NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
arXiv:2005.01056
Abstract
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.
arXiv commentCVPRW 2020
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- SGDR: Stochastic Gradient Descent with Warm Restarts
- The relativistic discriminator: a key element missing from standard GAN
- Wide Activation for Efficient and Accurate Image Super-Resolution
- Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
- Gated Multiple Feedback Network for Image Super-Resolution