AI Paper Atlas

Research map / Benchmarks / ShapeNetPart

ShapeNetPart leaderboard

93 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ShapeNetPart. Best instance mIoU: 90.26 (PointRWKV, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ShapeNetPart · instance mIoU

32 papers, each with its best reported number for its own method; higher is better.

22 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · mIoU

21 papers, each with its best reported number for its own method; higher is better.

11 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · class mIoU

19 papers, each with its best reported number for its own method; higher is better.

9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · Cls. mIoU

16 papers, each with its best reported number for its own method; higher is better.

#Cls. mIoU ↑MethodPaperTopic
186.5DeepLA-24DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis
CVPR 2025 · Table 4
Point cloud classification
285.6GSPointGraph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis
AAAI 2026 · Table 2
Point cloud classification
385.4PointMCPointMC: Multi-view Consistent Encoding and Center-Global Feature Fusion for Point Clouds Understanding
AAAI 2026 · Table 2
Point cloud classification
485.3PointMetaBase-S + DMR
PointMetaBase-S
Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis
AAAI 2025 · Table 5
Point cloud classification
585.3PCMPoint Cloud Mamba: Point Cloud Learning via State Space Model
AAAI 2025 · Table: Part segmentation in Sh
Point cloud classification
685.1QPointQPoint: End-to-End Lightweight Point Cloud Processing via Robust Quaternion Feature Learning
ICML 2026 · Table 2
Point cloud classification
785.1PointMetaBase-S (C=160)Meta Architecture for Point Cloud Analysis
CVPR 2023 · Table: Part segmentation on Sh
Point cloud classification
884.9PCP-MAEPCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
NeurIPS 2024 · Segmentation results table
Point cloud classification
984.8MVNet-B
Transformer
Multi-View Representation is What You Need for Point-Cloud Pre-Training
ICLR 2024 · Table 3
Segmentation and detection
1084.73Point-MAE + Ours(D)
Point-MAE
Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
ICML 2025 · Table 2
Point cloud classification
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · Ins. mIoU

15 papers, each with its best reported number for its own method; higher is better.

#Ins. mIoU ↑MethodPaperTopic
188DeLA w/ GHEA
DeLA
Generative Hard Example Augmentation for Semantic Point Cloud Segmentation
CVPR 2025 · Table 1
Segmentation and detection
288DeepLA-24DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis
CVPR 2025 · Table 4
Point cloud classification
387.2GSPointGraph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis
AAAI 2026 · Table 2
Point cloud classification
487.2HPENet V2-S (c=160)Efficient Point Cloud Processing With High-Dimensional Positional Encoding and Non-Local MLPs
TPAMI 2026 · Table 7
Point cloud classification
587.1PointMetaBase-S + DMR
PointMetaBase-S
Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis
AAAI 2025 · Table 5
Point cloud classification
687.1PointMetaBase-S (C=160)Meta Architecture for Point Cloud Analysis
CVPR 2023 · Table: Part segmentation on Sh
Point cloud classification
787PCMPoint Cloud Mamba: Point Cloud Learning via State Space Model
AAAI 2025 · Table: Part segmentation in Sh
Point cloud classification
886.9PointMCPointMC: Multi-view Consistent Encoding and Center-Global Feature Fusion for Point Clouds Understanding
AAAI 2026 · Table 2
Point cloud classification
986.9GCD-sampling
PointNeXt
GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud
AAAI 2025 · Table 3
Point cloud classification
1086.9PointVector-S (C=64)
PointNeXt-S
PointVector: A Vector Representation in Point Cloud Analysis
CVPR 2023 · Table: Object Part Segmentatio
Point cloud classification
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · mIoU_c

14 papers, each with its best reported number for its own method; higher is better.

#mIoU_c ↑MethodPaperTopic
185.66Ours(Point-M2AE)
Point-M2AE
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner
ICCV 2025 · Table 1
Point cloud classification
285.5UniPre3D (PointMLP)
PointMLP
UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
CVPR 2025 · Table 2
Point cloud classification
385.2PointMLP+TAP
PointMLP
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
ICCV 2023 · Table 3
Point cloud classification
485.15I2P-MAE
ViT-Base CLIP
Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders
CVPR 2023 · Table: Part Segmentation
Point cloud classification
585StruMamba3DStruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
ICCV 2025 · Table 2
Point cloud classification
684.9DAP-MAE
ReCon-SMC
DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
ICCV 2025 · Table 5
Point cloud classification
784.9Point-FEMAE
Point-MAE
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
AAAI 2024 · Table: Part Segmentation
Point cloud classification
884.5PointSD (Ours)
Point Transformer (22.1M)
Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
ICCV 2025 · Table 3
Point cloud classification
984.4KR-MAEReliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding
AAAI 2026 · Table 3
Point cloud classification
1084.15Point-GT-DM (Ours)Geodesic Self-Attention for 3D Point Clouds
NeurIPS 2022 · Table 4
Point cloud classification
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ShapeNetPart · mIoU_I

12 papers, each with its best reported number for its own method; higher is better.

#mIoU_I ↑MethodPaperTopic
186.91Ours(Point-M2AE)
Point-M2AE
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner
ICCV 2025 · Table 1
Point cloud classification
286.9PointMLP+TAP
PointMLP
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
ICCV 2023 · Table 3
Point cloud classification
386.76I2P-MAE
ViT-Base CLIP
Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders
CVPR 2023 · Table: Part Segmentation
Point cloud classification
486.7StruMamba3DStruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
ICCV 2025 · Table 2
Point cloud classification
586.5P2P (CN-L-UPer)
ConvNeXt-L
P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting
NeurIPS 2022 · Table 3
Point cloud classification
686.3Recon w/ PMA
Recon
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
CVPR 2025 · Table 3
Point cloud classification
786.3DAP-MAE
ReCon-SMC
DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
ICCV 2025 · Table 5
Point cloud classification
886.3Point-FEMAE
Point-MAE
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
AAAI 2024 · Table: Part Segmentation
Point cloud classification
986.2CASLCASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection
AAAI 2026 · Table 4
OOD and anomaly detection
1086.2KR-MAEReliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding
AAAI 2026 · Table 3
Point cloud classification
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.