E-NeRF: Neural Radiance Fields from a Moving Event Camera
This addresses a critical issue for robotics applications, such as navigation and inspection, by enabling robust 3D scene reconstruction in dynamic, low-light environments, representing a novel domain-specific advancement.
The paper tackles the problem of estimating neural radiance fields (NeRFs) in challenging conditions like fast motion and poor illumination, where traditional frame-based methods fail, by introducing E-NeRF, which uses event camera data to recover high-quality NeRFs and outperforms state-of-the-art approaches under severe motion blur.
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.