# Convolutional Transformer-Based Image Compression

arXiv: https://arxiv.org/abs/2409.04118 · HTML: https://mlsanity.com/paper/2409.04118/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2024.

## Built on by (most cited first, 2 of 2)

- [Alias-Free ViT: Fractional Shift Invariance via Linear Attention](https://mlsanity.com/paper/2510.22673/) (2025)
- [Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset](https://mlsanity.com/paper/2501.08924/) (2025)

## Abstract (arXiv)

In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies between tokens, eliminating the need for positional encoding by integrating convolutional operations within the multi-head attention mechanism. We demonstrate through experiments that our proposed framework surpasses state-of-the-art CNN-based architectures in terms of the trade-off between bit-rate and distortion and achieves comparable results to transformer-based methods while maintaining lower computational complexity.