基于黎曼度量保持的可变形曲面重构
Deformable Surface Reconstruction via Riemannian Metric Preservation
摘要：
从单目图像中估计物体的姿态是计算机视觉中的基本逆问题。这个问题的不适定性质需要结合变形先验来解决它。在实践中，许多材料在操纵时不会明显收缩或延伸，这构成了一个强大而众所周知的先验。在数学上，这转化为黎曼度量的保持。神经网络提供了一个完美的操场来解决表面重建问题，因为它们可以近似表面与任意精度，并允许计算微分几何量。本文提出了一种从图像序列中推断连续可变形表面的方法，该方法以几种技术为基准，并且在不需要离线训练的情况下获得了最先进的性能。
英文摘要：
Estimating the pose of an object from a monocular image is an inverse problem fundamental in computer vision. The ill-posed nature of this problem requires incorporating deformation priors to solve it. In practice, many materials do not perceptibly shrink or extend when manipulated, constituting a powerful and well-known prior. Mathematically, this translates to the preservation of the Riemannian metric. Neural networks offer the perfect playground to solve the surface reconstruction problem as they can approximate surfaces with arbitrary precision and allow the computation of differential geometry quantities. This paper presents an approach to inferring continuous deformable surfaces from a sequence of images, which is benchmarked against several techniques and obtains state-of-the-art performance without the need for offline training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
