E-NeRF: Neural Radiance Fields from a Moving Event Camera

TL;DR

E-NeRF introduces a novel method to estimate neural radiance fields from fast-moving event camera data, enabling high-quality scene reconstruction in challenging conditions like motion blur and high dynamic range.

Contribution

This work is the first to estimate NeRFs solely from event camera data, improving robustness to motion and lighting conditions compared to traditional frame-based methods.

Findings

Successfully reconstructs NeRFs from fast-moving event data.

Outperforms state-of-the-art methods in high-dynamic-range and motion blur scenarios.

Combining events and frames enhances NeRF quality and robustness.

Abstract

Estimating neural radiance fields (NeRFs) from "ideal" images has been extensively studied in the computer vision community. Most approaches assume optimal illumination and slow camera motion. These assumptions are often violated in robotic applications, where images may contain motion blur, and the scene may not have suitable illumination. This can cause significant problems for downstream tasks such as navigation, inspection, or visualization of the scene. To alleviate these problems, we present E-NeRF, the first method which estimates a volumetric scene representation in the form of a NeRF from a fast-moving event camera. Our method can recover NeRFs during very fast motion and in high-dynamic-range conditions where frame-based approaches fail. We show that rendering high-quality frames is possible by only providing an event stream as input. Furthermore, by combining events and frames, we can estimate NeRFs of higher quality than state-of-the-art approaches under severe motion blur. We also show that combining events and frames can overcome failure cases of NeRF estimation in scenarios where only a few input views are available without requiring additional regularization.