论文标题
来自嘈杂的摄像机观察的神经隐式表面重建
Neural Implicit Surface Reconstruction from Noisy Camera Observations
论文作者
论文摘要
在过去的几年中，用神经辐射场代表3D对象和场景已经非常受欢迎。最近，已经提出了基于表面的表示，可以从简单照片中重建3D对象。但是，大多数当前技术都需要准确的相机校准，即与每个图像相对应的摄像机参数，这通常是在现实生活中很难完成的任务。为此，我们提出了一种从嘈杂的相机参数学习3D表面的方法。我们表明，我们可以学习相机参数以及学习表面表示，即使在嘈杂的相机观察中也可以展示高质量的3D表面重建。
Representing 3D objects and scenes with neural radiance fields has become very popular over the last years. Recently, surface-based representations have been proposed, that allow to reconstruct 3D objects from simple photographs. However, most current techniques require an accurate camera calibration, i.e. camera parameters corresponding to each image, which is often a difficult task to do in real-life situations. To this end, we propose a method for learning 3D surfaces from noisy camera parameters. We show that we can learn camera parameters together with learning the surface representation, and demonstrate good quality 3D surface reconstruction even with noisy camera observations.
