Towards Real Scene Super-Resolution with Raw Images
This work addresses the challenge of real-world image super-resolution for applications like photography and surveillance, though it is incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of poor super-resolution performance in real scenarios by generating realistic training data through camera imaging simulation and using raw images with a dual CNN to exploit radiance information, achieving superior results in single image super-resolution.
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.