Deblur image using selective state space model and simplified channel attention with ALGBlock
Deblur image using selective state space model and simplified channel attention with ALGBlock
Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring
arXiv paper abstract https://arxiv.org/abs/2403.20106
arXiv PDF paper https://arxiv.org/pdf/2403.20106.pdf
Image deblurring ... restore a high-quality image from ... blurred ... selective state space model (SSM) shows promise in modeling long-range dependencies with linear complexity ... encounters challenges such as local pixel forgetting and channel redundancy.
... propose an efficient image deblurring network that leverages selective state spaces model to aggregate enriched and accurate features.
... introduce ... (ALGBlock) designed to effectively capture and integrate both local invariant properties and non-local information.
The ALGBlock comprises two primary modules: a module for capturing local and global features (CLGF), and a feature aggregation module (FA).
... CLGF ... composed of two branches: the global branch captures long-range dependency features via a selective state spaces model, while the local branch employs simplified channel attention to model local connectivity ... reducing local pixel forgetting and channel redundancy.
... Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches on widely used benchmarks.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments