Improving Dynamic HDR Imaging with Fusion Transformer
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (1) , 340-349
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.Keywords
This publication has 14 references indexed in Scilit:
- Wavelet-based network for high dynamic range imagingComputer Vision and Image Understanding, 2023
- Constrained Predictive Filters for Single Image Bokeh RenderingIEEE Transactions on Computational Imaging, 2022
- Learning Frequency Domain Priors for Image DemoireingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- HDR-GAN: HDR Image Reconstruction From Multi-Exposed LDR Images With Large MotionsIEEE Transactions on Image Processing, 2021
- Fast Multi-Scale Structural Patch Decomposition for Multi-Exposure Image FusionIEEE Transactions on Image Processing, 2020
- Deep HDR Imaging via A Non-Local NetworkIEEE Transactions on Image Processing, 2020
- Implicit Dual-Domain Convolutional Network for Robust Color Image Compression Artifact ReductionIEEE Transactions on Circuits and Systems for Video Technology, 2019
- A Fast, Scalable, and Reliable Deghosting Method for Extreme Exposure Fusion2019
- Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition ApproachIEEE Transactions on Image Processing, 2017
- Automatic High-Dynamic Range Image Generation for Dynamic ScenesIEEE Computer Graphics and Applications, 2008