Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.01569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916080350396416 |
|---|---|
| author | Fu, Kang Peng, Yicong Zhang, Zicheng Xu, Qihang Liu, Xiaohong Wang, Jia Zhai, Guangtao |
| author_facet | Fu, Kang Peng, Yicong Zhang, Zicheng Xu, Qihang Liu, Xiaohong Wang, Jia Zhai, Guangtao |
| contents | Recently, many algorithms have employed image-adaptive lookup tables (LUTs) to achieve real-time image enhancement. Nonetheless, a prevailing trend among existing methods has been the employment of linear combinations of basic LUTs to formulate image-adaptive LUTs, which limits the generalization ability of these methods. To address this limitation, we propose a novel framework named AttentionLut for real-time image enhancement, which utilizes the attention mechanism to generate image-adaptive LUTs. Our proposed framework consists of three lightweight modules. We begin by employing the global image context feature module to extract image-adaptive features. Subsequently, the attention fusion module integrates the image feature with the priori attention feature obtained during training to generate image-adaptive canonical polyadic tensors. Finally, the canonical polyadic reconstruction module is deployed to reconstruct image-adaptive residual 3DLUT, which is subsequently utilized for enhancing input images. Experiments on the benchmark MIT-Adobe FiveK dataset demonstrate that the proposed method achieves better enhancement performance quantitatively and qualitatively than the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancement Fu, Kang Peng, Yicong Zhang, Zicheng Xu, Qihang Liu, Xiaohong Wang, Jia Zhai, Guangtao Computer Vision and Pattern Recognition Recently, many algorithms have employed image-adaptive lookup tables (LUTs) to achieve real-time image enhancement. Nonetheless, a prevailing trend among existing methods has been the employment of linear combinations of basic LUTs to formulate image-adaptive LUTs, which limits the generalization ability of these methods. To address this limitation, we propose a novel framework named AttentionLut for real-time image enhancement, which utilizes the attention mechanism to generate image-adaptive LUTs. Our proposed framework consists of three lightweight modules. We begin by employing the global image context feature module to extract image-adaptive features. Subsequently, the attention fusion module integrates the image feature with the priori attention feature obtained during training to generate image-adaptive canonical polyadic tensors. Finally, the canonical polyadic reconstruction module is deployed to reconstruct image-adaptive residual 3DLUT, which is subsequently utilized for enhancing input images. Experiments on the benchmark MIT-Adobe FiveK dataset demonstrate that the proposed method achieves better enhancement performance quantitatively and qualitatively than the state-of-the-art methods. |
| title | AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.01569 |