2025/08/25 by Fanjiang Ye, Ye, Fanjiang, Yi Mu +24
Computer Science · #Advanced Image Processing Techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Quality Assessment #Machine Learning (cs.LG) #Systems and Control (eess.SY) #Video Coding and Compression Technologies #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2508.17756
openalex publication_date 2025/08/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) platforms remains challenging due to the excessive re-training requirements and prohibitively high computational and memory costs. To this end, we introduce SUPERGEN, an efficient tile-based framework for ultra-high-resolution video generation. SUPERGEN features a novel training-free algorithmic innovation with tiling to successfully support a wide range of resolutions without additional training efforts while significantly reducing both memory footprint and computational complexity. Moreover, SUPERGEN incorporates a tile-tailored, adaptive, region-aware caching strategy that accelerates video generation by exploiting redundancy across denoising steps and spatial regions. SUPERGEN also integrates cache-guided, communication-minimized tile parallelism for enhanced throughput and minimized latency. Evaluations show that SUPERGEN maximizes performance gains while achieving high output quality across various benchmarks.