A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
This provides a tool for researchers and developers in computer vision to enhance neural network training with differentiable routines, though it is incremental as it builds on existing libraries like OpenCV and PyTorch.
The authors introduced Kornia, an open-source differentiable computer vision library for PyTorch that tackles generic computer vision problems by enabling integration of operators into neural networks, resulting in faster systems on GPUs.
This work presents Kornia, an open source computer vision library built upon a set of differentiable routines and modules that aims to solve generic computer vision problems. The package uses PyTorch as its main backend, not only for efficiency but also to take advantage of the reverse auto-differentiation engine to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be integrated into neural networks to train models to perform a wide range of operations including image transformations,camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations on graphical processing units, generating faster systems. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.