Mirror Surface Reconstruction from a Single Image

This paper tackles the problem of reconstructing the shape of a smooth mirror surface from a single image. In particular, we consider the case where the camera is observing the reflection of a static reference target in the unknown mirror. We first study the reconstruction problem given dense correspondences between 3D points on the reference target and image locations. In such conditions, our differential geometry analysis provides a theoretical proof that the shape of the mirror surface can be uniquely recovered if the pose of the reference target is known. We then relax our assumptions by considering the case where only sparse correspondences are available. In this scenario, we formulate reconstruction as an optimization problem, which can be solved using a nonlinear least-squares method. We demonstrate the effectiveness of our method on both synthetic and real images.

[1]  Brian A. Barsky,et al.  Reconstructing curved surfaces from specular reflection patterns using spline surface fitting of normals , 1996, SIGGRAPH.

[2]  Ohad Ben-Shahar,et al.  Toward a Theory of Shape from Specular Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[3]  Jürgen Beyerer,et al.  Multiview specular stereo reconstruction of large mirror surfaces , 2011, CVPR 2011.

[4]  Aswin C. Sankaranarayanan,et al.  Specular surface reconstruction from sparse reflection correspondences , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Peter F. Sturm,et al.  Voxel carving for specular surfaces , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  A. Torralba,et al.  Specular reflections and the perception of shape. , 2004, Journal of vision.

[7]  Michael J. Black,et al.  Specular Flow and the Recovery of Surface Structure , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Tim Weyrich,et al.  Dense 3D reconstruction from specularity consistency , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Michael Lindenbaum,et al.  Dense Mirroring Surface Recovery from 1D Homographies and Sparse Correspondences , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[11]  Shree K. Nayar,et al.  Single viewpoint catadioptric cameras , 2001 .

[12]  Hans-Peter Seidel,et al.  3D acquisition of mirroring objects using striped patterns , 2005, Graph. Model..

[13]  Visesh Chari,et al.  A Theory of Refractive Photo-Light-Path Triangulation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Shree K. Nayar,et al.  Non-Single Viewpoint Catadioptric Cameras: Geometry and Analysis , 2006, International Journal of Computer Vision.

[15]  Min Chen,et al.  Local Shape from Mirror Reflections , 2005, International Journal of Computer Vision.

[16]  Ohad Ben-Shahar,et al.  Shape from specular flow: Is one flow enough? , 2011, CVPR 2011.

[17]  E. Süli,et al.  An introduction to numerical analysis , 2003 .

[18]  Pau Gargallo,et al.  General Specular Surface Triangulation , 2006, ACCV.

[19]  Peter F. Sturm,et al.  How to Compute the Pose of an Object Without a Direct View? , 2006, ACCV.

[20]  Shree K. Nayar,et al.  A Theory of Specular Surface Geometry , 2004, International Journal of Computer Vision.

[21]  Kiriakos N. Kutulakos,et al.  A Theory of Refractive and Specular 3D Shape by Light-Path Triangulation , 2005, ICCV.

[22]  Andrew Blake,et al.  The information available to a moving observer from specularities , 1989, Image and Vision Computing.

[23]  Zhenwen Dai,et al.  Pose estimation from reflections for specular surface recovery , 2011, 2011 International Conference on Computer Vision.

[24]  Ohad Ben-Shahar,et al.  A linear formulation of shape from specular flow , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[25]  Arnold Neumaier,et al.  Introduction to Numerical Analysis , 2001 .