HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

3D Point Cloud Classification On Scanobjectnn

Metrics

Mean Accuracy
OBJ-BG (OA)
OBJ-ONLY (OA)
Overall Accuracy

Results

Performance results of various models on this benchmark

Model Name
Mean Accuracy
OBJ-BG (OA)
OBJ-ONLY (OA)
Overall Accuracy
Paper TitleRepository
point2vec86.091.290.487.5Point2Vec for Self-Supervised Representation Learning on Point Clouds
ULIP-2 + Point-BERT---89.0ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Point-BERT-87.4388.1283.1Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
Point-PN---87.1Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
ULIP-2 + PointNeXt (no voting)90.3--90.8ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
PointNet63.4--68.2PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
PatchAugment79.7--81.0PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification
Mamba3D (no voting)-92.9492.0891.81Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
Point-TnT81.0--83.5Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
Point-JEPA-92.9±0.4--Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud-
PointNeXt+HyCoRe87.0--88.3Rethinking the compositionality of point clouds through regularization in the hyperbolic space
RepSurf-U---84.6Surface Representation for Point Clouds
ACT---89.17Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
ReCon (no voting)-95.1893.2990.63Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
SimpleView---80.5Revisiting Point Cloud Classification with a Simple and Effective Baseline
I2P-MAE (no voting)-94.1591.5790.11Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
KPConvX-L88.1--89.3KPConvX: Modernizing Kernel Point Convolution with Kernel Attention-
ULIP + PointBERT---86.4ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
RepSurf-U (2x)---86.0Surface Representation for Point Clouds
PointNeXt86.8--88.2PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
0 of 75 row(s) selected.