A Technique for Finding the Symmetry Axes of Implicit Polynomial Curves under Perspective Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Symmetry-based 3-D reconstruction from perspective images
Computer Vision and Image Understanding
Symmetric architecture modeling with a single image
ACM SIGGRAPH Asia 2009 papers
Symmetry-based 3-D reconstruction from perspective images
Computer Vision and Image Understanding
Pattern Recognition
Geometrical scene analysis using co-motion statistics
ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
3D modeling with a symmetric sketch
Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling
Dense 3D reconstruction of symmetric scenes from a single image
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Self-calibration and motion recovery from silhouettes with two mirrors
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
| Hi-index | 0.00 |
We address the problem of 3-D reconstruction from a single perspective view of a mirror symmetric scene. We establish the fundamental result that it is geometrically equivalent to observing the scene with two cameras, the cameras being symmetrical with respect to the unknown 3-D symmetry plane. All traditional tools of classical 2-view stereo can then be applied, and the concepts of fundamental/essential matrix, epipolar geometry, rectification anddisparity hold. However, the problems are greatly simplified here, as the rectification process and the computation of epipolar geometry can be easily performed from the original view only. If the camera is calibrated, we show how to synthesize the symmetric image generated by thesame physical camera. An Euclidean reconstruction of the scene can then be computed from the resulting stereo pair. To validate this novel formulation, we have processed many real images, and show examples of 3-D reconstruction.