paper-with-me

홈 › Papers

Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration

2019-12-05 · ECCV 2020 8 · Bruno Lecouat, Jean Ponce, Julien Mairal

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.

📄 PDF Abstract BibTeX arXiv:1912.02456

Code (1)

bruno-31/groupsc 공식 구현 pytorch

Tasks

DemosaickingDenoisingImage Restoration

Similar Papers 제목 키워드 기반

A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding

2020-06-26 · NeurIPS 2020 12 · Bruno Lecouat, Jean Ponce, Julien Mairal

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+1

Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning

2023-06-02 · Nikola Janjušević, Amirhossein Khalilian-Gourtani, Adeen Flinker, Yao Wang

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+1

An Interpretable X-ray Style Transfer via Trainable Local Laplacian Filter

2024-11-11 · Dominik Eckert, Ludwig Ritschl, Christopher Syben, Christian Hümmer 외

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 Transfer

A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Medical Image Classification

2025-04-11 · Kerol Djoumessi, Samuel Ofosu Mensah, Philipp Berens

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 Classification

GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention

2024-07-19 · Nikola Janjusevic, Amirhossein Khalilian-Gourtani, Adeen Flinker, Li Feng 외

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