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

Showing 125 of 93 papers

TitleStatusHype
PointLLM: Empowering Large Language Models to Understand Point CloudsCode2
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D PriorsCode2
PCP-MAE: Learning to Predict Centers for Point Masked AutoencodersCode2
Uni3D: Exploring Unified 3D Representation at ScaleCode2
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud UnderstandingCode2
Regularization Strategy for Point Cloud via Rigidly Mixed SampleCode1
PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point SetsCode1
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World DataCode1
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape AnalysisCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
Block Coordinate Descent for Sparse NMFCode1
PointMixer: MLP-Mixer for Point Cloud UnderstandingCode1
Point TransformerCode1
PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape RepresentationCode1
MATE: Masked Autoencoders are Online 3D Test-Time LearnersCode1
Cascaded Refinement Network for Point Cloud Completion with Self-supervisionCode1
FPConv: Learning Local Flattening for Point ConvolutionCode1
Open-Pose 3D Zero-Shot Learning: Benchmark and ChallengesCode1
diffConv: Analyzing Irregular Point Clouds with an Irregular ViewCode1
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point CloudCode1
DC3DO: Diffusion Classifier for 3D ObjectsCode1
Extending Multi-modal Contrastive RepresentationsCode1
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point CloudsCode1
Exploiting Inductive Bias in Transformer for Point Cloud Classification and SegmentationCode1
Point Cloud Self-supervised Learning via 3D to Multi-view Masked AutoencoderCode1
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OursClassification Accuracy93.6Unverified
2G3DNet-18 MLP, Fine-Tuned, VoteClassification Accuracy91.7Unverified
3CrossMoCoClassification Accuracy91.49Unverified
4O-CNN(6)Classification Accuracy89.9Unverified
5Spherical KernelClassification Accuracy89.3Unverified
63D-PointCapsNetClassification Accuracy89.3Unverified
7ECC (12 votes)Classification Accuracy83.2Unverified
#ModelMetricClaimedVerifiedStatus
1PolyNetAccuracy94.93Unverified
2ORIONAccuracy93.8Unverified
3G3DNet-18 SVM, Fine-Tuned, VoteAccuracy93.1Unverified
4ECC (12 votes)Accuracy90Unverified
#ModelMetricClaimedVerifiedStatus
1SceneGraphFusionTop-10 Accuracy0.8Unverified
23DSSG [Wald2020_3dssg]Top-10 Accuracy0.78Unverified
#ModelMetricClaimedVerifiedStatus
1YOLO-Xmean average precision0.99Unverified