Long-Term Image Boundary Prediction

Authors

  • Apratim Bhattacharyya Max Planck Institute for Informatics
  • Mateusz Malinowski Max Planck Institute for Informatics
  • Bernt Schiele Max Planck Institute for Informatics
  • Mario Fritz Max Planck Institute for Informatics

DOI:

https://doi.org/10.1609/aaai.v32i1.11811

Keywords:

Vision, Image Boundaries, Prediction

Abstract

Boundary estimation in images and videos has been a very active topic of research, and organizing visual information into boundaries and segments is believed to be a corner stone of visual perception. While prior work has focused on estimating boundaries for observed frames, our work aims at predicting boundaries of future unobserved frames. This requires our model to learn about the fate of boundaries and corresponding motion patterns---including a notion of "intuitive physics." We experiment on natural video sequences along with synthetic sequences with deterministic physics-based and agent-based motions. While not being our primary goal, we also show that fusion of RGB and boundary prediction leads to improved RGB predictions.

Downloads

Published

2018-04-29

How to Cite

Bhattacharyya, A., Malinowski, M., Schiele, B., & Fritz, M. (2018). Long-Term Image Boundary Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11811