We present ANISE, a method that reconstructs a 3D shape from partial observations (images or sparse point clouds) using a part-aware neural implicit shape representation. It is formulated as an assembly of neural implicit functions, each representing a different shape part. In contrast to previous approaches, the prediction of this representation proceeds in a coarse-to-fine manner. Our network first predicts part transformations which are associated with part neural implicit functions conditioned on those transformations. The part implicit functions can then be combined into a single, coherent shape, enabling part-aware shape reconstructions from images and point clouds. Those reconstructions can be obtained in two ways: (i) by directly decoding combining the refined part implicit functions; or (ii) by using part latents to query similar parts in a part database and assembling them in a single shape. We demonstrate that, when performing reconstruction by decoding part representations into implicit functions, our method achieves state-of-the-art part-aware reconstruction results from both images and sparse point clouds. When reconstructing shapes by assembling parts queried from a dataset, our approach significantly outperforms traditional shape retrieval methods even when significantly restricting the size of the shape database. We present our results in well-known sparse point cloud reconstruction and single-view reconstruction benchmarks.
翻译:我们提出 ANISE, 这是一种利用部分观测( 图像或稀有点云) 重建 3D 形状的方法, 该方法使用部分觉悟神经隐含形状的表示方式, 将3D 形状从部分观察( 图像或稀有点云) 重建为 部分觉悟神经隐含形状 。 它是一个由部分神经隐含功能组成的集合, 代表不同的形状 。 与以前的方法不同, 对这种表示方式的预测以粗略方式进行。 我们的网络首先预测与部分神经隐含功能相关的部分变化 。 然后, 部分隐含功能可以合并成一个单一的、 连贯的形状, 使部分觉悟从图像和点云中重建。 这些重建可以通过以下两种方式进行:( 一) 直接解码, 将精细的隐含形状合并成一个不同的形状 。 或者 (二) 利用部分隐含的隐含功能来查询一个部分的类似部分的数据库, 并将它们合并成一个单一形状。 我们证明, 当通过将部分隐含的显示部分的表示为隐含的功能进行重建时, 我们的方法从已知的图象和稀薄点重建时,, 我们的重建的方式大大地改变了了 的蓝图的形状。