PuSH - Publication Server of Helmholtz Zentrum München

Chobola, T. ; Müller, G.* ; Dausmann, V.* ; Theileis, A.* ; Taucher, J.* ; Huisken, J.* ; Peng, T.

Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration.

IEEE Xplore, 3876-3885 (2023)
DOI
Non-blind deconvolution aims to restore a sharp image from its blurred counterpart given an obtained kernel. Existing deep neural architectures are often built based on large datasets of sharp ground truth images and trained with supervision. Sharp, high quality ground truth images, however, are not always available, especially for biomedical applications. This severely hampers the applicability of current approaches in practice. In this paper, we propose a novel non-blind deconvolution method that leverages the power of deep learning and classic iterative deconvolution algorithms. Our approach combines a pre-trained network to extract deep features from the input image with iterative Richardson-Lucy deconvolution steps. Subsequently, a zero-shot optimisation process is employed to integrate the deconvolved features, resulting in a high-quality reconstructed image. By performing the preliminary reconstruction with the classic iterative deconvolution method, we can effectively utilise a smaller network to produce the final image, thus accelerating the reconstruction whilst reducing the demand for valuable computational resources. Our method demonstrates significant improvements in various real-world applications non-blind deconvolution tasks.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Deconvolution ; Microscopy ; Self Supervised ; Zero Shot; Algorithm; Removal
ISSN (print) / ISBN 2375-9232
e-ISSN 2375-9259
Conference Title Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Journal IEEE Xplore
Quellenangaben Volume: , Issue: , Pages: 3876-3885 Article Number: , Supplement: ,
Publisher IEEE
Publishing Place 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1264 Usa
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Helmholtz Association under the joint research school "Munich School for Data Science -MUDS"