Papers with Code 아카이브
3D Object Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 122
3D Object Tracking is a computer vision task dedicated to monitoring and precisely locating objects as they navigate within a three-dimensional environment. It frequently utilizes 3D object detection techniques to pinpoint the objects and establish unique identifications that persist across multiple frames.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
TrackOcc: Camera-based 4D Panoptic Occupancy Tracking
A Modular Pipeline for 3D Object Tracking Using RGB Cameras
Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions
GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack
Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking
3D Single-object Tracking in Point Clouds with High Temporal Variation
SiamMo: Siamese Motion-Centric 3D Object Tracking
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
FlowTrack: Point-level Flow Network for 3D Single Object Tracking
DGD: Dynamic 3D Gaussians Distillation
PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds
SceneTracker: Long-term Scene Flow Estimation Network
Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking
RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception
SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking
GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance
Towards Category Unification of 3D Single Object Tracking on Point Clouds
Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Tracking
Robust 3D Tracking with Quality-Aware Shape Completion
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Tracking
CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View
The Interstate-24 3D Dataset: a new benchmark for 3D multi-camera vehicle tracking
Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking
Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
BOTT: Box Only Transformer Tracker for 3D Object Tracking
STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.