Real-world aerial scene understanding is limited by a lack of datasets that contain densely annotated images curated under a diverse set of conditions. Due to inherent challenges in obtaining such images in controlled real-world settings, we present SkyScenes, a synthetic dataset of densely annotated aerial images captured from Unmanned Aerial Vehicle (UAV) perspectives. We carefully curate SkyScenes images from CARLA to comprehensively capture diversity across layouts (urban and rural maps), weather conditions, times of day, pitch angles and altitudes with corresponding semantic, instance and depth annotations. Through our experiments using SkyScenes, we show that (1) models trained on SkyScenes generalize well to different real-world scenarios, (2) augmenting training on real images with SkyScenes data can improve real-world performance, (3) controlled variations in SkyScenes can offer insights into how models respond to changes in viewpoint conditions (height and pitch), weather and time of day, and (4) incorporating additional sensor modalities (depth) can improve aerial scene understanding. Our dataset and associated generation code are publicly available at: https://hoffman-group.github.io/SkyScenes/
@article{arxiv.2312.06719,
title = {SkyScenes: A Synthetic Dataset for Aerial Scene Understanding},
author = {Sahil Khose and Anisha Pal and Aayushi Agarwal and Deepanshi and Judy Hoffman and Prithvijit Chattopadhyay},
journal= {arXiv preprint arXiv:2312.06719},
year = {2024}
}
Comments
Accepted at The 18th European Conference on Computer Vision ECCV 2024