Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Sijie, Li, Siqi, Zhang, Yawei, Yu, Shangshu, Yuan, Shenghai, She, Rui, Guo, Quanjiang, Zheng, JinXuan, Howe, Ong Kang, Chandra, Leonrich, Srijeyan, Shrivarshann, Sivadas, Aditya, Aggarwal, Toshan, Liu, Heyuan, Zhang, Hongming, Chen, Chujie, Jiang, Junyu, Xie, Lihua, Tay, Wee Peng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.22412
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918107654651904
author Wang, Sijie
Li, Siqi
Zhang, Yawei
Yu, Shangshu
Yuan, Shenghai
She, Rui
Guo, Quanjiang
Zheng, JinXuan
Howe, Ong Kang
Chandra, Leonrich
Srijeyan, Shrivarshann
Sivadas, Aditya
Aggarwal, Toshan
Liu, Heyuan
Zhang, Hongming
Chen, Chujie
Jiang, Junyu
Xie, Lihua
Tay, Wee Peng
author_facet Wang, Sijie
Li, Siqi
Zhang, Yawei
Yu, Shangshu
Yuan, Shenghai
She, Rui
Guo, Quanjiang
Zheng, JinXuan
Howe, Ong Kang
Chandra, Leonrich
Srijeyan, Shrivarshann
Sivadas, Aditya
Aggarwal, Toshan
Liu, Heyuan
Zhang, Hongming
Chen, Chujie
Jiang, Junyu
Xie, Lihua
Tay, Wee Peng
contents Multi-modal perception is essential for unmanned aerial vehicle (UAV) operations, as it enables a comprehensive understanding of the UAVs' surrounding environment. However, most existing multi-modal UAV datasets are primarily biased toward localization and 3D reconstruction tasks, or only support map-level semantic segmentation due to the lack of frame-wise annotations for both camera images and LiDAR point clouds. This limitation prevents them from being used for high-level scene understanding tasks. To address this gap and advance multi-modal UAV perception, we introduce UAVScenes, a large-scale dataset designed to benchmark various tasks across both 2D and 3D modalities. Our benchmark dataset is built upon the well-calibrated multi-modal UAV dataset MARS-LVIG, originally developed only for simultaneous localization and mapping (SLAM). We enhance this dataset by providing manually labeled semantic annotations for both frame-wise images and LiDAR point clouds, along with accurate 6-degree-of-freedom (6-DoF) poses. These additions enable a wide range of UAV perception tasks, including segmentation, depth estimation, 6-DoF localization, place recognition, and novel view synthesis (NVS). Our dataset is available at https://github.com/sijieaaa/UAVScenes
format Preprint
id arxiv_https___arxiv_org_abs_2507_22412
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UAVScenes: A Multi-Modal Dataset for UAVs
Wang, Sijie
Li, Siqi
Zhang, Yawei
Yu, Shangshu
Yuan, Shenghai
She, Rui
Guo, Quanjiang
Zheng, JinXuan
Howe, Ong Kang
Chandra, Leonrich
Srijeyan, Shrivarshann
Sivadas, Aditya
Aggarwal, Toshan
Liu, Heyuan
Zhang, Hongming
Chen, Chujie
Jiang, Junyu
Xie, Lihua
Tay, Wee Peng
Computer Vision and Pattern Recognition
Multi-modal perception is essential for unmanned aerial vehicle (UAV) operations, as it enables a comprehensive understanding of the UAVs' surrounding environment. However, most existing multi-modal UAV datasets are primarily biased toward localization and 3D reconstruction tasks, or only support map-level semantic segmentation due to the lack of frame-wise annotations for both camera images and LiDAR point clouds. This limitation prevents them from being used for high-level scene understanding tasks. To address this gap and advance multi-modal UAV perception, we introduce UAVScenes, a large-scale dataset designed to benchmark various tasks across both 2D and 3D modalities. Our benchmark dataset is built upon the well-calibrated multi-modal UAV dataset MARS-LVIG, originally developed only for simultaneous localization and mapping (SLAM). We enhance this dataset by providing manually labeled semantic annotations for both frame-wise images and LiDAR point clouds, along with accurate 6-degree-of-freedom (6-DoF) poses. These additions enable a wide range of UAV perception tasks, including segmentation, depth estimation, 6-DoF localization, place recognition, and novel view synthesis (NVS). Our dataset is available at https://github.com/sijieaaa/UAVScenes
title UAVScenes: A Multi-Modal Dataset for UAVs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.22412