A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf
.
Filters
3D Mesh Segmentation using Local Geometry
2015
International Journal of Computer Graphics & Animation
We propose a new region growing technique starting fromthese boundary vertices leading to a segmentation of the surface thatis subsequently simplified by a region-merging method. ...
Experiments indicatethat our algorithm segments a broad range of 3D models at aquality comparable to existing algorithms. ...
Page et al [15] in 2003 introduced a method called Fast Marching Water-sheds that splits a triangle mesh into segments that fit the definition of visual parts according to the minima rule proposed by ...
doi:10.5121/ijcga.2015.5204
fatcat:wpqqo4amgzcnlf7477bmspi5ra
Palette-based image decomposition, harmonization, and color transfer
[article]
2018
arXiv
pre-print
We also conducted three large-scale, wide-ranging perceptual studies on the perception of harmonic colors and harmonization algorithms. ...
We present a palette-based framework for color composition for visual applications. Color composition is a critical aspect of visual applications in art, design, and visualization. ...
For further improvement, our approach could be parallelized by dividing the image into tiles, since the convex hull of a set of convex hulls is the same as the convex hull of the underlying data. ...
arXiv:1804.01225v3
fatcat:vjpcavx44favfla5w7dnu4xwva
Surface Mesh Segmentation Using Local Geometry
2009
2009 Sixth International Conference on Computer Graphics, Imaging and Visualization
We present a novel algorithm to segment a 3D surface mesh into visually meaningful regions. Our approach is based on an analysis of the local geometry of vertices. ...
Experiments indicate that our algorithm segments a broad range of 3D models at a quality comparable to existing algorithms. ...
Page et al [12] in 2003 introduced a method called Fast Marching Watersheds that splits a triangle mesh into segments that fit the definition of visual parts according to the minima rule proposed by ...
doi:10.1109/cgiv.2009.15
dblp:conf/IEEEcgiv/ChuonG09a
fatcat:4yfszzgp7bdxpkyfupvw7t3444
Real-Time Vision Based Mouth Tracking and Parameterization for a Humanoid Imitation Task
[chapter]
2007
Humanoid Robots: New Developments
This book presents a series of researches inspired by this ideal, carried through by various researchers worldwide, looking for to analyze and to discuss diverse subjects related to humanoid robots. ...
However, with increasing technological advances based on theoretical and experimental researches, man gets, in a way, to copy or to imitate some systems of the human body. ...
This research was conducted as part of "Research on Human Communication" with funding from the National Institute of Information and Communications Technology (NiCT), Japan. Thanks are due to Dr. ...
doi:10.5772/4870
fatcat:pzijbcufazdy3gffzmpvxz3mzm
CLODs: Dual Hierarchies for Multiresolution Collision Detection
[article]
2003
Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing
Given a polyhedral model, our algorithm automatically builds a "dual hierarchy", both a multiresolution representation of the original model and its bounding volume hierarchy for accelerating collision ...
Compared to the existing exact collision detection algorithms, we observe significant performance improvement using CLODs on some benchmarks, with little degradation in the visual rendering of simulations ...
Acknowledgments This research is supported in part by a fellowship of the Government of the Basque Country, National Science Foundation, Office of Naval Research, U.S. ...
doi:10.2312/sgp/sgp03/094-101
fatcat:q5e7sv4xl5aftc6z6vw547l4ly
Shape decomposition and understanding of point cloud objects based on perceptual information
2010
Proceedings of the 9th ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications in Industry - VRCAI '10
Figure 1 : Overview of our algorithm. From a point cloud model, our algorithm extracts some perceptual feature points, according to which the decomposition is implemented. ...
The decomposition is mainly based on human visual perception, which is referred to as the basic capability of the human visual system to derive relevant groupings and structures from 3D objects without ...
We should select several feature points which meet human perception, so we obtain the points on the convex hull (see in Figure 8 (c)) and then refine them by further clustering (i.e. k-nearest neighborhood ...
doi:10.1145/1900179.1900221
dblp:conf/vrcai/NingLZW10
fatcat:v7xptgm7cffd5ieapdv4sicsvm
Global vs. local information processing in visual/spatial problem solving: The case of traveling salesman problem
2007
Cognitive Systems Research
Human visual/spatial problem solving often requires both global and local information to be processed. ...
A model was built to simulate human TSP performance and was used to investigate further the relationship between global information processing and local information processing. ...
Acknowledgement Work on this project was supported by grants N00014-02-1-0113 and N00014-03-1-0061 to the second author from the Office of Naval Research. ...
doi:10.1016/j.cogsys.2007.06.002
fatcat:xpdxpdzvvjhnthjn3moc5bok44
An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors
2017
Sensors
vision perception [31] . ...
The contour-based images were obtained by jointly using the color and depth image by some contour detection algorithms. ...
