Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.01742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918019876257792 |
|---|---|
| author | Mao, Yu Li, Jingzong Wang, Jun Xu, Hong Kuo, Tei-Wei Guan, Nan Xue, Chun Jason |
| author_facet | Mao, Yu Li, Jingzong Wang, Jun Xu, Hong Kuo, Tei-Wei Guan, Nan Xue, Chun Jason |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01742 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs Mao, Yu Li, Jingzong Wang, Jun Xu, Hong Kuo, Tei-Wei Guan, Nan Xue, Chun Jason Image and Video Processing Machine Learning 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. |
| title | Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2505.01742 |