Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic data may not generalize to practical scenarios, where point clouds are typically incomplete, non-uniformly distributed, and noisy. Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured. To this end, we propose an integrated scheme consisting of physically realistic synthesis of object point clouds via rendering stereo images via projection of speckle patterns onto CAD models and a novel quasi-balanced self-training designed for more balanced data distribution by sparsity-driven selection of pseudo labeled samples for long tailed classes. Experiment results can verify the effectiveness of our method as well as both of its modules for unsupervised domain adaptation on point cloud classification, achieving the state-of-the-art performance. Source codes and the SpeckleNet synthetic dataset are available at https://github.com/Gorilla-Lab-SCUT/QS3.
翻译:对对象点云进行语义分析,主要是通过发布基准数据集,包括从目标 CAD 模型取样的合成数据,来推动对对象点云进行语义分析。然而,从合成数据中学习可能不会概括到实际情景,因为点云通常不完全、不统一分布和吵闹。模拟到真实(Sim2Real)域间差距的这种挑战可以通过对域适应的学习算法来减轻;然而,我们认为,通过更实际更现实的投影法生成合成点云是一种强有力的替代方案,因为系统的非统一噪音模式可以被捕捉。为此,我们提议了一个综合计划,包括以物理上现实的方式合成对象点云,通过向 CAD 模型投射闪光图来显示立立立立音图像,并设计出一种新的准平衡的自我训练,通过宽度驱动选择长尾层的假贴标签样品来更均衡地传播数据。实验结果可以验证我们的方法的有效性,以及其用于在点云级分类上进行非超光化域适应的模块,从而实现状态-艺术性性能。源码码代码和Speckle-Uppor-LQ的合成数据可在 http://Scls/SG/SG/Q。