3D Object Classification
38 papers with code • 3 benchmarks • 6 datasets
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
Datasets
Latest papers
Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid Approach
The proposed approach is a combination of the GRU and LSTM.
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder
However, a notable limitation of these approaches is that they do not fully utilize the multi-view attributes inherent in 3D point clouds, which is crucial for a deeper understanding of 3D structures.
Extending Multi-modal Contrastive Representations
Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces.
Uni3D: Exploring Unified 3D Representation at Scale
Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language.
PointLLM: Empowering Large Language Models to Understand Point Clouds
The unprecedented advancements in Large Language Models (LLMs) have shown a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding.
Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations
In contrast to other $G$-invariant architectures in the literature, the preactivations of the$G$-DNNs presented here are able to transform by \emph{signed} permutation representations (signed perm-reps) of $G$.
PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
To solve this problem, we propose a rotation-invariant geometric relation to restore the relative pose with equivariant information for patches defined over different scales.
MATE: Masked Autoencoders are Online 3D Test-Time Learners
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data.
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.