There are a lot of promising results in 3D recognition, including classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated real-world 3D data, which is highly time-consuming and expensive to obtain, limiting the scalability of 3D recognition tasks. Thus in this paper, we study unsupervised 3D recognition and propose a Self-supervised-Self-Labeled 3D Recognition (SL3D) framework. SL3D simultaneously solves two coupled objectives, i.e., clustering and learning feature representation to generate pseudo labeled data for unsupervised 3D recognition. SL3D is a generic framework and can be applied to solve different 3D recognition tasks, including classification, object detection, and semantic segmentation. Extensive experiments demonstrate its effectiveness. Code is available at https://github.com/fcendra/sl3d.

翻译：在三维识别方面有许多大有希望的结果,包括分类、物体探测和语义分割。然而,其中许多结果依靠人工收集密集的注解真实世界的三维数据,这些数据耗时费钱,限制了三维识别任务的可缩放性。因此,在本文件中,我们研究不受监督的三维识别,并提议一个自我监督的自我保密三维识别框架。 SL3D同时解决两个结合的目标,即集群和学习特征代表,为不受监督的三维识别生成假标签数据。 SL3D是一个通用框架,可用于解决不同的三维识别任务,包括分类、对象探测和语义分割。广泛的实验证明了其有效性。代码可在https://github.com/fcendra/sl3d查阅。