Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-4

Unsupervised 3D Point Cloud Linear Evaluation

3260 papers • 126 benchmarks • 313 datasets

Training a linear classifier(e.g. SVM) on the representations learned in an unsupervised manner on the pretrained(e.g. ShapeNet) dataset.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unsupervised-3d-point-cloud-linear-evaluation-4

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find unsupervised-3d-point-cloud-linear-evaluation-4 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

Jiajun Wu, J. Tenenbaum, Tianfan Xue, Chengkai Zhang, Bill Freeman•Sun Oct 23 2016

A novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets, and a powerful 3D shape descriptor which has wide applications in 3D object recognition.

2085

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

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

Gim Hee Lee, Jiaxin Li, Ben M. Chen•Sun Mar 11 2018

The proposed SO-Net, a permutation invariant architecture for deep learning with orderless point clouds, demonstrates performance that is similar with or better than state-of-the-art approaches in recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval.

990 0

Paper Graph

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

Yiru Shen, Chen Feng, Yaoqing Yang, Dong Tian•Mon Dec 18 2017

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. In this work, a novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds. On the encoder side, a graph-based enhancement is enforced to promote local structures on top of PointNet. Then, a novel folding-based decoder deforms a canonical 2D grid onto the underlying 3D object surface of a point cloud, achieving low reconstruction errors even for objects with delicate structures. The proposed decoder only uses about 7% parameters of a decoder with fully-connected neural networks, yet leads to a more discriminative representation that achieves higher linear SVM classification accuracy than the benchmark. In addition, the proposed decoder structure is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid. Our code is available at http://www.merl.com/research/license#FoldingNet

1326 0

Paper Graph

Self-Supervised Learning of Point Clouds via Orientation Estimation

Vladimir G. Kim, Omid Poursaeed, Tianxing Jiang, Quintessa Qiao, N. Xu•Fri Jul 31 2020

This paper leverages 3D self-supervision for learning downstream tasks on point clouds with fewer labels and demonstrates that its approach outperforms the state-of-the-art.

140 0

Paper Graph

Unsupervised Point Cloud Pre-training via Occlusion Completion

Matt J. Kusner, Hanchen Wang, Joan Lasenby, Qi Liu, Xiangyu Yue•Thu Oct 01 2020

This paper shows that this method outperforms previous pre-training methods in object classification, and both part-based and semantic segmentation tasks, and even when it pre-train on a single dataset (ModelNet40), improves accuracy across different datasets and encoders.

305 0

Paper Graph

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

Song-Chun Zhu, Siyuan Huang, Yichen Xie, Yixin Zhu•Tue Aug 31 2021

Experimental results demonstrate that, compared with supervised learning methods, the learned self-supervised representation facilitates various models to attain comparable or even better performances while capable of generalizing pre-trained models to downstream tasks, including 3D shape classification, 3D object detection, and 3D semantic segmentation.

253 0

Paper Graph

Adding a benchmark result helps the community track progress.

Unsupervised 3D Point Cloud Linear Evaluation | State-of-the-Art