Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-09 · 46 (9) · 6263-6279
DOI: 10.1109/tpami.2024.3381710 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-09. Verfasst von Xiaoxiao Long und 8 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 66 Literaturangaben.
Abstract (Originalsprache)
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to accurately enforce the consistency between the different geometric properties, thereby leading to a bottleneck of geometric estimation quality. We therefore propose the Adaptive Surface Normal (ASN) constraint, a simple yet efficient method. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. By dynamically determining reliable local geometry from randomly sampled candidates, we establish a surface normal constraint, where the validity of these candidates is evaluated using the geometric context. Furthermore, our normal estimation leverages the geometric context to prioritize regions that exhibit significant geometric variations, which makes the predicted normals accurately capture intricate and detailed geometric information. Through the integration of geometric context, our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images. We validate the superiority of our approach over state-of-the-art methods through extensive evaluations and comparisons on diverse indoor and outdoor datasets, showcasing its efficiency and robustness.
Zitieren
APA
Long, X., Zheng, Y., Zheng, Y., Tian, B., Lin, C., Liu, L., Zhao, H., Zhou, G., & Wang, W. (2024). Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(9), 6263-6279. https://doi.org/10.1109/tpami.2024.3381710
Vancouver
Long X, Zheng Y, Zheng Y, Tian B, Lin C, Liu L, et al. Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(9):6263-6279. doi:10.1109/tpami.2024.3381710
BibTeX
@article{Long2024,
author = {Long, Xiaoxiao and Zheng, Yuhang and Zheng, Yupeng and Tian, Beiwen and Lin, Cheng and Liu, Lingjie and Zhao, Hao and Zhou, Guyue and Wang, Wenping},
title = {Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {9},
pages = {6263--6279},
doi = {10.1109/tpami.2024.3381710}
}
EUVIMED