论文标题
SERP：使用扰动点云的自我监督表示学习
SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
论文作者
论文摘要
我们提出SERP，这是3D点云的自我监督学习的框架。 SERP由编码器架构组成，该体系结构将被扰动或损坏的点云作为输入和旨在重建原始点云而无需损坏。编码器在低维子空间中学习了点云的高级潜在表示，并恢复了原始结构。在这项工作中，我们使用了基于变压器和基于点网的自动编码器。所提出的框架还解决了基于变形金刚的掩盖自动编码器的一些局限性，这些框架容易泄漏位置信息和不均匀的信息密度。我们在完整的Shapenet数据集上训练了模型，并将它们作为下游分类任务评估。我们已经表明，审计的模型比从头开始训练的网络实现了0.5-1％的分类精度。此外，我们还提出了VASP：对矢量定量的自动编码器，用于对点云进行自我监督的表示学习，这些学习对基于变压器的自动编码器的离散表示学习采用了矢量定量化。
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without corruption. The encoder learns the high-level latent representations of the points clouds in a low-dimensional subspace and recovers the original structure. In this work, we have used Transformers and PointNet-based Autoencoders. The proposed framework also addresses some of the limitations of Transformers-based Masked Autoencoders which are prone to leakage of location information and uneven information density. We trained our models on the complete ShapeNet dataset and evaluated them on ModelNet40 as a downstream classification task. We have shown that the pretrained models achieved 0.5-1% higher classification accuracies than the networks trained from scratch. Furthermore, we also proposed VASP: Vector-Quantized Autoencoder for Self-supervised Representation Learning for Point Clouds that employs Vector-Quantization for discrete representation learning for Transformer-based autoencoders.
