Publication
Unsupervised 3D reconstruction and grouping of rigid and non-rigid categories
Journal Article (2022)
Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pages
519-532
Volume
44
Number
1
Doc link
https://doi.org/10.1109/TPAMI.2020.3008276
File
Abstract
In this paper we present an approach to jointly recover camera pose, 3D shape, and object and deformation type grouping, from incomplete 2D annotations in a multi-instance collection of RGB images. Our approach is able to handle indistinctly both rigid and non-rigid categories. This advances existing work, which only addresses the problem for one single object or, they assume the groups to be known a priori when multiple instances are handled. In order to address this broader version of the problem, we encode object deformation by means of multiple unions of subspaces, that is able to span from small rigid motion to complex deformations. The model parameters are learned via Augmented Lagrange Multipliers, in a completely unsupervised manner that does not require any training data at all. Extensive experimental evaluation is provided in a wide variety of synthetic and real scenarios, including rigid and non-rigid categories with small and large deformations. We obtain state-of-the-art solutions in terms of 3D reconstruction accuracy, while also providing grouping results that allow splitting the input images into object instances and their associated type of deformation.
Categories
computer vision.
Author keywords
Category Reconstruction, Multiple Unions of Subspaces, Class Clustering, Augmented Lagrange Multipliers.
Scientific reference
A. Agudo. Unsupervised 3D reconstruction and grouping of rigid and non-rigid categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1): 519-532, 2022.
Follow us!