cs.CVOct 29, 2026

Dreams Are Cheaper Than Flights: Curated World-Model Data Improves Aerial Detection

Authors: Rugved Katole, Vedant Patil, Jenna Kline, Christopher Stewart

Organizations: Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA

Abstract

Robot perception is increasingly data driven, yet field data is slow, costly, and sometimes disruptive to collect. Video world models offer a cheaper source: seeded with real frames, they extend a recorded scene into new footage with the deployment's sensor, altitude, and environment. We ask whether such synthetic data matches the utility of real field data and whether detectors trained with it perform in the field. Seeding a 7B-parameter world model with wildlife drone video, we more than double the training set with curated frames. On held-out videos from the same drones, mAP@50--95 rises 4.3% when these frames are added to real data and 10.3% when they replace it, and up to 33.5% on an urban benchmark. Although an expert rejects an estimated 87.5% of generated clips, the data costs about $1,100 of GPU time, against more than $3,200 of field labor alone for a less useful real training set. Synthetic data thus shifts data costs from fieldwork to compute.

Figures & tables

Explore similar work

CardsList
  1. Beyond Clear Skies: Synthetic Seasonal and Weather Variations for Real-World Drone Detection

    Aug 17, 2026Tamara R. Lenhard, Andreas Weinmann, Tobias KochAerial Object DetectionSynthetic Data Augmentation

  2. Training with synthetic data for drone detection in thermal imagery

    Aug 18, 2026Tanel Liiv, Sander Soodla, Nzamba Bignoumba +2Infrared Object DetectionSynthetic Data Pretraining

  3. Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models

    Jul 2, 2026Stanislav Panev, Minhyek Jeon, Vaishnavi Khindkar +5Synthetic Data AugmentationSynthetic Data Generation