Swin Transformer Based Network with Residual Channel Attention for Bit-Depth Expansion
-
- Tsuchihashi Ai
- Graduate School of Engineering, Tamagawa University
-
- Iriyama Taishi
- Department of Information and Computer Science, Saitama University
-
- Sato Masatoshi
- Graduate School of Engineering, Tamagawa University
-
- Aomori Hisashi
- Department of Electronic Engineering, Chukyo University
-
- Otake Tsuyoshi
- Graduate School of Engineering, Tamagawa University
この論文をさがす
説明
<p>Bit-depth expansion is a technique for reconstructing a high-bit image by predicting the missing bits in a low-bit image. With the development of high-bit monitors, corresponding high-bit images are needed to maximize their performance. However, many image data are still in 8-bit format. It is a complicated task to accurately recover lost information by expanding the bit depth while distinguishing between false contours and edges in real images. In this study, we propose a novel bit-depth expansion method using a Swin Transformer-based network with Channel Attention Layers (CALs). This network achieves high-performance bit-depth expansion by utilizing not only spatial features, which is an advantage of the Swin Transformer-based network, but also the correlation between channels obtained by CALs. Experimental results show that the proposed method outperforms conventional methods.</p>
収録刊行物
-
- 信号処理
-
信号処理 28 (4), 169-172, 2024-07-01
信号処理学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390863629154735744
-
- ISSN
- 18801013
- 13426230
-
- 本文言語コード
- en
-
- 資料種別
- journal article
-
- データソース種別
-
- JaLC
- Crossref
- KAKEN
- OpenAIRE
-
- 抄録ライセンスフラグ
- 使用不可