Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes

TL;DR

SelfHDR is a self-supervised method for HDR imaging from multi-exposure images in dynamic scenes, avoiding the need for HDR ground-truth data and achieving state-of-the-art results.

Contribution

It introduces a self-supervised HDR reconstruction framework that learns from multi-exposure images without requiring labeled HDR data.

Findings

Outperforms existing self-supervised methods in HDR quality

Achieves comparable results to supervised methods

Effective in dynamic scene scenarios

Abstract

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