Neural-network-based adaptive hybrid-reflectance model for 3-D surface reconstruction

• Published in: IEEE transaction on neural networks and learning systems 2005-11, Vol.16 (6), p.1601-1615
• Main Authors: LIN, Chin-Teng, CHENG, Wen-Chang, LIANG, Sheng-Fu
• Format: Article
• Language: English
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Brightness; Cluster Analysis; Computer science; control theory; systems; Computer vision; Connectionism. Neural networks; Cost function; Enforcing integrability; Exact sciences and technology; Face - anatomy & histology; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image reconstruction; Imaging, Three-Dimensional - methods; Information Storage and Retrieval - methods; Lambertian model; Light sources; neural network; Neural networks; Neural Networks (Computer); Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Photography - methods; Pixel; reflectance model; Reproducibility of Results; Sensitivity and Specificity; Shape; shape from shading; Studies; Supervised learning; surface normal; Surface reconstruction
• ISSN: 1045-9227; 2162-237X; 1941-0093; 2162-2388
• DOI: 10.1109/TNN.2005.853333

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.