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.
MeshCNN: A Network with an Edge
Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
Spherical Convolutional Neural Network for 3D Point Clouds
Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems
General-Purpose Deep Point Cloud Feature Extractor
3D Object Classification via Spherical Projections
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
Wide and deep volumetric residual networks for volumetric image classification
Learning a Hierarchical Latent-Variable Model of 3D Shapes
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
OctNet: Learning Deep 3D Representations at High Resolutions
FusionNet: 3D Object Classification Using Multiple Data Representations
Orientation-boosted Voxel Nets for 3D Object Recognition
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
Block Coordinate Descent for Sparse NMF
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.