# Joint High Dynamic Range Imaging and Super-Resolution from a Single Image

## TL;DR

This paper introduces a CNN-based framework that simultaneously enhances image resolution and dynamic range by focusing on high-frequency reflectance details, outperforming cascade methods.

## Contribution

The novel joint HDRI and super-resolution framework leverages reflectance-based high-frequency detail reconstruction with a specialized loss function, improving image quality.

## Key findings

- Outperforms cascade CNN-based SR and HDRI methods
- Focuses on reflectance component for detail enhancement
- Uses a tailored loss function for naturalness

## Abstract

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.