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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/abhinanda-punnakkal/BABEL
공식 코드https://github.com/afford-motion/afford-motion
공식 코드Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
https://github.com/aioz-ai/AIOZ-GDANCE
공식 코드https://github.com/aioz-ai/GCD
공식 코드https://github.com/alessiosam/ladiff
공식 코드https://github.com/alexhang212/dataset-3dpop
공식 코드https://github.com/alxead/sfc
공식 코드https://github.com/amathislab/kinesis
공식 코드https://github.com/anindita127/IMoS
공식 코드IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions
https://github.com/anindita127/ReMoS
공식 코드ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions
https://github.com/anindita127/complextext2animation
공식 코드Synthesis of Compositional Animations from Textual Descriptions
https://github.com/anindita127/duetgen
공식 코드DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
https://github.com/athn-nik/teach
공식 코드https://github.com/bandainamcoresearchinc/bandai-namco-research-motiondataset
공식 코드Motion Capture Dataset for Practical Use of AI-based Motion Editing and Stylization
https://github.com/boeun-kim/most
공식 코드MoST: Motion Style Transformer between Diverse Action Contents
https://github.com/boreshkinai/delta-interpolator
공식 코드https://github.com/brachiation-rl/brachiation
공식 코드https://github.com/briqr/recurrent_transformer_vae_multi_action
공식 코드Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
https://github.com/bujiazi/motionclone
공식 코드MotionClone: Training-Free Motion Cloning for Controllable Video Generation
https://github.com/chaiyujin/glow-pytorch
공식 코드MoGlow: Probabilistic and controllable motion synthesis using normalising flows
https://github.com/chenfengye/motion-latent-diffusion
공식 코드Executing your Commands via Motion Diffusion in Latent Space
https://github.com/christsa/dgrasp
공식 코드D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
https://github.com/cr7anand/neural_temporal_models
공식 코드https://github.com/cure-lab/MotionCraft
공식 코드MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
https://github.com/cvlabbonn/hands_3d_motion_viewer
공식 코드Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points
https://github.com/deepmind/threednel
공식 코드3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation
https://github.com/degardinbruno/kinetic-gan
공식 코드Generative Adversarial Graph Convolutional Networks for Human Action Synthesis
https://github.com/dehezhang2/point_based_nerf_editing
공식 코드Point-Based Radiance Fields for Controllable Human Motion Synthesis
https://github.com/desai-nisarg/openapepose
공식 코드OpenApePose: a database of annotated ape photographs for pose estimation
https://github.com/dlr-rm/3dobjecttracking
공식 코드SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
https://github.com/dmoltisanti/brace
공식 코드BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis
https://github.com/doughtmw/hmd-ego-pose
공식 코드https://github.com/electronicarts/character-motion-vaes
공식 코드https://github.com/eth-siplab/avatarposer
공식 코드AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
https://github.com/exitudio/BAMM
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.