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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution
From Real Artifacts to Virtual Reference: A Robust Framework for Translating Endoscopic Images
X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing
3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications
Occluded Human Pose Estimation based on Limb Joint Augmentation
Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis
Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities
Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization
CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation
Facial Chick Sexing: An Automated Chick Sexing System From Chick Facial Image
Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos
LucidGrasp: Robotic Framework for Autonomous Manipulation of Laboratory Equipment with Different Degrees of Transparency via 6D Pose Estimation
RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation
Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation
OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
FürElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?
SpecTrack: Learned Multi-Rotation Tracking via Speckle Imaging
Unsupervised Model Diagnosis
D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation
Comparison of marker-less 2D image-based methods for infant pose estimation
LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation
Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localization
HRVMamba: High-Resolution Visual State Space Model for Dense Prediction
Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
A Generic Observer Design for Inertial Navigation Systems Using an LTV Framework
Unsupervised Prior Learning: Discovering Categorical Pose Priors from Videos
Learning Truncated Causal History Model for Video Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.