Related papers: AD-PT: Autonomous Driving Pre-Training with Large-…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Point cloud data has been extensively studied due to its compact form and flexibility in representing complex 3D structures. The ability of point cloud data to accurately capture and represent intricate 3D geometry makes it an ideal choice…

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 is the reconstruction of the surface on which the 3D…

The pre-training and fine-tuning paradigm has revolutionized satellite remote sensing applications. However, this approach remains largely underexplored for airborne laser scanning (ALS), an important technology for applications such as…

With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on…

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive,…

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia.…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation tasks involving 3D datasets that are often significantly…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this…

Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised…

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…

Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However, due to the unordered and non-uniform density characteristics of point clouds, it is non-trivial…

In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…

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 and fine-tuning paradigm in both vision and language tasks,…