We investigate the generalization capabilities of neural signed distance functions (SDFs) for learning 3D object representations for unseen and unlabeled point clouds. Existing methods can fit SDFs to a handful of object classes and boast fine detail or fast inference speeds, but do not generalize well to unseen shapes. We introduce a two-stage semi-supervised meta-learning approach that transfers shape priors from labeled to unlabeled data to reconstruct unseen object categories. The first stage uses an episodic training scheme to simulate training on unlabeled data and meta-learns initial shape priors. The second stage then introduces unlabeled data with disjoint classes in a semi-supervised scheme to diversify these priors and achieve generalization. We assess our method on both synthetic data and real collected point clouds. Experimental results and analysis validate that our approach outperforms existing neural SDF methods and is capable of robust zero-shot inference on 100+ unseen classes. Code can be found at https://github.com/princeton-computational-imaging/gensdf.
翻译:我们调查了神经签名远程函数(SDFs)的通用能力,用于学习隐形和未贴标签点云的 3D 对象表达方式。 现有方法可以将 SDFs 安装到少数对象类别, 并具有细细的细节或快速推断速度, 但不能对不可见的形状进行概括化。 我们引入了两阶段半监督的元学习方法, 将先前的标签数据从标签数据转换为无标签数据, 以重建不可见物体类别。 第一阶段使用非常规培训计划, 模拟关于未贴标签数据的培训, 以及元 Learns 初始形状的形状 。 第二阶段后将无标签数据与脱节的分类引入半监督的系统, 以使这些前科多样化并实现普遍性。 我们评估了合成数据和实际收集的点云的方法。 实验结果和分析证实, 我们的方法已经超越了现有的神经 SDFF 方法, 并且能够在100+ 不可见的类别上进行强力的零点推断 。 代码可在 https://github.com/princenttonton-computationalational- imputationalging/genfing.