Image Compression-Aware Deep Camera ISP Network
- Authors
- Uhm, Kwang-Hyun; Choi, Kyuyeon; Jung, Seung-Won; Ko, Sung-Jea
- Issue Date
- 2021
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Image coding; Transform coding; Cameras; Training; Pipelines; Task analysis; Noise reduction; Camera ISP; compression artifacts; convolutional neural network; image compression
- Citation
- IEEE ACCESS, v.9, pp.137824 - 137832
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 9
- Start Page
- 137824
- End Page
- 137832
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/138641
- DOI
- 10.1109/ACCESS.2021.3116702
- ISSN
- 2169-3536
- Abstract
- Several recent studies have attempted to fully replace the conventional camera image signal processing (ISP) pipeline with convolutional neural networks (CNNs). However, the previous CNN-based ISPs, simply referred to as ISP-Nets, have not explicitly considered that images have to be lossy-compressed in most cases, especially by the off-the-shelf JPEG. To address this issue, in this paper, we propose a novel compression-aware deep camera ISP learning framework. At first, we introduce a new use case of compression artifacts simulation network (CAS-Net), which operates in the opposite way of commonly used compression artifacts reduction networks. Then, the CAS-Net is connected with an ISP-Net such that the ISP network can be trained with consideration of image compression. Throughout experimental studies, we show that our compression-aware camera ISP network can produce images with a better tradeoff between bit-rate and image quality compared to its compression-agnostic version when the performance is evaluated after JPEG compression.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.