WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments
The International Journal of Robotics Research · 2025-04 · 44 (4) · 532-549
DOI: 10.1177/02783649241278369 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 20.09.2024. Verfasst von Kavisha Vidanapathirana und 10 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Recent progress in semantic scene understanding has primarily been enabled by the availability of semantically annotated bi-modal (camera and LiDAR) datasets in urban environments. However, such annotated datasets are also needed for natural, unstructured environments to enable semantic perception for applications, including conservation, search and rescue, environment monitoring, and agricultural automation. Therefore, we introduce WildScenes , a bi-modal benchmark dataset consisting of multiple large-scale, sequential traversals in natural environments, including semantic annotations in high-resolution 2D images and dense 3D LiDAR point clouds, and accurate 6-DoF pose information. The data is (1) trajectory-centric with accurate localization and globally aligned point clouds, (2) calibrated and synchronized to support bi-modal training and inference, and (3) containing different natural environments over 6 months to support research on domain adaptation. Our 3D semantic labels are obtained via an efficient, automated process that transfers the human-annotated 2D labels from multiple views into 3D point cloud sequences, thus circumventing the need for expensive and time-consuming human annotation in 3D. We introduce benchmarks on 2D and 3D semantic segmentation and evaluate a variety of recent deep-learning techniques to demonstrate the challenges in semantic segmentation in natural environments. We propose train-val-test splits for standard benchmarks as well as domain adaptation benchmarks and utilize an automated split generation technique to ensure the balance of class label distributions. The WildScenes benchmark webpage is https://csiro-robotics.github.io/WildScenes , and the data is publicly available at https://data.csiro.au/collection/csiro:61541 .
Zitieren
APA
Vidanapathirana, K., Knights, J., Hausler, S., Cox, M., Ramezani, M., Jooste, J., Griffiths, E., Mohamed, S., Sridharan, S., Fookes, C., & Moghadam, P. (2025). WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments. The International Journal of Robotics Research, 44(4), 532-549. https://doi.org/10.1177/02783649241278369
Vancouver
Vidanapathirana K, Knights J, Hausler S, Cox M, Ramezani M, Jooste J, et al. WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments. The International Journal of Robotics Research. 2025;44(4):532-549. doi:10.1177/02783649241278369
BibTeX
@article{Vidanapathirana2025,
author = {Vidanapathirana, Kavisha and Knights, Joshua and Hausler, Stephen and Cox, Mark and Ramezani, Milad and Jooste, Jason and Griffiths, Ethan and Mohamed, Shaheer and Sridharan, Sridha and Fookes, Clinton and Moghadam, Peyman},
title = {WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments},
journal = {The International Journal of Robotics Research},
year = {2025},
volume = {44},
number = {4},
pages = {532--549},
doi = {10.1177/02783649241278369}
}
EUVIMED