Abstract
High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.
Original language | English |
---|---|
Article number | 103881 |
Journal | Computer Vision and Image Understanding |
Early online date | 7 Nov 2023 |
DOIs | |
Publication status | Published - 1 Jan 2024 |
Bibliographical note
Open Access via the Elsevier agreementsData Availability Statement
I have shared the code on GitHub: https://github.com/TianhongDai/wavelet-hdr.Keywords
- High dynamic range image
- Ghosting artifacts
- Discrete wavelet transform
- RAW HDR imaging dataset
Fingerprint
Dive into the research topics of 'Wavelet-based Network for High Dynamic Range Imaging'. Together they form a unique fingerprint.Datasets
-
Data From Wavelet-based network for high dynamic range imaging
Dai, T. (Creator), Li, W. (Creator), Cao, X. (Creator), Liu, J. (Creator), Jia, X. (Creator), Leonardis, A. (Creator), Yan, Y. (Creator) & Yuan, S. (Creator), University of Aberdeen, Nov 2023
DOI: 10.1016/j.cviu.2023.103881, https://github.com/TianhongDai/wavelet-hdr and one more link, https://cseweb.ucsd.edu/~viscomp/projects/SIG17HDR/PaperData/SIGGRAPH17_HDR.pdf (show fewer)
Dataset