Multi-View Stereo With Geometric Encoding for Large-Scale Dense Scene Reconstruction
- 9 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 22568-22586
Abstract
Multi-view stereo (MVS) implicitly encodes photometric and geometric cues into the cost volume for multi-view correspondence matching, transferring insufficient geometric cues essential to depth estimation and reconstruction. This paper proposes GE-MVS, a novel multi-view stereo network with geometric encoding for more accurate and complete depth estimation and point cloud reconstruction. First, the cross-view adaptive cost volume aggregation module is proposed to strengthen the encoding of multi-view geometric cues during cost volume construction. Then, the depth consistency optimization is performed in 3D point space during learning by invoking ground-truth depth cues from adjacent views. Finally, the surface normal geometries are explicitly encoded to refine the sampled depth hypotheses to be consistent in the local neighbor regions. Extensive experiments on the standard MVS benchmarks including DTU, Tanks and Temples, and BlendedMVS demonstrate the state-of-the-art depth estimation and point cloud reconstruction performance of GE-MVS. The GE-MVS is further deployed in real-world experiments for UAV-based large-scale reconstruction, where our method outperforms the prevalent industrial reconstruction solutions in terms of reconstruction efficiency and effectiveness. Supplementary video can be found at https://youtu.be/Z4tGROatVjU.Keywords
Funding Information
- Research Grants Council of Hong Kong, SAR (14206821, 14217922, 14209623)
- InnoHK Clusters of the Hong Kong SAR Government via Hong Kong Centre for Logistics Robotics
This publication has 65 references indexed in Scilit:
- Autonomous design framework for deploying building integrated photovoltaicsApplied Energy, 2024
- Vis-MVSNet: Visibility-Aware Multi-view Stereo NetworkInternational Journal of Computer Vision, 2022
- Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation2020
- Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking2020
- MVSNet: Depth Inference for Unstructured Multi-view Stereo2018
- OpenMVG: Open Multiple View Geometry2017
- Pixelwise View Selection for Unstructured Multi-View Stereo2016
- Large-Scale Data for Multiple-View StereopsisInternational Journal of Computer Vision, 2016
- Efficient large-scale multi-view stereo for ultra high-resolution image setsMachine Vision and Applications, 2011
- Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo2008