As stated earlier, symmetry plays an important role in both human visual perception and computer vision. ...
doi:10.3390/s17030451
pmid:28245553
pmcid:PMC5375737
fatcat:dvorrzsye5em7ltrmly4sn5z4u
Object discovery in 3D scenes via shape analysis
2013
2013 IEEE International Conference on Robotics and Automation
Our algorithm first decomposes the scene into a set of candidate mesh segments and then ranks each segment according to its "objectness"a quality that distinguishes objects from clutter. ...
To do so, we propose five intrinsic shape measures: compactness, symmetry, smoothness, and local and global convexity. ...
Visual perception studies have shown that the human visual system uses a global convexity prior when inferring 3D shape [28] , [29] . ...
doi:10.1109/icra.2013.6630857
dblp:conf/icra/KarpathyMF13
fatcat:llyc2kdlyfd3nj43h2dnsotdly
Interaction in Distributed Virtual Environments
[article]
2005
Eurographics State of the Art Reports
visual perception system. ...
In particular the motivations for perceptually-inspired force models for haptic texture rendering, interaction between such models and GPU techniques for fast haptic texture rendering. ...
for their help with SWIFT++ and DEEP; Nitin Jain, Avneesh Sud, and Naga Govindaraju for their contributions in haptic texture rendering; Roberta Klatzky and Susan Lederman for their insights on haptic perception ...
doi:10.2312/egt.20051057
fatcat:y3cgrhdjojdf3ij4p5aloxefwm
Resource Allocation for Personalized Video Summarization
2014
IEEE transactions on multimedia
We formulate video summarization as a discrete optimization problem, where the optimal summary is determined by adopting Lagrangian relaxation and convex-hull approximation to solve a resource allocation ...
We perform clip-level fast-forwarding by selecting the playback speeds from discrete options, which naturally include content truncation as special case with infinite playback speed. ...
If we construct a set of convex hulls from the curves of B m (a mk ) with respect to |a mk |, we can use a greedy algorithm to search for the optimum under a given constraint u L . ...
doi:10.1109/tmm.2013.2291967
fatcat:dsh7saemvvb5rgdhhxcb5g6lhq
Saliency-Guided Object Candidates Based on Gestalt Principles
[chapter]
2015
Lecture Notes in Computer Science
These candidates are created by successively adding segments to a seed segment in a saliency-guided way. Finally, the resulting object candidates are ranked based on Gestalt principles. ...
We show that the proposed algorithm clearly outperforms three other recent methods for object discovery on the challenging Kitchen dataset. ...
Conclusion We have presented a method for finding arbitrary, unknown objects in RGB-D data that utilizes principles of human object perception -visual attention and Gestalt psychology. ...
doi:10.1007/978-3-319-20904-3_4
fatcat:ys2yf6rb7zcsvpvi5zucccrwwy
Saliency-based segmentation of dermoscopic images using color information
[article]
2021
arXiv
pre-print
coupled with new perceptual criteria, inspired by the human visual perception, related to the properties of saliency and color of the input image data distribution. ...
As a means of refining the accuracy of the proposed method, the segmentation step is preceded by a pre-processing aimed at reducing the computation burden, removing artifacts, and improving contrast. ...
Acknowledgments This work has been supported by GNCS (Gruppo Nazionale di Calcolo Scientifico) of the INDAM (Istituto Nazionale di Alta Matematica). ...
arXiv:2011.13179v3
fatcat:rrpjvlp3q5baljnoeul66wyajm
3D Mesh Model Exterior Salient Part Segmentation Using Prominent Feature Points and Marching Plane
2019
KSII Transactions on Internet and Information Systems
This paper presents a 3D mesh model segmentation algorithm that focuses on removing exterior salient parts from the original 3D mesh model based on prominent feature points and marching plane. ...
We evaluated our algorithm on the Princeton Segmentation Benchmark, and the evaluation results show that our algorithm works well for some categories. ...
Feature point extraction and filtering Inspired by a previous report [7] , coarse feature points are extracted by using multidimensional scaling (MDS) and its convex hull on a original simplified 3D mesh ...
doi:10.3837/tiis.2019.03.017
fatcat:l5t5bci5ezdjppfykt2kmyerpm
Developable Surfaces from Arbitrary Sketched Boundaries
[article]
2007
Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing
We present an efficient method for clustering by providing a Rigid Error Function that finds the best rigid transformation from a set of points in a robust, space efficient manner and supports fast clustering ...
To create the skeleton, we first estimate the rigid transformations of the bones using a fast, face clustering approach. ...
This research was partially supported by NSERC, MITACS NCE, and IBM. ...
doi:10.2312/sgp/sgp07/163-172
fatcat:vtdgan46drbbln472ef56isv24
« Previous
Showing results 1 — 15 out of 1,089 results