Collaborative Blind Image Deblurring
Abstract
Blurry images usually exhibit similar blur at various locations across the image domain, a property barely captured in nowadays blind deblurring neural networks. We show that when extracting patches of similar underlying blur is possible, jointly processing the stack of patches yields superior accuracy than handling them separately. Our collaborative scheme is implemented in a neural architecture with a pooling layer on the stack dimension. We present three practical patch extraction strategies for image sharpening, camera shake removal and optical aberration correction, and validate the proposed approach on both synthetic and real-world benchmarks. For each blur instance, the proposed collaborative strategy yields significant quantitative and qualitative improvements.
Cite
Text
Eboli et al. "Collaborative Blind Image Deblurring." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00792Markdown
[Eboli et al. "Collaborative Blind Image Deblurring." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/eboli2024cvprw-collaborative/) doi:10.1109/CVPRW63382.2024.00792BibTeX
@inproceedings{eboli2024cvprw-collaborative,
title = {{Collaborative Blind Image Deblurring}},
author = {Eboli, Thomas and Morel, Jean-Michel and Facciolo, Gabriele},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2024},
pages = {7943-7952},
doi = {10.1109/CVPRW63382.2024.00792},
url = {https://mlanthology.org/cvprw/2024/eboli2024cvprw-collaborative/}
}