Towards Real Scene Super-Resolution With Raw Images

Xiangyu Xu, Yongrui Ma, Wenxiu Sun; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1723-1731

Abstract


Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic training data by simulating the imaging process of digital cameras. And to remedy the information loss of the input, we develop a dual convolutional neural network to exploit the originally captured radiance information in raw images. In addition, we propose to learn a spatially-variant color transformation which helps more effective color corrections. Extensive experiments demonstrate that super-resolution with raw data helps recover fine details and clear structures, and more importantly, the proposed network and data generation pipeline achieve superior results for single image super-resolution in real scenarios.

Related Material


[pdf]
[bibtex]
@InProceedings{Xu_2019_CVPR,
author = {Xu, Xiangyu and Ma, Yongrui and Sun, Wenxiu},
title = {Towards Real Scene Super-Resolution With Raw Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}