3D Object Classification
42 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.
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
To this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation.
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.
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud
In this study, we introduce a novel selfsupervised method called CrossMoCo, which learns the representations of unlabelled point cloud data in a multi-modal setup that also utilizes the 2D rendered images of the point clouds.
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.