Learning Controllable ISP for Image Enhancement
- Authors
- Kim, Heewon; Lee, Kyoung Mu
- Issue Date
- Aug-2024
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Image enhancemen; image manipulation; deep learning
- Citation
- IEEE TRANSACTIONS ON IMAGE PROCESSING, v.33, pp 867 - 880
- Pages
- 14
- Journal Title
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- Volume
- 33
- Start Page
- 867
- End Page
- 880
- URI
- https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/49239
- DOI
- 10.1109/TIP.2023.3305816
- ISSN
- 1057-7149
1941-0042
- Abstract
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.