|
PointGST
|
Parameter-Efficient Fine-Tuning in Spectral Domai…
|
96.18
|
2024-10-10
|
|
|
OmniVec
|
OmniVec: Learning robust representations with cro…
|
96.10
|
2023-11-07
|
|
|
GPSFormer
|
GPSFormer: A Global Perception and Local Structur…
|
95.40
|
2024-07-18
|
|
|
ReCon++
|
ShapeLLM: Universal 3D Object Understanding for E…
|
95.25
|
2024-02-27
|
|
|
AsymDSD-B* (no voting)
|
Asymmetric Dual Self-Distillation for 3D Self-Sup…
|
93.72
|
2025-06-26
|
|
|
PointGPT
|
PointGPT: Auto-regressively Generative Pre-traini…
|
93.40
|
2023-05-19
|
|
|
GPSFormer-elite
|
GPSFormer: A Global Perception and Local Structur…
|
93.30
|
2024-07-18
|
|
|
Mamba3D
|
Mamba3D: Enhancing Local Features for 3D Point Cl…
|
92.64
|
2024-04-23
|
|
|
Mamba3D (no voting)
|
Mamba3D: Enhancing Local Features for 3D Point Cl…
|
91.81
|
2024-04-23
|
|
|
ULIP-2 + PointNeXt
|
ULIP-2: Towards Scalable Multimodal Pre-training …
|
91.50
|
2023-05-14
|
|
|
ReCon
|
Contrast with Reconstruct: Contrastive 3D Represe…
|
91.26
|
2023-02-05
|
|
|
ExpPoint-MAE
|
ExpPoint-MAE: Better interpretability and perform…
|
90.88
|
2023-06-19
|
|
|
ULIP-2 + PointNeXt (no voting)
|
ULIP-2: Towards Scalable Multimodal Pre-training …
|
90.80
|
2023-05-14
|
|
|
ReCon (no voting)
|
Contrast with Reconstruct: Contrastive 3D Represe…
|
90.63
|
2023-02-05
|
|
|
AsymDSD-S (no voting)
|
Asymmetric Dual Self-Distillation for 3D Self-Sup…
|
90.53
|
2025-06-26
|
|
|
DeLA
|
Decoupled Local Aggregation for Point Cloud Learn…
|
90.40
|
2023-08-31
|
|
|
PCP-MAE
|
PCP-MAE: Learning to Predict Centers for Point Ma…
|
90.35
|
2024-08-16
|
|
|
PointConT
|
Point Cloud Classification Using Content-based Tr…
|
90.30
|
2023-03-08
|
|
|
Point-RAE (no voting)
|
Regress Before Construct: Regress Autoencoder for…
|
90.28
|
2023-09-25
|
|
|
Point-FEMAE
|
Towards Compact 3D Representations via Point Feat…
|
90.22
|
2023-12-17
|
|
|
I2P-MAE (no voting)
|
Learning 3D Representations from 2D Pre-trained M…
|
90.11
|
2022-12-13
|
|
|
ULIP + PointNeXt
|
ULIP: Learning a Unified Representation of Langua…
|
89.70
|
2022-12-10
|
|
|
ReCon+PPT
|
Positional Prompt Tuning for Efficient 3D Represe…
|
89.52
|
2024-08-21
|
|
|
3D-JEPA
|
3D-JEPA: A Joint Embedding Predictive Architectur…
|
89.52
|
2024-09-24
|
|
|
PointMLP∗ + JM3D
|
Beyond First Impressions: Integrating Joint Multi…
|
89.50
|
2023-08-06
|
|
|
ULIP + PointMLP
|
ULIP: Learning a Unified Representation of Langua…
|
89.40
|
2022-12-10
|
|
|
KPConvX-L
|
KPConvX: Modernizing Kernel Point Convolution wit…
|
89.30
|
2024-05-21
|
|
|
P2P
|
P2P: Tuning Pre-trained Image Models for Point Cl…
|
89.30
|
2022-08-04
|
|
|
ACT
|
Autoencoders as Cross-Modal Teachers: Can Pretrai…
|
89.17
|
2022-12-16
|
|
|
ULIP-2 + Point-BERT
|
ULIP-2: Towards Scalable Multimodal Pre-training …
|
89.00
|
2023-05-14
|
|
|
PointNeXt+Local
|
Local Neighborhood Features for 3D Classification
|
88.60
|
2022-12-09
|
|
|
SPoTr
|
Self-positioning Point-based Transformer for Poin…
|
88.60
|
2023-03-29
|
|
|
IDPT
|
Instance-aware Dynamic Prompt Tuning for Pre-trai…
|
88.51
|
2023-04-14
|
|
