Papers with Code 아카이브
Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 31
- 보존된 평가 기록
- 235
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Multi-Transmotion: Pre-trained Model for Human Motion Prediction
Activating Self-Attention for Multi-Scene Absolute Pose Regression
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Whole-Herd Elephant Pose Estimation from Drone Data for Collective Behavior Analysis
SCRREAM : SCan, Register, REnder And Map:A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation
LiVisSfM: Accurate and Robust Structure-from-Motion with LiDAR and Visual Cues
Yoga Pose Classification Using Transfer Learning
BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment
Synthetica: Large Scale Synthetic Data for Robot Perception
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior
Neural Fields in Robotics: A Survey
DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems
VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
YOLOv11: An Overview of the Key Architectural Enhancements
Robust Two-View Geometry Estimation with Implicit Differentiation
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images
Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
QuickBind: A Light-Weight And Interpretable Molecular Docking Model
YOLO11 and Vision Transformers based 3D Pose Estimation of Immature Green Fruits in Commercial Apple Orchards for Robotic Thinning
POSE: Pose estimation Of virtual Sync Exhibit system
Neural Active Structure-from-Motion in Dark and Textureless Environment
Unlabeled Action Quality Assessment Based on Multi-dimensional Adaptive Constrained Dynamic Time Warping
Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior
Object Pose Estimation Using Implicit Representation For Transparent Objects
Sparse Prototype Network for Explainable Pedestrian Behavior Prediction
Optimizing Multi-Task Learning for Accurate Spacecraft Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.