mit-han-lab/bevfusion
A multi-sensor fusion framework for autonomous driving that unifies camera and LiDAR data in bird's-eye view for 3D perception tasks.
Not currently ranked — collecting fresh signals.
star history
BEVFusion is an ICRA 2023 paper that addresses limitations of point-level sensor fusion by unifying camera and LiDAR features in a shared bird’s-eye view representation. It performs both 3D object detection and semantic segmentation tasks using a PyTorch-based architecture. The system ranks first on multiple 3D detection benchmarks including Waymo, nuScenes, and Argoverse.
Frequently asked
- What is mit-han-lab/bevfusion?
- A multi-sensor fusion framework for autonomous driving that unifies camera and LiDAR data in bird's-eye view for 3D perception tasks.
- Is bevfusion open source?
- Yes — mit-han-lab/bevfusion is open source, released under the Apache-2.0 license.
- What language is bevfusion written in?
- mit-han-lab/bevfusion is primarily written in Python.
- How popular is bevfusion?
- mit-han-lab/bevfusion has 3.2k stars on GitHub.
- Where can I find bevfusion?
- mit-han-lab/bevfusion is on GitHub at https://github.com/mit-han-lab/bevfusion.