Sciweavers

43 search results - page 5 / 9
» Normal and Feature Approximations from Noisy Point Clouds
Sort
View
ICCV
1999
IEEE
13 years 12 months ago
Robust Estimation of Curvature Information from Noisy 3D Data for Shape Description
We describe an effective and novel approach to infer sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local su...
Chi-Keung Tang, Gérard G. Medioni
ICRA
2009
IEEE
248views Robotics» more  ICRA 2009»
14 years 2 months ago
Comparison of surface normal estimation methods for range sensing applications
— As mobile robotics is gradually moving towards a level of semantic environment understanding, robust 3D object recognition plays an increasingly important role. One of the most...
Klaas Klasing, Daniel Althoff, Dirk Wollherr, Mart...
VIS
2004
IEEE
214views Visualization» more  VIS 2004»
14 years 8 months ago
Surface Reconstruction of Noisy and Defective Data Sets
We present a novel surface reconstruction algorithm that can recover high-quality surfaces from noisy and defective data sets without any normal or orientation information. A set ...
Hui Xie, Kevin T. McDonnell, Hong Qin
NIPS
1998
13 years 9 months ago
Divisive Normalization, Line Attractor Networks and Ideal Observers
Gain control by divisive inhibition, a.k.a. divisive normalization, has been proposed to be a general mechanism throughout the visual cortex. We explore in this study the statisti...
Sophie Deneve, Alexandre Pouget, Peter E. Latham
CORR
2011
Springer
211views Education» more  CORR 2011»
12 years 11 months ago
Labeling 3D scenes for Personal Assistant Robots
—Inexpensive RGB-D cameras that give an RGB image together with depth data have become widely available. We use this data to build 3D point clouds of a full scene. In this paper,...
Hema Swetha Koppula, Abhishek Anand, Thorsten Joac...