Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones
This addresses a critical challenge for drone applications like inspection and search-and-rescue by enabling high-fidelity 3D reconstruction under high-speed conditions, representing a strong domain-specific advancement.
The paper tackles the problem of dense 3D reconstruction from fast-flying drones, where motion blur and noisy pose estimates degrade Neural Radiance Fields (NeRFs), by proposing a unified framework that fuses event streams with motion-blurred frames to recover sharp radiance fields and accurate trajectories without ground-truth supervision, achieving over 50% performance gain on real-world data compared to state-of-the-art methods.
Fast-flying aerial robots promise rapid inspection under limited battery constraints, with direct applications in infrastructure inspection, terrain exploration, and search and rescue. However, high speeds lead to severe motion blur in images and induce significant drift and noise in pose estimates, making dense 3D reconstruction with Neural Radiance Fields (NeRFs) particularly challenging due to their high sensitivity to such degradations. In this work, we present a unified framework that leverages asynchronous event streams alongside motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights. By embedding event-image fusion into NeRF optimization and jointly refining event-based visual-inertial odometry priors using both event and frame modalities, our method recovers sharp radiance fields and accurate camera trajectories without ground-truth supervision. We validate our approach on both synthetic data and real-world sequences captured by a fast-flying drone. Despite highly dynamic drone flights, where RGB frames are severely degraded by motion blur and pose priors become unreliable, our method reconstructs high-fidelity radiance fields and preserves fine scene details, delivering a performance gain of over 50% on real-world data compared to state-of-the-art methods.