Abstract 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.
Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images
Computer Vision – ACCV 2006 ; 4 ; 409-418
Lecture Notes in Computer Science ; 3851 , 4
2006-01-01
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Input Image , Volume Rendering , Foreground Object , Visual Hull , Reprojection Error Computer Science , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Image Processing and Computer Vision , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images
British Library Conference Proceedings | 2006
|Three-dimensional volume rendering from sector scanning images [5253-83]
British Library Conference Proceedings | 2003
|Polarization-based inverse rendering from a single view
IEEE | 2003
|Polarization-Based Inverse Rendering from a Single View
British Library Conference Proceedings | 2003
|