標題: Neural-network-based adaptive hybrid-reflectance model for 3-D surface reconstruction
作者: Lin, CT
Cheng, WC
Liang, SF
生物科技學系
資訊工程學系
電控工程研究所
Department of Biological Science and Technology
Department of Computer Science
Institute of Electrical and Control Engineering
關鍵字: enforcing integrability;Lambertian model;neural network;reflectance model;shape from shading;surface normal
公開日期: 1-Nov-2005
摘要: This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D) surface reconstruction model. The neural network automatically 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 are applied to enforce integrability when reconstructing 3-D objects. Facial images and images of other general objects were used to test the proposed approach. The experimental results demonstrate that the proposed neural-network-based adaptive hybrid-reflectance model can be successfully applied to objects generally and perform 3-D surface reconstruction better than some existing approaches.
URI: http://dx.doi.org/10.1109/TNN.2005.853333
http://hdl.handle.net/11536/13118
ISSN: 1045-9227
DOI: 10.1109/TNN.2005.853333
期刊: IEEE TRANSACTIONS ON NEURAL NETWORKS
Volume: 16
Issue: 6
起始頁: 1601
結束頁: 1615
Appears in Collections:Articles


Files in This Item:

  1. 000233350300025.pdf