Dong Gong

Attention-guided Network for Ghost-free High Dynamic Range Imaging (AHDR)

Dong Gong*, Qingsen Yan*, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang,

*The first two authors contributed equally to this work.

framework 

Abstract

Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes. Previous methods first register the input low dynamic range (LDR) images using optical flow before merging them, which are error-prone and cause ghosts in results. A very recent work tries to bypass optical flows via a deep network with skip-connections, however, which still suffers from ghosting artifacts for severe movement. To avoid the ghosting from the source, we propose a novel attention-guided end-to-end deep neural network (AHDRNet) to produce high-quality ghost-free HDR images. Unlike previous methods directly stacking the LDR images or features for merging, we use attention modules to guide the merging according to the reference image. The attention modules automatically suppress undesired components caused by misalignments and saturation and enhance desirable fine details in the non-reference images. In addition to the attention model, we use dilated residual dense block (DRDB) to make full use of the hierarchical features and increase the receptive field for hallucinating the missing details. The proposed AHDRNet is a non-flow-based method, which can also avoid the artifacts generated by optical-flow estimation error. Experiments on different datasets show that the proposed AHDRNet can achieve state-of-the-art quantitative and qualitative results.

Examples of the Estimated Attention Maps

attmap 

Examples of the Results

results 

Paper

Qingsen Yan*, Dong Gong*, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang.
Attention-guided Network for Ghost-free High Dynamic Range Imaging.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
(* Equal contribution)

[Paper] [arXiv] [Code]

Bibtex

@InProceedings{gong2019ahdr,
author = {Yan, Qingsen and Gong, Dong and Shi, Qinfeng and van den Hengel, Anton and Shen, Chunhua and Reid, Ian and Zhang, Yanning},
title = {Attention-guided Network for Ghost-free High Dynamic Range Imaging},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}