| dc.contributor | 資訊系 | |
| dc.creator (作者) | 彭彥璁 | |
| dc.creator (作者) | Peng, Yan-Tsung;Liu, Po-Sheng;Tsai, Fu-Jen;Tsai, Chung-Chi;Lin, Chia-Wen;Lin, Yen-Yu | |
| dc.date (日期) | 2022-11 | |
| dc.date.accessioned | 16-Feb-2024 15:36:54 (UTC+8) | - |
| dc.date.available | 16-Feb-2024 15:36:54 (UTC+8) | - |
| dc.date.issued (上傳時間) | 16-Feb-2024 15:36:54 (UTC+8) | - |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/149883 | - |
| dc.description.abstract (摘要) | Previous deblurring methods devote to training a generic model with blur and sharp training pairs. However, these methods might lead to sub-optimal results caused by the domain gap between the training and testing set. In this paper, we proposed a reblur-deblur meta-transferring scheme to realize test-time adaptation for the dynamic scene deblurring. Since blur and sharp pairs are hard to obtain during testing, we leverage blurred videos to find some relative-sharp patches as pseudo ground truths, which would be reblurred by a reblurring model to form pseudo blur and sharp pairs. Our pseudo pairs can enable meta-learning to achieve test-time adaptation with few gradien updates. Extensive experimental results show that our reblur-deblur meta-learning scheme improves the existing deblurring models in various datasets, including, DVD, REDS, and RealBlur. | |
| dc.format.extent | 100 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | British Machine Vision Conference (BMVC), The British Machine Vision Association and Society for Pattern Recognition | |
| dc.title (題名) | Meta Transferring for Deblurring | |
| dc.type (資料類型) | conference | |
