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 1–50 of 93 papers

TitleStatusHype
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D PriorsCode2
Uni3D: Exploring Unified 3D Representation at ScaleCode2
PCP-MAE: Learning to Predict Centers for Point Masked AutoencodersCode2
PointLLM: Empowering Large Language Models to Understand Point CloudsCode2
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud UnderstandingCode2
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point CloudsCode1
FPConv: Learning Local Flattening for Point ConvolutionCode1
Cascaded Refinement Network for Point Cloud Completion with Self-supervisionCode1
PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape RepresentationCode1
Point TransformerCode1
Block Coordinate Descent for Sparse NMFCode1
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point SetsCode1
PointMixer: MLP-Mixer for Point Cloud UnderstandingCode1
Point Cloud Self-supervised Learning via 3D to Multi-view Masked AutoencoderCode1
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
DC3DO: Diffusion Classifier for 3D ObjectsCode1
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape AnalysisCode1
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D SequencesCode1
diffConv: Analyzing Irregular Point Clouds with an Irregular ViewCode1
Open-Pose 3D Zero-Shot Learning: Benchmark and ChallengesCode1
MATE: Masked Autoencoders are Online 3D Test-Time LearnersCode1
ScanNet: Richly-annotated 3D Reconstructions of Indoor ScenesCode1
Exploiting Inductive Bias in Transformer for Point Cloud Classification and SegmentationCode1
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World DataCode1
Extending Multi-modal Contrastive RepresentationsCode1
Regularization Strategy for Point Cloud via Rigidly Mixed SampleCode1
A Graph-CNN for 3D Point Cloud ClassificationCode0
3D Point Capsule NetworksCode0
Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid ApproachCode0
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point CloudCode0
Densely Connected G-invariant Deep Neural Networks with Signed Permutation RepresentationsCode0
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on GraphsCode0
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud ClassifiersCode0
A Fast Hybrid Cascade Network for Voxel-based 3D Object ClassificationCode0
General-Purpose Deep Point Cloud Feature ExtractorCode0
Improved Training for 3D Point Cloud ClassificationCode0
InSphereNet: a Concise Representation and Classification Method for 3D ObjectCode0
Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional NetworksCode0
Learning a Hierarchical Latent-Variable Model of 3D ShapesCode0
MeshCNN: A Network with an EdgeCode0
OctNet: Learning Deep 3D Representations at High ResolutionsCode0
On Automatic Data Augmentation for 3D Point Cloud ClassificationCode0
PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose RestorationCode0
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised ViewpointsCode0
Spherical Kernel for Efficient Graph Convolution on 3D Point CloudsCode0
L3DOC: Lifelong 3D Object Classification—0
Spherical Transformer: Adapting Spherical Signal to CNNs—0
SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsModelNet40ModelNet103R-ScanRemote Flash LiDAR Vehicles Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OursClassification Accuracy93.6—Unverified
2G3DNet-18 MLP, Fine-Tuned, VoteClassification Accuracy91.7—Unverified
3CrossMoCoClassification Accuracy91.49—Unverified
4O-CNN(6)Classification Accuracy89.9—Unverified
5Spherical KernelClassification Accuracy89.3—Unverified
63D-PointCapsNetClassification Accuracy89.3—Unverified
7ECC (12 votes)Classification Accuracy83.2—Unverified
#ModelMetricClaimedVerifiedStatus
1PolyNetAccuracy94.93—Unverified
2ORIONAccuracy93.8—Unverified
3G3DNet-18 SVM, Fine-Tuned, VoteAccuracy93.1—Unverified
4ECC (12 votes)Accuracy90—Unverified
#ModelMetricClaimedVerifiedStatus
1SceneGraphFusionTop-10 Accuracy0.8—Unverified
23DSSG [Wald2020_3dssg]Top-10 Accuracy0.78—Unverified
#ModelMetricClaimedVerifiedStatus
1YOLO-Xmean average precision0.99—Unverified