Publication

Deformable motion 3D reconstruction by union of regularized subspaces

Conference Article

Conference

IEEE International Conference on Image Processing (ICIP)

Edition

25th

Pages

2930-2934

Doc link

https://doi.org/10.1109/ICIP.2018.8451235

File

Download the digital copy of the doc pdf document

Abstract

This paper presents an approach to jointly retrieve camera pose, time-varying 3D shape, and automatic clustering based on motion primitives, from incomplete 2D trajectories in a monocular video. We introduce the concept of order-varying temporal regularization in order to exploit video data, that can be indistinctly applied to the 3D shape evolution as well as to the similarities between images. This results in a union of regularized subspaces which effectively encodes the 3D shape deformation. All parameters are learned via augmented Lagrange multipliers, in a unified and unsupervised manner that does not assume any training data at all. Experimental validation is reported on human motion from sparse to dense shapes, providing more robust and accurate solutions than state-of-the-art approaches in terms of 3D reconstruction, while also obtaining motion grouping results.

Categories

computer vision, optimisation.

Author keywords

Non-Rigid Structure from Motion, Order-Varying Regularization, Union of Regularized Subspaces

Scientific reference

A. Agudo and F. Moreno-Noguer. Deformable motion 3D reconstruction by union of regularized subspaces, 25th IEEE International Conference on Image Processing, 2018, Athens, Greece, pp. 2930-2934.