{"ID":2868314,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16507","arxiv_id":"2509.16507","title":"OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution","abstract":"Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple diffusion steps. Compared to image super-resolution (ISR), VSR methods needs to process each frame in a video, which poses challenges to its inference efficiency. However, video quality and inference efficiency have always been a trade-off for the diffusion-based VSR methods. In this work, we propose One-Step Diffusion model for real-world Video Super-Resolution, namely OS-DiffVSR. Specifically, we devise a novel adjacent frame adversarial training paradigm, which can significantly improve the quality of synthetic videos. Besides, we devise a multi-frame fusion mechanism to maintain inter-frame temporal consistency and reduce the flicker in video. Extensive experiments on several popular VSR benchmarks demonstrate that OS-DiffVSR can even achieve better quality than existing diffusion-based VSR methods that require dozens of sampling steps.","short_abstract":"Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple diffusion steps. Compared to image super-resolution (ISR), VSR methods needs to process each frame in a...","url_abs":"https://arxiv.org/abs/2509.16507","url_pdf":"https://arxiv.org/pdf/2509.16507v1","authors":"[\"Hanting Li\",\"Huaao Tang\",\"Jianhong Han\",\"Tianxiong Zhou\",\"Jiulong Cui\",\"Haizhen Xie\",\"Yan Chen\",\"Jie Hu\"]","published":"2025-09-20T03:04:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}