HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Few Shot 3D Point Cloud Classification On 4

Metrics

Overall Accuracy
Standard Deviation

Results

Performance results of various models on this benchmark

Paper Title
ReCon++96.53.0ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
Point-JEPA96.42.7Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud
3D-JEPA96.32.43D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
PointGPT96.12.8PointGPT: Auto-regressively Generative Pre-training from Point Clouds
PCP-MAE95.92.7PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
Point-RAE95.83.0Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
Point-FEMAE95.8-Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
ReCon95.83.0Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
point2vec95.83.1Point2Vec for Self-Supervised Representation Learning on Point Clouds
ACT95.62.8Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
OTMae3D95.62.6-
I2P-MAE95.53.0Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
IDPT95.4-Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
Point-LGMask95.13.4Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
Point-MAE95.03.0Masked Autoencoders for Point Cloud Self-supervised Learning
Point-M2AE95.03.0Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
MaskPoint93.43.5Masked Discrimination for Self-Supervised Learning on Point Clouds
Point-BERT92.75.1Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
CrossMoCo91.03.4CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud
OcCo+PointNet89.71.5Unsupervised Point Cloud Pre-Training via Occlusion Completion
0 of 31 row(s) selected.