Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
arXiv:1912.02456
Abstract
Non-local self-similarity and sparsity principles have proven to be powerful priors for natural image modeling. We propose a novel differentiable relaxation of joint sparsity that exploits both principles and leads to a general framework for image restoration which is (1) trainable end to end, (2) fully interpretable, and (3) much more compact than competing deep learning architectures. We apply this approach to denoising, jpeg deblocking, and demosaicking, and show that, with as few as 100K parameters, its performance on several standard benchmarks is on par or better than state-of-the-art methods that may have an order of magnitude or more parameters.
arXiv commentECCV 2020
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Task-Driven Dictionary Learning
- Structured Variable Selection with Sparsity-Inducing Norms
- Residual Non-local Attention Networks for Image Restoration
- Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
- Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
- Deep Convolution Networks for Compression Artifacts Reduction
- Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis
- Rethinking the CSC Model for Natural Images