We address the problem of active visual exploration of large 360{\deg} inputs. In our setting an active agent with a limited camera bandwidth explores its 360{\deg} environment by changing its viewing direction at limited discrete time steps. As such, it observes the world as a sequence of narrow field-of-view 'glimpses', deciding for itself where to look next. Our proposed method exceeds previous works' performance by a significant margin without the need for deep reinforcement learning or training separate networks as sidekicks. A key component of our system are the spatial memory maps that make the system aware of the glimpses' orientations (locations in the 360{\deg} image). Further, we stress the advantages of retina-like glimpses when the agent's sensor bandwidth and time-steps are limited. Finally, we use our trained model to do classification of the whole scene using only the information observed in the glimpses.
@article{arxiv.1909.10304,
title = {Where to Look Next: Unsupervised Active Visual Exploration on 360{\deg} Input},
author = {Soroush Seifi and Tinne Tuytelaars},
journal= {arXiv preprint arXiv:1909.10304},
year = {2019}
}
Comments
Oral Presentation and best Paper Award at 360 Perception and Interaction Workshop at ICCV 2019