SOTAVerified

Point Cloud Pre-training

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 26 papers

TitleStatusHype
Self-supervised Point Cloud Representation Learning via Separating Mixed ShapesCode1
Point Cloud Pre-training with Diffusion Models—0
A Unified Framework for Human-centric Point Cloud Video Understanding—0
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space—0
EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding—0
Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting—0
Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training—0
Multi-View Representation is What You Need for Point-Cloud Pre-Training—0
PatchContrast: Self-Supervised Pre-training for 3D Object Detection—0
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.