PyTorch implementation of Histogram Layers from DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

PyTorch modules are ready to be used (metrics & histogram layers). Run hist_loss to produce plots and metrics for example images.

The official implementation using TensorFlow can be found here.

Please cite the original publication if you use this code in your work:

M. Avi-Aharon, A. Arbelle and T. R. Raviv,
"Differentiable Histogram Loss Functions for Intensity-based Image-to-Image Translation,"
in IEEE Transactions on Pattern Analysis and Machine Intelligence,
vol. 45, no. 10, pp. 11642-11653, Oct. 2023, doi: 10.1109/TPAMI.2023.3278287.