研究人员开发了NeR-SC，一个新颖的神经网络表示框架，专门用于屏幕内容视频压缩。该框架基于SNeRV骨干网络，并引入了三个关键模块：一个可学习的颜色调色板来模拟离散颜色结构，一个多门控密集融合模块以增强特征交互，以及一个嵌入级帧跳过策略来绕过静态帧，从而实现实时解码。实验表明，NeR-SC在DSCVC和VCD数据集上，优于现有的神经视频表示方法，并在低比特率下超越了H.264和H.265，实现了具有竞争力的PSNR值。 AI
影响 这项研究推进了神经视频压缩技术，可能带来更高效的屏幕内容流媒体传输和存储。
排序理由 该集群包含两篇学术论文，详细介绍了神经视频表示和压缩的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.27024v1 Announce Type: new Abstract: Implicit neural representations have emerged as a promising paradigm for video compression, with recent methods achieving competitive performance on natural video. However, screen content video -- common in remote desktop, online ed…
Implicit neural representations have emerged as a promising paradigm for video compression, with recent methods achieving competitive performance on natural video. However, screen content video -- common in remote desktop, online education, and cloud gaming -- exhibits distinct s…
arXiv:2403.12401v2 Announce Type: replace Abstract: Neural Representations for Videos(NeRV) have emerged as a promising paradigm for video compression by representing videos as compact neural networks with efficient decoding. Hybrid NeRV methods further improve reconstruction qua…