Filters








241,493 Hits in 7.0 sec

Deep Structure for end-to-end inverse rendering [article]

Shima Kamyab, Ali Ghodsi, S. Zohreh Azimifar
2017 arXiv   pre-print
Inverse rendering in a 3D format denoted to recovering the 3D properties of a scene given 2D input image(s) and is typically done using 3D Morphable Model (3DMM) based methods from single view images.  ...  The empirical results verify the power of deep framework in finding accurate 3D shapes of human faces from their corresponding 2D images on synthetic datasets of human faces.  ...  Methods for inverse rendering usually work based on defining a shape space for the desired object class structure and generating new shapes by morphing between existing basis vectors. 3D morphable models  ... 
arXiv:1708.08998v1 fatcat:bflqguoesfeu7ajwccrkbhpdwy

Order-preserving clustering and its application to gene expression data

T. Syeda-Mahmood
2004 Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.  
Clustering of the data then reduces to grouping curves based on shape similarity. We develop a novel measure of shape similarity between curves using scale-space distance.  ...  In this paper, we present a general order-preserving clustering algorithm that allows arbitrary patterns of data evolution by representing each ordered set as a curve.  ...  Conclusions In this paper, we have introduced a new pattern recognition-based method for order-preserving clustering.  ... 
doi:10.1109/icpr.2004.1333853 dblp:conf/icpr/Syeda-Mahmood04 fatcat:hygtsnga4vdovaemlfehdl4r3u

Characterizing human shape variation using 3D anthropometric data

Zouhour Ben Azouz, Marc Rioux, Chang Shu, Richard Lepage
2006 The Visual Computer  
In this paper, we present a new method for extracting the main modes of variations of the human shape from a 3D anthropometric database. Previous approaches rely on anatomical landmarks.  ...  This technology opens up opportunities to extract new measurements for quantifying the body shape.  ... 
doi:10.1007/s00371-006-0006-6 fatcat:txqxvxc4zfgbzo755r4uuvzm3i

New Experiments on ICP-Based 3D Face Recognition and Authentication

B.B. Amor, M. Ardabilian, L. Chen
2006 18th International Conference on Pattern Recognition (ICPR'06)  
A new multi-view registered 3D face database, including these variations, is developed within BioSecure Workshop 2005 in order to perform significant experiments.  ...  The general paradigm consists in building a full 3D face gallery using a laser-based scanner (the off-line phase).  ...  A second family of recent works, known as 3D model-based, exploits threedimensional face shape in order to mitigate some of these variations.  ... 
doi:10.1109/icpr.2006.855 dblp:conf/icpr/AmorAC06 fatcat:fpxz3g6dk5azrjntgnkjgtvprq

Shape from Suggestive Contours Using 3D Priors

Stefanie Wuhrer, Chang Shu
2012 2012 Ninth Conference on Computer and Robot Vision  
We learn a functional mapping from the shape space of suggestive contours to the space of 3D shapes and use this mapping to predict 3D shapes based on a single input image.  ...  We use suggestive contour, a shape-suggesting image feature developed in computer graphics in the context of non-photorealistic rendering, to reconstruct 3D shapes.  ...  In order to establish the functional mapping, both the 3D shape space and the image space are represented by statistical shape models.  ... 
doi:10.1109/crv.2012.38 dblp:conf/crv/WuhrerS12 fatcat:vyfm7yar3ja4ziiuquxsvjrzie

Efficient Detection of Second-Degree Variations in 2D and 3D Images

Per-Erik Danielsson, Qingfen Lin, Qin-Zhong Ye
2001 Journal of Visual Communication and Image Representation  
Qingfen Lin was granted to do some of her work reported here as a graduate student at National University of Singapore, which is also gratefully acknowledged.  ...  2 Acknowledgements This work has been sponsored by the Swedish Foundation for Strategic Research via the VISIT program, which is hereby gratefully acknowledged.  ...  blob-like shapes, too low a value for second order variations, which in the shape space of Figure 11 are located on the equator.  ... 
doi:10.1006/jvci.2000.0472 fatcat:mrbh3eznnbauzlwtnnpvtbo2hy

Scale-Space Processing of Point-Sampled Geometry for Efficient 3D Object Segmentation

H. LAGA
2005 IEICE transactions on information and systems  
In this paper, we present a new framework for analyzing and segmenting point-sampled 3D objects.  ...  We demonstrate and discuss the performance of our framework on a collection of point sampled 3D objects.  ...  The test data of bunny and dragon models are from the Stanford 3D Scanning Repository. We would like to aknowledge the Stanford Computer Graphics Laboratory for making those data available.  ... 
doi:10.1093/ietisy/e88-d.5.963 fatcat:vcmlyngh3zg2dh54bf4nnvqc2e

