Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/133427
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Dual-attention-guided network for ghost-free high dynamic range imaging |
Author: | Yan, Q. Gong, D. Shi, J.Q. van den Hengel, A. Shen, C. Reid, I. Zhang, Y. |
Citation: | International Journal of Computer Vision, 2021; 130(1) |
Publisher: | Springer Science and Business Media LLC |
Issue Date: | 2021 |
ISSN: | 0920-5691 1573-1405 |
Statement of Responsibility: | Qingsen Yan, Dong Gong, Javen Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid and Yanning Zhang |
Abstract: | Ghosting artifacts caused by moving objects and misalignments are a key challenge in constructing high dynamic range (HDR) images. Current methods first register the input low dynamic range (LDR) images using optical flow before merging them. This process is error-prone, and often causes ghosting in the resulting merged image. We propose a novel dual-attention-guided end-to-end deep neural network, called DAHDRNet, which produces high-quality ghost-free HDR images. Unlike previous methods that directly stack the LDR images or features for merging, we use dual-attention modules to guide the merging according to the reference image. DAHDRNet thus exploits both spatial attention and feature channel attention to achieve ghost-free merging. The spatial attention modules automatically suppress undesired components caused by misalignments and saturation, and enhance the fine details in the non-reference images. The channel attention modules adaptively rescale channel-wise features by considering the inter-dependencies between channels. The dual-attention approach is applied recurrently to further improve feature representation, and thus alignment. A dilated residual dense block is devised to make full use of the hierarchical features and increase the receptive field when hallucinating missing details. We employ a hybrid loss function, which consists of a perceptual loss, a total variation loss, and a content loss to recover photo-realistic images. Although DAHDRNet is not flow-based, it can be applied to flow-based registration to reduce artifacts caused by optical-flow estimation errors. Experiments on different datasets show that the proposed DAHDRNet achieves state-of-the-art quantitative and qualitative results. |
Keywords: | High dynamic range imaging; de-ghosting; attention mechanism; deep learning |
Rights: | © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021 |
DOI: | 10.1007/s11263-021-01535-y |
Grant ID: | http://purl.org/au-research/grants/arc/DP140102270 http://purl.org/au-research/grants/arc/DP160100703 |
Published version: | http://dx.doi.org/10.1007/s11263-021-01535-y |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.