THE benchmark: Transferable representation learning for monocular height estimation

Z Xiong, W Huang, J Hu, XX Zhu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Generating 3-D city models rapidly is crucial for many applications. Monocular height
estimation (MHE) is one of the most efficient and timely ways to obtain large-scale geometric …

3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions

W Li, H Yang, Z Hu, J Zheng… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D building reconstruction from monocular remote sensing images is an important
and challenging research problem that has received increasing attention in recent years …

Synrs3d: A synthetic dataset for global 3d semantic understanding from monocular remote sensing imagery

J Song, H Chen, W Xuan, J Xia, N Yokoya - arXiv preprint arXiv …, 2024 - arxiv.org
Global semantic 3D understanding from single-view high-resolution remote sensing (RS)
imagery is crucial for Earth Observation (EO). However, this task faces significant challenges …

Self-Supervised Pre-Training with Monocular Height Estimation for Semantic Segmentation

Z Xiong, S Chen, Y Shi, XX Zhu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Monocular height estimation (MHE) is key for generating 3-D city models, essential for swift
disaster response. Moving beyond the traditional focus on performance enhancement, our …

Handling image and label resolution mismatch in remote sensing

S Workman, A Hadzic… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Though semantic segmentation has been heavily explored in vision literature, unique
challenges remain in the remote sensing domain. One such challenge is how to handle …

Weakly-supervised 3D Building Reconstruction from Monocular Remote Sensing Images

W Li, Z Hu, L Meng, J Wang, J Zheng… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
3-D building reconstruction from monocular remote sensing imagery is an important
research problem that has been extensively studied for several decades. Although …

Disentangled latent transformer for interpretable monocular height estimation

Z Xiong, S Chen, Y Shi, XX Zhu - arXiv preprint arXiv:2201.06357, 2022 - arxiv.org
Monocular height estimation (MHE) from remote sensing imagery has high potential in
generating 3D city models efficiently for a quick response to natural disasters. Most existing …

HTC-DC Net: Monocular Height Estimation From Single Remote Sensing Images

S Chen, Y Shi, Z Xiong, XX Zhu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Three-dimensional geoinformation is of great significance for understanding the living
environment; however, 3-D perception from remote sensing data, especially on a large …

LIE-DSM: Leveraging Single Remote Sensing Imagery to Enhance Digital Surface Model Resolution

Z Siyuan, D Jingxian, TB Kabika… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
Digital surface models (DSMs) have numerous valuable applications in infrastructure and
industrial development. However, the spatial resolutions of DSMs are often limited due to …

Impact of architecture on robustness and interpretability of multispectral deep neural networks

C Godfrey, E Bishoff, M McKay, E Byler - arXiv preprint arXiv:2309.12463, 2023 - arxiv.org
Including information from additional spectral bands (eg, near-infrared) can improve deep
learning model performance for many vision-oriented tasks. There are many possible ways …