Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes
This addresses the costly data collection issue for HDR imaging in dynamic scenes, offering a practical solution for photographers and computer vision applications, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of ghosting artifacts in high dynamic range (HDR) imaging from multi-exposure images in dynamic scenes by proposing SelfHDR, a self-supervised method that eliminates the need for labeled HDR ground-truth data, achieving superior results against state-of-the-art self-supervised methods and comparable performance to supervised ones.
Merging multi-exposure images is a common approach for obtaining high dynamic range (HDR) images, with the primary challenge being the avoidance of ghosting artifacts in dynamic scenes. Recent methods have proposed using deep neural networks for deghosting. However, the methods typically rely on sufficient data with HDR ground-truths, which are difficult and costly to collect. In this work, to eliminate the need for labeled data, we propose SelfHDR, a self-supervised HDR reconstruction method that only requires dynamic multi-exposure images during training. Specifically, SelfHDR learns a reconstruction network under the supervision of two complementary components, which can be constructed from multi-exposure images and focus on HDR color as well as structure, respectively. The color component is estimated from aligned multi-exposure images, while the structure one is generated through a structure-focused network that is supervised by the color component and an input reference (\eg, medium-exposure) image. During testing, the learned reconstruction network is directly deployed to predict an HDR image. Experiments on real-world images demonstrate our SelfHDR achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones. Codes are available at https://github.com/cszhilu1998/SelfHDR