{"ID":23475169,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19973","arxiv_id":"2609.19973","title":"An Event Preserving Velocity Invariant Representation for Event Cameras","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.","short_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...","url_abs":"https://arxiv.org/abs/2609.19973","url_pdf":"https://arxiv.org/pdf/2609.19973v1","authors":"[\"Mikihiro Ikura\",\"Luna Gava\",\"Jiahang Wu\",\"Chiara Bartolozzi\",\"Arren Glover\"]","published":"2026-09-17T09:46:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}