Papers with Code 아카이브
Video Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 16
- 보존된 평가 기록
- 130
<span style="color:grey; opacity: 0.6">( Various Video Generation Tasks. Gif credit: MaGViT )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model
Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Navigation World Models
OmniCreator: Self-Supervised Unified Generation with Universal Editing
VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
Motion Prompting: Controlling Video Generation with Motion Trajectories
HunyuanVideo: A Systematic Framework For Large Video Generative Models
FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation
MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models
CPA: Camera-pose-awareness Diffusion Transformer for Video Generation
InfinityDrive: Breaking Time Limits in Driving World Models
World-consistent Video Diffusion with Explicit 3D Modeling
Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
DIVD: Deblurring with Improved Video Diffusion Model
Human Action CLIPs: Detecting AI-generated Human Motion
Motion Dreamer: Realizing Physically Coherent Video Generation through Scene-Aware Motion Reasoning
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
Fleximo: Towards Flexible Text-to-Human Motion Video Generation
Motion Modes: What Could Happen Next?
SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
MSG score: A Comprehensive Evaluation for Multi-Scene Video Generation
Trajectory Attention for Fine-grained Video Motion Control
OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Open-Sora Plan: Open-Source Large Video Generation Model
MotionCharacter: Identity-Preserving and Motion Controllable Human Video Generation
Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models
Towards Chunk-Wise Generation for Long Videos
AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
Free$^2$Guide: Gradient-Free Path Integral Control for Enhancing Text-to-Video Generation with Large Vision-Language Models
PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.