OpenDriveLab/Birds-eye-view-Perception resource

Health v2 · maintenance only

Adoption not part of the score

1381 stars · 122 forks observed · 2026-08-28

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

An awesome-list and survey companion for bird's-eye-view (BEV) perception in autonomous driving, paired with an open-source PyTorch BEV toolbox. It curates papers across camera, LiDAR, and fusion modalities and provides recipes for state-of-the-art 3D detection.

Use cases

• find BEV perception papers for autonomous driving
• learn bird's-eye-view 3D object detection from scratch
• get recipes to improve camera-based 3D detection performance
• compare BEV algorithms for lidar and camera fusion
• find a starting point for BEV perception research
• reproduce state-of-the-art BEV detection results

When to choose

• you are a researcher or engineer working on BEV perception for autonomous driving
• you want a curated literature survey plus practical training recipes
• you need a PyTorch toolbox baseline for camera-based 3D detection

When to avoid

• you need a production-ready perception stack for a deployed vehicle
• your task is unrelated to bird's-eye-view or 3D perception
• you want a plug-and-play tool with no ML background

Facets

learning-resource · maturity active

machine-learning computer-vision benchmarking documentation autonomous-vehicles computer-vision deep-learning tutorials python birds-eye-view 3d-object-detection lidar camera-perception awesome-list survey-paper autonomous-driving gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="OpenDriveLab/Birds-eye-view-Perception")