List your company
ResearchFormerly WizWand

3D object recognition on ScanObjectNN OBJ_BG (test)

94.49Top-1 AccuracyPointGST
27.940445.217762.49579.7723Apr 1, 2024Jul 16, 2024Oct 31, 2024Feb 14, 2025Jun 1, 2025Sep 15, 2025Dec 31, 2025
Updated 8mo ago

Evaluation results

MethodLinks
PointGSTPre-trained model=RECON [62], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.1294.49
FullPre-trained model=RECON [62], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.1294.32
DAPTPre-trained model=RECON [62], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.1294.32
CLoRAPre-trained model=RECON [62], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.4 (1.81%), #GFLOPs=4.76(-)2025.1294.32
PointLoRAPre-trained model=RECON [62], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.8 (3.43%), #GFLOPs=5.06(↑)2025.1293.46
IDPTPre-trained model=RECON [62], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.1293.29
Point-PEFTPre-trained model=RECON [62], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.1291.91
PointGSTPre-trained model=Point-MAE [61], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.1291.74
CLoRAPre-trained model=Point-BERT [60], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.3 (1.36%), #GFLOPs=4.76(-)2025.1291.74
CLoRAPre-trained model=Point-MAE [61], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.3 (1.36%), #GFLOPs=4.76(-)2025.1291.57
PointGSTPre-trained model=Point-BERT [60], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.1291.39
IDPTPre-trained model=Point-MAE [61], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.1291.22
DAPTPre-trained model=Point-BERT [60], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.1291.05
DAPTPre-trained model=Point-MAE [61], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.1290.88
PointLoRAPre-trained model=Point-MAE [61], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.8 (3.43%), #GFLOPs=5.06(↑)2025.1290.71
FullPre-trained model=Point-MAE [61], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.1290.02
PointLoRAPre-trained model=Point-BERT [60], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.9 (4.07%), #GFLOPs=5.06(↑)2025.1289.85
Point-PEFTPre-trained model=Point-MAE [61], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.1289.67
Point-PEFTPre-trained model=Point-BERT [60], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.1288.81
IDPTPre-trained model=Point-BERT [60], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.1288.12
FullPre-trained model=Point-BERT [60], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.1287.43
SUGAR (single)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0468
SUGAR (multi)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0465.6
SUGAR (single)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0456.2
SUGAR (multi)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0453.2
OpenShape-PointBERTPretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0452.6
OpenShape-PointBERTPretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0451.4
SUGAR (multi)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0450.8
SUGAR (single)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0450.3
SUGAR (multi)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0447.9
SUGAR (single)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0446.3
OpenShape-PointBERTPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.0442.4
OpenShape-PointBERTPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0441.9
ReConPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0438
CLIP2PointPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.0430.5