cs.CVNov 5, 2026

FlyingDrones: A Dataset and Benchmark for Optical Flow Estimation from UAV motion

Authors: Laurenz Ruzicka, Roman Pflugfelder, Daniel Cremers

Organizations: Digital Safety and Security; Data Science and Artificial Intelligence; Austrian Institute of Technology · School of Computation, Information and Technology; Technical University of Munich; Munich Center for Machine Learning (MCML)

Abstract

Optical flow is an important cue for drone analysis in aerial surveillance, airspace monitoring, and long-range target tracking, where motion remains informative when appearance is weak. Estimating the motion of small Unmanned Aerial Vehicles, however, is difficult because distant targets occupy few pixels, have low contrast, and move against complex dynamic backgrounds. Standard optical-flow benchmarks emphasize large, object-centric motions and therefore do not characterize distant aerial targets well. We introduce FlyingDrones, a generated benchmark with dense ground-truth optical flow and segmentation masks derived from physically based rendering, and define resolution-normalized metrics (EPE Norm) that normalize flow by image dimensions. We evaluate 16 state-of-the-art model families on a motion- and size-stratified subset of 999 flow pairs at three resolutions. Every family recovers drone motion better than the zero-flow reference, but the gap between families widens with resolution: at 1920x1080, global-matching, recurrent, transformer, and short-window temporal models separate clearly from pyramid, classical, self-supervised, lightweight, and diffusion models. Within-family checkpoint spread is comparable to or larger than between-family spread, so the training curriculum is as important as the architecture. Two complementary studies test the benchmark beyond synthetic accuracy: a ground-truth-free motion-alignment evaluation on 21 cameras of real UAV footage shows that the synthetic ranking carries a moderate, significant signal about real-world performance (Spearman \r{ho} = 0.63 over 41 checkpoints) while the exact top ranks differ, and a fine-tuning study shows that 800 FlyingDrones pairs reduce held-out drone-region error by up to 37% and improve drone localization on the real footage for all four architectures tested.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. On the Real-World Generalisability of Optical Flow Models

    Jul 11, 2026Petter Reijalt, Sander Gielisse, Rickard Karlsson +1Optical Flow

  2. Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions

    Mar 6, 2026Jingtao Ye, Kexin Zhang, Xunchi Ma +6Multi-Object Tracking

  3. OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos

    Jun 24, 2026Oussema Dhaouadi, Zuria Bauer, Johannes Michael Meier +3UAV NavigationCamera Pose Estimation