Solid shape
Stereo Correspondence by Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computation of component image velocity from local phase information
International Journal of Computer Vision
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Robust computation of optical flow in a multi-scale differential framework
International Journal of Computer Vision
Direct computation of shape cues using scale-adapted spatial derivative operators
International Journal of Computer Vision - Special issue: machine vision research at the Royal Institute of Technology
Binocular dense depth reconstruction using isotropy constraint
Selected papers from the 9th Scandinavian conference on Image analysis : theory and applications of image analysis II: theory and applications of image analysis II
A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Occlusions and Binocular Stereo
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Computation of coherent optical flow by using multiple constraints
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Dynamic Scale–Space Paradigm
Journal of Mathematical Imaging and Vision
Computing Optic Flow by Scale-Space Integration of Normal Flow
Scale-Space '01 Proceedings of the Third International Conference on Scale-Space and Morphology in Computer Vision
SCALE-SPACE '99 Proceedings of the Second International Conference on Scale-Space Theories in Computer Vision
Hi-index | 0.00 |
Grey-scale images consist of physical measurements of light.Scale-space theories have been developed to unconfound thesemeasurements from the detector grid. In this framework, we look intothe problem of binocular stereo. On a sufficiently large scale, apixel carries information not only of the grey-value, but of theentire grey-value n-jet, i.e., derivatives up to order n. Thesubject of this paper is to show, in a general context, how thescale-space n-jet can be exploited for binocular matching. Theanalysis leads (under appropriate assumptions) to a directdetermination of the local n-jet of the disparity field. The generalresult is an analysis which could be incorporated into many existingstereo algorithms to improve their use of the grey value data. In thecomputational scheme presented here, the estimations are strictlylocal, but based on image derivatives at a scale where the imagestructure is significant. This scale is automatically selected byminimising computational uncertainty. Results are shown as directcomputations of surface normals on synthetic and real images.