Home |
3D Reconstruction We live in a three-dimensional dynamic world and possess stereo vision thanks to the pair of our eyes. Inspired by this natural endowment, a fundamental problem of computer vision is to obtain 3D geometric information of the scene from captured planar images. This process is traditionally termed 3D reconstruction.3D reconstruction is useful because the resultant 3D models have wide application in virtual reality, computer aided design and engineering etc. It may also facilitate high-accuracy object recognition since the 3D data eliminates the headache-causing variance due to perspective projection in the imaging process and changing illumination. |
|||||
| Relative Epipolar Motion of Tracked Features for Correspondence in Binocular Stereo. Hao Du, Danping Zou, Yan Qiu Chen. International Conference on Computer Vision, 2007. | ||||||
| Abstract. Most 3D reconstruction solutions focus on surfaces, and there has not been much research attention paid to the problem of reconstructing 3D scenes made up of large numbers of particles, while the ability to reconstruct such dynamic scenes is potentially very useful in many areas such as colony behavior research and visual modeling. This paper proposes an approach - Relative Epipolar Motion (REM) - towards solving the correspondence problem in stereopsis by utilizing the motion clue. It matches feature trajectories instead of the features themselves as used by existing methods. The proposed method has the following new capabilities: (1) It supports reconstructing dynamic 3D scenes of large number of undistinguishable drifting particles; (2) It is applicable to correspondence extablishment for dynamic surfaces made up of repetitive textures; (3) It offers an alternative way to project structured light in active mode for deforming surface reconstruction. Experiment results on both simulated and real-world scenes demonstrate its effectiveness. |
|
|||||
|
|
||||||