Papers with Code 아카이브
3D Object Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 4
- 보존된 평가 기록
- 14
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PointMixer: MLP-Mixer for Point Cloud Understanding
Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation
PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation
Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
ABD-Net: Attention Based Decomposition Network for 3D Point Cloud Decomposition
Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification
Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
Spherical Transformer: Adapting Spherical Signal to CNNs
Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
Classification of Single-View Object Point Clouds
I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting
A Fast Hybrid Cascade Network for Voxel-based 3D Object Classification
Point Transformer
Cascaded Refinement Network for Point Cloud Completion with Self-supervision
Generalized Multi-view Shared Subspace Learning using View Bootstrapping
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
FPConv: Learning Local Flattening for Point Convolution
InSphereNet: a Concise Representation and Classification Method for 3D Object
L3DOC: Lifelong 3D Object Classification
Data-Free Point Cloud Network for 3D Face Recognition
Addressing the Sim2Real Gap in Robotic 3D Object Classification
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
Octree guided CNN with Spherical Kernels for 3D Point Clouds
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
3D Point Capsule Networks
3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN
A Graph-CNN for 3D Point Cloud Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.