Papers with Code 아카이브

Point Cloud Pre-training

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

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.

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Point Cloud Pre-training

논문

Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting

EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

A Unified Framework for Human-centric Point Cloud Video Understanding

Point Cloud Pre-training with Diffusion Models

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

PatchContrast: Self-Supervised Pre-training for 3D Object Detection

Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking

Multi-View Representation is What You Need for Point-Cloud Pre-Training

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training

Ponder: Point Cloud Pre-training via Neural Rendering

3D Point Cloud Pre-training with Knowledge Distillation from 2D Images

BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

Boosting Point-BERT by Multi-choice Tokens

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

POS-BERT: Point Cloud One-Stage BERT Pre-Training

Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes

Unsupervised Point Cloud Pre-Training via Occlusion Completion

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

Self-Supervised Deep Learning on Point Clouds by Reconstructing Space