3D face shape approximation from intensities using Partial Least Squares

Mario Castelan, Johan Van Horebeek
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
We exploit this idea to construct statistical models of intensity and 3D shape that express strongly linked variations in both spaces.  ...  In this paper, we apply Partial Least Squares (PLS) regression to predict 3D face shape from a single image.  ...  For each panel, variations in intensity and 3D shape (as a frontal reillumination) are shown column-wise.  ... 
doi:10.1109/cvprw.2008.4563049 dblp:conf/cvpr/CastelanH08 fatcat:gavl54pba5bdxcl4m7ivnsqrji

STATISTICAL SHAPE ANALYSIS VIA PRINCIPAL FACTOR ANALYSIS

Mauricio Aguirre, Marius Linguraru, Kostas Marias, Nicholas Ayache, Lutz-peter Nolte, Miguel Gonzalez Ballester
2007 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
Then, a study of the 3D shape variability of the human left femur is performed.  ...  shape variability into a reduced set of interpretable components.  ...  The principal components are the set of new ordered basis vectors.  ... 
doi:10.1109/isbi.2007.357077 dblp:conf/isbi/ReyesLMANB07 fatcat:f3b2qb2wszgm3pwc6it2a4jske

Manifold Estimation in View-Based Feature Space for Face Synthesis across Poses [chapter]

Xinyu Huang, Jizhou Gao, Sen-ching S. Cheung, Ruigang Yang
2010 Lecture Notes in Computer Science  
This paper presents a new approach to synthesize face images under different pose changes given a single input image.  ...  The approach is based on two observations: 1. a series of face images of a single person under different poses could be mapped to a smooth manifold in the unified feature space. 2. the manifolds from different  ...  Similar to this idea, the morphable model [6] is formulated as a vector space of 3D shapes and surface textures that are spanned by a training set that contains 200 laser scanned 3D face models. 3D shape  ... 
doi:10.1007/978-3-642-12307-8_4 fatcat:q7vffq4ql5djxafgkyqxaqu45e

Computing the Uniform Component of Shape Variation

F. James Rohlf, Fred L. Bookstein
2003 Systematic Biology  
Any change in shape of a configuration of landmark points in two or three dimensions includes a uniform component, a component that is a wholly linear (affine) transformation.  ...  The component can be estimated by regression in either one space or the other: regression on the partial warps, followed by their removal, or regression on a basis for the uniform component itself.  ...  This is contribution 1104 from the Graduate Studies in Ecology and Evolution, State University of New York, Stony Brook.  ... 
doi:10.1080/10635150390132759 pmid:12554441 fatcat:lyalf4oa4jdsnphkjamfzw4di4

DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces [article]

Minhyuk Sung, Zhenyu Jiang, Panos Achlioptas, Niloy J. Mitra, Leonidas J. Guibas
2020 arXiv   pre-print
in 3D.  ...  We propose DeformSyncNet, a new approach that allows consistent and synchronized shape deformations without requiring explicit correspondence information.  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their comments and suggestions. N. J.  ... 
arXiv:2009.01456v1 fatcat:m3ux5clzyndotkhuc47bmfyjni

Multi-scale feature extraction for 3d surface registration using local shape variation

Huy Tho Ho, Danny Gibbins
2008 2008 23rd International Conference Image and Vision Computing New Zealand  
This paper describes a method for extracting salient local features from 3D models using shape variation which has application to 3D surface registration.  ...  The local surface variation is then measured by calculating the variation of the shape index of every point in the neighbourhood.  ...  Mian from the University of Western Australia for making their 3D datasets publicly available.  ... 
doi:10.1109/ivcnz.2008.4762120 fatcat:wtrk5zqskbd5dfecksxd3amp3q

Kernel principal component analysis of the ear morphology

Reza Zolfaghari, Nicolas Epain, Craig T. Jin, Joan Glaunes, Anthony Tew
2017 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The statistical analysis conducted over the space of ear shapes uses a kernel principal component analysis (KPCA).  ...  This paper describes features in the ear shape that change across a population of ears and explores the corresponding changes in ear acoustics.  ...  There is an HRIR filter for each ear and each direction in space and these HRIR filters enable the rendering of binaural 3D audio for a listener.  ... 
doi:10.1109/icassp.2017.7952202 dblp:conf/icassp/ZolfaghariEJGT17 fatcat:dnvprr7mdra2hgp7ckxaeq2wfa

Manifold Learning in Quotient Spaces

Eloi Mehr, Andre Lieutier, Fernando Sanchez Bermudez, Vincent Guitteny, Nicolas Thome, Matthieu Cord
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper we introduce a new autoencoder model for encoding and synthesis of 3D shapes.  ...  To get rid of undesirable input variability our model learns a manifold in a quotient space of the input space. Typically, we propose to quotient the space of 3D models by the action of rotations.  ...  shapes (see [3] and also [20, 27] for extensions to a variational framework).  ... 
doi:10.1109/cvpr.2018.00955 dblp:conf/cvpr/MehrLBGTC18 fatcat:5ib5i2txtfdfxkljuvjmrlnv64
« Previous Showing results 1 — 15 out of 241,493 results