Image Denoising with Control over Deep Network Hallucination

01/02/2022
by   Qiyuan Liang, et al.
4

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.

READ FULL TEXT

page 4

page 5

research
06/17/2021

Controllable Confidence-Based Image Denoising

Image denoising is a classic restoration problem. Yet, current deep lear...
research
10/28/2018

Enhanced CNN for image denoising

Due to the flexible architectures of deep convolutional neural networks ...
research
06/16/2023

CANDID: Correspondence AligNment for Deep-burst Image Denoising

With the advent of mobile phone photography and point-and-shoot cameras,...
research
03/29/2023

Real-time Controllable Denoising for Image and Video

Controllable image denoising aims to generate clean samples with human p...
research
11/26/2020

Image Denoising for Strong Gaussian Noises With Specialized CNNs for Different Frequency Components

In machine learning approach to image denoising a network is trained to ...
research
10/18/2019

Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images

Deep learning based image denoising methods have been extensively invest...

Please sign up or login with your details

Forgot password? Click here to reset