.png){kind=icon}
.png){kind=icon}
Return
Deep K-SVD Denoising
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2021.3090531.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This work considers noise removal from images, focusing on the well-known K-SVD denoising algorithm. This sparsity-based method was proposed in 2006, and for a short while it was considered as state-of-the-art. However, over the years it has been surpassed by other methods, including the recent deep-learning-based newcomers. The question we address in this paper is whether K-SVD was brought to its peak in its original conception, or whether it can be made competitive again. The approach we take in answering this question is to redesign the algorithm to operate in a supervised manner. More specifically, we propose an end-to-end deep architecture with the exact K-SVD computational path, and train it for optimized denoising. Our work shows how to overcome difficulties arising in turning the K-SVD scheme into a differentiable, and thus learnable, machine. With a small number of parameters to learn and while preserving the original K-SVD essence, the proposed architecture is shown to outperform the classical K-SVD algorithm substantially, and getting closer to recent state-of-the-art learning-based denoising methods. Adopting a broader context, this work touches on themes around the design of deep-learning solutions for image processing tasks, while paving a bridge between classic methods and novel deep-learning-based ones.
Keywords:
Noise reduction
Dictionaries
Image denoising
Task analysis
Noise measurement
Training
Bridges
K-SVD denoising algorithm
network unfolding
iterative shrinkage algorithms
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W