Efficient Image Deblurring Networks based on Diffusion Models

This article introduces a sliding window model for defocus deblurring that achieves the best performance to date with extremely low memory usage. Named Swintormer, the method utilizes a diffusion model to generate latent prior features that assist in restoring more detailed images. It also extends t...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Chen, Kang, Liu, Yuanjie
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.01.2024
Subjects
Ablation
Image restoration
Impact analysis
Memory devices
Signal to noise ratio
Sliding
Source code
Online AccessGet full text

Cover

More Information
Summary:This article introduces a sliding window model for defocus deblurring that achieves the best performance to date with extremely low memory usage. Named Swintormer, the method utilizes a diffusion model to generate latent prior features that assist in restoring more detailed images. It also extends the sliding window strategy to specialized Transformer blocks for efficient inference. Additionally, we have further optimized Multiply-Accumulate operations (Macs). Compared to the currently top-performing GRL method, our Swintormer model drastically reduces computational complexity from 140.35 GMACs to 8.02 GMacs, while also improving the Signal-to-Noise Ratio (SNR) for defocus deblurring from 27.04 dB to 27.07 dB. This new method allows for the processing of higher resolution images on devices with limited memory, significantly expanding potential application scenarios. The article concludes with an ablation study that provides an in-depth analysis of the impact of each network module on final performance. The source code and model will be available at the following website: https://github.com/bnm6900030/swintormer.
ISSN:2331-8422