Monocular 3D shape reconstruction using deep neural networks

Abstract

This paper presents a novel approach to reconstructing the 3D shape of an object from a single image. The approach combines deep neural networks with a silhouette-based 3D reconstruction process. The optimal 3D shape is sought efficiently inside an extremely low-dimensional latent shape space, and the viewpoint and the object shape are jointly optimized based on the result of image segmentation. Evaluation of this approach shows a nearly 20 percent performance gain in viewpoint estimation subsequent to the optimization.

DOI: 10.1109/IVS.2016.7535403

9 Figures and Tables

Cite this paper

@article{Rao2016Monocular3S, title={Monocular 3D shape reconstruction using deep neural networks}, author={Qing Rao and Lars Kr{\"{u}ger and Klaus C. J. Dietmayer}, journal={2016 IEEE Intelligent Vehicles Symposium (IV)}, year={2016}, pages={310-315} }