Papers with Code 아카이브
Human Dynamics
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/JianZhang-chick/EMOdiffhead
공식 코드EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion
https://github.com/KwaiVGI/LivePortrait
공식 코드LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
https://github.com/MingtaoGuo/relightable-portrait-animation
공식 코드https://github.com/Sirui-Xu/InterDiff
공식 코드InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
https://github.com/SkyworkAI/SkyReels-A1
공식 코드SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers
https://github.com/XiaoyuBIE1994/DVAE
공식 코드https://github.com/akanazawa/human_dynamics
공식 코드https://github.com/bytedance/LatentSync
공식 코드LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync
https://github.com/chaneyddtt/Convolutional-Sequence-to-Sequence-Model-for-Human-Dynamics
공식 코드https://github.com/davrempe/contact-human-dynamics
공식 코드https://github.com/eddyhkchiu/pose_forecast_wacv
공식 코드https://github.com/facebookresearch/AutoAvatar
공식 코드AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling
https://github.com/frank-zy-dou/emdm
공식 코드EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
https://github.com/fudan-generative-vision/hallo3
공식 코드Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
https://github.com/habicrowd/HabiCrowd
공식 코드HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation
https://github.com/he-h/HuMob
공식 코드https://github.com/hkust-vgd/rfnet-4d
공식 코드https://github.com/hulianyuyy/dsta-slr
공식 코드Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition
https://github.com/inhwanbae/eigentrajectory
공식 코드EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting
https://github.com/inhwanbae/singulartrajectory
공식 코드SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model
https://github.com/jasonyzhang/phd
공식 코드https://github.com/jdh-algo/JoyVASA
공식 코드https://github.com/jeff-sjtu/dnd
공식 코드https://github.com/likenneth/acton
공식 코드https://github.com/megvii-research/megactor
공식 코드MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
https://github.com/megvii-research/megfaceanimate
공식 코드MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
https://github.com/qitaozhao/poseformerv2
공식 코드PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation
https://github.com/scutzzj/aniportrait
공식 코드AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
https://github.com/soraproducer/awesome-human-interaction-motion-generation
공식 코드https://github.com/tsinghua-fib-lab/citybench
공식 코드CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
https://github.com/vita-epfl/CrowdNav
공식 코드https://github.com/vita-epfl/DyNav
공식 코드https://github.com/xyz123xyz456/hallo4
공식 코드https://github.com/zhangdatalab/cosmos
공식 코드Paths of A Million People: Extracting Life Trajectories from Wikipedia
https://github.com/CompVis/behavior-driven-video-synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.