Event Guided Depth Sensing
Manasi Muglikar, Diederik Paul Moeys, Davide Scaramuzza

TL;DR
This paper introduces a bio-inspired, event-camera-driven depth sensing method that dynamically illuminates scene regions based on activity, significantly reducing power consumption while maintaining effective depth estimation in natural scenes.
Contribution
The paper presents a novel event-based structured light system that adaptively illuminates scene areas, improving efficiency and reducing power use compared to traditional uniform sampling methods.
Findings
Requires only 10% of the scene to be scanned in natural scenes.
Potential for 90% reduction in power consumption.
Feasibility demonstrated in simulated and real indoor sequences.
Abstract
Active depth sensors like structured light, lidar, and time-of-flight systems sample the depth of the entire scene uniformly at a fixed scan rate. This leads to limited spatio-temporal resolution where redundant static information is over-sampled and precious motion information might be under-sampled. In this paper, we present an efficient bio-inspired event-camera-driven depth estimation algorithm. In our approach, we dynamically illuminate areas of interest densely, depending on the scene activity detected by the event camera, and sparsely illuminate areas in the field of view with no motion. The depth estimation is achieved by an event-based structured light system consisting of a laser point projector coupled with a second event-based sensor tuned to detect the reflection of the laser from the scene. We show the feasibility of our approach in a simulated autonomous driving scenario…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
