研究人员开发了 LiteVSR，一个用于适配预训练扩散 Transformer 进行视频超分辨率任务的新框架。与现有方法相比，该方法使用轻量级的 State-Aware Adapter，需要更少的训练参数和更短的训练时间。LiteVSR 利用流匹配高效适配冻结的 Transformer，以最少的计算资源实现具有竞争力的恢复质量。 AI
影响 为将大型生成模型适配于特定的视频增强任务提供了一种更具计算效率的方法。
排序理由 该集群包含一篇详细介绍视频超分辨率新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.09250v1 Announce Type: new Abstract: Adapting large-scale pre-trained video generators for Video Super-Resolution (VSR) in novel domains remains computationally prohibitive. Methods that reformulate generation as direct Low-Quality to High-Quality mappings deviate from…
Adapting large-scale pre-trained video generators for Video Super-Resolution (VSR) in novel domains remains computationally prohibitive. Methods that reformulate generation as direct Low-Quality to High-Quality mappings deviate from the original generative formulation, demanding …