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.
MSC: Multi-Scale Spatio-Temporal Causal Attention for Autoregressive Video Diffusion
LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era
TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
Mojito: Motion Trajectory and Intensity Control for Video Generation
Enhancing Facial Consistency in Conditional Video Generation via Facial Landmark Transformation
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
T-SVG: Text-Driven Stereoscopic Video Generation
UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
Video Creation by Demonstration
LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
Owl-1: Omni World Model for Consistent Long Video Generation
OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation
Doe-1: Closed-Loop Autonomous Driving with Large World Model
FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model
Physical Informed Driving World Model
SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
STIV: Scalable Text and Image Conditioned Video Generation
StyleMaster: Stylize Your Video with Artistic Generation and Translation
Multi-Shot Character Consistency for Text-to-Video Generation
3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
Accelerating Video Diffusion Models via Distribution Matching
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
FlexDiT: Dynamic Token Density Control for Diffusion Transformer
Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training
UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving
Mind the Time: Temporally-Controlled Multi-Event Video Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.