View : 375 Download: 0
Cross-Scale KNN Image Transformer for Image Restoration
- Title
- Cross-Scale KNN Image Transformer for Image Restoration
- Authors
- Lee H.; Choi H.; Sohn K.; Min D.
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2023
- Journal Title
- IEEE Access
- ISSN
- 2169-3536
- Citation
- IEEE Access vol. 11, pp. 13013 - 13027
- Keywords
- deblurring; denoising; deraining; Image restoration; k-nn search; low-level vision; self-attention; transformer
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- Numerous image restoration approaches have been proposed based on attention mechanism, achieving superior performance to convolutional neural networks (CNNs) based counterparts. However, they do not leverage the attention model in a form fully suited to the image restoration tasks. In this paper, we propose an image restoration network with a novel attention mechanism, called cross-scale k -NN image Transformer (CS-KiT), that effectively considers several factors such as locality, non-locality, and cross-scale aggregation, which are essential to image restoration. To achieve locality and non-locality, the CS-KiT builds k -nearest neighbor relation of local patches and aggregates similar patches through local attention. To induce cross-scale aggregation, we ensure that each local patch embraces different scale information with scale-aware patch embedding (SPE) which predicts an input patch scale through a combination of multi-scale convolution branches. We show the effectiveness of the CS-KiT with experimental results, outperforming state-of-the-art restoration approaches on image denoising, deblurring, and deraining benchmarks. © 2013 IEEE.
- DOI
- 10.1109/ACCESS.2023.3242556
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML