SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

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 presen...

Full description

Saved in:
Bibliographic Details
Main Authors: Tilmon, Brevin, Koppal, Sanjeev J.
Format: Conference Proceeding
Language:English
Subjects:
3D from a single image and shape-from-x
3D from multiview and other sensors
Adaptive systems
Animals
Computational photography
Computer vision
Estimation
Image resolution
Prototypes
Stereo
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00595