UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Neural re-simulation for generating bounces in single images

Innamorati, C; Russell, B; Kaufman, D; Mitra, N; (2020) Neural re-simulation for generating bounces in single images. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). (pp. pp. 8718-8727). IEEE: Seoul, South Korea. Green open access

[thumbnail of bounce-neural-resim.pdf]
Preview
Text
bounce-neural-resim.pdf - Accepted version

Download (11MB) | Preview

Abstract

We introduce a method to generate videos of dynamic virtual objects plausibly interacting via collisions with a still image's environment. Given a starting trajectory, physically simulated with the estimated geometry of a single, static input image, we learn to 'correct' this trajectory to a visually plausible one via a neural network. The neural network can then be seen as learning to 'correct' traditional simulation output, generated with incomplete and imprecise world information, to obtain context-specific, visually plausible re-simulated output - a process we call neural re-simulation. We train our system on a set of 50k synthetic scenes where a virtual moving object (ball) has been physically simulated. We demonstrate our approach on both our synthetic dataset and a collection of real-life images depicting everyday scenes, obtaining consistent improvement over baseline alternatives throughout.

Type: Proceedings paper
Title: Neural re-simulation for generating bounces in single images
Event: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICCV.2019.00881
Publisher version: https://doi.org/10.1109/ICCV.2019.00881
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Trajectory , Videos , Neural networks , Visualization , Geometry , Predictive models , Task analysis
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10095339
Downloads since deposit
14Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item