AI Paper Atlas

Research map / Point clouds / Point cloud classification

Unsupervised Point Cloud Representation Learning With Deep Neural Networks: A Survey

Aoran Xiao, Jiaxing Huang, Dayan Guan, Xiaoqin Zhang, Shijian Lu, Ling Shao

TPAMI 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 194 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unsupervised Point-BERT pre-trainingTransformer · ScanObjectNN OBJ-BGaccuracy: 79.9 -> 87.4Improved
add unsupervised Point-BERT pre-trainingTransformer · ModelNet40accuracy: 91.2 -> 93.4Improved
add unsupervised OcCo pre-trainingPointNet · ScanObjectNN OBJ-BGaccuracy: 73.5 -> 80.0Improved
add unsupervised OcCo pre-trainingDGCNN · ModelNet40accuracy: 92.5 -> 93.0Improved
add unsupervised Info3D pre-trainingDGCNN · ModelNet40accuracy: 93.5 -> 93.0Hurt
add Jigsaw3D pre-trainingPCN · ScanObjectNN OBJ-BGaccuracy: 78.3 -> 78.2No clear effect
add unsupervised Point-BERT pre-trainingTransformer · ShapeNetPartclass mIoU: 83.4 -> 84.1Improved
add OcCo pre-trainingTransformer · ShapeNetPartclass mIoU: 83.4 -> 83.4No clear effect
add ParAE pre-trainingDGCNN · S3DIS Area 5 (train Area1)mIoU: 43.6 -> 53.5Improved
add Jigsaw3D pre-trainingDGCNN · S3DIS Area 5 (train Area1)mIoU: 43.6 -> 44.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy