Papers with Code 아카이브
Pose Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 16
Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.
Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Example-based Motion Synthesis via Generative Motion Matching
Interactive Character Control with Auto-Regressive Motion Diffusion Models
Humans in 4D: Reconstructing and Tracking Humans with Transformers
Counter-Hypothetical Particle Filters for Single Object Pose Tracking
Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis
Guided Motion Diffusion for Controllable Human Motion Synthesis
Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation
HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
Design, Implementation and Evaluation of an External Pose-Tracking System for Underwater Cameras
Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition
TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis
Motion-Conditioned Diffusion Model for Controllable Video Synthesis
BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions
Event-based Camera Tracker by $\nabla$t NeRF
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
Generating Continual Human Motion in Diverse 3D Scenes
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models
Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance
Human from Blur: Human Pose Tracking from Blurry Images
Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)
Diverse Motion In-betweening with Dual Posture Stitching
GarmentTracking: Category-Level Garment Pose Tracking
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
PACE: Data-Driven Virtual Agent Interaction in Dense and Cluttered Environments
Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations
3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture
Music-Driven Group Choreography
Open-World Pose Transfer via Sequential Test-Time Adaption
ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer
Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase
Human Motion Diffusion as a Generative Prior
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.