WaveDM: Wavelet-Based Diffusion Models for Image Restoration

Understand

Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem.

• To tackle it, this paper proposes a Wavelet-Based Diffusion Model (WaveDM).
• WaveDM learns the distribution of clean images in the wavelet domain conditioned on the wavelet spectrum of degraded images after wavelet transform, which is more time-saving in each step of sampling than modeling in the spatial domain.
• To ensure restoration performance, a unique training strategy is proposed where the low-frequency and high-frequency spectrums are learned using distinct modules.