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.
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
DiffSLVA: Harnessing Diffusion Models for Sign Language Video Anonymization
DiffBindFR: An SE(3) Equivariant Network for Flexible Protein-Ligand Docking
FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration
RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling
BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning
GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence
GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence
Appearance-based gaze estimation enhanced with synthetic images using deep neural networks
HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation
Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning
Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency
HCA-Net: Hierarchical Context Attention Network for Intervertebral Disc Semantic Labeling
HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation
BundleMoCap: Efficient, Robust and Smooth Motion Capture from Sparse Multiview Videos
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Robot Hand-Eye Calibration using Structure-from-Motion
SniffyArt: The Dataset of Smelling Persons
LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models
Jenga Stacking Based on 6D Pose Estimation for Architectural Form Finding Process
Multiple View Geometry Transformers for 3D Human Pose Estimation
Synthetic Data Generation for Bridging Sim2Real Gap in a Production Environment
SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
LOSTU: Fast, Scalable, and Uncertainty-Aware Triangulation
BiHRNet: A Binary high-resolution network for Human Pose Estimation
Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration
Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation
Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation
Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery
Improved TokenPose with Sparsity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.