|
PointMLP+TAP
|
Take-A-Photo: 3D-to-2D Generative Pre-training of…
|
88.50
|
2023-07-27
|
|
|
PointNeXt+HyCoRe
|
Rethinking the compositionality of point clouds t…
|
88.30
|
2022-09-21
|
|
|
ACT (no voting)
|
Autoencoders as Cross-Modal Teachers: Can Pretrai…
|
88.21
|
2022-12-16
|
|
|
PointNeXt
|
PointNeXt: Revisiting PointNet++ with Improved Tr…
|
88.20
|
2022-06-09
|
|
|
PointConT (no voting)
|
Point Cloud Classification Using Content-based Tr…
|
88.00
|
2023-03-08
|
|
|
PointVector-S
|
PointVector: A Vector Representation In Point Clo…
|
87.80
|
2022-05-21
|
|
|
point2vec
|
Point2Vec for Self-Supervised Representation Lear…
|
87.50
|
2023-03-29
|
|
|
PointStack
|
Advanced Feature Learning on Point Clouds using M…
|
87.20
|
2022-05-20
|
|
|
Point-PN
|
Parameter is Not All You Need: Starting from Non-…
|
87.10
|
2023-03-14
|
|
|
PointCMT
|
Let Images Give You More:Point Cloud Cross-Modal …
|
86.70
|
2022-10-09
|
|
|
Point-JEPA
|
Point-JEPA: A Joint Embedding Predictive Architec…
|
86.60
|
2024-04-25
|
|
|
PointMLS
|
ModelNet-O: A Large-Scale Synthetic Dataset for O…
|
86.60
|
2024-01-16
|
|
|
Point-M2AE
|
Point-M2AE: Multi-scale Masked Autoencoders for H…
|
86.43
|
2022-05-28
|
|
|
ULIP + PointBERT
|
ULIP: Learning a Unified Representation of Langua…
|
86.40
|
2022-12-10
|
|
|
RepSurf-U (2x)
|
Surface Representation for Point Clouds
|
86.00
|
2022-05-11
|
|
|
PointMLP
|
Rethinking Network Design and Local Geometry in P…
|
85.70
|
2022-02-15
|
|
|
Point-MAE
|
Masked Autoencoders for Point Cloud Self-supervis…
|
85.20
|
2022-03-13
|
|
|
DeltaConv
|
DeltaConv: Anisotropic Operators for Geometric De…
|
84.70
|
2021-11-16
|
|
|
RepSurf-U
|
Surface Representation for Point Clouds
|
84.60
|
2022-05-11
|
|
|
APP-Net
|
APP-Net: Auxiliary-point-based Push and Pull Oper…
|
84.10
|
2022-05-02
|
|
|
PointMLP-elite
|
Rethinking Network Design and Local Geometry in P…
|
83.80
|
2022-02-15
|
|
|
PointNet++ + SageMix
|
SageMix: Saliency-Guided Mixup for Point Clouds
|
83.70
|
2022-10-13
|
|
|
DGCNN + SageMix
|
SageMix: Saliency-Guided Mixup for Point Clouds
|
83.60
|
2022-10-13
|
|
|
Point-TnT
|
Points to Patches: Enabling the Use of Self-Atten…
|
83.50
|
2022-04-08
|
|
|
Point-BERT
|
Point-BERT: Pre-training 3D Point Cloud Transform…
|
83.10
|
2021-11-29
|
|
|
MVTN
|
MVTN: Multi-View Transformation Network for 3D Sh…
|
82.80
|
2020-11-26
|
|
|
PRA-Net
|
PRA-Net: Point Relation-Aware Network for 3D Poin…
|
82.10
|
2021-12-09
|
|
|
GBNet
|
Geometric Back-projection Network for Point Cloud…
|
80.50
|
2019-11-28
|
|
|
DRNet
|
Dense-Resolution Network for Point Cloud Classifi…
|
80.30
|
2020-05-14
|
|
|
PointCNN
|
PointCNN: Convolution On $\mathcal{X}$-Transforme…
|
78.50
|
2018-01-23
|
|
|
DGCNN
|
Dynamic Graph CNN for Learning on Point Clouds
|
78.10
|
2018-01-24
|
|
|
PointNet++
|
PointNet++: Deep Hierarchical Feature Learning on…
|
77.90
|
2017-06-07
|
|
|
SpiderCNN
|
SpiderCNN: Deep Learning on Point Sets with Param…
|
73.70
|
2018-03-30
|
|
|
PointNet
|
PointNet: Deep Learning on Point Sets for 3D Clas…
|
68.20
|
2016-12-02
|
|