digital policy, geofencing, and two-way communication between mobility companies and public agencies worldwide.

[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"

Roach: End-to-End Urban Driving by Imitating a Reinforcement Learning Coach. ICCV 2021.

Real-time LIDAR-based Urban Road and Sidewalk detection for Autonomous Vehicles ?

Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning

[TNNLS] Differentiable Integrated Prediction and Planning Framework for Urban Autonomous Driving

A deep reinforcement learning (DRL) based approach for spatial layout of land use and roads in urban communities. (Nature Computational Science)

A professional list of Deep Learning and Large (Language) Models (LM, LLM, FM) for Trajectory Data Management and Mining.

Official implementation for "UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction" (KDD 2024)

A professional list on Multi-modal Data Fusion Models and Key Datasets for Urban Computing.

[ECCV'22 Oral] Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes

[CVPR 2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

[ICDE'2023] When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments (CVPR2023)

This repository contains the code for the paper "LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments".

[NeurIPS'2023] "GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks"

An efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc.

Official PyTorch implementation of "UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video"

[WWW'2023] "AutoST: Automated Spatio-Temporal Graph Contrastive Learning"