# Image Formation Model Guided Deep Image Super-Resolution

arXiv: https://arxiv.org/abs/1908.06444 · HTML: https://mlsanity.com/paper/1908.06444/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2019.

## Built on by (most cited first, 2 of 2)

- [A Two-Stage Attentive Network for Single Image Super-Resolution](https://mlsanity.com/paper/2104.10488/) (2021)
- [High-Frequency aware Perceptual Image Enhancement](https://mlsanity.com/paper/2105.11711/) (2021)

## Abstract (arXiv)

We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.