JiayuZou2020/DiffBEV

Official PyTorch implementation for a conditional diffusion probability model in BEV perception

37
/ 100
Emerging

DiffBEV helps autonomous driving engineers create more accurate bird's eye view (BEV) representations of a vehicle's surroundings. It takes in raw camera images and LiDAR scans, which often contain noise, and processes them to output a cleaner, more comprehensive BEV semantic map and 3D object detection. This improves the foundational data used for crucial tasks like vehicle planning and motion prediction.

255 stars. No commits in the last 6 months.

Use this if you need to improve the accuracy and robustness of BEV perception data for autonomous vehicle systems, especially when dealing with noisy sensor inputs.

Not ideal if you are looking for a general-purpose image processing tool or if your primary goal is not related to autonomous driving BEV perception.

autonomous-driving vehicle-perception bird's-eye-view 3d-object-detection semantic-segmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

255

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Apr 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JiayuZou2020/DiffBEV"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.