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.
Visual Representation Learning with Stochastic Frame Prediction
Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking
MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
Towards Practical Single-shot Motion Synthesis
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
Flexible Motion In-betweening with Diffusion Models
Shape Conditioned Human Motion Generation with Diffusion Model
IMU-Aided Event-based Stereo Visual Odometry
SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
MCM: Multi-condition Motion Synthesis Framework
MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
in2IN: Leveraging individual Information to Generate Human INteractions
You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects
OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion
BAMM: Bidirectional Autoregressive Motion Model
ParCo: Part-Coordinating Text-to-Motion Synthesis
Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark
Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
Contact-aware Human Motion Generation from Textual Descriptions
Diffusion-based Human Motion Style Transfer with Semantic Guidance
High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
Driving Animatronic Robot Facial Expression From Speech
Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space
Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives
Scaling Up Dynamic Human-Scene Interaction Modeling
Motion Mamba: Efficient and Long Sequence Motion Generation
Harmonious Group Choreography with Trajectory-Controllable Diffusion
MoST: Motion Style Transformer between Diverse Action Contents
Input-Output Extension of Underactuated Nonlinear Systems
DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception
VideoMAC: Video Masked Autoencoders Meet ConvNets
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.