# HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch

arXiv: https://arxiv.org/abs/1903.01814 · HTML: https://mlsanity.com/paper/1903.01814/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2019.

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

- [Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes](https://mlsanity.com/paper/2110.09401/) (2021)
- [HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks](https://mlsanity.com/paper/2101.10897/) (2021)
- [Exploring the impact of spatiotemporal granularity on the demand prediction of dynamic ride-hailing](https://mlsanity.com/paper/2203.10301/) (2022)
- [Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Generation](https://mlsanity.com/paper/2101.00337/) (2021)
- [Resampling and super-resolution of hexagonally sampled images using deep learning](https://mlsanity.com/paper/2111.02520/) (2021)
- [A deep ensemble approach to X-ray polarimetry](https://mlsanity.com/paper/2111.03047/) (2021)
- [Biologically inspired deep residual networks for computer vision applications](https://mlsanity.com/paper/2205.02551/) (2022)
- [Localized Observation Abstraction Using Piecewise Linear Spatial Decay for Reinforcement Learning in Combat Simulations](https://mlsanity.com/paper/2408.13328/) (2024)
- [Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks](https://mlsanity.com/paper/2502.13918/) (2025)

## Abstract (arXiv)

HexagDLy is a Python-library extending the PyTorch deep learning framework with convolution and pooling operations on hexagonal grids. It aims to ease the access to convolutional neural networks for applications that rely on hexagonally sampled data as, for example, commonly found in ground-based astroparticle physics experiments.