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 1–25 of 26 papers

TitleStatusHype
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training ParadigmCode2
GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-TrainingCode1
Point Cloud Pre-Training With Natural 3D StructuresCode1
PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in ClusteringCode1
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingCode1
POS-BERT: Point Cloud One-Stage BERT Pre-TrainingCode1
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
Unsupervised Point Cloud Pre-Training via Occlusion CompletionCode1
BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving ScenariosCode1
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
Ponder: Point Cloud Pre-training via Neural Rendering—0
Boosting Point-BERT by Multi-choice TokensCode0
Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio MaskingCode0
PRED: Pre-training via Semantic Rendering on LiDAR Point CloudsCode0
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised LearningCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.