X Yu, L Tang, Y Rao, T Huang… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present Point-BERT, a novel paradigm for learning Transformers to generalize the concept of BERT onto 3D point cloud. Following BERT, we devise a Masked Point Modeling …
X Yi, J Deng, Q Sun, XS Hua… - Proceedings of the …, 2023 - openaccess.thecvf.com
We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-pretrained 2D model …
T Zheng, C Chen, J Yuan, B Li… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Abstract 3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise …
In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer …
W Zeng, T Gevers - Proceedings of the European …, 2018 - openaccess.thecvf.com
Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point …
C Sharma, M Kaul - Advances in Neural Information …, 2020 - proceedings.neurips.cc
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 …
Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language (VL) pre-training methods to …
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a …
Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from single modality gradually meets its bottleneck. In this work, we …