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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/HDETR/H-PETR-3D
공식 코드https://github.com/HDETR/H-PETR-Pose
공식 코드https://github.com/HKUST-Aerial-Robotics/ESVO
공식 코드https://github.com/HKUST-Aerial-Robotics/VINS-Fusion
공식 코드A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors
https://github.com/HKUST-Aerial-Robotics/VINS-Mono
공식 코드Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM
https://github.com/HMX2013/Covex-hull-based-fitting-3D-LiDAR-ROS
공식 코드An Efficient Convex Hull-based Vehicle Pose Estimation Method for 3D LiDAR
https://github.com/HRNet/DEKR
공식 코드Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
https://github.com/HRNet/HRFormer
공식 코드https://github.com/HRNet/HRNet-Bottom-Up-Pose-Estimation
공식 코드Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates
https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation
공식 코드HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
https://github.com/HRNet/Lite-HRNet
공식 코드https://github.com/HSarham/automatic-ar
공식 코드Simultaneous Multi-View Camera Pose Estimation and Object Tracking with Square Planar Markers
https://github.com/HeCraneChen/3D-Crowd-Pose-Estimation-Based-on-MVG
공식 코드Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
https://github.com/Healthcare-Robotics/bodies-at-rest
공식 코드Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data
https://github.com/HendrikMuenster/superResolution
공식 코드https://github.com/HongwenZhang/DaNet-DensePose2SMPL
공식 코드https://github.com/HongwenZhang/PyMAF
공식 코드PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
https://github.com/HowieMa/NSRMhand
공식 코드Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation
https://github.com/HuaWeitong/REDE
공식 코드REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination
https://github.com/HuangJunJie2017/UDP-Pose
공식 코드The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
https://github.com/IBM/RegionViT
공식 코드RegionViT: Regional-to-Local Attention for Vision Transformers
https://github.com/IDEA-Research/HumanArt
공식 코드Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes
https://github.com/IDEA-Research/OSX
공식 코드One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
https://github.com/IDEA-Research/UniPose
공식 코드https://github.com/IDEA-Research/detrex
공식 코드https://github.com/IF-A-CAT/LIR-LIVO
공식 코드https://github.com/IIGROUP/PoseDet
공식 코드PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
https://github.com/IIT-PAVIS/lifting_events_to_3d_hpe
공식 코드https://github.com/IRMVLab/PWCLONet
공식 코드PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization
https://github.com/IRVLUTD/FewSOL-DataLoader
공식 코드FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
https://github.com/IRVLUTD/HO-Cap
공식 코드https://github.com/IRVLUTD/fewsol-toolkit
공식 코드FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
https://github.com/IRVLUTD/meta-dataset
공식 코드FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
https://github.com/IRVLab/unrolling
공식 코드IMU-Assisted Learning of Single-View Rolling Shutter Correction
https://github.com/IcarusWizard/PixelwiseRegression
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.