Joint High Dynamic Range Imaging and Super-Resolution from a Single Image
This work addresses image quality enhancement for applications like photography or computer vision, but it is incremental as it builds on existing CNN and Retinex methods.
The paper tackles the problem of jointly enhancing image resolution and dynamic range from a single image, using a convolutional neural network that focuses on reconstructing high-frequency details via Retinex-based decomposition, and it outperforms cascade implementations of super-resolution and high dynamic range imaging.
This paper presents a new framework for jointly enhancing the resolution and the dynamic range of an image, i.e., simultaneous super-resolution (SR) and high dynamic range imaging (HDRI), based on a convolutional neural network (CNN). From the common trends of both tasks, we train a CNN for the joint HDRI and SR by focusing on the reconstruction of high-frequency details. Specifically, the high-frequency component in our work is the reflectance component according to the Retinex-based image decomposition, and only the reflectance component is manipulated by the CNN while another component (illumination) is processed in a conventional way. In training the CNN, we devise an appropriate loss function that contributes to the naturalness quality of resulting images. Experiments show that our algorithm outperforms the cascade implementation of CNN-based SR and HDRI.