Self-Supervised Blind Image Deconvolution via Deep Generative Ensemble Learning
IEEE Transactions on Circuits and Systems for Video Technology · 2023-02 · 33 (2) · 634-647
DOI: 10.1109/tcsvt.2022.3207279 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-02. Verfasst von Mingqin Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Singapore Ministry of Education Academic Research Fund.
Abstract (Originalsprache)
Blind image deconvolution (BID) is about recovering a latent image with sharp details from its blurred observation generated by the convolution with an unknown smoothing kernel. Recently, deep generative priors from untrained neural networks (NNs) have emerged as a promising deep learning approach for BID, with the benefit of being free of external training samples. However, existing untrained-NN-based BID methods may suffer from under-deblurring or overfitting. In this paper, we propose an ensemble approach to better exploit the priors from untrained NNs for BID, which aggregates the deblurring results of multiple untrained NNs for improvement. To enjoy both the effectiveness and computational efficiency in ensemble learning, the untrained NNs are designed with a specific shared-base and multi-head architecture. In addition, a kernel-centering layer is proposed for handling the shift ambiguity among different predictions during ensemble, which also improves the robustness of kernel prediction to the setting of the kernel size parameter. Extensive experiments show that the proposed approach noticeably outperforms both exiting dataset-free methods and dataset-based methods.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
- Singapore Ministry of Education Academic Research Fund
Zitieren
APA
Chen, M., Quan, Y., Xu, Y., & Ji, H. (2023). Self-Supervised Blind Image Deconvolution via Deep Generative Ensemble Learning. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 634-647. https://doi.org/10.1109/tcsvt.2022.3207279
Vancouver
Chen M, Quan Y, Xu Y, Ji H. Self-Supervised Blind Image Deconvolution via Deep Generative Ensemble Learning. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(2):634-647. doi:10.1109/tcsvt.2022.3207279
BibTeX
@article{Chen2023,
author = {Chen, Mingqin and Quan, Yuhui and Xu, Yong and Ji, Hui},
title = {Self-Supervised Blind Image Deconvolution via Deep Generative Ensemble Learning},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2023},
volume = {33},
number = {2},
pages = {634--647},
doi = {10.1109/tcsvt.2022.3207279}
}
EUVIMED