Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a single global vector or of multiple local ones. The latter allows more flexibility but is prone to overfitting. In this paper, we advocate a hybrid approach representing shapes in terms of 3D meshes with a separate latent vector at each vertex. During training the latent vectors are constrained to have the same value, which avoids overfitting. For inference, the latent vectors are updated independently while imposing spatial regularization constraints. We show that this gives us both flexibility and generalization capabilities, which we demonstrate on several medical image processing tasks.
翻译:长期以来,人们都知道形状的前身在从吵闹或不完整的数据中重建 3D 形状时是有效的。在使用深层学习基于形状的形状表示法时,这往往涉及学习潜在的表示法,这种表示法可以是单一全球矢量的形式,也可以是多个局部矢量的形式。后者允许更大的灵活性,但容易过度适应。在本文中,我们提倡一种混合方法,代表3D 的形状,在每个顶点上都有单独的潜伏矢量。在培训潜在矢量时,其价值不同,避免过度适应。据推测,潜在矢量是独立更新的,同时施加空间规范限制。我们表明,这既给我们提供了灵活性,又提供了一般化能力,我们在几个医学图像处理任务上展示了这些灵活性和一般化能力。