Papers with Code 아카이브
Motion Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 13
- 보존된 평가 기록
- 123
Creating a video where people in the images move (such as blinking or smiling) requires specialized AI technology like Deepfake or Motion Synthesis, which I cannot do directly here.
However, if you want a video made from the images you provided, I can create an animated slideshow with cute effects and royalty-free background music. Would you be interested in this?
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels
Generative Adversarial Graph Convolutional Networks for Human Action Synthesis
GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction
Physics-based Human Motion Estimation and Synthesis from Videos
Stochastic Scene-Aware Motion Prediction
BABEL: Bodies, Action and Behavior with English Labels
Task-Generic Hierarchical Human Motion Prior using VAEs
Scene-aware Generative Network for Human Motion Synthesis
MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
Character Controllers Using Motion VAEs
Synthesis of Compositional Animations from Textual Descriptions
Single-Shot Motion Completion with Transformer
Robust Motion In-betweening
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
GlocalNet: Class-aware Long-term Human Motion Synthesis
Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
UNOC: Understanding Occlusion for Embodied Presence in Virtual Reality
Recognition and Synthesis of Object Transport Motion
Hierarchical Style-based Networks for Motion Synthesis
Learning to Generate Diverse Dance Motions with Transformer
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings
Cross-Conditioned Recurrent Networks for Long-Term Synthesis of Inter-Person Human Motion Interactions
Skeleton-Aware Networks for Deep Motion Retargeting
Unpaired Motion Style Transfer from Video to Animation
CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion
Music2Dance: DanceNet for Music-driven Dance Generation
Dancing to Music
PT-MMD: A Novel Statistical Framework for the Evaluation of Generative Systems
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis
Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.