Publications-Proceedings
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
-
Loading...Loading...
Related Publications in TAIR
| Title | Domain-adaptive Video Deblurring via Test-time Blurring |
| Creator | 彭彥璁 Peng, Yan-Tsung;He, Jin-Ting;Tsai, Fu-Jen;Wu, Jia-Hao;Tsai, Chung-Chi;Lin, Chia-Wen;Lin, Yen-Yu |
| Contributor | 資訊系 |
| Key Words | Video deblurring; Domain adaptation; Diffusion model |
| Date | 2024-09 |
| Date Issued | 7-Jan-2025 09:36:33 (UTC+8) |
| Summary | Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the domain gap between training and testing videos, especially for those captured in real-world scenarios. To address this issue, we propose a domain adaptation scheme based on a blurring model to achieve test-time fine-tuning for deblurring models in unseen domains. Since blurred and sharp pairs are unavailable for fine-tuning during inference, our scheme can generate domain-adaptive training pairs to calibrate a deblurring model for the target domain. First, a Relative Sharpness Detection Module is proposed to identify relatively sharp regions from the blurry input images and regard them as pseudo-sharp images. Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing. To synthesize blurred images in compliance with the target data distribution, we propose a Domain-adaptive Blur Condition Generation Module to create domain-specific blur conditions for the blurring model. Finally, the generated pseudo-sharp and blurred pairs are used to fine-tune a deblurring model for better performance. Extensive experimental results demonstrate that our approach can significantly improve state-of-the-art video deblurring methods, providing performance gains of up to 7.54dB on various real-world video deblurring datasets. The source code is available at https://github.com/Jin-Ting-He/DADeblur. |
| Relation | European Conference on Computer Vision (ECCV), Springer Science+Business Media |
| Type | conference |
| DOI | https://doi.org/10.1007/978-3-031-73404-5_8 |
| dc.contributor | 資訊系 | |
| dc.creator (作者) | 彭彥璁 | |
| dc.creator (作者) | Peng, Yan-Tsung;He, Jin-Ting;Tsai, Fu-Jen;Wu, Jia-Hao;Tsai, Chung-Chi;Lin, Chia-Wen;Lin, Yen-Yu | |
| dc.date (日期) | 2024-09 | |
| dc.date.accessioned | 7-Jan-2025 09:36:33 (UTC+8) | - |
| dc.date.available | 7-Jan-2025 09:36:33 (UTC+8) | - |
| dc.date.issued (上傳時間) | 7-Jan-2025 09:36:33 (UTC+8) | - |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/155071 | - |
| dc.description.abstract (摘要) | Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the domain gap between training and testing videos, especially for those captured in real-world scenarios. To address this issue, we propose a domain adaptation scheme based on a blurring model to achieve test-time fine-tuning for deblurring models in unseen domains. Since blurred and sharp pairs are unavailable for fine-tuning during inference, our scheme can generate domain-adaptive training pairs to calibrate a deblurring model for the target domain. First, a Relative Sharpness Detection Module is proposed to identify relatively sharp regions from the blurry input images and regard them as pseudo-sharp images. Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing. To synthesize blurred images in compliance with the target data distribution, we propose a Domain-adaptive Blur Condition Generation Module to create domain-specific blur conditions for the blurring model. Finally, the generated pseudo-sharp and blurred pairs are used to fine-tune a deblurring model for better performance. Extensive experimental results demonstrate that our approach can significantly improve state-of-the-art video deblurring methods, providing performance gains of up to 7.54dB on various real-world video deblurring datasets. The source code is available at https://github.com/Jin-Ting-He/DADeblur. | |
| dc.format.extent | 107 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | European Conference on Computer Vision (ECCV), Springer Science+Business Media | |
| dc.subject (關鍵詞) | Video deblurring; Domain adaptation; Diffusion model | |
| dc.title (題名) | Domain-adaptive Video Deblurring via Test-time Blurring | |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1007/978-3-031-73404-5_8 | |
| dc.doi.uri (DOI) | https://doi.org/10.1007/978-3-031-73404-5_8 |