Software

Alternating Direction Graph Matching. An implementation of the methods introduced in the paper Alternating Direction Graph Matching, CVPR 2017.
For more information, please visit this link.

An implementation of the algorithm described in the paper Fully Convolutional Dense Shape Regression In-the-Wild, CVPR 2017.
For more information, please visit this link.

A software programme that registers images originating from one or more modes by quickly and efficiently calculating a non-rigid/deformable field of deformation. DROP is a new, quick, and effective registration tool based on new algorithms that do not require a cost function derivative.
For more information, please visit this link.

A generic graph-based optimization platform written in C++ for the computer vision and medical imaging community (available here) developed at Ecole Centrale and University of Crete. This is the most efficient available platform in terms of a compromise of computational efficiency and ability to converge to a good minimum for the optimization of generic pair-wise MRFs.

Learning Based Symmetry Detection. LBSD implements the learning-based approach to symmetry detection. It includes code for running a detector, along with ground-truth symmetry annotations that we have introduced for the Berkeley Segmentation Dataset (BSD) benchmark.
For more information, please visit this link.

Deep Gaussian CRFs. An implementation of the Potts type G-CRF caffe layer introduced in the paper Fast, Exact and Multi-Scale Inference For Semantic Image Segmentation with Deep Gaussian CRFs, ECCV 2016.
For more information, please visit this link.

A generic image parsing library based on re-inforcement learning written in C++ (available here) developed at Ecole Centrale de Paris. It can handle grammars (binary-split, four-color, Hausmannian) and image-based rewards (Gaussian mixtures, Randomized Forests) of varying complexity while being modular and computationally efficient both in terms of grammar and image rewards.

This software provides a convenient API for learning to rank with high-order information. Samples are ranked according to a score that is proportional to the difference of max-marginals of the positive and negative classes. The parameters of the score function are computed by minimising an upper bound on the average precision loss. This software also provides an instantiation of the API for ranking samples according to their relevance to an action, using poselet features. The algorithms included in the API are Multiclass-SVM, AP-SVM, High-order Binary SVM, High-order AP-SVM, and M4 Learning.
For more information, please visit this link.