Publication

Image collection pop-up: 3D reconstruction and clustering of rigid and non-rigid categories

Conference Article

Conference

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

Edition

2018

File

Download the digital copy of the doc pdf document

Abstract

This paper introduces an approach to simultaneously estimate 3D shape, camera pose, and object and type of deformation clustering, from partial 2D annotations in a multi-instance collection of images. Furthermore, we can indistinctly process rigid and non-rigid categories. This advances existing work, which only addresses the problem for one single object or, if multiple objects are considered, they are assumed to be clustered a priori. To handle this broader version of the problem, we model object deformation using a formulation based on multiple unions of subspaces, able to span from small rigid motion to complex deformations. The parameters of this model are learned via Augmented Lagrange Multipliers, in a completely unsupervised manner that does not require any training data at all. Extensive validation is provided in a wide variety of synthetic and real scenarios, including rigid and non-rigid categories with small and large deformations. In all cases our approach outperforms state-of-the-art in terms of 3D reconstruction accuracy, while also providing clustering results that allow segmenting the images into object instances and their associated type of deformation (or action the object is performing).

Categories

computer vision, optimisation, pattern clustering.

Author keywords

3D Reconstruction; Rigid and Non-Rigid Categories

Scientific reference

A. Agudo, M. Pijoan and F. Moreno-Noguer. Image collection pop-up: 3D reconstruction and clustering of rigid and non-rigid categories, 2018 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, Salt Lake City, to appear.