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/wmcnally/deep-darts

공식 코드

DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera

https://github.com/wmcnally/evopose2d

공식 코드

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer

https://github.com/wmcnally/kapao

공식 코드

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

https://github.com/woven-planet/DiffusionNOCS

공식 코드

DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimation

https://github.com/wrld/PRoGAN

공식 코드

PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation

https://github.com/wrld/free-surgs

공식 코드

Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction

https://github.com/wrld/visual_navigation_pose_estimation

공식 코드

A Visual Navigation Perspective for Category-Level Object Pose Estimation

https://github.com/wsakobe/cylindertag

공식 코드

CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants

https://github.com/wtjiang98/PoseTrans

공식 코드

PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

https://github.com/wu-cvgl/GlobalPointer

공식 코드

GlobalPointer: Large-Scale Plane Adjustment with Bi-Convex Relaxation

https://github.com/wufeim/6d_pose_eccv22

공식 코드

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features

https://github.com/wufeim/imagenet3d

공식 코드

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding

https://github.com/wuhaozhe/audio2face_mm2023

공식 코드

Speech-Driven 3D Face Animation with Composite and Regional Facial Movements

https://github.com/wujinhuan/3d-human-pose

공식 코드

Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers

https://github.com/wujinhuan/depropose

공식 코드

DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion

https://github.com/wusize/multiview_pose

공식 코드

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

https://github.com/wyddmw/pomato

공식 코드

POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction

https://github.com/xahidbuffon/funie-gan

공식 코드

Fast Underwater Image Enhancement for Improved Visual Perception

https://github.com/xavier-zw/tdensernn_pose

공식 코드

A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation

https://github.com/xccyue/MutualDistance

공식 코드

Scene-aware Human Motion Forecasting via Mutual Distance Prediction

https://github.com/xhaughearl/haarmodic

공식 코드

Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform

https://github.com/xiangchenyin/grpose

공식 코드

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

https://github.com/xiaobenli00/u-hmr

공식 코드

Human Mesh Recovery from Arbitrary Multi-view Images

https://github.com/xiaobiaodu/DreamCar

공식 코드

DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction

https://github.com/xiaogang00/dp3df

공식 코드

Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution

https://github.com/xiaxx244/shadow_pose_estimation

공식 코드

Privacy-Preserving Pose Estimation for Human-Robot Interaction

https://github.com/xiekkki/motionbev

공식 코드

MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features

https://github.com/xierc/Semi_Human_Pose

공식 코드

An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

https://github.com/xieyuser/semi-sd

공식 코드

Semi-SD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving

https://github.com/xinghaochen/Pose-REN

공식 코드

Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation

https://github.com/xingyizhou/CenterNet

공식 코드

Objects as Points

https://github.com/xingyizhou/StarMap

공식 코드

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

https://github.com/xingyizhou/pose-hg-3d

공식 코드

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

https://github.com/xingyu-song/4a

공식 코드

An Animation-based Augmentation Approach for Action Recognition from Discontinuous Video

https://github.com/xingyu-song/q_gcn

공식 코드

Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training

https://github.com/xingzhehe/AutoLink-Self-supervised-Learning-of-Human-Skeletons-and-Object-Outlines-by-Linking-Keypoints

공식 코드

AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

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