# Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems

arXiv: https://arxiv.org/abs/2606.28398 · HTML: https://mlsanity.com/paper/2606.28398/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation](https://mlsanity.com/paper/2412.03069/) (2024)
- [UniTok: A Unified Tokenizer for Visual Generation and Understanding](https://mlsanity.com/paper/2502.20321/) (2025)
- [MaskBit: Embedding-free Image Generation via Bit Tokens](https://mlsanity.com/paper/2409.16211/) (2024)
- [SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2308.09361/) (2023)
- [WITT: A Wireless Image Transmission Transformer for Semantic Communications](https://mlsanity.com/paper/2211.00937/) (2022)
- [Generative AI-driven Semantic Communication Networks: Architecture, Technologies and Applications](https://mlsanity.com/paper/2401.00124/) (2023)
- [Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs](https://mlsanity.com/paper/2409.17557/) (2024)
- [Halton Scheduler For Masked Generative Image Transformer](https://mlsanity.com/paper/2503.17076/) (2025)
- [Generative AI for Physical Layer Communications: A Survey](https://mlsanity.com/paper/2312.05594/) (2023)
- [Generative AI for Secure Physical Layer Communications: A Survey](https://mlsanity.com/paper/2402.13553/) (2024)
- [Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission](https://mlsanity.com/paper/2404.17736/) (2024)
- [Process-and-Forward: Deep Joint Source-Channel Coding Over Cooperative Relay Networks](https://mlsanity.com/paper/2403.10613/) (2024)
- [Generative Semantic Communication for Joint Image Transmission and Segmentation](https://mlsanity.com/paper/2411.18005/) (2024)
- [SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models](https://mlsanity.com/paper/2503.12484/) (2025)

## Abstract (arXiv)

Resource-constrained visual Internet of Things (IoT) systems, such as edge cameras, unmanned sensing platforms, industrial inspection nodes, and remote monitoring sensors, often need to transmit task-relevant visual evidence over low-rate wireless links to an edge/cloud service. Existing image communication methods usually compress or transmit complete global representations, leaving limited room to exploit receiver-side generative restoration. This paper proposes a semantic-aware generative image transmission framework for edge-assisted visual IoT. The image captured by an IoT visual sensor is encoded into a discrete token grid by a VQ encoder. At the IoT transmitter or nearby gateway, token recoverability, estimated from prediction entropy and local structure complexity, is fused with semantic importance obtained from instance segmentation and category-aware scoring. A spatial dispersal sampler then selects the tokens to be transmitted under a bitrate budget. The transmitter sends only the quantization indices of kept tokens and a binary mask map, while the edge/cloud receiver recovers masked tokens through MaskGIT with Halton sequence scheduling. Experiments on Kodak and VisDrone scenes under AWGN and Rayleigh channels show that the proposed method provides a flexible bitrate-quality tradeoff for narrowband visual IoT links. At 0.074 bpp, it uses 44.6% of the transmitted bits of the 0.167-bpp DeepJSCC/WITT reference while achieving 29.9 dB PSNR. A pseudo-GT downstream detection study on Kodak further shows that semantic-aware masking preserves task-relevant objects better than random masking at both 30% and 50% mask ratios.