Point cloud data have been widely explored due to its superior accuracy and robustness
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in
autonomous driving to allow a vehicle to act safely in its 3D environment. The best …

We propose a new self-supervised method for pre-training the backbone of deep perception
models operating on point clouds. The core idea is to train the model on a pretext task which …

The use of pretrained backbones with fine-tuning has been successful for 2D vision and
natural language processing tasks, showing advantages over task-specific networks. In this …

This paper advocates the use of implicit surface representation in autoencoder-based self-
supervised 3D representation learning. The most popular and accessible 3D representation …

With the growing availability of extensive 3D datasets and the rapid progress in
computational power, deep learning (DL) has emerged as a highly promising approach for …

We develop a novel self-supervised learning method named Shape Self-Correction for point
cloud analysis. Our method is motivated by the principle that a good shape representation …

Recently, the pre-training paradigm combining Transformer and masked language modeling
in BERT has achieved tremendous success not only in NLP, but also in images and point …

The manual annotation for large-scale point clouds costs a lot of time and is usually
unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training …

We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to
guide the feature learning of a point cloud neural network with a pre-trained image network …