| dc.contributor | 資訊系 | |
| dc.creator (作者) | 彭彥璁 | |
| dc.creator (作者) | Peng, Wen-Yi;Lin, Yi-Ting;Chen, Zihao;Li, Wei-Hua;Yoon, Aiden J.;Peng, Yan-Tsung | |
| dc.date (日期) | 2025-12 | |
| dc.date.accessioned | 12-Mar-2026 15:07:52 (UTC+8) | - |
| dc.date.available | 12-Mar-2026 15:07:52 (UTC+8) | - |
| dc.date.issued (上傳時間) | 12-Mar-2026 15:07:52 (UTC+8) | - |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/162046 | - |
| dc.description.abstract (摘要) | Rain degrades outdoor image quality, making deraining a challenging task due to varying rain density and direction. We propose a novel Rain-Aware Image Deraining Network (RAINet), leveraging a Transformer-based architecture to strategically separate attention and MLP modules to decompose rain layers and clean backgrounds. It leverages global and local rain-aware attention to capture rain features, while dilated convolutions aggregate contextual background before MLP processing. This multi-stage strategy efficiently produces clear, rain-free images, outperforming state-of-the-art models across diverse conditions. | |
| dc.format.extent | 98 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | Electronics Letters, Vol.61, No.1, e70471 | |
| dc.subject (關鍵詞) | image enhancement; image restoration | |
| dc.title (題名) | RAINet: Rain-Aware Image Deraining Network with Multi-Stage Image Decomposition | |
| dc.type (資料類型) | article | |
| dc.identifier.doi (DOI) | 10.1049/ell2.70471 | |
| dc.doi.uri (DOI) | https://doi.org/10.1049/ell2.70471 | |
