Optimally Bridging Semantics and Data: Generative Semantic Communication via Schrödinger Bridge
For image transmission in narrow-band and high-noise channels, this work significantly improves quality and speed over existing GSC methods.
Existing generative semantic communication methods suffer from hallucination and high computational cost due to indirect transport trajectories. The proposed SBGSC framework uses Schrödinger Bridge for direct optimal transport, achieving at least 38% FID improvement, 49.3% SSIM improvement, and 8x inference speedup over state-of-the-art.
Generative Semantic Communication (GSC) is a promising solution for image transmission over narrow-band and high-noise channels. However, existing GSC methods rely on long, indirect transport trajectories from a Gaussian to an image distribution guided by semantics, causing severe hallucination and high computational cost. To address this, we propose a general framework named Schrödinger Bridge-based GSC (SBGSC). By leveraging the Schrödinger Bridge (SB) to construct optimal transport trajectories between arbitrary distributions, SBGSC breaks Gaussian limitations and enables direct generative decoding from semantics to images. Within this framework, we design Diffusion SB-based GSC (DSBGSC). DSBGSC reconstructs the nonlinear drift term of diffusion models using Schrödinger potentials, achieving direct optimal distribution transport to reduce hallucinations and computational overhead. To further accelerate generation, we propose a self-consistency-based objective guiding the model to learn a nonlinear velocity field pointing directly toward the image, bypassing Markovian noise prediction to significantly reduce sampling steps. Simulation results demonstrate that DSBGSC outperforms state-of-the-art GSC methods, improving FID by at least 38% and SSIM by 49.3%, while accelerating inference speed by over 8 times.