https://github.com/ShirleyMaxx/ContextPose-PyTorch-release
Context Modeling in 3D Human Pose Estimation: A Unified Perspective
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.
Context Modeling in 3D Human Pose Estimation: A Unified Perspective
Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning
MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
SuperGlue: Learning Feature Matching with Graph Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.