Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
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.
Code (1)
Tasks
DemosaickingDenoisingImage RestorationSimilar Papers 제목 키워드 기반
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems, and whose architectures are derived from an op…
compressed sensingDenoisingDiversityImage Denoising+1Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning
Nonlocal self-similarity within natural images has become an increasingly popular prior in deep-learning models. Despite their successful image restoration performance, such models remain largely uninterpretable due to t…
DenoisingDictionary LearningGrayscale Image DenoisingImage Denoising+1An Interpretable X-ray Style Transfer via Trainable Local Laplacian Filter
Radiologists have preferred visual impressions or 'styles' of X-ray images that are manually adjusted to their needs to support their diagnostic performance. In this work, we propose an automatic and interpretable X-ray …
DiagnosticSSIMStyle TransferA Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Medical Image Classification
In many medical imaging tasks, convolutional neural networks (CNNs) efficiently extract local features hierarchically. More recently, vision transformers (ViTs) have gained popularity, using self-attention mechanisms to …
image-classificationImage ClassificationMedical Image ClassificationGroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention
Nonlocal self-similarity within images has become an increasingly popular prior in deep-learning models. Despite their successful image restoration performance, such models remain largely uninterpretable due to their bla…
compressed sensingDenoisingDictionary LearningImage Denoising+2