Reconstruct image from several noisy, blurred, dim images by flow and spatial attention with IREANet
Reconstruct image from several noisy, blurred, dim images by flow and spatial attention with IREANet
Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation
arXiv paper abstract https://arxiv.org/abs/2404.10358
arXiv PDF paper https://arxiv.org/pdf/2404.10358.pdf
... address the Bracket Image Restoration and Enhancement (BracketIRE) task using a novel framework, which requires restoring a high-quality high dynamic range (HDR) image from a sequence of noisy, blurred, and low dynamic range (LDR) multi-exposure RAW inputs.
... present the IREANet, which improves the multiple exposure alignment and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM).
... FFAM incorporates the inter-frame optical flow as guidance to facilitate the deformable alignment and spatial attention modules for better feature alignment.
... EFAM ... employs ... Enhanced Residual Block (ERB) as ... component, wherein a unidirectional recurrent network aggregates the aligned temporal features to better reconstruct the results.
To improve model generalization and performance, ... additionally employ the Bayer preserving augmentation (BayerAug) strategy to augment the multi-exposure RAW inputs.
... experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods.
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
