Conference Paper

A line integration based method for depth recovery from surfacenormals

Dept. of Inf. Electron., Tsinghua Univ., Beijing
DOI: 10.1109/ICPR.1988.28301 Conference: Pattern Recognition, 1988., 9th International Conference on
Source: IEEE Xplore


A method for constructing a depth map from surface normals is described. In this depth recovery method, an arbitrary depth must first be preset for a point somewhere in the image, and then path-independent line integrals are computed to get the relative depths at every point in the image. The validity of the proposed method is discussed and its efficiency is tested using surface normals obtained by shape from the shading algorithm. A comparison to previous methods is made. Theoretical analysis and experimental results show that the present method is both powerful and easy to implement

11 Reads
  • Source
    • "The major differences between these two networks are the node representation in Layers 3 and 4 and the active function of Layer 5. Through the supervised learning algorithm derived in the following section, the normal surface vectors can be obtained automatically.[3] Then, integration methods can be used to obtain the depth information for reconstructing the 3-D surface of an object by the obtained normal vectors[4]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D) surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach
  • Source
    • "To recover the depth map, we need to determine f (x, y) from measured values of the unit normal. There are a number of ways in which a surface may be recovered from a field of surface normals [3] [8] [9] [12] [18] [10]. There are local and global methods based on trigonometry and the minimisation of error functionals, respectively and the most suitable could be selected for this part of the process. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a recursive algorithm for 3D surface recon- struction based on Photometric Stereo in the presence of highlights, and self and cast shadows. We assume that the surface reflectance outside the highlights can be approxi- mated by the Lambertian model. The algorithm works with as few as three light sources, and it can be generalised for N without any difficulties. Furthermore, this reconstruction method is able to identify areas where the majority of the lighting directions result in unreliable pixel intensities, pro- viding the capability to adjust a reconstruction algorithm and improve its performance avoiding the unreliable sources. We report results for both artificial and real images and compare them with the results of other state of the art photometric stereo algorithms.
    Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 06/2008; DOI:10.1109/CVPR.2008.4587762
  • Source
    • "There are two answers to this problem. The first one consists in using several integration paths between (x 0 , y 0 ) and (x, y), and to mean the integrals, as Wu and Li do (see [17] and Section 3.1). The second answer considers that Eqs. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We show how to use two existing methods of integration of a normal eld in the absence of boundary condition, which makes them more realistic. Moreover, we show how perspective can be taken into account, in order to render the 3D-reconstruction more accurate. Finally, the joint use of both these methods of integration allows us to obtain very satisfactory results, from the point of view of CPU time as well as that of the accuracy of the reconstructions. As an application, we use this new combined method of integration of a normal eld in the framework of photometric stereo, a technique which aims at computing a normal field to the surface of a scene from several images of this scene illuminated from various directions. The performances of the proposed method are illustrated on synthetic, as well as on real images
Show more