Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.01183 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916345179799552 |
|---|---|
| author | Shang, Xiaoke Li, Gehui Jiang, Zhiying Zhang, Shaomin Ding, Nai Liu, Jinyuan |
| author_facet | Shang, Xiaoke Li, Gehui Jiang, Zhiying Zhang, Shaomin Ding, Nai Liu, Jinyuan |
| contents | The correction of exposure-related issues is a pivotal component in enhancing the quality of images, offering substantial implications for various computer vision tasks. Historically, most methodologies have predominantly utilized spatial domain recovery, offering limited consideration to the potentialities of the frequency domain. Additionally, there has been a lack of a unified perspective towards low-light enhancement, exposure correction, and multi-exposure fusion, complicating and impeding the optimization of image processing. In response to these challenges, this paper proposes a novel methodology that leverages the frequency domain to improve and unify the handling of exposure correction tasks. Our method introduces Holistic Frequency Attention and Dynamic Frequency Feed-Forward Network, which replace conventional correlation computation in the spatial-domain. They form a foundational building block that facilitates a U-shaped Holistic Dynamic Frequency Transformer as a filter to extract global information and dynamically select important frequency bands for image restoration. Complementing this, we employ a Laplacian pyramid to decompose images into distinct frequency bands, followed by multiple restorers, each tuned to recover specific frequency-band information. The pyramid fusion allows a more detailed and nuanced image restoration process. Ultimately, our structure unifies the three tasks of low-light enhancement, exposure correction, and multi-exposure fusion, enabling comprehensive treatment of all classical exposure errors. Benchmarking on mainstream datasets for these tasks, our proposed method achieves state-of-the-art results, paving the way for more sophisticated and unified solutions in exposure correction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_01183 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction Shang, Xiaoke Li, Gehui Jiang, Zhiying Zhang, Shaomin Ding, Nai Liu, Jinyuan Computer Vision and Pattern Recognition The correction of exposure-related issues is a pivotal component in enhancing the quality of images, offering substantial implications for various computer vision tasks. Historically, most methodologies have predominantly utilized spatial domain recovery, offering limited consideration to the potentialities of the frequency domain. Additionally, there has been a lack of a unified perspective towards low-light enhancement, exposure correction, and multi-exposure fusion, complicating and impeding the optimization of image processing. In response to these challenges, this paper proposes a novel methodology that leverages the frequency domain to improve and unify the handling of exposure correction tasks. Our method introduces Holistic Frequency Attention and Dynamic Frequency Feed-Forward Network, which replace conventional correlation computation in the spatial-domain. They form a foundational building block that facilitates a U-shaped Holistic Dynamic Frequency Transformer as a filter to extract global information and dynamically select important frequency bands for image restoration. Complementing this, we employ a Laplacian pyramid to decompose images into distinct frequency bands, followed by multiple restorers, each tuned to recover specific frequency-band information. The pyramid fusion allows a more detailed and nuanced image restoration process. Ultimately, our structure unifies the three tasks of low-light enhancement, exposure correction, and multi-exposure fusion, enabling comprehensive treatment of all classical exposure errors. Benchmarking on mainstream datasets for these tasks, our proposed method achieves state-of-the-art results, paving the way for more sophisticated and unified solutions in exposure correction. |
| title | Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2309.01183 |