https://github.com/parskatt/dedode
공식 코드DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
DKM: Dense Kernelized Feature Matching for Geometry Estimation
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration
On the representation and methodology for wide and short range head pose estimation
PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Research
CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers
Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
A Robust Filter for Marker-less Multi-person Tracking in Human-Robot Interaction Scenarios
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
AGORA: Avatars in Geography Optimized for Regression Analysis
S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR
Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration
Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding
Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
Focal Length and Object Pose Estimation via Render and Compare
Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models
Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
Mobile-URSONet: an Embeddable Neural Network for Onboard Spacecraft Pose Estimation
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
PowerSkel: A Device-Free Framework Using CSI Signal for Human Skeleton Estimation in Power Station
Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation
Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.