# Fast Feature Field ($\\text{F}^3$): A Predictive Representation of Events

Source: [Fast Feature Field ($\\text{F}^3$): A Predictive Representation of Events](<https://www.sota2.com/research/paper/68fa7baf1e209131cea89df9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-04T05:00:05.532Z

Authors: Richeek Das, Kostas Daniilidis, Pratik Chaudhari

Published: 2025-09-29T17:52:31.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.25146>)

[PDF](<https://arxiv.org/pdf/2509.25146.pdf>)
