3D Point Cloud Linear Classification

13 papers with code • 1 benchmarks • 1 datasets

Training a linear classifier(e.g. SVM) on the embeddings/representations of 3D point clouds. The embeddings/representations are usually trained in an unsupervised manner.


Most implemented papers

FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation

AnTao97/UnsupervisedPointCloudReconstruction CVPR 2018

Recent deep networks that directly handle points in a point set, e. g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation.

SO-Net: Self-Organizing Network for Point Cloud Analysis

lijx10/SO-Net CVPR 2018

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds.

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

zrrskywalker/point-m2ae 28 May 2022

By fine-tuning on downstream tasks, Point-M2AE achieves 86. 43% accuracy on ScanObjectNN, +3. 36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme.

Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders

zrrskywalker/i2p-mae CVPR 2023

Pre-training by numerous image data has become de-facto for robust 2D representations.

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

qizekun/ReCon 5 Feb 2023

This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms.

Self-supervised Learning of Point Clouds via Orientation Estimation

OmidPoursaeed/Self_supervised_Learning_Point_Clouds 1 Aug 2020

A point cloud can be rotated in infinitely many ways, which provides a rich label-free source for self-supervision.

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

Microsoft/O-CNN 3 Aug 2020

Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods.

Unsupervised Point Cloud Pre-Training via Occlusion Completion

hansen7/OcCo ICCV 2021

We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks.

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

yichen928/STRL ICCV 2021

To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views, lighting, occlusions, etc.