神经部分：使用可逆神经网络学习表达性3D形状抽象
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
摘要：
令人印象深刻的进展，在3D形状提取导致表示，可以捕捉对象的几何形状与高保真度。并行地，基于连续性的方法寻求将对象表示为语义上一致的部件布置。然而，由于现有的图元表示的简单性，这些方法无法使用少量的图元/部分来准确地重建3D形状。我们解决了重建质量和神经部分，一种新的3D图元表示，使用可逆神经网络（INN），实现球和目标对象之间的同胚映射定义图元的零件数量之间的权衡。INN允许我们计算同胚的逆映射，这反过来又使基元及其网格的隐式曲面函数的有效计算成为可能，而无需任何额外的后处理。我们的模型学习将3D对象解析为语义一致的部件排列，而无需任何部件级监督。ShapeNet，D-FAUST和FreiHAND上的评估表明，我们的图元可以捕获复杂的几何形状，从而同时实现几何准确性以及可解释的重建，使用数量级比最先进的形状抽象方法少的图元。
英文摘要：
Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to the simplicity of existing primitive representations, these methods fail to accurately reconstruct 3D shapes using a small number of primitives/parts. We address the trade-off between reconstruction quality and number of parts with Neural Parts, a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) which implements homeomorphic mappings between a sphere and the target object. The INN allows us to compute the inverse mapping of the homeomorphism, which in turn, enables the efficient computation of both the implicit surface function of a primitive and its mesh, without any additional post-processing. Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision. Evaluations on ShapeNet, D-FAUST and FreiHAND demonstrate that our primitives can capture complex geometries and thus simultaneously achieve geometrically accurate as well as interpretable reconstructions using an order of magnitude fewer primitives than state-of-the-art shape abstraction methods.
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。
