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/SUTDCV/UAV-Human

공식 코드

UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

https://github.com/SadilKhan/MARVEL-FX3D

공식 코드

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

https://github.com/SaharAlmahfouzNasser/MeDAL-Retina

공식 코드

Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data

https://github.com/Santa-Clara-Media-Lab/MoEmo_Vision_Transformer

공식 코드

MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection

https://github.com/Santa-Clara-Media-Lab/SoloPose

공식 코드

SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation

https://github.com/SeanChenxy/HandMesh

공식 코드

Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration

https://github.com/SebastianJanampa/DETRPose

공식 코드

DETRPose: Real-time end-to-end transformer model for multi-person pose estimation

https://github.com/SeongJong-Yoo/VioPose

공식 코드

VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference

https://github.com/SergioRAgostinho/cvxpnpl

공식 코드

CvxPnPL: A Unified Convex Solution to the Absolute Pose Estimation Problem from Point and Line Correspondences

https://github.com/SeungBack/graspclutter6dAPI

공식 코드

GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes

https://github.com/Shiaoming/ALIKE

공식 코드

ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction

https://github.com/ShirleyMaxx/VirtualMarker

공식 코드

3D Human Mesh Estimation from Virtual Markers

https://github.com/ShuhongChen/bizarre-pose-estimator

공식 코드

Transfer Learning for Pose Estimation of Illustrated Characters

https://github.com/SimingYan/Hybrid_Relative_Pose

공식 코드

Extreme Relative Pose Network under Hybrid Representations

https://github.com/Sirui-Xu/InterDiff

공식 코드

InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion

https://github.com/Snapchat/MeshPose

공식 코드

MeshPose: Unifying DensePose and 3D Body Mesh reconstruction

https://github.com/Sophie-Xu/Pose_DomainAdaption

공식 코드

Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation

https://github.com/StanfordMSL/Splat-MOVER

공식 코드

Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting

https://github.com/StructuresComp/measure-anything

공식 코드

Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything

https://github.com/SwinTransformer/MIM-Depth-Estimation

공식 코드

Revealing the Dark Secrets of Masked Image Modeling

https://github.com/T1sweet/HEViTPose

공식 코드

HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation

https://github.com/TCXX/ObjaversePlusPlus

공식 코드

Objaverse++: Curated 3D Object Dataset with Quality Annotations

https://github.com/THU-DA-6D-Pose-Group/GDR-Net

공식 코드

GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator

https://github.com/THU-DA-6D-Pose-Group/Self6D-Diff-Renderer

공식 코드

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

https://github.com/THU-VCLab/HGGD

공식 코드

Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes

https://github.com/TOPO-EPFL/TOPO-DataGen

공식 코드

CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data

https://github.com/TRI-ML/KP2D

공식 코드

Neural Outlier Rejection for Self-Supervised Keypoint Learning

https://github.com/TRI-ML/KP3D

공식 코드

Self-Supervised 3D Keypoint Learning for Ego-motion Estimation

https://github.com/TaatiTeam/stgcn_parkinsonism_prediction

공식 코드

Estimating Parkinsonism Severity in Natural Gait Videos of Older Adults with Dementia

https://github.com/Tang1705/Semantic-Lens-AAAI24

공식 코드

Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution

https://github.com/TencentARC/GFPGAN

공식 코드

Towards Real-World Blind Face Restoration with Generative Facial Prior

https://github.com/TerenceCYJ/S2HAND

공식 코드

Model-based 3D Hand Reconstruction via Self-Supervised Learning

https://github.com/Tete-Xiao/ReSim

공식 코드

Region Similarity Representation Learning

https://github.com/Thmen/EGVSR

공식 코드

Real-Time Super-Resolution System of 4K-Video Based on Deep Learning

https://github.com/TimoBolkart/voca

공식 코드

Capture, Learning, and Synthesis of 3D Speaking Styles

https://github.com/Tombs98/SU-Net

공식 코드

SU-Net: Pose estimation network for non-cooperative spacecraft on-orbit

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