https://github.com/DLR-RM/3DObjectTracking/tree/master/SRT3D
공식 코드SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
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.
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
Polarized Self-Attention: Towards High-quality Pixel-wise Regression
Markerless tracking of user-defined features with deep learning
CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration
IFTD: Image Feature Triangle Descriptor for Loop Detection in Driving Scenes
AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
FaceFormer: Speech-Driven 3D Facial Animation with Transformers
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
Structured Context Enhancement Network for Mouse Pose Estimation
CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds
Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical Applications
DiffBindFR: An SE(3) Equivariant Network for Flexible Protein-Ligand Docking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.