Introduction
CVG (Computer Vision Group) is a young group of State Key Lab of CAD&CG, Zhejiang University. The main research interests of CVG focus on offline/realtime Structure-from-Motion, 3D Reconstruction, Video Segmentation/Matting and Editing.
- Structure-from-Motion
- Automatic Camera Tracking : we address two key issues in structure-from-motion. First, we propose a robust SFM method for efficiently and reliably handle long sequences with varying focal length (our CVPR07 paper ). Second, we propose an efficient non-consecutive feature tracking method to address the reconstruction drift problem for loop-back sequences. Based on the above two works, we have developed a robust and efficient camera tracking system ACTS.
- Keyframe-based Realtime Camera Tracking: a robust markerless real-time camera tracking system based on a novel keyframe selection and recognition method.
- 3D Reconstruction
- Depth Video Recovery: a novel method for recovering consistent depth maps from a video sequence. Based on this work, we have developed several applications, such as refilming, moving object extraction, and spatio-temporal segmentation.
- 3D Reconstruction of Dynamic Scenes: focus on recovering high-quality depth maps for dynamic scenes from very few synchronized cameras (i.e. 2~3 cameras). In CVPR 2012, we propose a novel dense depth recovery method for a trinocular video sequence. In ECCV 2012, we propose a more general method which only uses 2~3 handheld freely moving cameras. Compared to traditional methods, this data capturing setup is much more flexible and easier to use.
- Video Segmentation/Matting & Editing
- Moving Object Extraction: a new method for high-quality extracting the moving object from a video sequence taken by a handheld camera.
- Fast Bilayer Segmentation: a novel fast bilayer segmentation method which can effectively extract the dynamic foreground under rotational camera configuration.
- Spatio-Temporal Segmentation: a novel spatio-temporal segmentation method for depth-inferred videos.
- Refiliming: a new content-based video editing system for creating various kinds of visual effects, which includes but not limited to video composition, ``predator'' effect, bullet-time, depth-of-field, and fog synthesis.
