# Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs

arXiv: https://arxiv.org/abs/2505.01742 · HTML: https://mlsanity.com/paper/2505.01742/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 3 May 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [A Fast Transformer-based General-Purpose Lossless Compressor](https://mlsanity.com/paper/2203.16114/) (2022)
- [Deep Model-Based Super-Resolution with Non-uniform Blur](https://mlsanity.com/paper/2204.10109/) (2022)
- [Research on the Application of Computer Vision Based on Deep Learning in Autonomous Driving Technology](https://mlsanity.com/paper/2406.00490/) (2024)
- [Online Streaming Video Super-Resolution with Convolutional Look-Up Table](https://mlsanity.com/paper/2303.00334/) (2023)
- [Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation](https://mlsanity.com/paper/2404.19265/) (2024)
- [On the Compressibility of Quantized Large Language Models](https://mlsanity.com/paper/2403.01384/) (2024)
- [Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory](https://mlsanity.com/paper/2403.14849/) (2024)
- [HiRISE: High-Resolution Image Scaling for Edge ML via In-Sensor Compression and Selective ROI](https://mlsanity.com/paper/2408.03956/) (2024)
- [Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization](https://mlsanity.com/paper/2409.02388/) (2024)
- [Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge](https://mlsanity.com/paper/2302.09221/) (2023)
- [Ariadne: A Hotness-Aware and Size-Adaptive Compressed Swap Technique for Fast Application Relaunch and Reduced CPU Usage on Mobile Devices](https://mlsanity.com/paper/2502.12826/) (2025)

## Abstract (arXiv)

Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-compute-free image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a real-world testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.