Publication

DUST: Dual union of spatio-temporal subspaces for monocular multiple object 3D reconstruction

Conference Article

Conference

IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)

Edition

2017

File

Download the digital copy of the doc pdf document

Abstract

We present an approach to reconstruct the 3D shape of multiple deforming objects from incomplete 2D trajectories acquired by a single camera. Additionally, we simultaneously provide spatial segmentation (i.e., we identify each of the objects in every frame) and temporal clustering (i.e., we split the sequence into primitive actions). This advances existing work, which only tackled the problem for one single object and non-occluded tracks. In order to handle several objects at a time from partial observations, we model point trajectories as a union of spatial and temporal subspaces, and optimize the parameters of both modalities, the non-observed point tracks and the 3D shape via augmented Lagrange multipliers. The algorithm is fully unsupervised and results in a formulation which does not need initialization. We thoroughly validate the method on challenging scenarios with several human subjects performing different activities which involve complex motions and close interaction. We show our approach achieves state-of-the-art 3D reconstruction results, while it also provides spatial and temporal segmentation.

Categories

computer vision, optimisation, pattern clustering.

Author keywords

Spatio-Temporal Segmentation

Scientific reference

A. Agudo and F. Moreno-Noguer. DUST: Dual union of spatio-temporal subspaces for monocular multiple object 3D reconstruction, 2017 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2017, Honolulu, USA, IEEE, to appear.