Library for continuous convex optimization in image processing, together with a command line tool.
Implements several recent algorithms for inverse problems and image segmentation with (vectorial) total variation regularizers and (vectorial) labeling schemes with a number of penalizers.
Also included is a suite for variational light field analysis, which ties into the HCI light field data base and benchmark set and givens reference implementations for a number of our recently published algorithms.
- CUDA Implementations of recent algorithms for variational image analysis
- Library and example: command line tool for image processing
- Vectorial total variation: inverse problems, inpainting, optical flow
- Total variation: inverse problems, inpainting and segmentation
- Total Curvature: inverse problems, inpainting and segmentation
- Multilabel problems: lifting method for linear interactions and simplex relaxation for Potts
- Upcoming: more multilabel regularizers, light field analysis methods
Thank you for the nice work