Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Image

January 2006

Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Image

Authors:

Shuntaro Yamazaki, Masaaki Mochimaru, and Takeo Kanade

Abstract:

This paper presents a method of image-based 3D modeling for intricately-shaped objects, such as 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.
@conference{Yamazaki-2006-9378,
author = {Shuntaro Yamazaki And Masaaki Mochimaru And Takeo Kanade},
title = {Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Image},
booktitle = {Proceedings of Asian Conference on Computer Vision (ACCV '06)},
year = {2006},
month = {January},
pages = {409 - 418},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.