Papers with Code 아카이브
Point Cloud Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 11
3D point cloud segmentation is the process of classifying point clouds into multiple homogeneous regions, the points in the same region will have the same properties. The segmentation is challenging because of high redundancy, uneven sampling density, and lack explicit structure of point cloud data. This problem has many applications in robotics such as intelligent vehicles, autonomous mapping and navigation.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Point Cloud Segmentation Using Transfer Learning with RandLA-Net: A Case Study on Urban Areas
T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
Densify Your Labels: Unsupervised Clustering with Bipartite Matching for Weakly Supervised Point Cloud Segmentation
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment
OneFormer3D: One Transformer for Unified Point Cloud Segmentation
DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation
Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation
Addressing Data Misalignment in Image-LiDAR Fusion on Point Cloud Segmentation
Generalized Few-Shot Point Cloud Segmentation Via Geometric Words
Towards Robust Few-shot Point Cloud Semantic Segmentation
Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation
Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation
Autonomous Point Cloud Segmentation for Power Lines Inspection in Smart Grid
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
Clustering based Point Cloud Representation Learning for 3D Analysis
pCTFusion: Point Convolution-Transformer Fusion with Semantic Aware Loss for Outdoor LiDAR Point Cloud Segmentation
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar
BPNet: Bézier Primitive Segmentation on 3D Point Clouds
Point2Point : A Framework for Efficient Deep Learning on Hilbert sorted Point Clouds with applications in Spatio-Temporal Occupancy Prediction
Dynamic Clustering Transformer Network for Point Cloud Segmentation
Tinto: Multisensor Benchmark for 3D Hyperspectral Point Cloud Segmentation in the Geosciences
OctFormer: Octree-based Transformers for 3D Point Clouds
Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM models
Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation
Transformer-Based Visual Segmentation: A Survey
Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network
Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
Position-Guided Point Cloud Panoptic Segmentation Transformer
Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.