Software

We take open-source seriously, which is why you will find code for our newest papers on our Github account
TDV. Total Deep Variation Regularizer Code
Paper
Paper
bp-layers. Code for the Paper 'Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems' Code
Paper

optox. OPerator TO any deep learning framework

Code
PGMO Lecture of Thomas Pock on Vision, Optimization and Learning. Contains Jupyter Notebooks with code for several imaging problems Code
Tensorflow ICG. The repository contains newly developed features such as custom operators, functions and classes Code
Primal-Dual Toolbox. C++/Cuda implementation of various TV and second-order TGV problems Code
Paper
Tensorflow code for our paper Learning a Variational Network for Reconstruction of Accelerated MRI Data

Code
Data
Paper

Tensorflow code for our paper Variational Networks: Connecting Variational Methods and Deep Learning and Chen Yunjin's work On learning optimized reaction diffusion processes for effective image restoration

Code
Paper

Code for our paper End-to-End Training of Hybrid CNN-CRF Models for Stereo Code
Image Utilities. The basis for most of our high-performance CUDA implementations Code
Code for our paper Real-Time Panoramic Tracking for Event Cameras Code
Code for the automatic calibration of event cameras using MATLAB Code
Code for our paper Real-Time Intensity Image Reconstruction for Event Cameras using Manifold Regularisation Code
Paper
Code for our paper Joint Demosaicing and Denoising Based on Sequential Energy Minimization Code
Paper
Code for our paper Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo

Code
Paper