List your company
ResearchFormerly WizWand

Point Cloud Classification on ScanObjectNN OBJ-ONLY

92.75Overall AccuracyPoint-MAE w/ LCM
-2.8863221.9423446.77171.59966Jun 19, 2023Nov 16, 2023Apr 14, 2024Sep 11, 2024Feb 8, 2025Jul 8, 2025Dec 5, 2025
Updated 7mo ago

Evaluation results

MethodLinks
Point-MAE w/ LCMPretrain=MPM, #Params(M)=2.7, FLOPs(G)=1.32024.0592.75
ACT w/ LCMPretrain=MPM, #Params(M)=3.1, FLOPs(G)=2.82024.0592.66
PointGPT-BPretrain=GPT, #Params(M)=120.5, FLOPs(G)=36.2, Evaluation Setting=Original Paper2024.0592.5
Point-BERT w/ LCMPretrain=MPM, #Params(M)=3.1, FLOPs(G)=2.52024.0592.43
Point-M2AE w/ LCMPretrain=MPM, #Params(M)=2.5, FLOPs(G)=6.72024.0592.41
Point-MAEPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Reproduced downstream setting2024.0592.08
MaskPoint w/ LCMPretrain=MPM, #Params(M)=3.1, FLOPs(G)=2.52024.0591.98
ACTPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Original Paper2024.0591.91
PointMambaPretrain=MPM, #Params(M)=12.3, Evaluation Setting=Original Paper2024.0591.91
ACTPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Reproduced downstream setting2024.0591.7
MaskPointPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.5, Evaluation Setting=Reproduced downstream setting2024.0591.69
Point-BERTPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.5, Evaluation Setting=Reproduced downstream setting2024.0591.6
LCMPretrain=X, #Params(M)=2.7, FLOPs(G)=1.32024.0591.54
TransformerPretrain=X, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Reproduced downstream setting2024.0591.39
Point-M2AEPretrain=MPM, #Params(M)=12.9, FLOPs(G)=7.9, Evaluation Setting=Reproduced downstream setting2024.0591.22
Point-MAE w/ DAPTPretrain=MPM, #Params(M)=22.7, FLOPs(G)=5.0, Evaluation Setting=Original Paper2024.0590.19
ExpPoint-MAEunfreeze epoch=2502023.0690.02
Point-MAE w/ IDPTPretrain=MPM, #Params(M)=23.3, FLOPs(G)=7.1, Evaluation Setting=Original Paper2024.0590.02
MaskFeat3DBackbone=PointViT, Evaluation Protocol=fine-tuning2025.1290
MaskPoint2023.0689.7
ExpPoint-MAEextra domain adaptation pretraining=true2023.0689.67
Inter-MAEPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Original Paper2024.0589.6
ExpPoint-MAEunfreeze epoch=2002023.0689.33
MaskDiscrBackbone=PointViT, Evaluation Protocol=fine-tuning2025.1289.3
MaskSurfelBackbone=PointViT, Evaluation Protocol=fine-tuning2025.1289.2
Point-M2AE2023.0688.81
Point-M2AEPretrain=MPM, #Params(M)=12.9, FLOPs(G)=7.9, Evaluation Setting=Original Paper2024.0588.81
PointMAEBackbone=PointViT, Evaluation Protocol=fine-tuning2025.1288.3
Point-MAE2023.0688.29
Point-MAEPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Original Paper2024.0588.29
Point-BERT2023.0688.12
Point-BERTPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.5, Evaluation Setting=Original Paper2024.0588.12
MaskPointPretrain=MPM, #Params(M)=22.1, FLOPs(G)=4.5, Evaluation Setting=Original Paper2024.0588.1
PointBERTBackbone=PointViT, Evaluation Protocol=fine-tuning2025.1288.1
PointMambaPretrain=X, #Params(M)=12.3, Evaluation Setting=Original Paper2024.0587.78
TransformerPretrain=X, #Params(M)=22.1, FLOPs(G)=4.8, Evaluation Setting=Original Paper2024.0586.92
Foundrys=16, Frozen student=false2025.1186.29
PointNet++Pretrain=X, #Params(M)=1.5, FLOPs(G)=1.7, Evaluation Setting=Original Paper2024.0584.3
PointViTBackbone=PointViT, Evaluation Protocol=from scratch2025.1280.6
PointNetPretrain=X, #Params(M)=3.5, FLOPs(G)=0.5, Evaluation Setting=Original Paper2024.0579.2
Point-FEMAELearning Paradigm=Single-Modal Self-Supervised Learning, #Params (M)=27.4, Input Data=2k Points2023.120.9329
ReconLearning Paradigm=Cross-Modal Self-Supervised Learning, #Params (M)=44.3, Input Data=2k Points2023.120.9329
ACTLearning Paradigm=Cross-Modal Self-Supervised Learning, #Params (M)=22.1, Input Data=2k Points2023.120.9191
I2P-MAELearning Paradigm=Cross-Modal Self-Supervised Learning, #Params (M)=15.3, Input Data=2k Points2023.120.9157
Joint-MAELearning Paradigm=Cross-Modal Self-Supervised Learning, Input Data=2k Points2023.120.8886
Point-M2AELearning Paradigm=Single-Modal Self-Supervised Learning, #Params (M)=15.3, Input Data=2k Points2023.120.8881
Point-MAELearning Paradigm=Single-Modal Self-Supervised Learning, #Params (M)=22.1, Input Data=2k Points2023.120.8829
Point-BERTLearning Paradigm=Single-Modal Self-Supervised Learning, #Params (M)=22.1, Input Data=1k Points2023.120.8812
MaskPointLearning Paradigm=Single-Modal Self-Supervised Learning, #Params (M)=22.1, Input Data=2k Points2023.120.881
DGCNNLearning Paradigm=Supervised Learning Only, #Params (M)=1.8, Input Data=1k Points2023.120.862
PointNet++Learning Paradigm=Supervised Learning Only, #Params (M)=1.5, Input Data=1k Points2023.120.843
PointNetLearning Paradigm=Supervised Learning Only, #Params (M)=3.5, Input Data=1k Points2023.120.792