Advances in 3D pre-training and downstream tasks: a survey
Open Access
- 23 July 2024
- journal article
- review article
- Published by Springer Nature in Vicinagearth
- Vol. 1 (1) , 1-16
Abstract
Recent years have witnessed a signifcant breakthrough in the 3D domain. To track the most recent advances in the 3D field, in this paper, we provide a comprehensive survey of recent advances in the 3D feld, which encompasses a wide collection of topics, including diverse pre-training strategies, backbone designs and downstream tasks. Compared to the previous literature review on point cloud, our survey is more comprehensive. Our survey consists of the 3D pre-training methods, various downstream tasks, popular benchmarks, evaluation metrics as well as several promising future directions. We hope the survey can serve as the cornerstone for both academia and industry.Keywords
This publication has 77 references indexed in Scilit:
- Gradient modulated contrastive distillation of low-rank multi-modal knowledge for disease diagnosisMedical Image Analysis, 2023
- Cross-source point cloud registration: Challenges, progress and prospectsNeurocomputing, 2023
- Masked Autoencoders for Point Cloud Self-supervised Learning2022
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- Robust real-world point cloud registration by inlier detectionComputer Vision and Image Understanding, 2022
- PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution2020
- Fast Global Registration2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015