← Back to Benchmarks
simmediumquadrupedmetric · varies

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

Description

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 dee

Source

http://arxiv.org/abs/2509.25146v1