# Back-Projection Pipeline

arXiv: https://arxiv.org/abs/2101.10208 · HTML: https://mlsanity.com/paper/2101.10208/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2021.

## Built on by (most cited first, 1 of 1)

- [Compound Multi-branch Feature Fusion for Real Image Restoration](https://mlsanity.com/paper/2206.02748/) (2022)

## Abstract (arXiv)

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.