{"ID":2863842,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25146","arxiv_id":"2509.25146","title":"Fast Feature Field ($\\text{F}^3$): A Predictive Representation of Events","abstract":"This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\\text{F}^3$). We learn this representation by predicting future events from past events and show that it preserves scene structure and motion information. $\\text{F}^3$ exploits the sparsity of event data and is robust to noise and variations in event rates. It can be computed efficiently using ideas from multi-resolution hash encoding and deep sets - achieving 120 Hz at HD and 440 Hz at VGA resolutions. $\\text{F}^3$ represents events within a contiguous spatiotemporal volume as a multi-channel image, enabling a range of downstream tasks. We obtain state-of-the-art performance on optical flow estimation, semantic segmentation, and monocular metric depth estimation, on data from three robotic platforms (a car, a quadruped robot and a flying platform), across different lighting conditions (daytime, nighttime), environments (indoors, outdoors, urban, as well as off-road) and dynamic vision sensors (resolutions and event rates). Our implementations can predict these tasks at 25-75 Hz at HD resolution.","short_abstract":"This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\\text{F}^3$). We learn this representation by predicting future events from past events and show that it preserves scene structure and motion information. $\\text{F}...","url_abs":"https://arxiv.org/abs/2509.25146","url_pdf":"https://arxiv.org/pdf/2509.25146v1","authors":"[\"Richeek Das\",\"Kostas Daniilidis\",\"Pratik Chaudhari\"]","published":"2025-09-29T17:52:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\",\"cs.RO\"]","methods":"[]","has_code":false}