5had3z/motion-perceiver
Official Pytorch Implementation of MotionPerceiver: Real-Time Occuapncy Forecasting for Embedded Systems
This project helps self-driving car developers and researchers accurately predict how vehicle and pedestrian traffic will evolve in real-time. It takes sensor data like traffic signals, road layout, and detected agents as input, and outputs predictions of future occupancy grids—showing where things will be. This tool is designed for autonomous vehicle engineers and researchers who need efficient, real-time environmental awareness.
No commits in the last 6 months.
Use this if you are developing autonomous vehicles or robotics and need to forecast dynamic environments with high accuracy and low computational overhead on embedded systems.
Not ideal if your application doesn't require real-time occupancy prediction or if you are not working with autonomous systems and their specific sensor data.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/5had3z/motion-perceiver"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.