Improving Dynamic HDR Imaging with Fusion Transformer
Rufeng Chen, Bolun Zheng, Hua Zhang, Quan Chen, Chenggang Yan, Gregory Slabaugh, Shanxin Yuan
Abstract
Reconstructing a High Dynamic Range (HDR) image from several Low Dynamic Range (LDR) images with different exposures is a challenging task, especially in the presence of camera and object motion. Though existing models using convolutional neural networks (CNNs) have made great progress, challenges still exist, e.g., ghosting artifacts. Transformers, originating from the field of natural language processing, have shown success in computer vision tasks, due to their ability to address a large receptive field even within a single layer. In this paper, we propose a transformer model for HDR imaging. Our pipeline includes three steps: alignment, fusion, and reconstruction. The key component is the HDR transformer module. Through experiments and ablation studies, we demonstrate that our model outperforms the state-of-the-art by large margins on several popular public datasets.
BibTeX
@article{Chen_Zheng_Zhang_Chen_Yan_Slabaugh_Yuan_2023, title={Improving Dynamic HDR Imaging with Fusion Transformer}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25107}, DOI={10.1609/aaai.v37i1.25107}, abstractNote={Reconstructing a High Dynamic Range (HDR) image from several Low Dynamic Range (LDR) images with different exposures is a challenging task, especially in the presence of camera and object motion. Though existing models using convolutional neural networks (CNNs) have made great progress, challenges still exist, e.g., ghosting artifacts. Transformers, originating from the field of natural language processing, have shown success in computer vision tasks, due to their ability to address a large receptive field even within a single layer. In this paper, we propose a transformer model for HDR imaging. Our pipeline includes three steps: alignment, fusion, and reconstruction. The key component is the HDR transformer module. Through experiments and ablation studies, we demonstrate that our model outperforms the state-of-the-art by large margins on several popular public datasets.}, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chen, Rufeng and Zheng, Bolun and Zhang, Hua and Chen, Quan and Yan, Chenggang and Slabaugh, Gregory and Yuan, Shanxin}, year={2023}, month={Jun.}, pages={340-349} }