Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation
Paper
•
2309.03549
•
Published
•
5
Text-to-Video
-
-
CCEdit: Creative and Controllable Video Editing via Diffusion Models
Paper • 2309.16496 • Published • 9 -
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
Paper • 2310.11440 • Published • 15 -
LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation
Paper • 2310.10769 • Published • 8 -
Video Language Planning
Paper • 2310.10625 • Published • 9 -
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 9 -
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Paper • 2310.20700 • Published • 9 -
GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
Paper • 2311.12631 • Published • 13 -
FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline
Paper • 2311.13073 • Published • 56 -
Magic-Me: Identity-Specific Video Customized Diffusion
Paper • 2402.09368 • Published • 27 -
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
Paper • 2402.14797 • Published • 19 -
Sora Generates Videos with Stunning Geometrical Consistency
Paper • 2402.17403 • Published • 16
Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality
Paper • 2406.08845 • Published • 8Note 本論文提出的T2VHE協議大大提高了T2V模型評估的可靠性、重現性和實用性，並承諾開源所有評估流程和代碼，以促進社群內的模型評估和改進。
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Paper • 2406.08659 • Published • 8Note 研究者採用了擴散模型，將T2MVid生成問題分解為視角空間和時間組件，並利用預訓練的多視角圖像和2D視頻擴散模型層來確保視頻的多視角一致性和時間連續性。引入對齊模塊解決了由於2D和多視角數據之間的領域差異引起的層不兼容問題。此外，還貢獻了一個新的多視角視頻數據集。
-
MotionBooth: Motion-Aware Customized Text-to-Video Generation
Paper • 2406.17758 • Published • 18 -
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
Paper • 2407.21705 • Published • 26 -
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
Paper • 2408.06072 • Published • 35 -
T3M: Text Guided 3D Human Motion Synthesis from Speech
Paper • 2408.12885 • Published • 10