Where Does It End? - Reasoning About Hidden Surfaces by Object Intersection Constraints
Abstract
Dynamic scene understanding is an essential capability in robotics and VR/AR. In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information from intersection constraints. An object-level dynamic SLAM frontend detects, segments, tracks and maps dynamic objects in the scene. Our optimization backend completes the shapes using hull and intersection constraints between the objects. In experiments, we demonstrate our approach on real and synthetic dynamic scene datasets. We also assess the shape completion performance of our method quantitatively. To the best of our knowledge, our approach is the first method to incorporate such physical plausibility constraints on object intersections for shape completion of dynamic objects in an energy minimization framework.
Material
- CVPR teaser video
- arXiv Preprint
- Paper & supplemental material (CVF open access archive)
- Code
Referencing Co-Section
@inproceedings{strecke2020_cosection,
title = {Where Does It End? - Reasoning About Hidden Surfaces by Object Intersection Constraints},
author = {Strecke, Michael and St{\"u}ckler, J{\"o}rg},
booktitle = {Proceedings IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)},
publisher = {IEEE},
month = jun,
year = {2020},
note = {preprint Corr abs/2004.04630},
doi = {10.1109/CVPR42600.2020.00961},
month_numeric = {6}
}