A pretrained latent diffusion model is used as a channel denoiser in latent space, with an SNR-to-timestep mapping and input scaling, producing zero-shot image reconstruction without fine-tuning.
Joint source–channel coding: Fundamentals and recent progress in practical designs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application
A pretrained latent diffusion model is used as a channel denoiser in latent space, with an SNR-to-timestep mapping and input scaling, producing zero-shot image reconstruction without fine-tuning.