Previous | 
Home
Section: New Software and Platforms
FastPD
Keyword: Medical imaging
Functional Description: FastPD is an optimization platform in C++ for the computer vision and medical imaging community.
Overall Objectives
Research Program
Application Domains
New Results
- Graph Based Slice-to-Volume Deformable Registration
- Deformable Registration Through Learning of Context-Specific Metric Aggregation
- Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology
- Multi-atlas segmentation in medical imagery
- Protein function prediction
- Deformable group-wise registration using a physiological model: Application to diffusion-weighted MRI
- Variational Bayesian Approach for Image Restoration
- Non-Modular Loss Functions
- Graph Structure Discovery
- Structured and Efficient Convolutional Networks
- Stochastic Majorize-Minimize Subspace Algorithm
- Deconvolution and Deinterlacing of Video Sequences
- PALMA, an improved algorithm for DOSY signal processing
- Proximal Approaches for Solving Matrix Optimization Problems
- Fast Algorithm for Least-Squares Regression with GMRF Prior
- Optimization Approach for Deep Neural Network Training
- Auxiliary Variable Method for MCMC Algorithms in High Dimension
- Block Coordinate Approach for Sparse Logistic Regression
- An Alternating Proximal Approach for Blind Video Deconvolution
- BRANE Clust: Cluster-Assisted Gene Regulatory Network Inference Refinement
- Proximity Operators of Discrete Information Divergences
- Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations With Random Sweeping: Mean-Square and Linear Convergence
- Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision
- Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
- Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
- DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
- Structured Output Prediction and Learning for Deep Monocular 3D Human Pose Estimation
- Newton-type Methods for Inference in Higher-Order Markov Random Fields
- Alternating Direction Graph Matching
- Prediction and classification in biological and information networks
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Bibliography
Overall Objectives
Research Program
Application Domains
New Results
- Graph Based Slice-to-Volume Deformable Registration
- Deformable Registration Through Learning of Context-Specific Metric Aggregation
- Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology
- Multi-atlas segmentation in medical imagery
- Protein function prediction
- Deformable group-wise registration using a physiological model: Application to diffusion-weighted MRI
- Variational Bayesian Approach for Image Restoration
- Non-Modular Loss Functions
- Graph Structure Discovery
- Structured and Efficient Convolutional Networks
- Stochastic Majorize-Minimize Subspace Algorithm
- Deconvolution and Deinterlacing of Video Sequences
- PALMA, an improved algorithm for DOSY signal processing
- Proximal Approaches for Solving Matrix Optimization Problems
- Fast Algorithm for Least-Squares Regression with GMRF Prior
- Optimization Approach for Deep Neural Network Training
- Auxiliary Variable Method for MCMC Algorithms in High Dimension
- Block Coordinate Approach for Sparse Logistic Regression
- An Alternating Proximal Approach for Blind Video Deconvolution
- BRANE Clust: Cluster-Assisted Gene Regulatory Network Inference Refinement
- Proximity Operators of Discrete Information Divergences
- Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations With Random Sweeping: Mean-Square and Linear Convergence
- Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision
- Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
- Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
- DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
- Structured Output Prediction and Learning for Deep Monocular 3D Human Pose Estimation
- Newton-type Methods for Inference in Higher-Order Markov Random Fields
- Alternating Direction Graph Matching
- Prediction and classification in biological and information networks
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Bibliography