MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening
cs.CV, cs.AI, cs.LG
Submitted: 2026-03-14
Updated: 2026-11-10
Project page: https://motion-cfg.vercel.app
Terminology
Sources
- Characterizing Motion Encoding in Video Diffusion Timesteps
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
- Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
- Classifier-Free Diffusion Guidance
- Zero-Shot Audio Captioning via Audibility Guidance
- VidGen-1M: A Large-Scale Dataset for Text-to-video Generation
- Wan: Open and Advanced Large-Scale Video Generative Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs