MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

Documenti analoghi

• MotionStream: Real-Time Video Generation with Interactive Motion Controls
  di: Shin, Joonghyuk, et al.
  Pubblicazione: (2025)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
  di: Huang, Xun, et al.
  Pubblicazione: (2025)
• Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
  di: Xue, Haotian, et al.
  Pubblicazione: (2024)
• Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
  di: Chen, Yipu, et al.
  Pubblicazione: (2024)
• Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
  di: Xue, Haotian, et al.
  Pubblicazione: (2023)