Successive Refinement of Images with Deep Joint Source-Channel Coding
This work addresses efficient image transmission for wireless communication systems, presenting incremental improvements with novel deep learning strategies.
The paper tackled the problem of progressive image transmission over wireless channels by introducing deep learning-based communication methods, achieving graceful degradation with channel SNR and improved performance in low SNR and low bandwidth regimes compared to state-of-the-art digital techniques.
We introduce deep learning based communication methods for successive refinement of images over wireless channels. We present three different strategies for progressive image transmission with deep JSCC, with different complexity-performance trade-offs, all based on convolutional autoencoders. Numerical results show that deep JSCC not only provides graceful degradation with channel signal-to-noise ratio (SNR) and improved performance in low SNR and low bandwidth regimes compared to state-of-the-art digital communication techniques, but can also successfully learn a layered representation, achieving performance close to a single-layer scheme. These results suggest that natural images encoded with deep JSCC over Gaussian channels are almost successively refinable.