Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication
This work addresses the need for connectivity and topology preservation in semantic communication for applications like autonomous driving, representing an incremental improvement over existing DeepJSCC schemes.
The paper tackled the problem of preserving global structural information in wireless vision applications by proposing TopoJSCC, a topology-aware deep joint source-channel coding framework that integrates persistent-homology regularizers, resulting in improved topology preservation and peak signal-to-noise ratio (PSNR) in low SNR and bandwidth-ratio regimes.
Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end training. Specifically, we enforce topological consistency by penalizing Wasserstein distances between cubical persistence diagrams of original and reconstructed images, and between Vietoris--Rips persistence of latent features before and after the channel to promote a robust latent manifold. TopoJSCC is based on end-to-end learning and requires no side information. Experiments show improved topology preservation and peak signal-to-noise ratio (PSNR) in low signal-to-noise ratio (SNR) and bandwidth-ratio regimes.