Key points are not available for this paper at this time.
While sensing imagery in space missions has broad applications, the growing image resolution and data volume have caused a major challenge due to limited deep space channel capacities. To address this challenge, semantics-aware image compression becomes a promising direction. This paper is motivated to explore lossy compression at the ultra-low rate regime, which is a deviation from the high-fidelity- oriented tradition. Specifically, we propose an ultra-low rate deep image compression (DIC) codec by synthesizing multiple neural computing techniques such as style generative adversarial network (GAN), inverse GAN mapping, and contrastive disentangled representation learning. In addition, a residual-based progressive encoding framework is proposed to enable smooth transitions from the ultra-low rate regime to near- lossless regime. Experiments on the FFHQ and DOTA dataset demonstrate that compared with existing DICs, the proposed DIC can push the minimum rate boundary by about one order of magnitude while preserving the semantic attributes and maintaining a high perception quality. We further elaborate the design considerations for cross-rate-regime progressive DIC. Our study confirm that a semantically disentangled DIC holds the promise to bridge multiple rate regimes.
Building similarity graph...
Analyzing shared references across papers
Loading...
Weicheng Zhang
Xiamen University
Yajing Liu
Shenyang Institute of Automation
Lingyu Chen
Sun Yat-sen University
IEEE Journal on Selected Areas in Communications
Western University
Xiamen University
Building similarity graph...
Analyzing shared references across papers
Loading...
Zhang et al. (Mon,) studied this question.
synapsesocial.com/papers/68e778e0b6db6435876edd29 — DOI: https://doi.org/10.1109/jsac.2024.3369654