Multi-Outputs Is All You Need For Deblur

Image deblurring task is an ill-posed one, where exists infinite feasible solutions for blurry image. Modern deep learning approaches usually discard the learning of blur kernels and directly employ end-to-end supervised learning. Popu- lar deblurring datasets define the label as one of the feasi- ble solutions.

Data and Resources

Cite this as

Sidun Liu, Peng Qiao, Yong Dou (2024). Dataset: Multi-Outputs Is All You Need For Deblur. https://doi.org/10.57702/73oo5z65

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2208.13029
Author Sidun Liu
More Authors
Peng Qiao
Yong Dou
Homepage https://github.com/Liu-SD/multi-output-deblur