https://github.com/twehrbein/humr
공식 코드Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
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.
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model
Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos
Centroid Distance Keypoint Detector for Colored Point Clouds
NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud
CHSEL: Producing Diverse Plausible Pose Estimates from Contact and Free Space Data
A simple yet effective baseline for 3d human pose estimation
MARIO: Modular and Extensible Architecture for Computing Visual Statistics in RoboCup SPL
PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision
eKalibr: Dynamic Intrinsic Calibration for Event Cameras From First Principles of Events
Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training
A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty
FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion
BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception
Matching Features without Descriptors: Implicitly Matched Interest Points
SIPs: Succinct Interest Points from Unsupervised Inlierness Probability Learning
Learning Human-Object Interaction Detection using Interaction Points
3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views
3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views
Generalizable Pose Estimation Using Implicit Scene Representations
Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.