Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems

DOI10.1137/17M1141771zbMath1401.94024arXiv1707.00372OpenAlexW2777802649MaRDI QIDQ4689753

Eunju Cha, Yoseob Han, Jong Chul Ye

Publication date: 17 October 2018

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1707.00372

zbMATH Keywords

inverse problemsframeletsdeep learningconvolutional neural networkReLUperfect reconstruction condition

Mathematics Subject Classification ID

Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Learning and adaptive systems in artificial intelligence (68T05) Biomedical imaging and signal processing (92C55) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Radon transform (44A12) Numerical methods for wavelets (65T60) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Related Items

Fluid sensing using microcantilevers: from physics-based modeling to deep learning ⋮ Wide-Band Butterfly Network: Stable and Efficient Inversion Via Multi-Frequency Neural Networks ⋮ A finite element based deep learning solver for parametric PDEs ⋮ Universal approximation with quadratic deep networks ⋮ Directional mean curvature for textured image demixing ⋮ Estimating a Potential Without the Agony of the Partition Function ⋮ Wavelets in the deep learning era ⋮ A review on deep learning in medical image reconstruction ⋮ Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method ⋮ Big in Japan: regularizing networks for solving inverse problems ⋮ Networks for nonlinear diffusion problems in imaging ⋮ Shallow neural networks for fluid flow reconstruction with limited sensors ⋮ A Mathematical Framework for Deep Learning in Elastic Source Imaging ⋮ Deep learning on image denoising: an overview ⋮ Image fusion network for dual-modal restoration ⋮ Solving inverse problems using data-driven models ⋮ A dataset-free deep learning method for low-dose CT image reconstruction ⋮ Bilevel Methods for Image Reconstruction

Uses Software

• TensorFlow
• MatConvNet
• ImageNet
• Adam
• U-Net
• DeconvNet
• AlexNet
• DnCNN

Cites Work

• Unnamed Item
• Unnamed Item
• Framelets: MRA-based constructions of wavelet frames
• Convergence analysis of tight framelet approach for missing data recovery
• A framelet-based image inpainting algorithm
• Hankel Matrix Rank Minimization with Applications to System Identification and Realization
• Group Invariant Scattering
• Compressive Sampling Using Annihilating Filter-Based Low-Rank Interpolation
• Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples
• Matrix pencil method for estimating parameters of exponentially damped/undamped sinusoids in noise
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Split Bregman Methods and Frame Based Image Restoration
• Ten Lectures on Wavelets
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Annihilating Filter-Based Low-Rank Hankel Matrix Approach for Image Inpainting
• Sparse and Low-Rank Decomposition of a Hankel Structured Matrix for Impulse Noise Removal
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• 10.1162/153244303321897690
• Neural Network Learning
• A Tale of Two Bases: Local-Nonlocal Regularization on Image Patches with Convolution Framelets
• Image restoration: Total variation, wavelet frames, and beyond
• Sampling signals with finite rate of innovation
• A Review of Image Denoising Algorithms, with a New One
• Convex analysis and monotone operator theory in Hilbert spaces
• Compressed sensing