ML Anthology

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

Brevin Tilmon, Sanjeev J. Koppal
ICCV 2021 pp. 6009-6018
doi:10.1109/ICCV48922.2021.00595 /iccv/2021/tilmon2021iccv-saccadecam/

Abstract

Most monocular depth sensing methods use conventionally captured images that are created without considering scene content. In contrast, animal eyes have fast mechanical motions, called saccades, that control how the scene is imaged by the fovea, where resolution is highest. In this paper, we present the SaccadeCam framework for adaptively distributing resolution onto regions of interest in the scene. Our algorithm for adaptive resolution is a self-supervised network and we demonstrate results for end-to-end learning for monocular depth estimation. We also show preliminary results with a real SaccadeCam hardware prototype.

PDF ICCV Semantic Scholar

Cite

Text

Tilmon and Koppal. "SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00595

Markdown

[Tilmon and Koppal. "SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/tilmon2021iccv-saccadecam/) doi:10.1109/ICCV48922.2021.00595

BibTeX

@inproceedings{tilmon2021iccv-saccadecam,
  title     = {{SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing}},
  author    = {Tilmon, Brevin and Koppal, Sanjeev J.},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {6009-6018},
  doi       = {10.1109/ICCV48922.2021.00595},
  url       = {https://mlanthology.org/iccv/2021/tilmon2021iccv-saccadecam/}
}