Yan, Q.Gong, D.Shi, J.Q.van den Hengel, A.Shen, C.Reid, I.Zhang, Y.2021-11-262021-11-262021International Journal of Computer Vision, 2021; 130(1)0920-56911573-1405https://hdl.handle.net/2440/133427Ghosting 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.en© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021High dynamic range imaging; de-ghosting; attention mechanism; deep learningJournal article10.1007/s11263-021-01535-y2021-11-26593272Shi, J.Q. [0000-0002-9126-2107]van den Hengel, A. [0000-0003-3027-8364]Shen, C. [0000-0002-8648-8718]Reid, I. [0000-0001-7790-6423]