This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity. Our SPA-VAE infers a set of latent canonical candidate shapes for any given object, along with a set of rigid body transformations for each such candidate shape to one or more locations within the assembled object. In this way, noisy samples on the surface of, say, each leg of a table, are effectively combined to estimate a single leg prototype. When parts-based self-similarity exists in the raw data, sharing data among parts in this way confers numerous advantages: modeling accuracy, appropriately self-similar generative outputs, precise in-filling of occlusions, and model parsimony. SPA-VAE is trained end-to-end using a variational Bayesian approach which uses the Gumbel-softmax trick for the shared part assignments, along with various novel losses to provide appropriate inductive biases. Quantitative and qualitative analyses on ShapeNet demonstrate the advantage of SPA-VAE.
翻译:本文探讨的是未受监督的零配件感知点云层生成问题,其原始数据中存在基于部件的自相类似之处,因此,我们的SPA-VAE为任何特定天体推断出一套潜在的隐性阴性候选形状,同时为每个这种候选形状向组装物体内的一个或多个位置进行一系列僵硬的体形变换。这样,表的每条腿表面的杂乱样品就有效地组合在一起,以估计一个单一腿原型。当原始数据中存在基于部件的自相类似之处时,各部分之间以这种方式分享数据具有许多好处:建模精度、适当的自异基因输出、精确填充封闭物和模型等。SPA-VAE采用变式贝氏方法,利用古姆贝尔-软形魔术进行共享部分任务,加上各种新的损失,以提供适当的诱导偏差。关于ShapeNet的定量和定性分析显示了SPA-VAE的优势。