AI RESEARCH
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
arXiv CS.CV
•
ArXi:2602.11564v2 Announce Type: replace Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning, and detail synthesis. To address these limitations, we propose \textbf{LUVE}, a \textbf{L}atent-cascaded \textbf{U}HR \textbf{V}ideo generation framework built upon dual frequency \textbf{E}xperts.