.png){kind=icon}
返回
Learning Controllable ISP for Image Enhancement
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3305816.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present a plug-and-play Image Signal Processor (ISP) for image enhancement to better produce diverse image styles than the previous works. Our proposed method, ContRollable Image Signal Processor (CRISP), explicitly controls the parameters of the ISP that determine output image styles. ISP parameters for high-quality (HQ) image styles are encoded into low-dimensional latent codes, allowing fast and easy style adjustments. We empirically show that CRISP covers a wide range of image styles with high efficiency. On the MIT-Adobe FiveK dataset, CRISP can very closely estimate the reference styles produced by human experts and achieves better MOS with diverse image styles. Compared with the state-of-the-art method, our ISP comprises only 19 parameters, allowing CRISP to have $2\times $ smaller parameters and $100\times $ reduced FLOPs for an image output. CRISP outperforms previous works in PSNR and FLOPs with several scenarios for style adjustments.
Keyword:
Image enhancemen
image manipulation
deep learning
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
Understanding the constitutive presentation of MHC class I immunopeptidomes in primary tissues了解MHC I类免疫蛋白在原始组织中的组成性呈现.png)
iScience
OAAI
iScienceIF0
OAAI分享收藏分享收藏
查看更多内容