Blind image inpainting with sparse directional filter dictionaries for lightweight CNNs

DOI10.1007/s10851-022-01119-6zbMath1512.68424arXiv2205.06597MaRDI QIDQ6162154

Andrés Bruhn, Jenny Schmalfuss, Nikolaos Karantzas, Demetrio Labate, Heng Zhao, Erik Scheurer

Publication date: 15 June 2023

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2205.06597

zbMATH Keywords

neural networksimage restorationdeep learninginpaintingsparse representations

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• Unnamed Item
• Wavelet inpainting with the \(\ell_{0}\) sparse regularization
• A variational framework for exemplar-based image inpainting
• Wavelet frame based blind image inpainting
• Compactly supported shearlets are optimally sparse
• Image inpainting using sparse multiscale representations: image recovery performance guarantees
• Total variation wavelet inpainting
• Analysis of inpainting via clustered sparsity and microlocal analysis
• On the design of multi-dimensional compactly supported Parseval framelets with directional characteristics
• Simultaneous cartoon and texture image inpainting using morphological component analysis (MCA)
• Mathematical Models for Local Nontexture Inpaintings
• Learning Multiscale Sparse Representations for Image and Video Restoration
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Variational image inpainting
• Data compression and harmonic analysis
• Digital inpainting based on the Mumford–Shah–Euler image model
• Image restoration: Total variation, wavelet frames, and beyond
• Optimally Sparse Multidimensional Representation Using Shearlets

This page was built for publication: Blind image inpainting with sparse directional filter dictionaries for lightweight CNNs