# Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention

arXiv: https://arxiv.org/abs/2403.17677 · HTML: https://mlsanity.com/paper/2403.17677/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Breaking the Softmax Bottleneck: A High-Rank RNN Language Model](https://mlsanity.com/paper/1711.03953/) (2017)
- [Nonlinear Transform Coding](https://mlsanity.com/paper/2007.03034/) (2020)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methods](https://mlsanity.com/paper/2306.00385/) (2023)
- [Image Compression with Recurrent Neural Network and Generalized Divisive Normalization](https://mlsanity.com/paper/2109.01999/) (2021)
- [High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction](https://mlsanity.com/paper/1907.02959/) (2019)

## Built on by (most cited first, 5 of 5)

- [Compress-Align-Detect: onboard change detection from unregistered images](https://mlsanity.com/paper/2507.15578/) (2025)
- [Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network](https://mlsanity.com/paper/2507.20765/) (2025)
- [Adjustable Spatio-Spectral Hyperspectral Image Compression Network](https://mlsanity.com/paper/2507.23447/) (2025)
- [Scalable neural pushbroom architectures for real-time denoising of hyperspectral images onboard satellites](https://mlsanity.com/paper/2601.05020/) (2026)
- [HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoders](https://mlsanity.com/paper/2603.26468/) (2026)

## Abstract (arXiv)

Deep learning methods have traditionally been difficult to apply to compression of hyperspectral images onboard of spacecrafts, due to the large computational complexity needed to achieve adequate representational power, as well as the lack of suitable datasets for training and testing. In this paper, we depart from the traditional autoencoder approach and we design a predictive neural network, called LineRWKV, that works recursively line-by-line to limit memory consumption. In order to achieve that, we adopt a novel hybrid attentive-recursive operation that combines the representational advantages of Transformers with the linear complexity and recursive implementation of recurrent neural networks. The compression algorithm performs prediction of each pixel using LineRWKV, followed by entropy coding of the residual. Experiments on the HySpecNet-11k dataset and PRISMA images show that LineRWKV is the first deep-learning method to outperform CCSDS-123.0-B-2 at lossless and near-lossless compression. Promising throughput results are also evaluated on a 7W embedded system.