kornia
Differentiable computer vision for PyTorch, from research to robotics.
artificial-intelligencecomputer-visiondeep-learninghacktoberfest
Kornia is a geometric computer vision library for PyTorch that provides a comprehensive set of differentiable operators. It solves the problem of integrating traditional vision algorithms into modern deep learning pipelines by making them GPU-accelerated, batched, and fully differentiable. It's designed for researchers, engineers, and practitioners working on spatial AI, robotics, and any application requiring computer vision within a PyTorch ecosystem.
