autonomousvision/transfuser

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1606 stars · 245 forks observed · 2026-10-08

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of TransFuser, a transformer-based multi-modal sensor fusion model for end-to-end autonomous driving, published at CVPR 2021 and PAMI 2023. It includes training, dataset generation, and evaluation pipelines on the CARLA simulator.

Use cases

• train an end-to-end autonomous driving agent in CARLA
• fuse camera and LiDAR data with a transformer for driving
• reproduce PAMI 2023 TransFuser results on the CARLA leaderboard
• run imitation learning for self-driving research
• evaluate driving agents in CARLA 0.9.10
• compare multi-modal fusion approaches for autonomous driving

When to choose

• you need a state-of-the-art imitation learning baseline for CARLA-based driving research
• you want to study transformer-based camera-LiDAR fusion for end-to-end driving
• you need reproducible code from a peer-reviewed autonomous driving paper

When to avoid

• you need a production autonomous driving stack for real vehicles
• you cannot run CARLA or lack a GPU
• you want a general-purpose sensor fusion library outside driving simulation

Facets

library · maturity stable

machine-learning deep-learning computer-vision simulation autonomous-vehicles deep-learning machine-learning simulation python sensor-fusion imitation-learning transformers carla autonomous-driving research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="autonomousvision/transfuser")