EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A photorealistic synthetic stereo dataset with ground-truth depth and 6-DoF poses

Yan Medeiros Morona, Tiago Loureiro Figaro da Costa Pinto, Daniel Juchem Regner

Data in Brief · 2026-08 · 69 · 113222

DOI: 10.1016/j.dib.2026.113222 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data in Brief, 2026-08. Verfasst von Yan Medeiros Morona und 2 weiteren Autor:innen. Beteiligte Einrichtung: Federal University of Santa Catarina (UFSC), Department of Mechanical Engineering, Florianopolis, SC, Brazil. Die Arbeit nennt 9 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This data article presents a synthetic stereo vision dataset composed of synchronized RGB stereo images, ground-truth depth maps, and precise 6-DoF ground-truth poses generated using Unreal Engine 4 integrated with the AirSim simulation framework. Four indoor virtual scenes resembling industrial and enterprise-like environments were created, including structural elements such as pipes, pillars, walls, furniture, and occlusions. Multiple acquisition configurations were executed as closed-loop drone trajectories, resulting in a total of 36,838 stereo image pairs. The dataset includes multiple trajectory smoothness conditions, stereo baselines, and camera convergence configurations. All RGB images have a fixed resolution of 640 × 480 pixels and are provided alongside pixel-aligned depth maps and time-stamped ground-truth poses. The dataset also includes association files linking stereo images, depth maps, and poses, following formats commonly used in visual SLAM benchmarks. The acquisition is scripted and free of stochastic components, enabling benchmarking and development of stereo depth estimation, visual odometry, and SLAM algorithms under controlled and repeatable indoor conditions.

Schlagwörter

Stichwörter der Autor:innen

6-DoF trajectoryAirSimDepth ground truthSLAM benchmarkingStereo visionSynthetic datasetUnreal Engine

Autor:innen und Institutionen

  • Federal University of Santa Catarina (UFSC), Department of Mechanical Engineering, Florianopolis, SC, Brazil.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Zitieren

APA

Morona, Y. M., Pinto, T. L. F. D. C., & Regner, D. J. (2026). A photorealistic synthetic stereo dataset with ground-truth depth and 6-DoF poses. Data in Brief, 69, 113222. https://doi.org/10.1016/j.dib.2026.113222

Vancouver

Morona YM, Pinto TLFDC, Regner DJ. A photorealistic synthetic stereo dataset with ground-truth depth and 6-DoF poses. Data in Brief. 2026;69:113222. doi:10.1016/j.dib.2026.113222

BibTeX
@article{Morona2026,
  author = {Morona, Yan Medeiros and Pinto, Tiago Loureiro Figaro da Costa and Regner, Daniel Juchem},
  title = {A photorealistic synthetic stereo dataset with ground-truth depth and 6-DoF poses},
  journal = {Data in Brief},
  year = {2026},
  volume = {69},
  pages = {113222},
  doi = {10.1016/j.dib.2026.113222}
}
Kostenlos starten →