论文标题
GENSDF：可通用签名距离功能的两阶段学习
GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions
论文作者
论文摘要
我们研究了用于学习3D对象表示的神经签名距离函数（SDF）的概括功能，以了解未见和未标记的点云。现有方法可以将SDF拟合到少数几个对象类，并具有良好的细节或快速的推理速度，但不能很好地推广到看不见的形状。我们介绍了一种两阶段的半监督元学习方法，该方法从标记到未标记的数据转移了形状的先验，以重建看不见的对象类别。第一阶段使用情节训练方案模拟未标记的数据和元学习初始形状先验的训练。然后，第二阶段在半监督方案中引入了没有标记的数据，该数据具有不一致的类别，以使这些先验多样化并实现概括。我们评估合成数据和实际收集点云的方法。实验结果和分析验证了我们的方法表现优于现有的神经SDF方法，并且能够在100多个看不见的类别上进行稳健的零射击推断。代码可以在https://github.com/princeton-computational-imaging/gensdf上找到。
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.
