https://github.com/avhixd/human_pose_estimation
공식 코드Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe
Deep Slow Motion Video Reconstruction with Hybrid Imaging System
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users
Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions
Images Speak in Images: A Generalist Painter for In-Context Visual Learning
HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
Deep Learning Framework for Real-time Fetal Brain Segmentation in MRI
Spatial regularisation for improved accuracy and interpretability in keypoint-based registration
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications
Self-Supervised Equivariant Learning for Oriented Keypoint Detection
OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
UniPose: Unified Human Pose Estimation in Single Images and Videos
Occlusion-Robust Object Pose Estimation with Holistic Representation
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.