https://github.com/BarqueroGerman/BeLFusion
공식 코드BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
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/BarqueroGerman/FlowMDM
공식 코드Seamless Human Motion Composition with Blended Positional Encodings
https://github.com/DK-Jang/motion_puzzle
공식 코드https://github.com/DLR-RM/3DObjectTracking/tree/master/SRT3D
공식 코드SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
https://github.com/Dai-Wenxun/MotionLCM
공식 코드MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
https://github.com/DeepGesture/DeepGesture-Unity
공식 코드DeepGesture: A conversational gesture synthesis system based on emotions and semantics
https://github.com/EricGuo5513/TM2T
공식 코드TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
https://github.com/EricGuo5513/momask-codes
공식 코드https://github.com/FuxiCV/SSMCT
공식 코드https://github.com/Garfield-kh/TM2D
공식 코드TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
https://github.com/Godheritage/BOTH2Hands
공식 코드BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
https://github.com/Guanghan/lighttrack
공식 코드LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
https://github.com/HaiminLuo/Artemis
공식 코드Artemis: Articulated Neural Pets with Appearance and Motion synthesis
https://github.com/HalfSummer11/CAPTRA
공식 코드CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds
https://github.com/Hxxxz0/Free-T2m
공식 코드Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss
https://github.com/IDEA-Research/HumanTOMATO
공식 코드https://github.com/IRVLUTD/HO-Cap
공식 코드https://github.com/Khrylx/RFC
공식 코드Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
https://github.com/Mael-zys/T2M-GPT
공식 코드T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
https://github.com/Mathux/ACTOR
공식 코드Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
https://github.com/Mathux/TEMOS
공식 코드TEMOS: Generating diverse human motions from textual descriptions
https://github.com/MichiganCOG/Surgical_Hands_RELEASE
공식 코드Temporally Guided Articulated Hand Pose Tracking in Surgical Videos
https://github.com/Microsoft/human-pose-estimation.pytorch
공식 코드Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/NVlabs/BundleSDF
공식 코드BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
https://github.com/NVlabs/Dance2Music
공식 코드https://github.com/NVlabs/FoundationStereo
공식 코드FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
https://github.com/NVlabs/PoseRBPF
공식 코드PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking
https://github.com/PeizhuoLi/ganimator
공식 코드https://github.com/PolarisDane/KETA
공식 코드KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment
https://github.com/RAISELab-atUVA/Projected-Diffusion
공식 코드https://github.com/Sirui-Xu/InterDiff
공식 코드InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
https://github.com/Stanford-TML/EDGE
공식 코드https://github.com/Yi-Shi94/AMDM
공식 코드Interactive Character Control with Auto-Regressive Motion Diffusion Models
https://github.com/YuliangXiu/PoseFlow
공식 코드https://github.com/ZeyuLing/MotionLLaMA
공식 코드MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension
https://github.com/Zhongdao/UniTrack
공식 코드Do Different Tracking Tasks Require Different Appearance Models?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.