{"ID":2840689,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.13552","arxiv_id":"2511.13552","title":"TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Images","abstract":"Monocular height estimation plays a critical role in 3D perception for remote sensing, offering a cost-effective alternative to multi-view or LiDAR-based methods. While deep learning has significantly advanced the capabilities of monocular height estimation, these methods remain fundamentally limited by the availability of labeled data, which are expensive and labor-intensive to obtain at scale. The scarcity of high-quality annotations hinders the generalization and performance of existing models. To overcome this limitation, we propose leveraging large volumes of unlabeled data through a semi-supervised learning framework, enabling the model to extract informative cues from unlabeled samples and improve its predictive performance. In this work, we introduce TSE-Net, a self-training pipeline for semi-supervised monocular height estimation. The pipeline integrates teacher, student, and exam networks. The student network is trained on unlabeled data using pseudo-labels generated by the teacher network, while the exam network functions as a temporal ensemble of the student network to stabilize performance. The teacher network is formulated as a joint regression and classification model: the regression branch predicts height values that serve as pseudo-labels, and the classification branch predicts height value classes along with class probabilities, which are used to filter pseudo-labels. Height value classes are defined using a hierarchical bi-cut strategy to address the inherent long-tailed distribution of heights, and the predicted class probabilities are calibrated with a Plackett-Luce model to reflect the expected accuracy of pseudo-labels. We evaluate the proposed pipeline on three datasets spanning different resolutions and imaging modalities. Codes are available at https://github.com/zhu-xlab/tse-net.","short_abstract":"Monocular height estimation plays a critical role in 3D perception for remote sensing, offering a cost-effective alternative to multi-view or LiDAR-based methods. While deep learning has significantly advanced the capabilities of monocular height estimation, these methods remain fundamentally limited by the availabilit...","url_abs":"https://arxiv.org/abs/2511.13552","url_pdf":"https://arxiv.org/pdf/2511.13552v1","authors":"[\"Sining Chen\",\"Xiao Xiang Zhu\"]","published":"2025-11-17T16:22:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606992,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2840689,"paper_url":"https://arxiv.org/abs/2511.13552","paper_title":"TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Images","repo_url":"https://github.com/zhu-xlab/tse-net","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}