Abstract | ||
---|---|---|
High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based methods are typically prone to producing ghosting artifacts and intensity distortions in the presence of large motion and severe saturation. In this paper, we propose a novel Context-Aware Vision Transformer (CA-ViT) for ghost-free high dynamic range imaging. The CA-ViT is designed as a dual-branch architecture, which can jointly capture both global and local dependencies. Specifically, the global branch employs a window-based Transformer encoder to model long-range object movements and intensity variations to solve ghosting. For the local branch, we design a local context extractor (LCE) to capture short-range image features and use the channel attention mechanism to select informative local details across the extracted features to complement the global branch. By incorporating the CA-ViT as basic components, we further build the HDR-Transformer, a hierarchical network to reconstruct high-quality ghost-free HDR images. Extensive experiments on three benchmark datasets show that our approach outperforms state-of-the-art methods qualitatively and quantitatively with considerably reduced computational budgets. Codes are available at https://github.com/megvii-research/HDR-Transformer. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-19800-7_20 | European Conference on Computer Vision |
Keywords | DocType | Citations |
High dynamic range deghosting,Context-aware vision transformer | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhen Liu | 1 | 0 | 0.34 |
Y. L. Wang | 2 | 120 | 28.52 |
B Zeng | 3 | 1374 | 159.35 |
Shuaicheng Liu | 4 | 363 | 28.26 |