bm3d

pure Python implementation of BM3D

This is a companion software for the submission: "Higher-Order Total Directional Variation: Imaging Applications" by Simone Parisotto , Jan Lellmann, Simon Masnou, and Carola-Bibiane Schönlieb. SIAM J. Imaging Sci., 13(4), 2063–2104. (42 pages)

3D image denoising using a modified U-Net architecture that exploits a prior image. Models are trained using efficient tensorflow pipeline based on keras and tf.data.Dataset API

This is the companion software for the paper "Total Directional Variation for video denoising".

Rust-based bm3d algorithm for ring artifact removal in normalized sinogram with Python Bindings

Advanced image processing nodes for ComfyUI with DeepInv, BM3D, wavelet denoising, and more

BM3D & False Color Implemention

Video Denoising using Low Rank Matrix completion

Electron density maps denoising algorithms implementation

A deep learning model that finds out dental malpractice from tooth x-ray images.

Academic Project - This project afforded us a valuable opportunity to delve into the practical aspects of the Signal Processing field, with a specific emphasis on Image Processing. It involved a comparison between BM3D and Convolutional Autoencoders.

A Python-based image processing pipeline for enhancing amateur astrophotography. It improves deep-sky images by combining BM3D denoising, histogram stretching, and unsharp masking.

Physics-informed 3D reconstruction from low-dose 2D images.

Master's Thesis: Denoising Methods for Multi-Dimensional Photoemission Spectroscopy

Contains BM3D and NLM projects for CPU and GPU

Implementation and evaluation of classical and deep learning-based image denoising methods. The project compares Non-Local Means (NLM), BM3D, U-Net, and Denoising Autoencoders under different noise models (Gaussian, Salt & Pepper), using PSNR as the primary performance metric.

bm3d_core from https://github.com/ornlneutronimaging/bm3dornl — This is used as an operation in my wondermagick fork