提出快速视频隐式表示编码解码方法，速度提升百倍以上。
Fast Encoding and Decoding for Implicit Video Representation
- 用Transformer构建超网络实现无梯度优化编码，加速10000倍。
- 设计并行解码器，加载速度比传统编码快11倍，体积小65倍。
- 适合需要实时视频处理的场景，如流媒体与AR/VR应用。
尽管视频数据丰富且内容多样，但其高维特性给视频研究带来挑战。近期研究利用神经网络探索视频的隐式表示，在视频压缩与增强等任务中表现优异。然而，隐式神经表示（INRs）的编码时间过长仍是持续存在的难题。本文致力于提升隐式表示中的视频编码与解码速度。提出两个核心组件：基于Transformer的超网络NeRV-Enc，实现快速编码；以及并行解码器NeRV-Dec，用于高效视频加载。NeRV-Enc通过消除梯度优化，实现高达10⁴倍的速度提升；而NeRV-Dec简化了解码流程，加载速度较传统编码器快11倍，且在预解码视频下比内存加载快2.5倍，同时文件大小仅为原视频的1/65。
原文摘要 · Abstract (English)
Despite the abundant availability and content richness for video data, its high-dimensionality poses challenges for video research. Recent advancements have explored the implicit representation for videos using neural networks, demonstrating strong performance in applications such as video compression and enhancement. However, the prolonged encoding time remains a persistent challenge for video Implicit Neural Representations (INRs). In this paper, we focus on improving the speed of video encoding and decoding within implicit representations. We introduce two key components: NeRV-Enc, a transformer-based hyper-network for fast encoding; and NeRV-Dec, a parallel decoder for efficient video loading. NeRV-Enc achieves an impressive speed-up of $\mathbf{10^4\times}$ by eliminating gradient-based optimization. Meanwhile, NeRV-Dec simplifies video decoding, outperforming conventional codecs with a loading speed $\mathbf{11\times}$ faster, and surpassing RAM loading with pre-decoded videos ($\mathbf{2.5\times}$ faster while being $\mathbf{65\times}$ smaller in size).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。