# Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior

arXiv: https://arxiv.org/abs/2204.11146 · HTML: https://mlsanity.com/paper/2204.11146/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 23 Apr 2022.

## Builds on (most cited first, 13 of 13)

- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Robust and interpretable blind image denoising via bias-free convolutional neural networks](https://mlsanity.com/paper/1906.05478/) (2019)
- [Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds](https://mlsanity.com/paper/1808.10038/) (2018)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [Total Deep Variation for Linear Inverse Problems](https://mlsanity.com/paper/2001.05005/) (2020)
- [Learning step sizes for unfolded sparse coding](https://mlsanity.com/paper/1905.11071/) (2019)
- [Learned Convolutional Sparse Coding](https://mlsanity.com/paper/1711.00328/) (2017)
- [Deep K-SVD Denoising](https://mlsanity.com/paper/1909.13164/) (2019)
- [Rethinking the CSC Model for Natural Images](https://mlsanity.com/paper/1909.05742/) (2019)
- [Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks](https://mlsanity.com/paper/1705.04748/) (2017)
- [CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing](https://mlsanity.com/paper/2112.00913/) (2021)

## Built on by (most cited first, 1 of 1)

- [Noisy MRI Reconstruction via MAP Estimation with an Implicit Deep-Denoiser Prior](https://mlsanity.com/paper/2511.11963/) (2025)

## Abstract (arXiv)

Image processing neural networks, natural and artificial, have a long history with orientation-selectivity, often described mathematically as Gabor filters. Gabor-like filters have been observed in the early layers of CNN classifiers and even throughout low-level image processing networks. In this work, we take this observation to the extreme and explicitly constrain the filters of a natural-image denoising CNN to be learned 2D real Gabor filters. Surprisingly, we find that the proposed network (GDLNet) can achieve near state-of-the-art denoising performance amongst popular fully convolutional neural networks, with only a fraction of the learned parameters. We further verify that this parameterization maintains the noise-level generalization (training vs. inference mismatch) characteristics of the base network, and investigate the contribution of individual Gabor filter parameters to the performance of the denoiser. We present positive findings for the interpretation of dictionary learning networks as performing accelerated sparse-coding via the importance of untied learned scale parameters between network layers. Our network's success suggests that representations used by low-level image processing CNNs can be as simple and interpretable as Gabor filterbanks.