Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution

Abstract

This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPMs) and Discrete Wavelet Transformation (DWT). By enabling DDPMs to operate in the DWT domain, our DDPM models effectively hallucinate high-frequency information for super-resolved images on the wavelet spectrum, resulting in high-quality and detailed reconstructions in image space. Quantitatively, we outperform state-of-the-art diffusion-based SISR methods, namely SR3 and SRDiff, regarding PSNR, SSIM, and LPIPS on both face (8x scaling) and general (4x scaling) SR benchmarks. Meanwhile, using DWT enabled us to use fewer parameters than the compared models: 92M parameters instead of 550M compared to SR3 and 9.3M instead of 12M compared to SRDiff. Additionally, our method outperforms other state-of-the-art generative methods on classical general SR datasets while saving inference time. Finally, our work highlights its potential for various applications.

References in corpus (6)

• Denoising Diffusion Probabilistic Models
• Predictability and Surprise in Large Generative Models
• Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Face Super-Resolution Using Stochastic Differential Equations
• DWA: Differential Wavelet Amplifier for Image Super-Resolution

Cited by in corpus (2)

• Diffusion Models, Image Super-Resolution And Everything: A Survey
• Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution