Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 12528-12537Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.01232
Keywords
-
Funding
- Centre of Perceptual and Interactive Intelligence, CUHK Agreement [TS1712093]
- General Research Fund (GRF) of Hong Kong [14205719]
- Theme-based Research Scheme [T41-603/20-R]
- National Natural Science Foundation of China [61922065, 61771350, 41820104006]
Ask authors/readers for more resources
This study presents a novel method for 3D building reconstruction from monocular remote sensing imagery, which improves height estimation performance and segmentation F1-score by designing a multi-task building reconstruction network and utilizing prior knowledge for optimization, suitable for more complex remote sensing image scenarios.
3D building reconstruction from monocular remote sensing imagery is an important research problem and an economic solution to large-scale city modeling, compared with reconstruction from LiDAR data and multi-view imagery. However, several challenges such as the partial invisibility of building footprints and facades, the serious shadow effect, and the extreme variance of building height in large-scale areas, have restricted the existing monocular image based building reconstruction studies to certain application scenes, i.e., modeling simple low-rise buildings from near-nadir images. In this study, we propose a novel 3D building reconstruction method for monocular remote sensing images, which tackles the above difficulties, thus providing an appealing solution for more complicated scenarios. We design a multi-task building reconstruction network, named MTBR-Net, to learn the geometric property of oblique images, the key components of a 3D building model and their relations via four semantic-related and three offset-related tasks. The network outputs are further integrated by a prior knowledge based 3D model optimization method to produce the the final 3D building models. Results on a public 3D reconstruction dataset and a novel released dataset demonstrate that our method improves the height estimation performance by over 40% and the segmentation F1-score by 2% - 4% compared with current state-of-the-art.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available