Generative Model based Highly Efficient Semantic Communication Approach for Image Transmission
Tiancheng Han,Jiancheng Tang,Qianqian Yang,Yiping Duan,Zhaoyang Zhang,Zhiguo Shi +5 more
- 18 Nov 2022
TL;DR: Wang et al. as discussed by the authors proposed a generative model based semantic communication to further improve the efficiency of image transmission and protect private information, which employed a privacy filter and a knowledge base to erase private information and replace it with natural features in the knowledge base.
read more
Abstract: Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model based semantic communication to further improve the efficiency of image transmission and protect private information. In particular, the transmitter extracts the interpretable latent representation from the original image by a generative model exploiting the GAN inversion method. We also employ a privacy filter and a knowledge base to erase private information and replace it with natural features in the knowledge base. The simulation results indicate that our proposed method achieves comparable quality of received images while significantly reducing communication costs compared to the existing methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Fig. 1. The overall architecture of the proposed generative model based semantic communication system for image transmission. 
Fig. 2. Generated images with and without the knowledge base(KB). 
Fig. 4. LPIPS versus SNR for different approaches. Our methods’ compression ratio are 1/3072 and 10/3072, while the compression ratio of Deep JSCC is 1/24 
Fig. 5. PSNR versus k/n and the PSNR without normalizing flow. 
Fig. 6. Example of the privacy protection. 
Fig. 3. PSNR versus SNR for different approaches.Our methods’ compression ratio are 1/3072 and 10/3072, while the compression ratio of Deep JSCC is 1/24.
Citations
Contrastive Learning based Semantic Communications
Shunpu Tang,Qianqian Yang,Lisheng Fan,Xianfu Lei,Arumgam Nallanathan,George K. Karagiannidis +5 more
TL;DR: Contrastive learning-based semantic communication system achieves improved communication efficiency by prioritizing semantic information preservation over symbol accuracy. It introduces semantic contrastive loss and re-encoding approaches to address limitations in existing learning-based semantic communication systems.
13
A Unified Framework for Integrating Semantic Communication and AI-Generated Content in Metaverse
Yi-Lan Lin,Zhipeng Gao,Hongyang Du,Dusit Niyato,Jiawen Kang,Abbas Jamalipour,Xuemin Sherman Shen +6 more
TL;DR: In this paper , a unified framework that captures integrated semantic communication and AI-generated content (ISGC) two primary benefits is introduced, including integration gain for optimized resource allocation and coordination gain for goal-oriented high-quality content generation to improve immersion from both communication and content perspectives.
A Unified Framework for Integrating Semantic Communication and AI-Generated Content in Metaverse
Yijing Lin,Zhipeng Gao,Hongyang Du,Dusit Niyato,Jiawen Kang,Abbas Jamalipour,Xuemin Shen +6 more
TL;DR: A unified framework for integrating semantic communication and AI-generated content in the Metaverse improves immersion by optimizing resource allocation and generating high-quality content.
6
Language-Oriented Semantic Latent Representation for Image Transmission
Giordano Cicchetti,Eleonora Grassucci,Jihong Park,Jin-Ho Choi,Sergio Barbarossa,Danilo Comminiello +5 more
- 22 Sep 2024
Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators
TL;DR: In this article , a novel semantic generative communication (SGC) framework was introduced, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS).
4
References
A Style-Based Generator Architecture for Generative Adversarial Networks
Tero Karras,Samuli Laine,Timo Aila +2 more
- 15 Jun 2019
TL;DR: This paper proposed an alternative generator architecture for GANs, borrowing from style transfer literature, which leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images.
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Richard Zhang,Phillip Isola,Phillip Isola,Alexei A. Efros,Eli Shechtman,Oliver Wang +5 more
- 11 Jan 2018
TL;DR: In this paper, the authors introduce a new dataset of human perceptual similarity judgments, and systematically evaluate deep features across different architectures and tasks and compare them with classic metrics, finding that deep features outperform all previous metrics by large margins on their dataset.
•Posted Content
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
TL;DR: A new dataset of human perceptual similarity judgments is introduced and it is found that deep features outperform all previous metrics by large margins on this dataset, and suggests that perceptual similarity is an emergent property shared across deep visual representations.
7.5K
Generative Adversarial Networks: An Overview
TL;DR: Generative adversarial networks (GANs) as mentioned in this paper provide a way to learn deep representations without extensively annotated training data by deriving backpropagation signals through a competitive process involving a pair of networks.
3.1K
Generative Adversarial Networks: An Overview
TL;DR: The aim of this review article is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible, and point to remaining challenges in their theory and application.