Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision
IEEE Transactions on Image Processing · 2024 · 33 · 408-422
DOI: 10.1109/tip.2023.3343912 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Qi Mao und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Data Compression. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Project of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm's feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates (< 0.01 bpp), offering new insights for human-machine collaborative compression.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Project of China
- Fundamental Research Funds for the Central Universities
- Public Computing Cloud, CUC
Zitieren
APA
Mao, Q., Wang, C., Wang, M., Wang, S., Chen, R., Jin, L., & Ma, S. (2024). Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision. IEEE Transactions on Image Processing, 33, 408-422. https://doi.org/10.1109/tip.2023.3343912
Vancouver
Mao Q, Wang C, Wang M, Wang S, Chen R, Jin L, et al. Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision. IEEE Transactions on Image Processing. 2024;33:408-422. doi:10.1109/tip.2023.3343912
BibTeX
@article{Mao2024,
author = {Mao, Qi and Wang, Chongyu and Wang, Meng and Wang, Shiqi and Chen, Ruijie and Jin, Libiao and Ma, Siwei},
title = {Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {408--422},
doi = {10.1109/tip.2023.3343912}
}
EUVIMED