Shape reconstruction using extended photometric stereo
international conference on information and communication security（1997）
摘要
The main interest of previous researches for shape from shading was only on Lambertian surfaces which consists of diffuse reflectance surfaces. In practice, natural objects have hybrid reflectance, which limits the recovery of shape from intensity distribution. We propose a method of determining the shape using a neural network and diffuse illumination. The segmented region of the sphere surface is used for the training set, which can be determined by the shadow line and the surface edge. Diffuse illumination is used to avoid specular spikes and highlights which usually cause many problems such as intensity disparities. The diffuse illumination method using flat paper allows us to reduce these phenomena with a simple scheme. The neural network and diffuse illumination method is useful for shape from shading, because it can be applied to objects of unknown reflectance properties, but it is applied only to Torrance-Sparrow (1967) style reflectance
更多查看译文
关键词
image reconstruction,image segmentation,learning (artificial intelligence),neural nets,photometry,reflectivity,stereo image processing,lambertian surfaces,torrance-sparrow type reflectance,diffuse illumination,diffuse reflectance surfaces,extended photometric stereo,hybrid reflectance,intensity distribution,neural network,segmented region,shading,shadow line,shape reconstruction,sphere surface,surface edge,training set,diffuse reflectance,surface reconstruction,photometric stereo,shape,lighting,shape from shading,learning artificial intelligence,neural networks
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要