An Event Preserving Velocity Invariant Representation for Event Cameras

arXiv:2609.19973 · cs.CV · Submitted 2026-09-17 · Read on arXiv

cs.CV

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: @inproceedings{ikura2026event, title={An Event Preserving Velocity Invariant Representation for Event Cameras}, author={Ikura, Mikihiro and Gava, Luna and Wu, Jiahang and Glover, Arren and Bartolozzi, Chiara}, year={2026}, booktitle={ECCV 2026 Workshop-Event-Based Multimodal Vision: From Imaging to Perception and Understanding} }

Journal ref: Ikura, M., Gava, L., Wu, J., Glover, A. and Bartolozzi, C., An Event Preserving Velocity Invariant Representation for Event Cameras. In ECCV 2026 Workshop-Event-Based Multimodal Vision: From Imaging to Perception and Understanding

Code: https://github.com/robotology/event-driven

License: http://creativecommons.org/licenses/by/4.0/

The gist: Event cameras provide low-latency, high temporal resolution perception for real-time vision tasks such as robotics.The novel circuitry (i.e.

Terminology

Abstract

Event cameras provide low-latency, high temporal resolution perception for real-time vision tasks such as robotics.The novel circuitry (i.e. asynchronous, independent pixels) that enables these advantages also introduces new algorithmic challenges. Velocity-invariant representations alleviate missing observations under slow motion and motion blur under fast motion, but most discard temporal information by converting events into image-like representations. We propose Set of Centre Active Receptive Fields (SCARF), a real-time velocity-invariant representation that preserves raw events while consistently handling fast motion, stationary scenes, and independently moving objects. SCARF achieves state-of-the-art performance in both computational efficiency and representation quality.

Related papers