DIVA (Deep denoising by quantum InteractiVe pAtches)

This paper presents a deep neural network called DIVA unfolding a baseline adaptive denoising algorithm (DeQuIP) [see the DeQuIP_flow.pdf for a basic working principle], relying on the theory of quantum many-body physics.

Sample code of the papers:

Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration," Submitted, 2022.
Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "Deep Unfolding of Image Denoising by Quantum Interactive Patches," 2022 IEEE International Conference on Image Processing (ICIP), 2022.

Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "A Novel Image Denoising Algorithm Using Concepts of Quantum Many-Body Theory," Signal Processing, vol. 201, pp. 108690, 2022, doi: 10.1016/j.sigpro.2022.108690
Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "Image Denoising Inspired by Quantum Many-Body physics," 2021 IEEE International Conference on Image Processing (ICIP), 2021, pp. 1619-1623, doi: 10.1109/ICIP42928.2021.9506794.
Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "Quantum mechanics-based signal and image representation: Application to denoising," IEEE Open Journal of Signal Processing, vol. 2, pp. 190–206, 2021.
Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, and Denis Kouamé, "Despeckling Ultrasound Images Using Quantum Many-Body Physics," 2021 IEEE International Ultrasonics Symposium (IUS), 2021, pp. 1-4, doi: 10.1109/IUS52206.2021.9593778.

Python code prepard by Sayantan Dutta E-mail: sdu4004@med.cornell.edu and sayantan.dutta110@gmail.com

The following script shows an example of our image restoration algorithm Deep denoising by quantum InteractiVe pAtches (DIVA)