Unsupervised Object-centric Video Generation and Decomposition in 3D

Henderson, P. and Lampert, C. H. (2020) Unsupervised Object-centric Video Generation and Decomposition in 3D. In: 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 06-12 Dec 2020, pp. 3106-3117.

Full text not currently available from Enlighten.

Publisher's URL: https://proceedings.neurips.cc/paper/2020/hash/20125fd9b2d43e340a35fb0278da235d-Abstract.html


A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual complexity supported by state-of-the-art generative approaches. We evaluate our method on depth-prediction and 3D object detection -- tasks which cannot be addressed by those earlier works -- and show it out-performs them even on 2D instance segmentation and tracking.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Henderson, Dr Paul
Authors: Henderson, P., and Lampert, C. H.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record