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

Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder

zhimin-c/multiview-mae 17 Nov 2023

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.

6
17 Nov 2023

Extending Multi-modal Contrastive Representations

mcr-peft/ex-mcr 13 Oct 2023

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.

30
13 Oct 2023

Uni3D: Exploring Unified 3D Representation at Scale

baaivision/GeoDream 10 Oct 2023

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.

550
10 Oct 2023

PointLLM: Empowering Large Language Models to Understand Point Clouds

openrobotlab/pointllm 31 Aug 2023

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.

360
31 Aug 2023

Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation

jiamang/ibt 27 Apr 2023

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.

9
27 Apr 2023

Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations

dagrawa2/gdnn_code 8 Mar 2023

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 $G$.

0
08 Mar 2023

PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration

dingxin-zhang/PaRot 6 Feb 2023

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.

6
06 Feb 2023

MATE: Masked Autoencoders are Online 3D Test-Time Learners

jmiemirza/mate ICCV 2023

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.

14
21 Nov 2022

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

gfmei/softclu 6 Oct 2022

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.

16
06 Oct 2022