EUVIMEDEUVIMED entdecken
Crossref

Machines Serve Human: A Novel Variable Human–Machine Collaborative Compression Framework

Zifu Zhang, Shengxi Li, Xiancheng Sun, Mai Xu, Zhengyuan Liu, Jingyuan Xia

IEEE Transactions on Image Processing · 2026 · 35 · 7828-7842

DOI: 10.1109/tip.2026.3712352 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Zifu Zhang und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Data Compression, Compression Algorithms, Image Processing, Computer-Assisted, Artificial Intelligence. Die Arbeit nennt 77 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human-machine collaborative compression has been receiving increasing research efforts for reducing image/video data, serving as the basis for both human perception and machine intelligence. Existing collaborative methods are dominantly built upon the de facto human-vision compression pipeline, witnessing deficiency on complexity and bit-rates when aggregating the machine-vision compression. Indeed, machine vision solely focuses on the core regions within the image/video, requiring much less information compared with the compressed information for human vision. In this paper, we thus set out the first successful attempt by a novel collaborative compression method based on the machine-vision-oriented compression, instead of human-vision pipeline. In other words, machine vision serves as the basis for human vision within collaborative compression. A plug-and-play variable bit-rate strategy is also developed for machine vision tasks. Then, we propose to progressively aggregate the semantics from the machine-vision compression, whilst seamlessly tailing the diffusion prior to restore high-fidelity details for human vision, thus named as diffusion-prior based feature compression for human and machine visions (Diff-FCHM). Experimental results verify the consistently superior performances of our Diff-FCHM, on both machine-vision and human-vision compression with remarkable margins. The source code is available at https://github.com/bblgbr/Diff-FCHM.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Data CompressionCompression AlgorithmsImage Processing, Computer-AssistedArtificial IntelligenceHumansAlgorithmsVideo Recording

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Zhang, Z., Li, S., Sun, X., Xu, M., Liu, Z., & Xia, J. (2026). Machines Serve Human: A Novel Variable Human–Machine Collaborative Compression Framework. IEEE Transactions on Image Processing, 35, 7828-7842. https://doi.org/10.1109/tip.2026.3712352

Vancouver

Zhang Z, Li S, Sun X, Xu M, Liu Z, Xia J. Machines Serve Human: A Novel Variable Human–Machine Collaborative Compression Framework. IEEE Transactions on Image Processing. 2026;35:7828-7842. doi:10.1109/tip.2026.3712352

BibTeX
@article{Zhang2026,
  author = {Zhang, Zifu and Li, Shengxi and Sun, Xiancheng and Xu, Mai and Liu, Zhengyuan and Xia, Jingyuan},
  title = {Machines Serve Human: A Novel Variable Human–Machine Collaborative Compression Framework},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {7828--7842},
  doi = {10.1109/tip.2026.3712352}
}
Kostenlos starten →