Improved super-resolution for images by using flows
Improved super-resolution for images by using flows
Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution
arXiv paper abstract https://arxiv.org/abs/2111.03649
arXiv PDF paper https://arxiv.org/pdf/2111.03649.pdf
Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions.
... dominant paradigm is to employ pixel-wise losses, such as L_1, which drive the prediction towards a blurry average.
... address this issue by revisiting the L_1 loss and show that it corresponds to a one-layer conditional flow.
... explore general flows as a fidelity-based alternative to the L_1 objective.
... demonstrate that the flexibility of deeper flows leads to better visual quality and consistency when combined with adversarial losses.
... approach is shown to outperform state-of-the-art methods for photo-realistic super-resolution. ...
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