# DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

arXiv: https://arxiv.org/abs/2005.03995 · HTML: https://mlsanity.com/paper/2005.03995/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2020.

## Built on by (most cited first, 9 of 9)

- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [SAGE: SLAM with Appearance and Geometry Prior for Endoscopy](https://mlsanity.com/paper/2202.09487/) (2022)
- [Quantification using Permutation-Invariant Networks based on Histograms](https://mlsanity.com/paper/2403.15123/) (2024)
- [SketchCleanNet -- A deep learning approach to the enhancement and correction of query sketches for a 3D CAD model retrieval system](https://mlsanity.com/paper/2207.00732/) (2022)
- [Local and Global Information in Obstacle Detection on Railway Tracks](https://mlsanity.com/paper/2307.15478/) (2023)
- [Affine-Transformation-Invariant Image Classification by Differentiable Arithmetic Distribution Module](https://mlsanity.com/paper/2309.00752/) (2023)
- [Entropy-driven Unsupervised Keypoint Representation Learning in Videos](https://mlsanity.com/paper/2209.15404/) (2022)
- [DualVAE: Controlling Colours of Generated and Real Images](https://mlsanity.com/paper/2305.18769/) (2023)
- [High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm](https://mlsanity.com/paper/2503.00410/) (2025)

## Abstract (arXiv)

We present the DeepHist - a novel Deep Learning framework for augmenting a network by histogram layers and demonstrate its strength by addressing image-to-image translation problems. Specifically, given an input image and a reference color distribution we aim to generate an output image with the structural appearance (content) of the input (source) yet with the colors of the reference. The key idea is a new technique for a differentiable construction of joint and color histograms of the output images. We further define a color distribution loss based on the Earth Mover's Distance between the output's and the reference's color histograms and a Mutual Information loss based on the joint histograms of the source and the output images. Promising results are shown for the tasks of color transfer, image colorization and edges rightarrow photo, where the color distribution of the output image is controlled. Comparison to Pix2Pix and CyclyGANs are shown.