Searching for Controllable Image Restoration Networksopen access
- Authors
- Kim, Heewon; Baik, Sungyong; Choi, Myungsub; Choi, Janghoon; Lee, Kyoung Mu
- Issue Date
- Oct-2021
- Publisher
- IEEE COMPUTER SOC
- Citation
- 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), pp.14214 - 14223
- Indexed
- SCOPUS
- Journal Title
- 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
- Start Page
- 14214
- End Page
- 14223
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190318
- DOI
- 10.1109/ICCV48922.2021.01397
- ISSN
- 15505499
- Abstract
- We present a novel framework for controllable image restoration that can effectively restore multiple types and levels of degradation of a corrupted image. The proposed model, named TASNet, is automatically determined by our neural architecture search algorithm, which optimizes the efficiency-accuracy trade-off of the candidate model architectures. Specifically, we allow TASNet to share the early layers across different restoration tasks and adaptively adjust the remaining layers with respect to each task. The shared task-agnostic layers greatly improve the efficiency while the task-specific layers are optimized for restoration quality, and our search algorithm seeks for the best balance between the two. We also propose a new data sampling strategy to further improve the overall restoration performance. As a result, TASNet achieves significantly faster GPU latency and lower FLOPs compared to the existing state-of-the-art models, while also showing visually more pleasing outputs. The source code and pre-trained models are available at https://github.com/ghimhw/TASNet.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190318)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.