Sparse Optimisation Research Code
-
Updated
Apr 29, 2024 - Python
Sparse Optimisation Research Code
Scientific Computational Imaging COde
Python routines to compute the Total Variation (TV) of 2D, 3D and 4D images on CPU & GPU. Compatible with proximal algorithms (ADMM, Chambolle & Pock, ...)
Inpainting via convex optimization.
Cut-pursuit with preconditioned forward-Douglas-Rachford for regularization of classical functionals by graph total variation
Algorithms for total variation denoising
A Bayesian framework for Multi-Frame Image Super-Resolution. Based on "Bayesian Image Super-Resolution" (ME Tipping and CM Bishop, NeurIPS 2003)
[TVCG 2021] Mesh Total Generalized Variation for Denoising
UTV:A novel dark channel prior guided variational framework for underwater image restoration
Carpet: Neural Net based solver for the 1d-TV problem
Code for Adaptation Network introduced in "Block-wise Scrambled Image Recognition Using Adaptation Network" paper (AAAI WS 2020)
Primal-Dual Solver for Inverse Problems
External Module for Total Variation Algorithms, providing wrap for https://github.com/albarji/proxTV
Solving hyperbolic PDEs using the Lax-Wendroff Scheme and a finite volume method.
Deformable Groupwise Image Registration using Low-Rank and Sparse Decomposition
An Image Reconstructor that applies fast proximal gradient method (FISTA) to the wavelet transform of an image using L1 and Total Variation (TV) regularizations
Imaging Inverse Problems and Bayesian Computation - Python tutorials to learn about (accelerated) sampling for uncertainty quantification and other advanced inferences
Denoising based on TV used ADMM or Proximal Project or Primal Dual metohd.
Tomographic image reconstruction package in Julia
Code for creating maximal activation images (like Deep Dream) in pytorch with various regularizations / losses.
Add a description, image, and links to the total-variation topic page so that developers can more easily learn about it.
To associate your repository with the total-variation topic, visit your repo's landing page and select "manage topics."