Dong, Jiangxin ; Roth, Stefan ; Schiele, Bernt (2022)
DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 44 (12)
doi: 10.1109/TPAMI.2021.3138787
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. In contrast to existing methods that deblur the image directly in the standard image space, we propose to perform an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features, progressively recovering detail and small-scale structures. The proposed model is trained in an end-to-end manner and evaluated on scenarios with simulated Gaussian noise, saturated pixels, or JPEG compression artifacts as well as real-world images. Moreover, we present detailed analyses of the benefit of the feature-based Wiener deconvolution and of the multi-scale cascaded feature refinement as well as the robustness of the proposed approach. Our extensive experimental results show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Dong, Jiangxin ; Roth, Stefan ; Schiele, Bernt |
| Art des Eintrags: | Bibliographie |
| Titel: | DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring |
| Sprache: | Englisch |
| Publikationsjahr: | 1 Dezember 2022 |
| Verlag: | IEEE |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Jahrgang/Volume einer Zeitschrift: | 44 |
| (Heft-)Nummer: | 12 |
| DOI: | 10.1109/TPAMI.2021.3138787 |
| Kurzbeschreibung (Abstract): | We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. In contrast to existing methods that deblur the image directly in the standard image space, we propose to perform an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features, progressively recovering detail and small-scale structures. The proposed model is trained in an end-to-end manner and evaluated on scenarios with simulated Gaussian noise, saturated pixels, or JPEG compression artifacts as well as real-world images. Moreover, we present detailed analyses of the benefit of the feature-based Wiener deconvolution and of the multi-scale cascaded feature refinement as well as the robustness of the proposed approach. Our extensive experimental results show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin. |
| Freie Schlagworte: | Image deblurring, wiener deconvolution, feature-based deconvolution, multi-scale cascaded feature refinement, saturation, JPEG artifacts |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Visuelle Inferenz |
| Hinterlegungsdatum: | 18 Sep 2023 13:50 |
| Letzte Änderung: | 21 Sep 2023 13:37 |
| PPN: | 511843313 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum