Can I read RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior on EtoBox?

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior by Lee, Ching-Hua; Yang, Chouchang; Cho, Jaejin; Saidutta, Yashas Malur; Srinivasa, Rakshith Sharma; Shen, Yilin; Jin, Hongxia is a scholarly article available to read on EtoBox.

What is RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior about?

Denoising diffusion probabilistic models (DDPMs) can be utilized for recovering a clean signal from its degraded observation(s) by conditioning the model on the degraded signal. The degraded signals are themselves contaminated versions of the clean signals; due to this correlation, they may encompass certain useful information about the target clean data distribution. However, existing adoption of the standard Gaussian as the prior distribution in turn discards such information, resulting in sub-optimal performance. In this paper, we propose to improve conditional DDPMs for signal restoration by leveraging a more informative prior that is jointly learned with the diffusion model. The proposed framework, called RestoreGrad, seamlessly integrates DDPMs into the variational autoencoder framework and exploits the correlation between the degraded and clean signals to encode a better diffusion prior. On speech and image restoration tasks, we show that RestoreGrad demonstrates faster convergence (5-10 times fewer training steps) to achieve better quality of restored signals over existing DDPM baselines, and improved robustness to using fewer sampling steps in inference time (2-2.5 times f

Author

Lee, Ching-Hua; Yang, Chouchang; Cho, Jaejin; Saidutta, Yashas Malur; Srinivasa, Rakshith Sharma; Shen, Yilin; Jin, Hongxia

Published

2025

Language

EN