• DOI:10.1007/978-3-030-58523-5_12
Corpus ID: 221186914

Hidden Footprints: Learning Contextual Walkability from 3D Human Trails

@article{Sun2020HiddenFL,
  title={Hidden Footprints: Learning Contextual Walkability from 3D Human Trails},
  author={Jin Sun and Hadar Averbuch-Elor and Q. Wang and Noah Snavely},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.08701}
}

Jin Sun, Hadar Averbuch-Elor, +1 author Noah Snavely

Published 2020

Computer Science

ArXiv

Predicting where people can walk in a scene is important for many tasks, including autonomous driving systems and human behavior analysis. Yet learning a computational model for this purpose is challenging due to semantic ambiguity and a lack of labeled data: current datasets only tell you where people are, not where they could be. We tackle this problem by leveraging information from existing datasets, without additional labeling. We first augment the set of valid, labeled walkable regions by… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed