High Fidelity 3D Reconstructions with Limited Physical Views
High Fidelity 3D Reconstructions with Limited Physical Views
复制标题
DOI：
10.1109/3dv53792.2021.00137
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Mosam Dabhi;Chaoyang Wang;Kunal Saluja;László A. Jeni;Ian R. Fasel;S. Lucey
中科院分区：
文献类型：
--
作者：
Mosam Dabhi;Chaoyang Wang;Kunal Saluja;László A. Jeni;Ian R. Fasel;S. Lucey
多视图三角测量是从已知校准和足够视图的2D对应进行3D重建的黄金标准。然而，在实践中，需要昂贵的多视图设置-涉及数十甚至数百个相机-以便获得许多现代应用所必需的高保真3D重建。在本文中，我们提出了一种新的方法，利用神经形状先验在2D-3D提升方面的最新进展，同时还执行多视图等方差。我们展示了我们的方法如何使用有限（2-3）数量的未校准相机视图实现与昂贵的校准多视图钻机相当的保真度。
Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences given known calibration and sufficient views. However in practice, expensive multi-view setups – involving tens sometimes hundreds of cameras – are required in order to obtain the high fidelity 3D reconstructions necessary for many modern applications. In this paper we present a novel approach that leverages recent advances in 2D-3D lifting using neural shape priors while also enforcing multi-view equivariance. We show how our method can achieve comparable fidelity to expensive calibrated multi-view rigs using a limited (2-3) number of uncalibrated camera views.