# Image Denoising with Control over Deep Network Hallucination

arXiv: https://arxiv.org/abs/2201.00429 · HTML: https://mlsanity.com/paper/2201.00429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 2 Jan 2022.

## Builds on (most cited first, 18 of 18)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining](https://mlsanity.com/paper/1906.11129/) (2019)
- [Confidence-Aware Learning for Deep Neural Networks](https://mlsanity.com/paper/2007.01458/) (2020)
- [Regularization by Denoising: Clarifications and New Interpretations](https://mlsanity.com/paper/1806.02296/) (2018)
- [Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization](https://mlsanity.com/paper/2002.11244/) (2020)
- [A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images](https://mlsanity.com/paper/1812.10366/) (2018)
- [Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning](https://mlsanity.com/paper/1907.03029/) (2019)
- [Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks](https://mlsanity.com/paper/2003.07119/) (2020)
- [BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration](https://mlsanity.com/paper/2011.01406/) (2020)
- [Real-World Super-Resolution of Face-Images from Surveillance Cameras](https://mlsanity.com/paper/2102.03113/) (2021)
- [Confidence Measure Guided Single Image De-raining](https://mlsanity.com/paper/1909.04207/) (2019)
- [Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion](https://mlsanity.com/paper/2101.04631/) (2021)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)

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

- [Towards Robust Drone Vision in the Wild](https://mlsanity.com/paper/2208.12655/) (2022)

## Abstract (arXiv)

Deep image denoisers achieve state-of-the-art results but with a hidden cost. As witnessed in recent literature, these deep networks are capable of overfitting their training distributions, causing inaccurate hallucinations to be added to the output and generalizing poorly to varying data. For better control and interpretability over a deep denoiser, we propose a novel framework exploiting a denoising network. We call it controllable confidence-based image denoising (CCID). In this framework, we exploit the outputs of a deep denoising network alongside an image convolved with a reliable filter. Such a filter can be a simple convolution kernel which does not risk adding hallucinated information. We propose to fuse the two components with a frequency-domain approach that takes into account the reliability of the deep network outputs. With our framework, the user can control the fusion of the two components in the frequency domain. We also provide a user-friendly map estimating spatially the confidence in the output that potentially contains network hallucination. Results show that our CCID not only provides more interpretability and control, but can even outperform both the quantitative performance of the deep denoiser and that of the reliable filter, especially when the test data diverge from the training data.