Papers with Code 아카이브
3D Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 19
- 보존된 평가 기록
- 145
3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution
SeSame: Simple, Easy 3D Object Detection with Point-Wise Semantics
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding
MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding
Is Continual Learning Ready for Real-world Challenges?
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering
ODIN: A Single Model for 2D and 3D Segmentation
Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation
WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments
Language-Assisted 3D Scene Understanding
Point Transformer V3: Simpler, Faster, Stronger
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
Novel class discovery meets foundation models for 3D semantic segmentation
ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction
2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation
Seeing Beyond Cancer: Multi-Institutional Validation of Object Localization and 3D Semantic Segmentation using Deep Learning for Breast MRI
OneFormer3D: One Transformer for Unified Point Cloud Segmentation
Instance-aware 3D Semantic Segmentation powered by Shape Generators and Classifiers
Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation
GNeSF: Generalizable Neural Semantic Fields
Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving
Vision Transformers increase efficiency of 3D cardiac CT multi-label segmentation
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation
Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training
Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.