List your company
ResearchFormerly WizWand

Object Classification on ScanObjectNN Overall

90.6Overall AccuracyReCon
67.09673.19879.385.402Jul 27, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ReCon#Params (M)=44.3, Pre-training Strategy=With Pre-trained Image Model, Extra Knowledge=Pre-trained Image Models2023.0790.6
I2P-MAEPre-training Strategy=With Pre-trained Image Model, Extra Knowledge=Pre-trained Image Models2023.0790.1
PointMLP + TAP#Params (M)=12.6, Pre-training Strategy=Our Proposed TAP Pre-training2023.0788.5
ACT#Params (M)=22.1, Pre-training Strategy=With Pre-trained Image Model, Extra Knowledge=Pre-trained Image Models2023.0788.2
PointMLP (reproduce)#Params (M)=12.6, Pre-training Strategy=TAP Pre-training (Baseline), reproducibility=reproduced by this paper2023.0787.4
Point-M2AE#Params (M)=15.3, Pre-training Strategy=Transformers with Pre-training2023.0786.4
Point-MAE#Params (M)=22.1, Pre-training Strategy=Transformers with Pre-training2023.0785.2
RepSurf-U#Params (M)=1.5, Pre-training Strategy=Supervised Learning Only2023.0784.3
MaskPoint#Params (M)=22.1, Pre-training Strategy=Transformers with Pre-training2023.0784.3
Point-BERT#Params (M)=22.1, Pre-training Strategy=Transformers with Pre-training2023.0783.1
MVTN#Params (M)=11.2, Pre-training Strategy=Supervised Learning Only2023.0782.8
GBNet#Params (M)=8.8, Pre-training Strategy=Supervised Learning Only2023.0781
PRA-Net#Params (M)=2.3, Pre-training Strategy=Supervised Learning Only2023.0781
DRNetPre-training Strategy=Supervised Learning Only2023.0780.3
OcCo#Params (M)=22.1, Pre-training Strategy=Transformers with Pre-training2023.0778.8
PointCNN#Params (M)=0.6, Pre-training Strategy=Supervised Learning Only2023.0778.5
DGCNN#Params (M)=1.8, Pre-training Strategy=Supervised Learning Only2023.0778.1
PointNet++#Params (M)=1.5, Pre-training Strategy=Supervised Learning Only2023.0777.9
Transformer#Params (M)=22.1, Pre-training Strategy=Supervised Learning Only2023.0777.24
PointNet#Params (M)=3.5, Pre-training Strategy=Supervised Learning Only2023.0768