论文标题
固有点云通过双潜在空间导航
Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
论文作者
论文摘要
我们提出了一种基于学习的方法，用于插值和操纵为点云表示的3D形状，该方法是明确设计的，旨在保留固有的形状属性。我们的方法基于构建双重编码空间，该空间可以使形状合成，同时提供了指向内在形状信息的链接，通常在点云数据上不可用。我们的方法可以单独使用，并避免了现有技术采用的昂贵优化。此外，我们的双重潜在空间方法提供的强大正则化还有助于改善来自不同数据集的嘈杂点云的挑战性设置中的形状恢复。广泛的实验表明，与基准相比，我们的方法会导致更现实和更平滑的插值。
We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines.
