This project provides an implementation of steerable pyramids using PyTorch 2. Steerable pyramids are a type of multi-scale, multi-orientation image decomposition useful in various image processing and computer vision tasks.
It is a simple translation of the original project PyTorch Steerable Pyramids to PyTorch 2, with optimizations to use only native functions of the fft module.
This a simple implementation of the Complex Steerable Pyramid described in Portilla and Simoncelli (IJCV, 2000)