AI Paper Atlas

Research map / Benchmarks / ModelNet40 z/SO(3)

ModelNet40 z/SO(3) leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ModelNet40 z/SO(3). Best accuracy: 92.6 (Ours (pc+n), AAAI 2026).

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.

ModelNet40 z/SO(3) · accuracy

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

#accuracy ↑MethodPaperTopic
192.6Ours (pc+n)
pc+normals
Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms
AAAI 2026 · Table 1
Point cloud classification
292.4PaRI-Conv (pc+normal)
DGCNN
The Devil Is in the Pose: Ambiguity-Free 3D Rotation-Invariant Learning via Pose-Aware Convolution
CVPR 2022 · Table 1
Human pose estimation
391.8CRINCRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame
AAAI 2023 · Table 1
Point cloud classification
491.6LocoTrans
DGCNN
Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis
CVPR 2024 · Table 1
Point cloud classification
591.4DiPVNetHierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning
AAAI 2026 · Table 1
Point cloud classification
691PaRotPaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
AAAI 2023 · Table 1
Point cloud classification
791OursRethinking Rotation Invariance with Point Cloud Registration
AAAI 2023 · Table 1
Registration and matching
891RI-GCN with normalsRotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
NeurIPS 2020 · Table 1
Point cloud classification
990.5TetraSphere K=8
VN-DGCNN
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
CVPR 2024 · Table 3
Point cloud classification
1089.7OursUnified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
ICML 2022 · Table: ModelNet40 classificati
Point cloud classification
8 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.