Reconstruction of shape and reflectance properties based on visual hull

A method based on Visual Hull is proposed for simultaneously recovering an object's shape and its reflectance properties from multiple images. Here, the reflectance properties are described by the Ward BRDF model. Firstly, the shape represented by voxels is acquired by applying SFS (Shape from Silhouettes) method, and the triangular mesh of the surface is extracted by Marching Cube algorithm. Secondly, the appearance-like mesh vertices are clustered into categories, and non-linear optimization is applied to each category for calculating its reflectance model parameters. Last, diffuse parameters for each vertex are re-computed. The acquired object shape and its reflectance parameters can be used for photo-realistic rendering. The experimental results on multiple real objects images show the efficiency of the proposed method.