Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication

TL;DR

This paper introduces TopoJSCC, a topology-aware deep joint source-channel coding framework that uses persistent-homology regularizers to preserve structural information in wireless vision applications, outperforming existing pixel-focused methods.

Contribution

It presents a novel topology-preserving DeepJSCC method that integrates persistent-homology regularizers for end-to-end training without side information.

Findings

Enhanced topology preservation in reconstructed images

Improved PSNR in low SNR conditions

Better performance at low bandwidth ratios

Abstract

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.