论文标题
meshMVS：多视图立体指导的网格重建
MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
论文作者
论文摘要
基于深度学习的3D形状生成方法通常利用从颜色图像中提取的潜在特征编码对象的语义并指导形状生成过程。这些彩色图像语义仅隐式编码3D信息，可能限制了生成形状的准确性。在本文中，我们提出了一种多视图网格生成方法，该方法通过使用多视图立体声的中间深度表示的特征并将3D形状正规化为这些深度图像，从而明确合并了几何信息。首先，我们的系统通过概率合并体voxel占用网格从单个视图的预测中概率合并，从颜色图像中预测了粗糙的3D体积。然后，来自多视图立体声的深度图像以及粗细的渲染深度图像被用作对比度输入，其特征通过一系列图形卷积网络指导粗大的细化。值得注意的是，我们取得了比最先进的多视图生成方法获得的优势结果，其倒角距离与地面真相的距离下降了34％，而Shapenet数据集的F1得分提高了14％。
Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process. These color image semantics only implicitly encode 3D information, potentially limiting the accuracy of the generated shapes. In this paper we propose a multi-view mesh generation method which incorporates geometry information explicitly by using the features from intermediate depth representations of multi-view stereo and regularizing the 3D shapes against these depth images. First, our system predicts a coarse 3D volume from the color images by probabilistically merging voxel occupancy grids from the prediction of individual views. Then the depth images from multi-view stereo along with the rendered depth images of the coarse shape are used as a contrastive input whose features guide the refinement of the coarse shape through a series of graph convolution networks. Notably, we achieve superior results than state-of-the-art multi-view shape generation methods with 34% decrease in Chamfer distance to ground truth and 14% increase in F1-score on ShapeNet dataset.Our source code is available at https://git.io/Jmalg
