Papers with Code 아카이브

Pose Estimation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/mgb45/mkfbodytracker_pdaf

공식 코드

Single camera pose estimation using Bayesian filtering and Kinect motion priors

https://github.com/mgholamikn/AdaptPose

공식 코드

AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

https://github.com/mgiant/mp-gcn

공식 코드

Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph

https://github.com/michel-liu/grouppose

공식 코드

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

https://github.com/michel-liu/grouppose-paddle

공식 코드

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

https://github.com/michigancog/forcepose

공식 코드

Learning to Estimate External Forces of Human Motion in Video

https://github.com/microsoft/MeshTransformer

공식 코드

End-to-End Human Pose and Mesh Reconstruction with Transformers

https://github.com/microsoft/meshgraphormer

공식 코드

Mesh Graphormer

https://github.com/microsoft/multiview-human-pose-estimation-pytorch

공식 코드

Cross View Fusion for 3D Human Pose Estimation

https://github.com/microsoft/scenelandmarklocalization

공식 코드

Improved Scene Landmark Detection for Camera Localization

https://github.com/microsoft/voxelpose-pytorch

공식 코드

VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment

https://github.com/microsoft/vsr-challenge

공식 코드

ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencing

https://github.com/minghanz/e2pn

공식 코드

E2PN: Efficient SE(3)-Equivariant Point Network

https://github.com/mingyuyng/visual-selective-vio

공식 코드

Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection

https://github.com/minhaolee/2d3dmatr

공식 코드

2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds

https://github.com/minnjung/ep2p-loc

공식 코드

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

https://github.com/mit-han-lab/litepose

공식 코드

Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

https://github.com/mit-spark/c-3po

공식 코드

Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training

https://github.com/mit-spark/pace

공식 코드

Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints

https://github.com/mkocabas/EpipolarPose

공식 코드

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry

https://github.com/mkocabas/PARE

공식 코드

PARE: Part Attention Regressor for 3D Human Body Estimation

https://github.com/mkocabas/SPEC

공식 코드

SPEC: Seeing People in the Wild with an Estimated Camera

https://github.com/mkocabas/VIBE

공식 코드

VIBE: Video Inference for Human Body Pose and Shape Estimation

https://github.com/mks0601/3DMPPE_POSENET_RELEASE

공식 코드

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE

공식 코드

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

https://github.com/mks0601/Hand4Whole_RELEASE

공식 코드

Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation

https://github.com/mks0601/I2L-MeshNet_RELEASE

공식 코드

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image

https://github.com/mks0601/IntegralAction_RELEASE

공식 코드

IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos

https://github.com/mks0601/NeuralAnnot_RELEASE

공식 코드

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

https://github.com/mks0601/PoseFix_RELEASE

공식 코드

PoseFix: Model-agnostic General Human Pose Refinement Network

https://github.com/mks0601/V2V-PoseNet_RELEASE

공식 코드

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

https://github.com/mlgig/bodymts_2021

공식 코드

Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers

https://github.com/mlpc-ucsd/PRTR

공식 코드

Pose Recognition with Cascade Transformers

https://github.com/mlvlab/UP-NeRF

공식 코드

UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields

https://github.com/mmahdavian/stpotr

공식 코드

STPOTR: Simultaneous Human Trajectory and Pose Prediction Using a Non-Autoregressive Transformer for Robot Following Ahead

https://github.com/mmlab-cv/deca

공식 코드

DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.