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 Structure-from-Motion, 3D Reconstruction, Realtime Camera Tracking, Video Segmentation/Matting and Video Enhancement/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
  • Video Segmentation/Matting
    • 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.
  • Video Enhancement/Editing
    • Refilming: 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.
    • Stereoscopic Video Synthesis: a novel approach for synthesizing stereoscopic videos from monocular videos.
    • Video Stabilization: a novel approach to stabilize video sequences based on a 3D perspective camera model.

Developed Software

ACTS is an automatic camera tracking system which can recover camera motion and 3D scene structure from videos and film sequences, providing the ease of automatic tracking. It can track all kinds of the camera motion efficiently and stably, which can be rotational or free-moving. It is a cornerstone for many other computer vision tasks. [software]