UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions
Open Access
- 30 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Abstract
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.Keywords
This publication has 18 references indexed in Scilit:
- Transformer-guided Feature Pyramid Network for Multi-View StereoNeurocomputing, 2024
- Feature distribution normalization network for multi-view stereoThe Visual Computer, 2024
- Large-scale aerial scene perception based on self-supervised multi-view stereo via cycled generative adversarial networkInformation Fusion, 2024
- A contrastive learning based unsupervised multi-view stereo with multi-stage self-training strategyDisplays, 2024
- ADR-MVSNet: A cascade network for 3D point cloud reconstruction with pixel occlusionPattern Recognition, 2022
- Point-Based Multi-View Stereo Network2019
- The connected-component labeling problem: A review of state-of-the-art algorithmsPattern Recognition, 2017
- Large-Scale Data for Multiple-View StereopsisInternational Journal of Computer Vision, 2016
- Massively Parallel Multiview Stereopsis by Surface Normal Diffusion2015
- Photorealistic Scene Reconstruction by Voxel ColoringInternational Journal of Computer Vision, 1999