FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model

• URL: http://arxiv.org/abs/2605.19600v1
• Date: Tue, 19 May 2026 09:41:04 GMT
• Title: FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model
• Abstract summary: FlyMirage is a highly scalable and fully automated data generation pipeline for aerial VLN.<n>We generate a large-scale, diverse, and photorealistic aerial VLN dataset, with dynamically feasible flying trajectories.
• Score: 13.125579202955384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relying on either costly real-world scenes or visually limited simulations. To address these challenges, we introduce FlyMirage, a highly scalable and fully automated data generation pipeline for aerial VLN. Our approach leverages large language models (LLM) as an environment designer to promote scene diversity, paired with a generative world model that instantiates these designs into high-fidelity 3D Gaussian Splatting (3DGS) scenes. To substantially reduce human labor and ensure the feasibility of flight data, FlyMirage automates scene exploration and semantic information acquisition, and further integrates a dynamically feasible planner for uncrewed aerial vehicle (UAV) trajectory generation. Utilizing this toolchain, we generate a large-scale, diverse, and photorealistic aerial VLN dataset, with dynamically feasible flying trajectories, designed to support the development of next-generation embodied navigation models.

Related papers

• MotionScape: A Large-Scale Real-World Highly Dynamic UAV Video Dataset for World Models [6.680381992984212]
  We present MotionScape, a large-scale real-world UAVview video dataset with highly dynamic motion for world modeling.<n>MotionScape contains over 30 hours of 4K UAV-view videos, totaling more than 4.5M frames.<n>This novel dataset features semantically and geometrically aligned training samples, where diverse real-world UAV videos are tightly coupled with accurate 6-DoF camera trajectories and fine-grained natural language descriptions.
  arXiv  Detail & Related papers  (2026-04-09T08:59:40Z)
• Mirage2Matter: A Physically Grounded Gaussian World Model from Video [87.9732484393686]
  We present Simulate Anything, a graphics-driven world modeling and simulation framework.<n>Our approach reconstructs real-world environments into a photorealistic scene representation using 3D Gaussian Splatting (3DGS)<n>We then leverage generative models to recover a physically realistic representation and integrate it into a simulation environment via a precision calibration target.
  arXiv  Detail & Related papers  (2026-01-24T07:43:57Z)
• AirNav: A Large-Scale Real-World UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions [6.369522034276603]
  We propose AirNav, a large-scale UAV VLN benchmark constructed from real urban aerial data.<n>We also introduce the AirVLN-R1, which combines Supervised Fine-Tuning and Reinforcement Fine-Tuning to enhance performance and generalization.
  arXiv  Detail & Related papers  (2026-01-07T08:46:09Z)
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space [48.19308247102762]
  We propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions.<n> ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection.<n> Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments.
  arXiv  Detail & Related papers  (2025-12-26T06:22:39Z)
• UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data [47.317955428393134]
  We introduce UAV-MM3D, a high-fidelity multimodal synthetic dataset for low-altitude UAV perception and motion understanding.<n>It comprises 400K synchronized frames across diverse scenes (urban areas, suburbs, forests, coastal regions) and weather conditions.<n>Each frame provides 2D/3D bounding boxes, 6-DoF poses, and instance-level annotations, enabling core tasks related to UAVs such as 3D detection, pose estimation, target tracking, and short-term trajectory forecasting.
  arXiv  Detail & Related papers  (2025-11-27T12:30:28Z)
• Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles [16.745245388756533]
  Small Unmanned Aerial Vehicles (UAVs) exhibit immense potential for navigating indoor and hard-to-reach areas.<n>We introduce a novel system architecture that enables fully autonomous, high-fidelity 3D scanning of static objects using UAVs weighing under 100 grams.
  arXiv  Detail & Related papers  (2025-09-15T21:08:32Z)
• OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation [49.697035403548966]
  Vision-Language Navigation (VLN) aims to guide agents by leveraging language instructions and visual cues, playing a pivotal role in embodied AI.<n>We propose OpenFly, a platform comprising various rendering engines, a versatile toolchain, and a large-scale benchmark for aerial VLN.<n>We construct a large-scale aerial VLN dataset with 100k trajectories, covering diverse heights and lengths across 18 scenes.
  arXiv  Detail & Related papers  (2025-02-25T09:57:18Z)
• EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation [55.26713167507132]
  We introduce a generative robotics foundation model that constructs and interprets embodied spaces.<n>EnerVerse employs an autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning.<n>We present EnerVerse-D, a data engine pipeline combining the generative model with 4D Gaussian Splatting, forming a self-reinforcing data loop to reduce the sim-to-real gap.
  arXiv  Detail & Related papers  (2025-01-03T17:00:33Z)
• 3D-VLA: A 3D Vision-Language-Action Generative World Model [68.0388311799959]
  Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. We propose 3D-VLA by introducing a new family of embodied foundation models that seamlessly link 3D perception, reasoning, and action. Our experiments on held-in datasets demonstrate that 3D-VLA significantly improves the reasoning, multimodal generation, and planning capabilities in embodied environments.
  arXiv  Detail & Related papers  (2024-03-14T17:58:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.