A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications

TL;DR

This paper addresses the challenge of transmitting visual data efficiently by shifting to semantic communication (SemCom) and classifying SemCom-Vision by semantic quantization schemes and goals, guided by quantities such as semantic entropy $H(\mathbf{s})$, mutual information $I(\mathbf{s};\hat{\mathbf{s}})$, and the information bottleneck objective. It surveys ML-based encoder–decoder architectures, including ResNet/DenseNet backbones, autoencoders, diffusion models, and transformers, along with loss functions that realize SPC, SEC, and SRC. It analyzes knowledge structures, notably knowledge graphs (TS/PGD/Hypergraph and probabilistic/neural/multimodal extensions) for guidance, reasoning, and adaptive transmission. It also highlights applications in Digital Twins, Metaverse, and Wireless Perception and outlines future research directions to advance practical SemCom-Vision systems.

Abstract

Semantic communication (SemCom) emerges as a transformative paradigm for traffic-intensive visual data transmission, shifting focus from raw data to meaningful content transmission and relieving the increasing pressure on communication resources. However, to achieve SemCom, challenges are faced in accurate semantic quantization for visual data, robust semantic extraction and reconstruction under diverse tasks and goals, transceiver coordination with effective knowledge utilization, and adaptation to unpredictable wireless communication environments. In this paper, we present a systematic review of SemCom for visual data transmission (SemCom-Vision), wherein an interdisciplinary analysis integrating computer vision (CV) and communication engineering is conducted to provide comprehensive guidelines for the machine learning (ML)-empowered SemCom-Vision design. Specifically, this survey first elucidates the basics and key concepts of SemCom. Then, we introduce a novel classification perspective to categorize existing SemCom-Vision approaches as semantic preservation communication (SPC), semantic expansion communication (SEC), and semantic refinement communication (SRC) based on communication goals interpreted through semantic quantization schemes. Moreover, this survey articulates the ML-based encoder-decoder models and training algorithms for each SemCom-Vision category, followed by knowledge structure and utilization strategies. Finally, we discuss potential SemCom-Vision applications.

Figures (2)

• Figure 1: The construction of SemCom-Vision includes three major parts: 1) semantic quantization and SemCom classification, 2) encoder-decoder construction, 3) knowledge for SemCom-Vision.
• Figure 2: Typical ML model architectures for encoder-decoder design.