UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.10.2026
DOI: 10.1145/3861002 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 30.10.2026. Verfasst von Mingwei Cao und 5 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben.
Abstract (Originalsprache)
Deep learning-based multi-view stereo (MVS) techniques have advanced substantially in recent years. However, because large-scale, annotated datasets are limited, interest has grown in unsupervised MVS methods that do not require ground-truth depth. One primary challenge for these unsupervised approaches is handling occluded regions, as they rely on photometric consistency. To address these issues, we propose Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions (UMVS). Our UMVS comprises three core modules. First, a feature-level perceptual consistency module minimizes reconstruction errors by comparing high-level semantic feature disparities across images. Second, a structured occlusion-generation module improves depth estimation accuracy and completeness by generating augmented samples tailored for contrastive learning. Third, the DLA-Net module serves as a normalization component to overcome the limitations of a narrow receptive field. By aggregating global contextual information, DLA-Net improves depth map estimation accuracy. We evaluated the proposed UMVS on the DTU and Tanks & Temples datasets, and the results demonstrate its effectiveness and superiority.
Zitieren
APA
Cao, M., Wang, Q., Li, N., Zhao, H., Xue, F., & Lyu, Z. (2026). UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/3861002
Vancouver
Cao M, Wang Q, Li N, Zhao H, Xue F, Lyu Z. UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026. doi:10.1145/3861002
BibTeX
@article{Cao2026,
author = {Cao, Mingwei and Wang, Qiuju and Li, Ning and Zhao, Haifeng and Xue, Feng and Lyu, Zhihan},
title = {UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
doi = {10.1145/3861002}
}
EUVIMED