Sciweavers

17 search results - page 3 / 4
» Do Ambiguous Reconstructions Always Give Ambiguous Images
Sort
View
PAMI
2006
358views more  PAMI 2006»
13 years 5 months ago
Recovering 3D Human Pose from Monocular Images
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
Ankur Agarwal, Bill Triggs
PAMI
2007
336views more  PAMI 2007»
13 years 4 months ago
Topological Equivalence between a 3D Object and the Reconstruction of Its Digital Image
— Digitization is not as easy as it looks. If one digitizes a 3D object even with a dense sampling grid, the reconstructed digital object may have topological distortions and in ...
Peer Stelldinger, Longin Jan Latecki, Marcelo Siqu...
CVPR
2007
IEEE
14 years 7 months ago
Integration of Motion Cues in Optical and Sonar Videos for 3-D Positioning
Target-based positioning and 3-D target reconstruction are critical capabilities in deploying submersible platforms for a range of underwater applications, e.g., search and inspec...
Shahriar Negahdaripour, Hamed Pirsiavash, Hicham S...
AMR
2006
Springer
119views Multimedia» more  AMR 2006»
13 years 7 months ago
The Potential of User Feedback Through the Iterative Refining of Queries in an Image Retrieval System
Inaccurate or ambiguous expressions in queries lead to poor results in information retrieval. We assume that iterative user feedback can improve the quality of queries. To this end...
Maher Ben Moussa, Marco Pasch, Djoerd Hiemstra, Pa...
CVPR
2005
IEEE
14 years 7 months ago
Interactive Shape from Shading
Shape from shading (SfS) has always been difficult for real applications due to its intrinsic ill-posedness. In this paper, we propose an interactive SfS method which efficiently ...
Gang Zeng, Yasuyuki Matsushita, Long Quan, Heung-Y...