Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation
This work addresses the challenge of 3D reconstruction for symmetric, non-rigid objects like cars and airplanes, which is incremental as it builds on existing SfM methods with symmetry constraints.
The paper tackles the problem of estimating 3D structures of symmetric objects from multiple images of the same category, such as cars, by extending non-rigid structure from motion algorithms to incorporate symmetry constraints and handle occlusions. Results on the Pascal3D+ dataset show significant performance improvements over baseline methods.
Many objects, especially these made by humans, are symmetric, e.g. cars and aeroplanes. This paper addresses the estimation of 3D structures of symmetric objects from multiple images of the same object category, e.g. different cars, seen from various viewpoints. We assume that the deformation between different instances from the same object category is non-rigid and symmetric. In this paper, we extend two leading non-rigid structure from motion (SfM) algorithms to exploit symmetry constraints. We model the both methods as energy minimization, in which we also recover the missing observations caused by occlusions. In particularly, we show that by rotating the coordinate system, the energy can be decoupled into two independent terms, which still exploit symmetry, to apply matrix factorization separately on each of them for initialization. The results on the Pascal3D+ dataset show that our methods significantly improve performance over baseline methods.