Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems
Quick Answer
The paper presents a semantic-aware generative image transmission framework for resource-constrained visual IoT systems, achieving a bitrate of 0.074 bpp with 29.9 dB PSNR, significantly improving efficiency over existing methods.
Quick Take
The paper presents a semantic-aware generative image transmission framework for resource-constrained visual IoT systems, achieving a bitrate of 0.074 bpp with 29.9 dB PSNR, significantly improving efficiency over existing methods. By utilizing a VQ encoder and MaskGIT for token recovery, it effectively balances quality and bandwidth, outperforming traditional approaches by preserving task-relevant objects better than random masking.
Key Points
- Achieves 0.074 bpp using 44.6% of bits from DeepJSCC/WITT reference.
- Utilizes VQ encoder for token grid encoding and MaskGIT for recovery.
- Demonstrates 29.9 dB PSNR under narrowband visual IoT conditions.
- Semantic-aware masking outperforms random masking in preserving relevant objects.
- Flexible bitrate-quality tradeoff suitable for low-rate wireless links.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 11 pages, 6 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV) |
| Cite as: | arXiv:2606.28398 [cs.CV] |
| (or arXiv:2606.28398v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.28398 arXiv-issued DOI via DataCite |
Submission history
From: Jia Guo [view email]
[v1]
Wed, 24 Jun 2026 08:18:31 UTC (2,940 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.