Sciweavers

CVPR
2008
IEEE
14 years 3 months ago
Evaluation of color descriptors for object and scene recognition
Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used. To increas...
Koen E. A. van de Sande, Theo Gevers, Cees G. M. S...
CVPR
2008
IEEE
14 years 3 months ago
Stereoscopic inpainting: Joint color and depth completion from stereo images
We present a novel algorithm for simultaneous color and depth inpainting. The algorithm takes stereo images and estimated disparity maps as input and fills in missing color and d...
Liang Wang, Hailin Jin, Ruigang Yang, Minglun Gong
CVPR
2008
IEEE
14 years 3 months ago
High resolution matting via interactive trimap segmentation
We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain co...
Christoph Rhemann, Carsten Rother, Alex Rav-Acha, ...
CVPR
2008
IEEE
14 years 3 months ago
Global stereo reconstruction under second order smoothness priors
Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithm...
Oliver J. Woodford, Philip H. S. Torr, Ian D. Reid...
CVPR
2008
IEEE
14 years 3 months ago
Bayesian tactile face
Computer users with visual impairment cannot access the rich graphical contents in print or digital media unless relying on visual-to-tactile conversion, which is done primarily b...
Zheshen Wang, Xinyu Xu, Baoxin Li
CVPR
2008
IEEE
14 years 3 months ago
A theoretical analysis of linear and multi-linear models of image appearance
Linear and multi-linear models of object shape/appearance (PCA, 3DMM, AAM/ASM, multilinear tensors) have been very popular in computer vision. In this paper, we analyze the validi...
Yilei Xu, Amit K. Roy Chowdhury
CVPR
2008
IEEE
14 years 3 months ago
Photogeometric structured light: A self-calibrating and multi-viewpoint framework for accurate 3D modeling
Structured-light methods actively generate geometric correspondence data between projectors and cameras in order to facilitate robust 3D reconstruction. In this paper, we present ...
Daniel G. Aliaga, Yi Xu
SIGGRAPH
2009
ACM
14 years 3 months ago
Multi-touch everywhere!
In this paper, we describe a set of hardware and software tools for creating musical controllers with any flat surface or simple object, such as tables, walls, metallic plates, wo...
Alain Crevoisier, Greg Kellum
SCALESPACE
2009
Springer
14 years 3 months ago
Momentum Based Optimization Methods for Level Set Segmentation
Abstract. Segmentation of images is often posed as a variational problem. As such, it is solved by formulating an energy functional depending on a contour and other image derived t...
Gunnar Läthén, Thord Andersson, Reiner...