EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unified and Scalable Deep Image Compression Framework for Human and Machine

Gai Zhang, Xinfeng Zhang, Lv Tang

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.10.2024 · 20 (10) · 1-22

DOI: 10.1145/3678472 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 30.10.2024. Verfasst von Gai Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image compression aims to minimize the amount of data in image representation while maintaining a certain visual quality for humans, which is an essential technique for storage and transmission. Recently, along with the development of computer vision, machines have become another primary receiver for images and require compressed images at a certain quality level, which may be different from that of human vision. In many scenarios, compressed images should serve both human and machine vision tasks, but few compression methods are designed for both goals simultaneously. In this article, we propose a unified and scalable deep image compression (USDIC) framework that jointly optimizes the image quality according to human and machine vision in an end-to-end style. For the encoder, we propose an information splitting mechanism (ISM) to separate images into semantic and visual features, which mainly aims at machine analysis and human viewing tasks. For the decoder, we design a scalable decoding architecture. The encoded semantic feature is first decoded for machine analysis tasks, and the image is decoded and reconstructed further by leveraging the decoded semantic features. Herein, to further remove the redundancy between the semantic and visual features of images, we propose a scalable entropy model (SEM) with a joint optimization strategy to reconstruct the image using the two kinds of decoded features. Extensive experimental results show that the proposed USDIC achieves much better performance on the image analysis task while maintaining competitive performance on the traditional image reconstruction task compared with popular image compression methods.

Förderung

  • National Natural Science Foundation
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhang, G., Zhang, X., & Tang, L. (2024). Unified and Scalable Deep Image Compression Framework for Human and Machine. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(10), 1-22. https://doi.org/10.1145/3678472

Vancouver

Zhang G, Zhang X, Tang L. Unified and Scalable Deep Image Compression Framework for Human and Machine. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(10):1-22. doi:10.1145/3678472

BibTeX
@article{Zhang2024,
  author = {Zhang, Gai and Zhang, Xinfeng and Tang, Lv},
  title = {Unified and Scalable Deep Image Compression Framework for Human and Machine},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2024},
  volume = {20},
  number = {10},
  pages = {1--22},
  doi = {10.1145/3678472}
}
Kostenlos starten →