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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 21–30 of 93 papers

Title	Date	Tasks	Status	Hype
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud	Dec 20, 2020	3D Object Classification3D Part Segmentation	CodeCode Available	1
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder	Nov 17, 2023	3D Object Classification3D Object Detection	CodeCode Available	1
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets	Oct 14, 2024	3D Classification3D Object Classification	CodeCode Available	1
Point Transformer	Nov 2, 2020	3D Object Classification3D Part Segmentation	CodeCode Available	1
diffConv: Analyzing Irregular Point Clouds with an Irregular View	Nov 29, 2021	3D Object Classification3D Point Cloud Classification	CodeCode Available	1
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges	Dec 12, 2023	3D Object ClassificationClassification	CodeCode Available	1
FPConv: Learning Local Flattening for Point Convolution	Feb 25, 2020	3D Object ClassificationScene Segmentation	CodeCode Available	1
ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes	Feb 14, 2017	3D Object ClassificationGeneral Classification	CodeCode Available	1
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis	Jun 1, 2019	3D Object Classification3D Object Recognition	—Unverified	0
Efficient Spatio-Temporal Signal Recognition on Edge Devices Using PointLCA-Net	Nov 21, 2024	3D Object ClassificationComputational Efficiency	—Unverified	0

Show:10 25 50

← PrevPage 3 of 10Next →

All datasets ModelNet40 ModelNet10 3R-Scan Remote Flash LiDAR Vehicles Dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Ours	Classification Accuracy	93.6	—	Unverified
2	G3DNet-18 MLP, Fine-Tuned, Vote	Classification Accuracy	91.7	—	Unverified
3	CrossMoCo	Classification Accuracy	91.49	—	Unverified
4	O-CNN(6)	Classification Accuracy	89.9	—	Unverified
5	Spherical Kernel	Classification Accuracy	89.3	—	Unverified
6	3D-PointCapsNet	Classification Accuracy	89.3	—	Unverified
7	ECC (12 votes)	Classification Accuracy	83.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PolyNet	Accuracy	94.93	—	Unverified
2	ORION	Accuracy	93.8	—	Unverified
3	G3DNet-18 SVM, Fine-Tuned, Vote	Accuracy	93.1	—	Unverified
4	ECC (12 votes)	Accuracy	90	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SceneGraphFusion	Top-10 Accuracy	0.8	—	Unverified
2	3DSSG [Wald2020_3dssg]	Top-10 Accuracy	0.78	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	YOLO-X	mean average precision	0.99	—	Unverified