Neural network architecture for 3D object representation

The paper discusses a neural network architecture for 3D object modeling. A multi-layered feedforward structure having as inputs the 3D-coordinates of the object points is employed to model the object space. Cascaded with a transformation neural network module, the proposed architecture can be used to generate and train 3D objects, perform transformations, set operations and object morphing. A possible application for object recognition is also presented.

[1]  Chris Aldrich,et al.  Visualization of transformed multivariate data sets with autoassociative neural networks , 1998, Pattern Recognit. Lett..

[2]  Aly A. Farag,et al.  Integrating shape from shading and range data using neural networks , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[3]  Adnan Acan,et al.  Modeling an isosurface with a neural network , 2000, Proceedings the Eighth Pacific Conference on Computer Graphics and Applications.

[4]  Yizhou Yu.  Surface Reconstruction from Unorganized Points Using Self-Organizing Neural Networks , 1999 .

[5]  Yukio Kosugi,et al.  Self‐organizing elastic networks for generating a 3D model for many images , 1999 .

[6]  Richard K. Beatson,et al.  Smooth surface reconstruction from noisy range data , 2003, GRAPHITE '03.

[7]  Jenq-Neng Hwang,et al.  A translation/rotation/scaling/occlusion invariant neural network for 2D/3D object classification , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Patrick Reuter,et al.  Point-based modelling and rendering using radial basis functions , 2003, GRAPHITE '03.

[9]  Jenq-Neng Hwang,et al.  3D motion estimation using single perspective sparse range data via surface reconstruction neural networks , 1993, IEEE International Conference on Neural Networks.

[10]  C S Tseng,et al.  Application of three-dimensional orthogonal neural network to craniomaxillary reconstruction. , 2001, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[11]  Ovidio Salvetti,et al.  An efficient method to map a regular mesh into a 3D neural network , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[12]  Roberto Pirrone,et al.  A Two Stage Neural Architecture for Segmentation and Superquadrics Recovery from Range Data , 2002, WIRN.

[13]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[14]  Itsuo Kumazawa,et al.  Affine transformations of 3D objects represented with neural networks , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[15]  Sei-Wang Chen,et al.  SO dynamic deformation for building of 3-D models , 1996, IEEE Trans. Neural Networks.

[16]  Qingjin Peng,et al.  Using image processing based on neural networks in reverse engineering , 2001 .

[17]  Itsuo Kumazawa,et al.  3D Shape Reconstruction from Multiple Silhouettes: Generalization from Few Views by Neural Network Learning , 2001, IWVF.

[18]  Jenq-Neng Hwang,et al.  3-D heart contour delineation and motion tracking of ultrasound images using continuous distance transform neural networks , 1996, Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop.

[19]  Helge J. Ritter,et al.  Representing object manifolds by parametrized SOMs , 2002, Object recognition supported by user interaction for service robots.

[20]  Itsuo Kumazawa.  Compact and parametric shape representation by a tree of sigmoid functions for automatic shape modeling, , 2000, Pattern Recognit. Lett..

[21]  Emil M. Petriu,et al.  Neural Networks for Measurement and Instrumentation in Virtual Environments , 2003 .

[22]  Richard K. Beatson,et al.  Reconstruction and representation of 3D objects with radial basis functions , 2001, SIGGRAPH.

[23]  Sven Loncaric,et al.  Construction of virtual environment for endoscopy , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[24]  Tilo Lilienblum,et al.  Improvement of 3-D data by neural networks , 1996, Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing.

[25]  George K. Knopf,et al.  Adaptive reconstruction of free-form surfaces using Bernstein basis function networks , 2001 .

[26]  Jenq-Neng Hwang,et al.  Three-dimensional object representation and invariant recognition using continuous distance transform neural networks , 1997, IEEE Trans. Neural Networks.

[27]  Geoff A. W. West,et al.  Refining 3D models using a two-stage neural network-based iterative process , 2002, Object recognition supported by user interaction for service robots.

[28]  Anath Fischer,et al.  Parameterization and Reconstruction from 3D Scattered Points Based on Neural Network and PDE Techniques , 2001, IEEE Trans. Vis. Comput. Graph..

[29]  Tommy W. S. Chow,et al.  A neural-learning-based reflectance model for 3-D shape reconstruction , 2000, IEEE Trans. Ind. Electron..

[30]  Alan H. Barr,et al.  Global and local deformations of solid primitives , 1984, SIGGRAPH.