Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones

TL;DR

This work presents a unified framework that leverages asynchronous event streams alongside motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights and preserves fine scene details, delivering a performance gain of over 50% on real-world data compared to state-of-the-art methods.

Abstract

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.

Figures (8)

• Figure 1: Our system recovers sharp geometry and texture from footage captured by a drone flying at 2 m/s, learning a neural radiance field directly from motion-blurred images and event data collected during flight (top). Without relying on ground-truth poses or external motion capture, it refines the drone’s trajectory during training, starting from a rough visual-inertial odometry prior. Once optimized, the model can render photorealistic views from novel perspectives (bottom), paving the way for high-speed, vision-based inspection tasks in agile robotics.
• Figure 2: Overview of our proposed architecture. We reconstruct a sharp radiance field from a set of motion-blurred RGB frames and events. The estimated trajectory from an event-based SLAM system, $T_{init}$, is refined through a learned Pose Refiner that takes a query timestamp $t$ as input and predicts residual corrections at arbitrary time resolutions. This refined trajectory is used to supervise the radiance field through three complementary branches: a blur branch models image formation across the exposure time; an event branch supervises high-temporal-resolution brightness changes via a learned event camera response function; and a prior branch introduces model-based deblur constraints. All branches share the same learned camera trajectory, allowing events and images to jointly refine the scene representation and motion estimates.
• Figure 3: Data collection setup. A beamsplitter with an RGB and an event camera is attached to a quadrotor platform.
• Figure 4: Factory (top) and Trolley (bottom) trajectory analysis on NoisyPose-EvDeblurBlender at noise level 4. We present the change of trajectory errors with traveled distance (left), for both translation (meters and percentage) and rotation (degrees and degrees per meter), along with a visual comparison of the trajectories (right).
• Figure 5: Novel view synthesis comparison on the Ev-DeblurCDAVIS dataset.