论文标题
m^3vsnet：无监督的多项式多视线立体网络
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
论文作者
论文摘要
与传统的MVS方法相比，具有监督基于学习的网络的当前多视图立体声（MVS）方法具有令人印象深刻的性能。但是，很难获得用于培训的基础深度图，并且处于有限种类的情况下。在本文中，我们提出了一个新颖的无监督的多米数MVS网络，名为M^3vsnet，用于密集的点云重建，而无需任何监督。为了提高点云重建的鲁棒性和完整性，我们提出了一种新型的多金属损耗函数，该功能结合了像素方面和特征损耗函数，以从匹配对应关系的不同角度学习固有的约束。此外，我们还以3D点云格式结合了正常的深度一致性，以提高估计深度图的准确性和连续性。实验结果表明，M3VSNET建立了最新的无监督方法，并与以前的DTU数据集上的先前监督MVSNET相当地表现了可比性的性能，并证明了对坦克和神庙标准的强大概括能力，并有效改进。我们的代码可在https://github.com/whubaichuan/m3vsnet上找到
The present Multi-view stereo (MVS) methods with supervised learning-based networks have an impressive performance comparing with traditional MVS methods. However, the ground-truth depth maps for training are hard to be obtained and are within limited kinds of scenarios. In this paper, we propose a novel unsupervised multi-metric MVS network, named M^3VSNet, for dense point cloud reconstruction without any supervision. To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences. Besides, we also incorporate the normal-depth consistency in the 3D point cloud format to improve the accuracy and continuity of the estimated depth maps. Experimental results show that M3VSNet establishes the state-of-the-arts unsupervised method and achieves comparable performance with previous supervised MVSNet on the DTU dataset and demonstrates the powerful generalization ability on the Tanks and Temples benchmark with effective improvement. Our code is available at https://github.com/whubaichuan/M3VSNet
