# Efficient Semantic Image Communication for Traffic Monitoring at the Edge

arXiv: https://arxiv.org/abs/2604.12622 · HTML: https://mlsanity.com/paper/2604.12622/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [Generative Compression](https://mlsanity.com/paper/1703.01467/) (2017)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems](https://mlsanity.com/paper/2112.10948/) (2021)
- [Vision-Language Models for Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/2502.07855/) (2025)
- [One-Step Diffusion-Based Image Compression with Semantic Distillation](https://mlsanity.com/paper/2505.16687/) (2025)
- [Personalized Saliency in Task-Oriented Semantic Communications: Image Transmission and Performance Analysis](https://mlsanity.com/paper/2209.12274/) (2022)
- [Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement](https://mlsanity.com/paper/1702.06441/) (2017)
- [HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression](https://mlsanity.com/paper/2404.13372/) (2024)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [Semantic Communications with Computer Vision Sensing for Edge Video Transmission](https://mlsanity.com/paper/2503.07252/) (2025)
- [SQ-GAN: Semantic Image Communications Using Masked Vector Quantization](https://mlsanity.com/paper/2502.09520/) (2025)
- [TLIC: Learned Image Compression with ROI-Weighted Distortion and Bit Allocation](https://mlsanity.com/paper/2401.08154/) (2024)
- [Privacy-Preserving Data Fusion for Traffic State Estimation: A Vertical Federated Learning Approach](https://mlsanity.com/paper/2401.11836/) (2024)
- [Convolutional variational autoencoders for secure lossy image compression in remote sensing](https://mlsanity.com/paper/2404.03696/) (2024)
- [Semantic Communication based on Generative AI: A New Approach to Image Compression and Edge Optimization](https://mlsanity.com/paper/2502.01675/) (2025)
- [Semantics-Guided Generative Image Compression](https://mlsanity.com/paper/2505.24015/) (2025)

## Abstract (arXiv)

Many visual monitoring systems operate under strict communication constraints, where transmitting full-resolution images is impractical and often unnecessary. In such settings, visual data is often used for object presence, spatial relationships, and scene context rather than exact pixel fidelity. This paper presents two semantic image communication pipelines for traffic monitoring, MMSD and SAMR, that reduce transmission cost while preserving meaningful visual information. MMSD (Multi-Modal Semantic Decomposition) targets very high compression together with data confidentiality, since sensitive pixel content is not transmitted. It replaces the original image with compact semantic representations, namely segmentation maps, edge maps, and textual descriptions, and reconstructs the scene at the receiver using a diffusion-based generative model. SAMR (Semantic-Aware Masking Reconstruction) targets higher visual quality while maintaining strong compression. It selectively suppresses non-critical image regions according to semantic importance before standard JPEG encoding and restores the missing content at the receiver through generative inpainting. Both designs follow an asymmetric sender-receiver architecture, where lightweight processing is performed at the edge and computationally intensive reconstruction is offloaded to the server. On a Raspberry Pi~5, the edge-side processing time is about 15s for MMSD and 9s for SAMR. Experimental results show average transmitted-data reductions of 99% for MMSD and 99.1% for SAMR. In addition, MMSD achieves lower payload size than the recent SPIC baseline while preserving strong semantic consistency, whereas SAMR provides a better quality-compression trade-off than standard JPEG and SQ-GAN under comparable operating conditions.