Schrödinger Bridge-based generative semantic communication (SBGSC) enables direct optimal distribution transport from semantics to images, cutting hallucinations and achieving 38% better FID, 49.3% better SSIM, and over 8x faster inference than prior GSC methods.
Likelihood Training of Schr¨odinger Bridge using Forward-Backward SDEs Theory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimally Bridging Semantics and Data: Generative Semantic Communication via Schr\"odinger Bridge
Schrödinger Bridge-based generative semantic communication (SBGSC) enables direct optimal distribution transport from semantics to images, cutting hallucinations and achieving 38% better FID, 49.3% better SSIM, and over 8x faster inference than prior GSC methods.