https://github.com/Ayumu-J-S/Point-JEPA
공식 코드Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud
Papers with Code 아카이브
3D Point Cloud Linear Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 24
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/OmidPoursaeed/Self_supervised_Learning_Point_Clouds
공식 코드Self-supervised Learning of Point Clouds via Orientation Estimation
https://github.com/hansen7/OcCo
공식 코드Unsupervised Point Cloud Pre-Training via Occlusion Completion
https://github.com/lijx10/SO-Net
공식 코드https://github.com/lulutang0608/Point-BERT
공식 코드Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
https://github.com/mohamedafham/crosspoint
공식 코드CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
https://github.com/qizekun/ReCon
공식 코드Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://github.com/qizekun/ShapeLLM
공식 코드ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/simingyan/iae
공식 코드Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
https://github.com/yichen928/STRL
공식 코드Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
https://github.com/zrrskywalker/i2p-mae
공식 코드Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
https://github.com/zrrskywalker/point-m2ae
공식 코드Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
https://github.com/AnTao97/UnsupervisedPointCloudReconstruction
FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
https://github.com/LONG-9621/SO-Net
https://github.com/Microsoft/O-CNN
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
https://github.com/MindSpore-paper-code-2/code400/tree/main/MAE
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
https://github.com/XuyangBai/FoldingNet
FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
https://github.com/aHapBean/PCP-MAE
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://github.com/asterisci/point-gcc
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://github.com/black0017/3D-GAN-pytorch
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
https://github.com/chinokenochkan/3dgan-keras
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
https://github.com/donnyruixu/pc-elm-ae
https://github.com/julie-tang00/point-bert
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
https://github.com/lmd0311/pointmamba
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
https://github.com/qinglew/FoldingNet
FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
https://github.com/qizekun/vpp
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://github.com/runpeidong/act
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://github.com/snehaputul/CrossMoCo
https://github.com/virgantara/AdaCrossNet
https://github.com/zck119/3dgan-release
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.