期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 4106-4115出版社
IEEE
DOI: 10.1109/ICCV48922.2021.00409
关键词
-
资金
- National Key Research and Development Program of China [2020AAA0107400]
- Zhejiang Provincial Natural Science Foundation of China [LZ18F020002]
- Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies
In this paper, a deep learning-based image enhancement method called StarEnhancer is proposed to cover multiple tonal styles using a single model. Users can customize the model with a one-time setting to make the enhanced images more in line with their aesthetics. The method outperforms contemporary single-style image enhancement methods in terms of processing speed and quality metrics.
Image enhancement is a subjective process whose targets vary with user preferences. In this paper, we propose a deep learning-based image enhancement method covering multiple tonal styles using only a single model dubbed StarEnhancer. It can transform an image from one tonal style to another, even if that style is unseen. With a simple one-time setting, users can customize the model to make the enhanced images more in line with their aesthetics. To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS. Finally, our proposed enhancement method has good interactability, which allows the user to fine-tune the enhanced image using intuitive options.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据