Generative Video
Papers in Generative Video
10 papers
- Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory
Introducing Memory-V2V, a video editing tool that enhances consistency in multi-turn edits through memory-augmented diffusion models.
Generative VideoViability: 8.0 - LoL: Longer than Longer, Scaling Video Generation to Hour
Lightweight solution for mitigating coherence decay in long-form video generation with minimal quality loss.
Generative VideoViability: 6.0 - CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
CounterVid enhances video-language models by generating counterfactual videos to reduce action and temporal hallucinations.
Generative VideoViability: 8.0 - PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization
PrevizWhiz simplifies and speeds up film previsualization by combining rough 3D scenes with generative video technology.
Generative VideoViability: 7.0 - Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model
Morphe leverages vision foundation models to revolutionize video streaming with high fidelity and 62.5% bandwidth savings for real-time applications.
Generative VideoViability: 7.0 - PaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication
Transform academic papers into engaging short-form videos with generative AI.
Generative VideoViability: 7.0 - Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
Create controllable talking avatars that interact with objects through text-driven animations.
Generative VideoViability: 8.0 - Rethinking Video Generation Model for the Embodied World
RBench offers a comprehensive framework for evaluating and training video generation models for robotics in embodied AI.
Generative VideoViability: 8.0 - FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
FairT2V offers a training-free solution to mitigate gender bias in text-to-video diffusion models, enhancing fairness without compromising video quality.
Generative VideoViability: 6.0 - DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
DreamActor-M2 empowers universal character animation with a novel spatiotemporal learning framework for superior motion transfer and identity preservation.
Generative VideoViability: 6.0