Sciweavers

3208 search results - page 205 / 642
» Methods and views
Sort
View
CVPR
2000
IEEE
16 years 6 months ago
Towards Automatic Discovery of Object Categories
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
Markus Weber, Max Welling, Pietro Perona
124
Voted
ICIP
2009
IEEE
16 years 5 months ago
Efficient Edge, Motion And Depth-range Adaptive Processing For Enhancement Of Multi-view Depth Map Sequences
We present a novel and efficient multi-view depth map enhancement method proposed as a post-processing of initially estimated depth maps. The proposed method is based on edge, mot...
109
Voted
ICRA
2008
IEEE
130views Robotics» more  ICRA 2008»
15 years 10 months ago
An easy calibration for oblique-viewing endoscopes
— Oblique-viewing endoscopes (oblique scopes) are widely used in minimally invasive surgery. The viewing direction of an oblique endoscope can be changed by rotating the scope cy...
Chenyu Wu, Branislav Jaramaz
SMI
2007
IEEE
136views Image Analysis» more  SMI 2007»
15 years 10 months ago
Realistic Hair from a Sketch
This paper explores a sketch-based interface for quickly yet accurately creating visually realistic hair for virtual characters. Recently, physically-based models have proved succ...
Jamie Wither, Florence Bertails, Marie-Paule Cani
ESOP
2007
Springer
15 years 10 months ago
On the Relationship Between Concurrent Separation Logic and Assume-Guarantee Reasoning
We study the relationship between Concurrent Separation Logic (CSL) and the assume-guarantee (A-G) method (a.k.a. rely-guarantee method). We show in three steps that CSL can be tre...
Xinyu Feng, Rodrigo Ferreira, Zhong Shao