SOTAVerified

3D Object Classification

3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.

Image: Sedaghat et al

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 93 papers

TitleStatusHype
RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network—0
Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation—0
Efficient Spatio-Temporal Signal Recognition on Edge Devices Using PointLCA-Net—0
Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization—0
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point SetsCode1
MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model construction—0
Formula-Supervised Visual-Geometric Pre-training—0
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection—0
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning—0
PCP-MAE: Learning to Predict Centers for Point Masked AutoencodersCode2
Show:102550
← PrevPage 1 of 10Next →
All datasetsModelNet40ModelNet103R-ScanRemote Flash LiDAR Vehicles Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PolyNetAccuracy94.93—Unverified
2ORIONAccuracy93.8—Unverified
3G3DNet-18 SVM, Fine-Tuned, VoteAccuracy93.1—Unverified
4ECC (12 votes)Accuracy90—Unverified