Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

By Qingsen Yan, Dong Gong, Javen Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian David Reid, Yanning Zhang. Computer Vision and Pattern Recognition, 2019

301 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cc20befe4b33049d8a4eb21fb05572ecaf95acca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Zhaoyang Lyu
2. Wei Zhong
3. Bo Dai
4. Zhongxuan Luo
5. Long Ma
6. Tian-jian Luo
7. Jinyuan Liu
8. Bo Zhang

Citations in the corpus

• AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system (2020, unknown): “The medical image segmentation and deep neural network [22–27] plays an important role in AI-assisted COVID-19 analysis in many works.”
• Generative Diffusion Prior for Unified Image Restoration and Enhancement (2023, methodology): “Moreover, we also show more samples compared with the state-of-the-art methods, including AHDRNet [91], HDR-GAN [59], DeepHDR [90] and deep-high-dynamicrange [30].”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, methodology): “In specific, we utilize two parallel dilated residual dense blocks (DRDB) [37, 38] to extract features from visual and infrared images.”