Fix defocus blur image using diffusion model to make prior features with Swintormer
Fix defocus blur image using diffusion model to make prior features with Swintormer
Efficient Image Deblurring Networks based on Diffusion Models
arXiv paper abstract https://arxiv.org/abs/2401.05907
arXiv PDF paper https://arxiv.org/pdf/2401.05907.pdf
GitHub https://github.com/bnm6900030/swintormer
… 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.
… extends the sliding window strategy to specialized Transformer blocks for efficient inference … have further optimized Multiply-Accumulate operations (Macs).
Compared to … top-performing GRL method, … Swintormer model … reduces computational complexity from 140.35 GMACs to 8.02 GMacs, while … improving the Signal-to-Noise Ratio … 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
… concludes with an ablation study that provides an in-depth analysis of the impact of each network module on final performance …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
