(EI 2022) Controllable Confidence-Based Image Denoising

Related tags

Deep LearningCCID
Overview

Image Denoising with Control over Deep Network Hallucination

Paper and arXiv preprint

-- Our frequency-domain insights derive from SFM and the concept of restoration reliability from BUIFD and BIGPrior --

Authors: Qiyuan Liang, Florian Cassayre, Haley Owsianko, Majed El Helou, and Sabine Süsstrunk

Python 3.7 pytorch 1.8.1

CCID framework

The figure below illustrates the CCID framework. By exploiting a reliable filter in parallel with a deep network, fused in the frequency domain, it enables users to control the hallucination contributions of the deep network and safeguard against its failures.

Abstract: 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. We show deep network hallucination can be exploited when the test data are similar to the training data, but is otherwise detrimental.

Structure overview

The code is structured as follows: pipeline.py and pipeline_no_gui.py implement the overall logic of the pipeline. All denoiser related code is stored inside the denoiser folder, confidence prediction code in the confidence folder, and frequency-domain fusion related code in the fusion folder. The library folder contains the datasets and deep learning models that we use for evaluation.

Run the program

  • With visualization:
    python3 -m CCID.pipeline
    For the visualization to work, you might need to install the tkinter module if it is not already present. Users can use the left and right arrows to switch the selected images.
  • Without visualization:
    python3 -m CCID.pipeline_no_gui
    The list of arguments can be retrieved with the --help flag.

Confidence prediction network

In the confidence folder, there are
(1) data_generation.py generates the data used for training the confidence prediction network. Given the clean image, our current implementation augments the data by rotating, flipping, and scaling. A random Gaussian noise component with level ranging in 0-100 is added to the image to simulate the scenario of out-of-distribution noise levels. It may be extended to include also different noise types and different image domains.

(2) confidence_train.py trains the novel confidence prediction network. The training argumentation is not given in args, but is a built-in value inside the file.

(3) confidence.py provides the high-level confidence prediction (testing) API: the prediction is performed given the noisy image and its denoised version, the result is a confidence map with lower resolution.

Citation

@article{liang2022image,
    title   = {Image Denoising with Control over Deep Network Hallucination},
    author  = {Liang, Qiyuan and Cassayre, Florian and Owsianko, Haley and El Helou, Majed and S\"usstrunk, Sabine},
    journal = {IS&T Electronic Imaging Proceedings, Computational Imaging XX},
    year    = {2022}
}
Owner
Images and Visual Representation Laboratory (IVRL) at EPFL
Code associated with our published research
Images and Visual Representation Laboratory (IVRL) at EPFL
An AutoML Library made with Optuna and PyTorch Lightning

An AutoML Library made with Optuna and PyTorch Lightning Installation Recommended pip install -U gradsflow From source pip install git+https://github.

GradsFlow 294 Dec 17, 2022
Official repository for Hierarchical Opacity Propagation for Image Matting

HOP-Matting Official repository for Hierarchical Opacity Propagation for Image Matting 🚧 🚧 🚧 Under Construction 🚧 🚧 🚧 🚧 🚧 🚧   Coming Soon   

Li Yaoyi 54 Dec 30, 2021
[MICCAI'20] AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes

AlignShift NEW: Code for our new MICCAI'21 paper "Asymmetric 3D Context Fusion for Universal Lesion Detection" will also be pushed to this repository

Medical 3D Vision 42 Jan 06, 2023
Template repository for managing machine learning research projects built with PyTorch-Lightning

Tutorial Repository with a minimal example for showing how to deploy training across various compute infrastructure.

Sidd Karamcheti 3 Feb 11, 2022
Agile SVG maker for python

Agile SVG Maker Need to draw hundreds of frames for a GIF? Need to change the style of all pictures in a PPT? Need to draw similar images with differe

SemiWaker 4 Sep 25, 2022
Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set

Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set This is the repository for the Deep Learning proje

Robert Krug 3 Feb 06, 2022
Job Assignment System by Real-time Emotion Detection

Emotion-Detection Job Assignment System by Real-time Emotion Detection Emotion is the essential role of facial expression and it could provide a lot o

1 Feb 08, 2022
Parallel and High-Fidelity Text-to-Lip Generation; AAAI 2022 ; Official code

Parallel and High-Fidelity Text-to-Lip Generation This repository is the official PyTorch implementation of our AAAI-2022 paper, in which we propose P

Zhying 77 Dec 21, 2022
Pca-on-genotypes - Mini bioinformatics project - PCA on genotypes

Mini bioinformatics project: PCA on genotypes This repo contains the code from t

Maria Nattestad 8 Dec 04, 2022
Boston House Prediction Valuation Tool

Boston-House-Prediction-Valuation-Tool From Below Anlaysis The Valuation Tool is Designed Correlation Matrix Regrssion Analysis Between Target Vs Pred

0 Sep 09, 2022
Semantic segmentation models, datasets and losses implemented in PyTorch.

Semantic Segmentation in PyTorch Semantic Segmentation in PyTorch Requirements Main Features Models Datasets Losses Learning rate schedulers Data augm

Yassine 1.3k Jan 07, 2023
One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking This is an official implementation for NEAS presented in CVPR

Multimedia Research 19 Sep 08, 2022
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation By Yi Li, Zhanghui Kuang, Liyang Liu, Yimin Chen, Wayne Zhang SenseTime, Tsinghua Unive

33 Oct 14, 2022
VIsually-Pivoted Audio and(N) Text

VIP-ANT: VIsually-Pivoted Audio and(N) Text Code for the paper Connecting the Dots between Audio and Text without Parallel Data through Visual Knowled

Yän.PnG 16 Nov 04, 2022
Contour-guided image completion with perceptual grouping (BMVC 2021 publication)

Contour-guided Image Completion with Perceptual Grouping Authors Morteza Rezanejad*, Sidharth Gupta*, Chandra Gummaluru, Ryan Marten, John Wilder, Mic

Sid Gupta 6 Dec 27, 2022
public repo for ESTER dataset and modeling (EMNLP'21)

Project / Paper Introduction This is the project repo for our EMNLP'21 paper: https://arxiv.org/abs/2104.08350 Here, we provide brief descriptions of

PlusLab 19 Oct 27, 2022
TyXe: Pyro-based BNNs for Pytorch users

TyXe: Pyro-based BNNs for Pytorch users TyXe aims to simplify the process of turning Pytorch neural networks into Bayesian neural networks by leveragi

87 Jan 03, 2023
⚾🤖⚾ Automatic baseball pitching overlay in realtime

⚾ Automatically overlaying pitch motion and trajectory with machine learning! This project takes your baseball pitching clips and automatically genera

Tony Chou 240 Dec 05, 2022
Wikidated : An Evolving Knowledge Graph Dataset of Wikidata’s Revision History

Wikidated Wikidated 1.0 is a dataset of Wikidata’s full revision history, which encodes changes between Wikidata revisions as sets of deletions and ad

Lukas Schmelzeisen 11 Aug 16, 2022
Source code for the ACL-IJCNLP 2021 paper entitled "T-DNA: Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation" by Shizhe Diao et al.

T-DNA Source code for the ACL-IJCNLP 2021 paper entitled Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adapta

shizhediao 17 Dec 22, 2022