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
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud UnderstandingCode2
Uni3D: Exploring Unified 3D Representation at ScaleCode2
PointLLM: Empowering Large Language Models to Understand Point CloudsCode2
PCP-MAE: Learning to Predict Centers for Point Masked AutoencodersCode2
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
Point TransformerCode1
DC3DO: Diffusion Classifier for 3D ObjectsCode1
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point CloudsCode1
Cascaded Refinement Network for Point Cloud Completion with Self-supervisionCode1
Block Coordinate Descent for Sparse NMFCode1
ScanNet: Richly-annotated 3D Reconstructions of Indoor ScenesCode1
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point SetsCode1
diffConv: Analyzing Irregular Point Clouds with an Irregular ViewCode1
PointMixer: MLP-Mixer for Point Cloud UnderstandingCode1
Open-Pose 3D Zero-Shot Learning: Benchmark and ChallengesCode1
Point Cloud Self-supervised Learning via 3D to Multi-view Masked AutoencoderCode1
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
MATE: Masked Autoencoders are Online 3D Test-Time LearnersCode1
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World DataCode1
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksCode1
Exploiting Inductive Bias in Transformer for Point Cloud Classification and SegmentationCode1
Regularization Strategy for Point Cloud via Rigidly Mixed SampleCode1
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape AnalysisCode1
Extending Multi-modal Contrastive RepresentationsCode1
PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape RepresentationCode1
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D SequencesCode1
FPConv: Learning Local Flattening for Point ConvolutionCode1
Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text—0
MVImgNet: A Large-scale Dataset of Multi-view Images—0
Wide and deep volumetric residual networks for volumetric image classification—0
Classification of Single-View Object Point Clouds—0
3D Object Classification via Spherical Projections—0
3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN—0
ABD-Net: Attention Based Decomposition Network for 3D Point Cloud Decomposition—0
Addressing the Sim2Real Gap in Robotic 3D Object Classification—0
An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease—0
Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation—0
Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization—0
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition—0
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis—0
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection—0
Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation—0
Data-Free Point Cloud Network for 3D Face Recognition—0
Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems—0
Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification—0
Efficient Spatio-Temporal Signal Recognition on Edge Devices Using PointLCA-Net—0
Fast Sparse 3D Convolution Network with VDB—0
Formula-Supervised Visual-Geometric Pre-training—0
FusionNet: 3D Object Classification Using Multiple Data Representations—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