arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11339cs.CV
收藏

探索实时超分辨率:面向流媒体内容的基准测试与微调

Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content

Lomonosov Moscow State University(罗蒙诺索夫莫斯科国立大学);AI Center, Lomonosov Moscow State University(Lomonosov莫斯科国立大学人工智能中心);MSU Institute for Artificial Intelligence, Lomonosov Moscow State University(MSU人工智能研究所,Lomonosov莫斯科国立大学)

Evgeney Bogatyrev, Khaled Abud, Ivan Molodetskikh, Nikita Alutis, Dmitriy Vatolin

AI总结:

本文提出EfRLFN模型,通过优化架构和损失函数提升实时超分辨率的效率和视觉质量,并通过微调其他模型提升流媒体应用性能。

摘要:

近年来,实时超分辨率技术的进步使高质量视频流媒体成为可能,但现有方法在处理压缩视频内容时面临独特挑战。常用数据集未能准确反映流媒体媒体的特性,限制了当前基准的相关性。为解决这一差距,我们引入了一个全面的数据集——StreamSR,来源于YouTube,涵盖多种视频类型和分辨率,代表真实世界流媒体场景。我们对11种最先进的实时超分辨率模型进行了基准测试,以评估其在流媒体应用中的性能。此外,我们提出EfRLFN,一种高效的实时模型,整合了高效的通道注意力机制和双曲正切激活函数——在实时超分辨率领域是一种新的设计选择。我们对架构进行了广泛优化,以最大化效率,并设计了一个复合损失函数,以提高训练收敛性。EfRLFN结合了现有架构的优势,同时在视觉质量和运行时间性能上有所提升。最后,我们展示了在我们的数据集上微调其他模型可以带来显著的性能提升,这种提升在各种标准基准上都能很好地推广。我们已将数据集、代码和基准发布在https://github.com/EvgeneyBogatyrev/EfRLFN。

英文摘要:

Recent advancements in real-time super-resolution have enabled higher-quality video streaming, yet existing methods struggle with the unique challenges of compressed video content. Commonly used datasets do not accurately reflect the characteristics of streaming media, limiting the relevance of current benchmarks. To address this gap, we introduce a comprehensive dataset - StreamSR - sourced from YouTube, covering a wide range of video genres and resolutions representative of real-world streaming scenarios. We benchmark 11 state-of-the-art real-time super-resolution models to evaluate their performance for the streaming use-case. Furthermore, we propose EfRLFN, an efficient real-time model that integrates Efficient Channel Attention and a hyperbolic tangent activation function - a novel design choice in the context of real-time super-resolution. We extensively optimized the architecture to maximize efficiency and designed a composite loss function that improves training convergence. EfRLFN combines the strengths of existing architectures while improving both visual quality and runtime performance. Finally, we show that fine-tuning other models on our dataset results in significant performance gains that generalize well across various standard benchmarks. We made the dataset, the code, and the benchmark available at https://github.com/EvgeneyBogatyrev/EfRLFN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