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.
AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution
Fast and Robust Localization for Humanoid Soccer Robot via Iterative Landmark Matching
Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses
Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation
VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames
6D Object Pose Tracking in Internet Videos for Robotic Manipulation
Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
Clothes-Changing Person Re-identification Based On Skeleton Dynamics
Better Together: Unified Motion Capture and 3D Avatar Reconstruction
GenHPE: Generative Counterfactuals for 3D Human Pose Estimation with Radio Frequency Signals
CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
Keypoint Detection and Description for Raw Bayer Images
Keypoint Semantic Integration for Improved Feature Matching in Outdoor Agricultural Environments
Acoustic Neural 3D Reconstruction Under Pose Drift
PoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM
Multi-Modal 3D Mesh Reconstruction from Images and Text
Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion
DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding
AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements
HumanMM: Global Human Motion Recovery from Multi-shot Videos
AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision
NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features
GaussianCAD: Robust Self-Supervised CAD Reconstruction from Three Orthographic Views Using 3D Gaussian Splatting
SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting
Multi-Grained Feature Pruning for Video-Based Human Pose Estimation
Novel Object 6D Pose Estimation with a Single Reference View
GAGrasp: Geometric Algebra Diffusion for Dexterous Grasping
Spatial regularisation for improved accuracy and interpretability in keypoint-based registration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.