# GIC-DLC: Differentiable Logic Circuits for Hardware-Friendly Grayscale Image Compression

arXiv: https://arxiv.org/abs/2601.14130 · HTML: https://mlsanity.com/paper/2601.14130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [EMNIST: an extension of MNIST to handwritten letters](https://mlsanity.com/paper/1702.05373/) (2017)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [C3: High-performance and low-complexity neural compression from a single image or video](https://mlsanity.com/paper/2312.02753/) (2023)
- [COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec](https://mlsanity.com/paper/2212.05458/) (2022)
- [PO-ELIC: Perception-Oriented Efficient Learned Image Coding](https://mlsanity.com/paper/2205.14501/) (2022)
- [Lossless Image Compression through Super-Resolution](https://mlsanity.com/paper/2004.02872/) (2020)
- [NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functions](https://mlsanity.com/paper/2403.00849/) (2024)
- [Recurrent Deep Differentiable Logic Gate Networks](https://mlsanity.com/paper/2508.06097/) (2025)
- [HyperCool: Reducing Encoding Cost in Overfitted Codecs with Hypernetworks](https://mlsanity.com/paper/2509.18748/) (2025)

## Abstract (arXiv)

Neural image codecs achieve higher compression ratios than traditional hand-crafted methods such as PNG or JPEG-XL, but often incur substantial computational overhead, limiting their deployment on energy-constrained devices such as smartphones, cameras, and drones. We propose Grayscale Image Compression with Differentiable Logic Circuits (GIC-DLC), a hardware-aware codec where we train lookup tables to combine the flexibility of neural networks with the efficiency of Boolean operations. Experiments on grayscale benchmark datasets show that GIC-DLC outperforms traditional codecs in compression efficiency while allowing substantial reductions in energy consumption and latency. These results demonstrate that learned compression can be hardware-friendly, offering a promising direction for low-power image compression on edge devices.