cs.RONov 19, 2026

AGE-Capture: Autonomous, General, and Efficient UAV Capture for High-Fidelity Scene Reconstruction

Authors: Xiaofeng Jin, Ningbo Bu, Matteo Frosi, Yiran Guo, Weilun Ren, Matteo Matteucci

Organizations: Politecnico di Milano · University of Chinese Academy of Sciences · Zhejiang University

Abstract

High-fidelity scene reconstruction with an unmanned aerial vehicle (UAV) requires more than identifying valuable viewpoints: the system must autonomously acquire informative observations and determine task completion under different sensing configurations and limited flight resources. We present AGE-Capture, an autonomous, sensor-adaptive, and efficient active-capture framework for real UAVs. Building on renderability, the framework uses a lightweight online state to evaluate the utility of candidate views, assess task progress, and guide flight execution. By decoupling geometric exploration from reconstruction observations and establishing a unified camera-ray interface, the framework allows different range sensors and RGB camera models to share a reconstruction-driven acquisition pipeline. Reconstruction-frontier viewpoints characterize residual acquisition value for region screening and autonomous termination; dynamics-aware hierarchical planning combined with asynchronous event-driven capture reduces unnecessary inter-region motion, time spent waiting for plans, and repeated observations. Across ten indoor and outdoor simulation scenes, AGE-Capture achieves a mean peak signal-to-noise ratio (PSNR) 3.303.30--3.53 dB3.53\,\mathrm{dB} higher than that of the online baselines while using 58.2%58.2\% of the common mission-time budget on average. Its mean peak GPU memory usage is 91.0%91.0\%--93.3%93.3\% lower than that of the same baselines. Experiments with different sensor configurations validate the adaptability of the shared acquisition pipeline, while flights in nine real-world scenes further demonstrate onboard closed-loop operation under practical computational and motion constraints.

Figures & tables

Explore similar work

CardsList
  1. Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles

    Sep 15, 2025Àlmos Veres-Vitàlyos, Filip Lemic, Daniel Johannes Bugelnig +5Aerial Robotics3D Reconstruction

  2. OpenFlyScan: A Quality-Guided Aerial Reconstruction System for Consumer Drones

    Sep 21, 2026Zhongrui You, Zhen Li, Junli Liu +23D Gaussian SplattingAerial Robotics

  3. Consensus Capture in Reference-Based UAV Video Stabilization: A Benchmark on Dynamic Urban Scenes

    Nov 12, 2026Robert Fonod, Nikolas GeroliminisFeature MatchingMulti-View Geometry