E-BARF: Bundle Adjusting Neural Radiance Fields from a Moving Event Camera

Neural radiance field (NeRF) training typically requires high-quality images with precise camera poses. These images are often captured with stationary cameras under favorable lighting conditions. Such constraints limit the use of NeRF models in real-world scenarios. Event cameras, a novel neuromorphic vision sensor, can capture visual information with microsecond temporal resolution in challenging lighting conditions, overcoming conventional camera limitations. Recent research has proposed methods to construct NeRFs from fast-moving event cameras, enabling neural radiance field modeling with handheld cameras in high-dynamic-range environments. However, current methods still rely on precise camera poses as input. To obtain this information, these approaches resort to external sensors like motion capture systems, introducing additional complexities such as sensor synchronization, calibration, and increased device costs. While existing camera pose estimation algorithms could potentially replace external sensors, they lack the accuracy needed for high-quality NeRF synthesis, resulting in blurry and low-quality novel views. To address these challenges, we propose E-BARF, a method that simultaneously trains a NeRF model and adjusts the estimated camera poses. This approach achieves high-quality NeRF reconstruction without relying on external sensors, simplifying the NeRF creation process for event cameras.