Problem
Research questions and friction points this paper is trying to address.
remote sensing image transmission
bandwidth limitation
data redundancy
communication cost
efficient image transfer
Text-RSIR: A Text-Guided Framework for Efficient Remote Sensing Image Transmission and Reconstruction
🤖 AI Summary
This study addresses the bandwidth and cost constraints in high-resolution remote sensing image transmission, where conventional pixel-level approaches suffer from significant redundancy. The authors propose a novel text-guided satellite-to-ground collaborative transmission and reconstruction framework that, for the first time, leverages compact textual descriptions as lightweight semantic carriers. Onboard the satellite, a textual summary encoding both spatial layout and semantic content is generated; on the ground, a cross-modal learning-based, text-conditioned image restoration model reconstructs high-fidelity images from this minimal representation. Evaluated on the Alsat-2B, UC Merced, and Aerial Image datasets, the method achieves PSNR values of 16.36 dB, 26.87 dB, and 27.41 dB, respectively, while reducing transmitted data to approximately 2% of the original image size—dramatically improving transmission efficiency without sacrificing critical information.
📝 Abstract
High-resolution remote sensing imagery is critical for environmental monitoring, urban mapping, and land cover analysis, but its transmission is often hindered by limited bandwidth and high communication costs. Conventional pipelines transmit full-resolution pixel data, resulting in redundant and inefficient delivery. This paper proposes a text-guided remote sensing image transmission system that replaces complete high-resolution data with low-resolution images accompanied by compact textual descriptions. An onboard text generator produces spatial and semantic summaries, reducing the transmitted data volume to approximately 2\% of the original size. For ground-based reconstruction, a text-conditioned image restoration model is introduced, which leverages cross-modal learning to recover fine spatial details and maintain semantic coherence. Experimental results on the Alsat-2B, UC Merced Land Use, and Aerial Image datasets demonstrate that the proposed framework achieves reconstruction PSNRs of 16.36 dB, 26.87 dB, and 27.41 dB, respectively, enabling efficient and information-preserving image transfer for remote sensing applications. The implementation will be made publicly available at \href{https://github.com/haoyangofficial/textrssr}{GitHub}.
Innovation
Methods, ideas, or system contributions that make the work stand out.
text-guided image reconstruction
remote sensing image transmission
cross-modal learning
data compression
semantic-aware restoration
🔎 Similar Papers
No similar papers found.
