# Optimally Bridging Semantics and Data: Generative Semantic Communication via Schr"odinger Bridge

arXiv: https://arxiv.org/abs/2604.17802 · HTML: https://mlsanity.com/paper/2604.17802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling](https://mlsanity.com/paper/2106.01357/) (2021)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [A survey of the Schr"odinger problem and some of its connections with optimal transport](https://mlsanity.com/paper/1308.0215/) (2013)
- [Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theory](https://mlsanity.com/paper/2110.11291/) (2021)
- [I2SB: Image-to-Image Schr"odinger Bridge](https://mlsanity.com/paper/2302.05872/) (2023)
- [Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2309.16948/) (2023)
- [On the relation between optimal transport and Schr"odinger bridges: A stochastic control viewpoint](https://mlsanity.com/paper/1412.4430/) (2014)
- [From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problems](https://mlsanity.com/paper/2012.15405/) (2020)
- [SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2308.09361/) (2023)
- [Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge](https://mlsanity.com/paper/2312.10299/) (2023)
- [Conditional Image Synthesis with Diffusion Models: A Survey](https://mlsanity.com/paper/2409.19365/) (2024)
- [High Perceptual Quality Wireless Image Delivery with Denoising Diffusion Models](https://mlsanity.com/paper/2309.15889/) (2023)
- [UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control](https://mlsanity.com/paper/2502.05749/) (2025)
- [Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmission](https://mlsanity.com/paper/2501.01138/) (2025)
- [Wireless End-to-End Image Transmission System using Semantic Communications](https://mlsanity.com/paper/2302.13721/) (2023)
- [Semantic Successive Refinement: A Generative AI-aided Semantic Communication Framework](https://mlsanity.com/paper/2408.05112/) (2024)
- [Lightweight Diffusion Models for Resource-Constrained Semantic Communication](https://mlsanity.com/paper/2410.02491/) (2024)
- [Agent-driven Generative Semantic Communication with Cross-Modality and Prediction](https://mlsanity.com/paper/2404.06997/) (2024)
- [Sequential Semantic Generative Communication for Progressive Text-to-Image Generation](https://mlsanity.com/paper/2309.04287/) (2023)
- [Generative Semantic Communication: Architectures, Technologies, and Applications](https://mlsanity.com/paper/2412.08642/) (2024)
- [Transmit What You Need: Task-Adaptive Semantic Communications for Visual Information](https://mlsanity.com/paper/2412.13646/) (2024)

## Abstract (arXiv)

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 Schr"odinger Bridge-based GSC (SBGSC). By leveraging the Schr"odinger 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 Schr"odinger 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.