Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power. However, unlike polygon mesh-based templates, it remains a challenge to reason dense correspondences or other semantic relationships across shapes represented by DIFs, which limits its applications in texture transfer, shape analysis and so on. To overcome this limitation and also make DIFs more interpretable, we propose Deep Implicit Templates, a new 3D shape representation that supports explicit correspondence reasoning in deep implicit representations. Our key idea is to formulate DIFs as conditional deformations of a template implicit function. To this end, we propose Spatial Warping LSTM, which decomposes the conditional spatial transformation into multiple affine transformations and guarantees generalization capability. Moreover, the training loss is carefully designed in order to achieve high reconstruction accuracy while learning a plausible template with accurate correspondences in an unsupervised manner. Experiments show that our method can not only learn a common implicit template for a collection of shapes, but also establish dense correspondences across all the shapes simultaneously without any supervision.
翻译:深度隐含功能(DIFs)作为一种3D形状的外观代表形式,在3D视觉界中越来越受欢迎,因为它们的紧凑性和强烈的外观力量。然而,与基于多边网格的模板不同,在DIF代表的形状之间如何解释密集的通信或其他语义关系仍然是一项挑战,这限制了其在纹理传输、形状分析等方面的应用。为了克服这一限制,并使DIF更便于解释,我们提出了一个新的3D形状代表形式,它支持在深度隐含演示中进行明确的对应推理。我们的关键思想是将DIF制成一个模板隐含功能的有条件变形。我们为此提议将空间扭曲LSTM制解压缩成多形形形形形形形形变,保证其普遍化能力。此外,培训损失是精心设计的,目的是在学习一个有准确对应的直截然对应方式的合理模板的同时实现高度的重建准确性。实验表明,我们的方法不仅能够学习一个收集形状的共同的隐含模板,而且还可以同时建立所有形状的密集对应,而没有受到任何监督。