IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape and motion from image streams under orthography: a factorization method
International Journal of Computer Vision
Geometric invariance in computer vision
Geometric invariance in computer vision
Geometry and photometry in three-dimensional visual recognition
Geometry and photometry in three-dimensional visual recognition
Geometric computation for machine vision
Geometric computation for machine vision
Object-centered surface reconstruction: combining multi-image stereo and shading
International Journal of Computer Vision
Multibody Grouping from Motion Images
International Journal of Computer Vision
What Is the Set of Images of an Object Under All Possible Illumination Conditions?
International Journal of Computer Vision
A Multibody Factorization Method for Independently Moving Objects
International Journal of Computer Vision
Robot Vision
3D Model Acquisition from Extended Image Sequences
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
Hyper-patches for 3D model acquisition and tracking
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Geotensity: Combining Motion and Lighting for 3D Surface Reconstruction
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Evaluation and Selection of Models for Motion Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Constructing Illumination Image Basis from Object Motion
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Hi-index | 0.00 |
We tackle the problem of 3D surface reconstruction by a single static camera, extracting the maximum amount of information from gray level changes caused by object motion under illumination by a fixed set of light sources. We basically search for the depth at each point on the surface of the object while exploiting the recently proposed Geotensity constraint [11] that accurately governs the relationship between four or more images of a moving object in spite of the illumination variance due to object motion. The thrust of this paper is then to extend the availability of the Geotensity constraint to the case of multiple point light sources instead of a single light source. We first show that it is mathematically possible to identify multiple illumination subspaces for an arbitrary unknown number of light sources. We then propose a new technique to effectively carry out the separation of the subspaces by introducing the surface interaction matrix. Finally, we construct a framework for surface recovery, taking the multiple illumination subspaces into account. The theoretical propositions are investigated through experiments and shown to be practically useful.