bradyz/cross_view_transformers
Cross-view Transformers for real-time Map-view Semantic Segmentation (CVPR 2022 Oral)
This project helps self-driving car developers and researchers convert raw camera footage from a vehicle into a detailed, bird's-eye-view semantic map in real-time. It takes multiple camera images and the vehicle's position as input and produces a segmented map showing different elements like roads, lanes, and pedestrians. This is ideal for those working on autonomous navigation, perception, and environmental understanding for self-driving vehicles.
573 stars. No commits in the last 6 months.
Use this if you need to generate highly accurate, real-time semantic maps from vehicle camera inputs for autonomous driving applications.
Not ideal if you are looking for a general-purpose image segmentation tool or if your primary input is not multi-view vehicle camera data.
Stars
573
Forks
83
Language
Python
License
MIT
Category
Last pushed
Nov 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bradyz/cross_view_transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.