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/fabi92/eccv18-rgb_pose_refinement
공식 코드https://github.com/facebookresearch/meshtalk
공식 코드MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
https://github.com/frank-zy-dou/emdm
공식 코드EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
https://github.com/frickyinn/SRPose
공식 코드SRPose: Two-view Relative Pose Estimation with Sparse Keypoints
https://github.com/giantai/pixtrack
공식 코드PixTrack: Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignment
https://github.com/gloria2tt/t3m
공식 코드https://github.com/godzillalla/dance-synthesis-project
공식 코드Diverse Dance Synthesis via Keyframes with Transformer Controllers
https://github.com/gohar-malik/intermask
공식 코드InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling
https://github.com/google-research/mint
공식 코드AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
https://github.com/google/mediapipe
공식 코드https://github.com/gorilla-lab-scut/ss-conv
공식 코드https://github.com/greatenanoymous/rgbtrack
공식 코드RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking
https://github.com/guytevet/motion-diffusion-model
공식 코드https://github.com/henningtjaden/RBOT
공식 코드A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking
https://github.com/hongfz16/avatarclip
공식 코드AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
https://github.com/hsp-iit/fast-ycb
공식 코드ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
https://github.com/hsp-iit/roft
공식 코드ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
https://github.com/iPaw-AI-LAB/LawDNet_2024
공식 코드LawDNet: Enhanced Audio-Driven Lip Synthesis via Local Affine Warping Deformation
https://github.com/inventec-ai-center/carl-siggraph2020
공식 코드CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion
https://github.com/irlab-therapeutics/mabe_2022
공식 코드MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
https://github.com/ismarou/How_to_track_your_Dragon
공식 코드https://github.com/ivclab/Part-Aware_Measurement_for_3D_Pose_Estimation_and_Tracking
공식 코드Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
https://github.com/j96w/6-PACK
공식 코드6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
https://github.com/jiashunwang/MRT
공식 코드https://github.com/jihoonerd/Conditional-Motion-In-Betweening
공식 코드https://github.com/jimmyzou/humanposetracking_snn
공식 코드Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer
https://github.com/jimmyzou/spikevideoformer
공식 코드https://github.com/jnnan/chairs
공식 코드https://github.com/jonepatr/lets_face_it
공식 코드https://github.com/jutanke/mv3dpose
공식 코드Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views
https://github.com/kakaobrain/flame
공식 코드https://github.com/kumapowerliu/human-motionformer
공식 코드Human MotionFormer: Transferring Human Motions with Vision Transformers
https://github.com/kwanyun/AnyMoLe
공식 코드AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
https://github.com/leolyliu/HOI4D-Instructions
공식 코드HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
https://github.com/leolyliu/teg-track
공식 코드Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.