computer-vision-5
Point Cloud Pre-training
3260 papers • 126 benchmarks • 313 datasets
Point cloud data represents 3D shapes as a set of discrete points in 3D space. This kind of data is primarily sourced from 3D scanners, LiDAR systems, and other similar technologies. Point cloud processing has a wide range of applications, such as robotics, autonomous vehicles, and augmented/virtual reality. Pre-training on point cloud data is similar in spirit to pre-training on images or text. By pre-training a model on a large, diverse dataset, it learns essential features of the data type, which can then be fine-tuned on a smaller, task-specific dataset. This two-step process (pre-training and fine-tuning) often results in better performance, especially when the task-specific dataset is limited in size.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in point-cloud-pre-training-5
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find point-cloud-pre-training-5 models and implementations
2 papers 1,092
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Hongsheng Li, Renrui Zhang, Peng Gao, Ziyu Guo, Rongyao Fang, Bingyan Zhao, Dong Wang, Y. Qiao•Fri May 27 2022
Point-M2AE is proposed, a strong Multi-scale MAE pre-training framework for hierarchical self-supervised learning of 3D point clouds that modifications the encoder and decoder into pyramid architectures to progressively model spatial geometries and capture both fine-grained and high-level semantics of3D shapes.
354