Sep 17, 2026 · cs.CVJ/K move · Enter open · S save
Mikihiro Ikura, Luna Gava, Jiahang Wu, Chiara Bartolozzi+1
Istituto Italiano di Tecnologia, Via Morego 30 16163 Genova, Italy
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.