3D reconstruction algorithms and bundle adjustment methods. Rolling shutter video rectification. Extraction of image features that make use of projective geometry.
- 3D Model Based Video Coding
- This project studied how representations of 3D structure and camera motion can be used to improve video coding efficiency.
- Fast Three-view Triangulation
- NEW algorithm for three-view triangulation.
- Torchlight Navigation
- A common computer vision task is navigation and mapping. Many indoor navigation tasks require depth knowledge of flat, unstructured surfaces (walls, floor, ceiling). With passive illumination only, this is an ill-posed problem. Inspired by small children using a torchlight, we use a spotlight for active illumination. Using our torchlight approach, depth and orientation estimation of unstructured, flat surfaces boils down to estimation of ellipse parameters. The extraction of ellipses is very robust and requires little computational effort.
- Learnable Camera Motion Models
- A project that studies how to model and learn 3D camera trajectories.
- Virtual Global Shutters for CMOS Cameras
- A project that studies the use of projective geometry for rolling shutter and push-broom sensors.
- MATRIS project
- A project on Markerless real-time Tracking for Augmented Reality Image Synthesis.
Last updated: 2019-04-23