HyperAI

Few Shot 3D Point Cloud Classification On 3

Metriken

Overall Accuracy
Standard Deviation

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Overall Accuracy
Standard Deviation
Paper TitleRepository
PCP-MAE93.53.7PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
GPr-Net + Euc (1024)62.11.9GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
Point-BERT91.05.4Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
MaskPoint91.44.0Masked Discrimination for Self-Supervised Learning on Point Clouds
DGCNN19.856.5Dynamic Graph CNN for Learning on Point Clouds
Point-M2AE92.34.5Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
GPr-Net + Hyp (1024)70.41.8GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
IDPT92.8-Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
PointNet46.6013.5PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Point-RAE93.34.0Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
Point-LGMask92.64.3Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
ReCon++94.54.1ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
GPr-Net + Euc (512)62.32.0GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
Point-MAE92.64.1Masked Autoencoders for Point Cloud Self-supervised Learning
PointCNN46.604.8PointCNN: Convolution On X-Transformed Points
3D-JEPA94.33.63D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning-
PointGPT94.33.3PointGPT: Auto-regressively Generative Pre-training from Point Clouds
OcCo+DGCNN82.91.3Unsupervised Point Cloud Pre-Training via Occlusion Completion
PointNet++23.057.0PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Point-FEMAE94.0-Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
0 of 31 row(s) selected.