# Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising

arXiv: https://arxiv.org/abs/2103.03070 · HTML: https://mlsanity.com/paper/2103.03070/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 4 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [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)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [When AWGN-based Denoiser Meets Real Noises](https://mlsanity.com/paper/1904.03485/) (2019)
- [A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising](https://mlsanity.com/paper/1807.04364/) (2018)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [Self-Organized Operational Neural Networks with Generative Neurons](https://mlsanity.com/paper/2004.11778/) (2020)
- [RENOIR - A Dataset for Real Low-Light Image Noise Reduction](https://mlsanity.com/paper/1409.8230/) (2014)
- [GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling](https://mlsanity.com/paper/1905.11172/) (2019)
- [Operational Neural Networks](https://mlsanity.com/paper/1902.11106/) (2019)
- [Self-Organized Operational Neural Networks for Severe Image Restoration Problems](https://mlsanity.com/paper/2008.12894/) (2020)
- [Kervolutional Neural Networks](https://mlsanity.com/paper/1904.03955/) (2019)
- [FastONN -- Python based open-source GPU implementation for Operational Neural Networks](https://mlsanity.com/paper/2006.02267/) (2020)
- [Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticity](https://mlsanity.com/paper/2009.08934/) (2020)

## Built on by (most cited first, 2 of 2)

- [Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-ONNs](https://mlsanity.com/paper/2402.05582/) (2024)
- [Image denoising by Super Neurons: Why go deep?](https://mlsanity.com/paper/2111.14948/) (2021)

## Abstract (arXiv)

Real-world blind denoising poses a unique image restoration challenge due to the non-deterministic nature of the underlying noise distribution. Prevalent discriminative networks trained on synthetic noise models have been shown to generalize poorly to real-world noisy images. While curating real-world noisy images and improving ground truth estimation procedures remain key points of interest, a potential research direction is to explore extensions to the widely used convolutional neuron model to enable better generalization with fewer data and lower network complexity, as opposed to simply using deeper Convolutional Neural Networks (CNNs). Operational Neural Networks (ONNs) and their recent variant, Self-organized ONNs (Self-ONNs), propose to embed enhanced non-linearity into the neuron model and have been shown to outperform CNNs across a variety of regression tasks. However, all such comparisons have been made for compact networks and the efficacy of deploying operational layers as a drop-in replacement for convolutional layers in contemporary deep architectures remains to be seen. In this work, we tackle the real-world blind image denoising problem by employing, for the first time, a deep Self-ONN. Extensive quantitative and qualitative evaluations spanning multiple metrics and four high-resolution real-world noisy image datasets against the state-of-the-art deep CNN network, DnCNN, reveal that deep Self-ONNs consistently achieve superior results with performance gains of up to 1.76dB in PSNR. Furthermore, Self-ONNs with half and even quarter the number of layers that require only a fraction of computational resources as that of DnCNN can still achieve similar or better results compared to the state-of-the-art.