Sciweavers

10 search results - page 2 / 2
» Inferring Segmented Dense Motion Layers Using 5D Tensor Voti...
Sort
View
PAMI
2006
110views more  PAMI 2006»
13 years 5 months ago
Video Repairing under Variable Illumination Using Cyclic Motions
This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video. These missing pix...
Jiaya Jia, Yu-Wing Tai, Tai-Pang Wu, Chi-Keung Tan...
ICPR
2006
IEEE
14 years 6 months ago
Multi-layer Mosaics in the Presence of Motion and Depth Effects
In this paper, we present a new segmentation-based 2D mosaic framework. Most of current mosaic algorithms do not explicitly remove moving objects from images before registration, ...
Changki Min, Gérard G. Medioni, Qian Yu
CVPR
2006
IEEE
13 years 11 months ago
Perceptually-Inspired and Edge-Directed Color Image Super-Resolution
Inspired by multi-scale tensor voting, a computational framework for perceptual grouping and segmentation, we propose an edge-directed technique for color image superresolution gi...
Yu-Wing Tai, Wai-Shun Tong, Chi-Keung Tang
SCVMA
2004
Springer
13 years 10 months ago
A Generative Model of Dense Optical Flow in Layers
We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, varia...
Anitha Kannan, Brendan J. Frey, Nebojsa Jojic
AMFG
2007
IEEE
327views Biometrics» more  AMFG 2007»
13 years 11 months ago
Model-Assisted 3D Face Reconstruction from Video
Abstract. This paper describes a model-assisted system for reconstruction of 3D faces from a single consumer quality camera using a structure from motion approach. Typical multi-vi...
Douglas Fidaleo, Gérard G. Medioni