List your company
ResearchFormerly WizWand

Object Classification on ScanObjectNN OBJ_BG v1.0

97.2AccuracyPointGPT-L
72.34478.79785.2591.703May 19, 2023Aug 2, 2023Oct 17, 2023Jan 1, 2024Mar 17, 2024Jun 1, 2024Aug 16, 2024
Updated 8mo ago

Evaluation results

MethodLinks
PointGPT-LLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.0597.2
PointGPT-BLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.0595.8
PCP-MAE#P (M)=22.1, Input=2k Points2024.0895.52
ReConLearning Paradigm=Cross-modal Information and Teacher Models2023.0595.4
Point-FEMAE#P (M)=27.4, Input=2k Points2024.0895.18
ReCon#P (M)=43.6, Input=2k Points2024.0895.18
I2P-MAE#P (M)=15.3, Input=2k Points2024.0894.14
ACTLearning Paradigm=Cross-modal Information and Teacher Models2023.0593.3
ACT#P (M)=22.1, Input=2k Points2024.0893.29
MVTNLearning Paradigm=Supervised Learning Only2023.0592.6
MVTN#P (M)=11.2, Input=20 Images2024.0892.6
PointGPT-SLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=false, Post-pre-training stage=false2023.0591.6
PointGPT#P (M)=19.5, Input=2k Points2024.0891.6
Point-M2AE#P (M)=15.3, Input=2k Points2024.0891.22
Point-M2AELearning Paradigm=Self-Supervised Representation Learning2023.0591.2
Joint-MAEInput=2k Points2024.0890.94
TAP#P (M)=22.1, Input=2k Points2024.0890.36
Point-MAE#P (M)=22.1, Input=2k Points2024.0890.02
Point-MAELearning Paradigm=Self-Supervised Representation Learning2023.0590
MaskPointLearning Paradigm=Self-Supervised Representation Learning2023.0589.3
MaskPointInput=2k Points2024.0889.3
Point-BERT#P (M)=22.1, Input=1k Points2024.0887.43
Point-BERTLearning Paradigm=Self-Supervised Representation Learning2023.0587.4
PointCNNLearning Paradigm=Supervised Learning Only2023.0586.1
DGCNNLearning Paradigm=Supervised Learning Only2023.0582.8
DGCNN#P (M)=1.8, Input=1k Points2024.0882.8
PointNet++#P (M)=1.5, Input=1k Points2024.0882.3
PointNetLearning Paradigm=Supervised Learning Only2023.0573.3
PointNet#P (M)=3.5, Input=1k Points2024.0873.3