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.
Articulated Kinematics Distillation from Video Diffusion Models
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer
DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios
Target-Aware Video Diffusion Models
DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
SceneMI: Motion In-betweening for Modeling Human-Scene Interactions
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
Less is More: Improving Motion Diffusion Models with Sparse Keyframes
A Modular Edge Device Network for Surgery Digitalization
Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control
Motion Synthesis with Sparse and Flexible Keyjoint Control
Stereo Event-based, 6-DOF Pose Tracking for Uncooperative Spacecraft
Versatile Physics-based Character Control with Hybrid Latent Representation
PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data
Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation
Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control
6D Object Pose Tracking in Internet Videos for Robotic Manipulation
Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion
Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Motion Anything: Any to Motion Generation
PersonaBooth: Personalized Text-to-Motion Generation
Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction
BioMoDiffuse: Physics-Guided Biomechanical Diffusion for Controllable and Authentic Human Motion Synthesis
Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data
Instrument-Splatting: Controllable Photorealistic Reconstruction of Surgical Instruments Using Gaussian Splatting
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis
Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
V-HOP: Visuo-Haptic 6D Object Pose Tracking
Human Motion Prediction, Reconstruction, and Generation
SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion
Robust 6DoF Pose Tracking Considering Contour and Interior Correspondence Uncertainty for AR Assembly Guidance
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.