# Large Receptive Field Networks for High-Scale Image Super-Resolution

arXiv: https://arxiv.org/abs/1804.08181 · HTML: https://mlsanity.com/paper/1804.08181/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2018.

## Built on by (most cited first, 5 of 5)

- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Revisiting Image Deblurring with an Efficient ConvNet](https://mlsanity.com/paper/2302.02234/) (2023)
- [Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution](https://mlsanity.com/paper/2105.03939/) (2021)
- [Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection](https://mlsanity.com/paper/2210.06512/) (2022)
- [FREDSR: Fourier Residual Efficient Diffusive GAN for Single Image Super Resolution](https://mlsanity.com/paper/2211.16678/) (2022)

## Abstract (arXiv)

Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being challenging to train. We propose Large Receptive Field Networks which strive to directly expand the receptive field of Super-Resolution networks without increasing depth or parameter count. In particular, we use two different methods to expand the network receptive field: 1-D separable kernels and atrous convolutions. We conduct considerable experiments to study the performance of various arrangement schemes of the 1-D separable kernels and atrous convolution in terms of accuracy (PSNR / SSIM), parameter count, and speed, while focusing on the more challenging high upscaling factors. Extensive benchmark evaluations demonstrate the effectiveness of our approach.