Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images

摘要

This paper presents a method of image-based 3D modeling for intricately-shaped objects, such as a fur, tree leaves and human hair. We formulate the imaging process of these small geometric structures as volume rendering followed by image matting, and prove that the inverse problem can be solved by reducing the nonlinear equations to a large linear system. This estimation, which we call inverse volume rendering, can be performed efficiently through expectation maximization method, even when the linear system is under-constrained owing to data sparseness. We reconstruct object shape by a set of coarse voxels that can model the spatial occupancy inside each voxel. Experimental results show that intricately-shaped objects can successfully be modeled by our proposed method, and the original and other novel view-images of the objects can be synthesized by forward volume rendering.