| Autor: |
Michelini, Pablo Navarrete, Liu, Hanwen, Lu, Yunhua, Jiang, Xingqun |
| Rok vydání: |
2021 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
We propose a simple extension of residual networks that works simultaneously in multiple resolutions. Our network design is inspired by the iterative back-projection algorithm but seeks the more difficult task of learning how to enhance images. Compared to similar approaches, we propose a novel solution to make back-projections run in multiple resolutions by using a data pipeline workflow. Features are updated at multiple scales in each layer of the network. The update dynamic through these layers includes interactions between different resolutions in a way that is causal in scale, and it is represented by a system of ODEs, as opposed to a single ODE in the case of ResNets. The system can be used as a generic multi-resolution approach to enhance images. We test it on several challenging tasks with special focus on super-resolution and raindrop removal. Our results are competitive with state-of-the-arts and show a strong ability of our system to learn both global and local image features. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
