Deblurring via Stochastic Refinement
Authors:
Preprint
Abstract
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. We present an alternative framework for blind deblurring based on conditional diffusion models. Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input. This leads to a significant improvement in perceptual quality over existing state-of-the-art methods across multiple standard benchmarks. Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. Combined with a carefully tuned network architecture and inference procedure, our method is competitive in terms of distortion metrics such as PSNR. These results show clear benefits of our diffusion-based method for deblurring and challenge the widely used strategy of producing a single, deterministic reconstruction.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- BANet: A Blur-Aware Attention Network for Dynamic Scene DeblurringIEEE Transactions on Image Processing, 2022
- Image Super-Resolution Via Iterative RefinementIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- SRDiff: Single image super-resolution with diffusion probabilistic modelsNeurocomputing, 2022
- Polyblur: Removing Mild Blur by Polynomial ReblurringIEEE Transactions on Computational Imaging, 2021
- Blind Image Deconvolution Using Deep Generative PriorsIEEE Transactions on Computational Imaging, 2020
- Deep Learning Techniques for Inverse Problems in ImagingIEEE Journal on Selected Areas in Information Theory, 2020
- Removing Camera Shake via Weighted Fourier Burst AccumulationIEEE Transactions on Image Processing, 2015
- Making a “Completely Blind” Image Quality AnalyzerIEEE Signal Processing Letters, 2012
- Deconvolving PSFs for a Better Motion Deblurring Using Multiple Images2012
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004