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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Microsoft/O-CNN
공식 코드O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
https://github.com/RosettaWYzhang/AdaPC
공식 코드On Automatic Data Augmentation for 3D Point Cloud Classification
https://github.com/ShunChengWu/3DSSG
공식 코드SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
https://github.com/ShunChengWu/SceneGraphFusion
공식 코드SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
https://github.com/aHapBean/PCP-MAE
공식 코드PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
https://github.com/ali-stanford/pointnet_kan_graphic
공식 코드PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets
https://github.com/baaivision/uni3d
공식 코드https://github.com/cscvlab/InSphereNet
공식 코드InSphereNet: a Concise Representation and Classification Method for 3D Object
https://github.com/dagrawa2/gdnn_code
공식 코드Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations
https://github.com/dingxin-zhang/PaRot
공식 코드PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
https://github.com/dogyoonlee/RSMix-official
공식 코드Regularization Strategy for Point Cloud via Rigidly Mixed Sample
https://github.com/engelnico/point-transformer
공식 코드https://github.com/gfmei/softclu
공식 코드Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
https://github.com/griegler/octnet
공식 코드OctNet: Learning Deep 3D Representations at High Resolutions
https://github.com/hkust-vgd/scanobjectnn
공식 코드https://github.com/hlei-ziyan/SPH3D-GCN
공식 코드Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
https://github.com/jiamang/ibt
공식 코드Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation
https://github.com/jmiemirza/mate
공식 코드https://github.com/kanezaki/rotationnet
공식 코드https://github.com/lifebeyondexpectations/eccv22-pointmixer
공식 코드https://github.com/lorenmt/vsl
공식 코드https://github.com/lyqun/FPConv
공식 코드https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification
공식 코드https://github.com/mcr-peft/ex-mcr
공식 코드https://github.com/mmmmimic/diffconvnet
공식 코드diffConv: Analyzing Irregular Point Clouds with an Irregular View
https://github.com/mohamedafham/crosspoint
공식 코드CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
https://github.com/mutianxu/GDANet
공식 코드https://github.com/myavartanoo/PolyNet_PyTorch
공식 코드PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation
https://github.com/mys007/ecc
공식 코드Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
https://github.com/openrobotlab/pointllm
공식 코드PointLLM: Empowering Large Language Models to Understand Point Clouds
https://github.com/qizekun/ShapeLLM
공식 코드ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/ranahanocka/MeshCNN
공식 코드https://github.com/raoyongming/PointGLR
공식 코드Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
https://github.com/saba99/classifying-objects-3d-point-clouds
공식 코드Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid Approach
https://github.com/sgi-2023/3d-building-classification
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.