An experiment is conducted to prove that multilayer feed-forward neural networks are capable of representing most classes of 3D objects, used in computer graphics. Furthermore, simple affine transformations were applied on those objects showing that modeling is possible using this type of representation. One network is used per one volumetric description of a 3D object. The neural network employed, is a function that takes as inputs 3D coordinates in object space and produces as output a value that indicates if the point belongs to the object or not. The representation method is tested by repeated evaluations of the network for points inside the object space. Objects that have a simple analytical form, e.g. a sphere or a cube, are represented by specifying the networks' parameters manually. For objects with more complicated shapes we generate training examples. These training examples consist of points on the objects' surface and points lying on inclosed and enclosing surfaces. The algorithm for generating the training data, is a simple heuristic that uses the surface normal to determine whether a point in the vicinity of the surface belongs to the inside or the outside of the object. The network is finally trained on the generated examples, using the back propagation technique. The experimental results prove that this representation method is accurate and compact. Feedforward neural networks being hardware implementable offer the ability for a faster representation. This paper is the second step, on a series of ideas, towards creating a real time 3D renderer based entirely on neural networks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Affine transformations of 3D objects represented with neural networks


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1075828 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Affine Transformations of 3D Objects Represented with Neural Networks

    Piperakis, E. / Kumazawa, I. / National Research Council of Canada | British Library Conference Proceedings | 2001


    Recognition, Resolution, and Complexity of Objects Subject to Affine Transformations

    Betke, M. / Makris, N. C. | British Library Online Contents | 2001


    Affine calibration from moving objects

    Manning, R.A. / Dyer, C.R. | IEEE | 2001


    Mathematical Morphological Operations of Boundary-Represented Geometric Objects

    Ghosh, P. K. / Haralick, R. M. | British Library Online Contents | 1996


    Affine Calibration from Moving Objects

    Manning, R. / Dyer, C. / IEEE | British Library Conference Proceedings | 2001