Papers with Code 아카이브

3D Shape Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

3

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Ensemble Quadratic Assignment Network for Graph Matching

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds

Multi-View Representation is What You Need for Point-Cloud Pre-Training

APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding

ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding

Frequency-domain Learning for Volumetric-based 3D Data Perception

Rethinking Rotation Invariance with Point Cloud Registration

MVTN: Learning Multi-View Transformations for 3D Understanding

LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers

PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition

VN-Transformer: Rotation-Equivariant Attention for Vector Neurons

Masked Discrimination for Self-Supervised Learning on Point Clouds

diffConv: Analyzing Irregular Point Clouds with an Irregular View

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network

POINTVIEW-GCN: 3D SHAPE CLASSIFICATION WITH MULTI-VIEW POINT CLOUDS

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

Point Cloud Learning with Transformer

Potential Convolution: Embedding Point Clouds into Potential Fields

Learning Equivariant Representations

MVTN: Multi-View Transformation Network for 3D Shape Recognition

RocNet: Recursive Octree Network for Efficient 3D Deep Representation

Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation

Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences

Shape retrieval of non-rigid 3d human models

Deep Learning for 3D Point Clouds: A Survey

A Topological Nomenclature for 3D Shape Analysis in Connectomics

HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition

View N-gram Network for 3D Object Retrieval

Rethinking Loss Design for Large-scale 3D Shape Retrieval

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.