Deep K-SVD Denoising
Meyer Scetbon, Michael Elad, Peyman Milanfar

TL;DR
This paper redesigns the classical K-SVD denoising algorithm into a deep learning architecture, enabling supervised training that significantly improves its performance and bridges the gap with modern deep-learning methods.
Contribution
It introduces a differentiable, end-to-end deep architecture based on K-SVD, combining classic sparsity methods with modern deep learning for image denoising.
Findings
Outperforms classical K-SVD substantially
Approaches the performance of recent deep-learning denoising methods
Maintains the core principles of K-SVD while enabling learnability
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
