MasterHow/CSFlow
[IV2022] pytorch implementation for 'CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving'
This project helps autonomous driving engineers analyze vehicle movement by precisely tracking how objects move across a sequence of camera images. It takes in pairs of consecutive video frames from a vehicle's cameras and outputs 'optical flow' data, which details the pixel-level motion between those frames. Autonomous driving perception engineers or researchers would use this to improve the vehicle's understanding of its surroundings.
No commits in the last 6 months.
Use this if you need highly accurate optical flow estimations from video streams to enhance autonomous vehicle navigation and perception systems.
Not ideal if your application is outside of autonomous driving, or if you need to run optical flow in real-time on resource-constrained embedded systems without dedicated AI acceleration.
Stars
37
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jun 30, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MasterHow/CSFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openspyrit/spyrit
A Python toolbox for deep image reconstruction, with emphasis on single-pixel imaging.
RobotLocomotion/pytorch-dense-correspondence
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
Fyusion/LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
pmh47/dirt
DIRT: a fast differentiable renderer for TensorFlow
marrlab/SHAPR_torch
SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D...