Kornia is an open-source differentiable computer vision library for PyTorch that focuses on geometric computer vision, differentiable rendering, and spatial AI capabilities. The library includes implementations for image transformations, feature detection, camera calibration, depth estimation, and more.

CodeFlash is an AI-powered code optimization platform that helps developers identify and implement performance improvements in their codebase. CodeFlash analyzes code patterns and suggests optimizations that maintain correctness while significantly improving execution speed.

The primary goal of this hackathon is to improve the performance of the Kornia library through high-quality contributions that optimize existing functionality without compromising correctness. Participants will use CodeFlash to identify potential optimizations and submit pull requests to the Kornia repository.

• Open to all college/university students (undergraduate and graduate) 

• Participants must be at least 18 years of age

• Individual participation only (no teams)

• Previous experience with PyTorch and/or computer vision is recommended but not required