Deconstruction of compound objects from image sets
This work addresses the problem of 3D reconstruction for compound objects, which is incremental as it builds on existing silhouette-based methods with a new representation.
The paper tackles the problem of recovering the 3D structure of compound objects from multiple silhouettes by representing them as collections of primitives from a library, addressing the combinatorial challenge with a sparse approach that scales to large part libraries.
We propose a method to recover the structure of a compound object from multiple silhouettes. Structure is expressed as a collection of 3D primitives chosen from a pre-defined library, each with an associated pose. This has several advantages over a volume or mesh representation both for estimation and the utility of the recovered model. The main challenge in recovering such a model is the combinatorial number of possible arrangements of parts. We address this issue by exploiting the sparse nature of the problem, and show that our method scales to objects constructed from large libraries of parts.