用频域分离增强视频神经表示，提升细节还原能力
FANeRV: Frequency Separation and Augmentation based Neural Representation for Video
- 通过小波变换分离帧的高低频成分，分别增强
- 在视频压缩、修复和插帧任务中均超越现有方法
- 适合需要高保真重建的视频处理场景
视频神经表示（NeRV）在各类视频任务中表现出色，但现有方法难以捕捉精细空间细节，导致重建模糊。本文提出基于频域分离与增强的视频神经表示（FANeRV），核心为小波频域升级模块。该模块利用离散小波变换将输入帧显式分离为高频与低频分量，并通过专用模块进行针对性增强。随后，设计的门控网络高效融合不同频率成分以实现最优重建。此外，在网络后段引入卷积残差增强块，均衡参数分布并改善高频细节恢复。实验表明，FANeRV显著提升重建性能，在视频压缩、修复和插帧等多项任务中优于现有NeRV方法。
原文摘要 · Abstract (English)
Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague reconstructions. In this paper, we present a Frequency Separation and Augmentation based Neural Representation for video (FANeRV), which addresses these limitations with its core Wavelet Frequency Upgrade Block. This block explicitly separates input frames into high and low-frequency components using discrete wavelet transform, followed by targeted enhancement using specialized modules. Finally, a specially designed gated network effectively fuses these frequency components for optimal reconstruction. Additionally, convolutional residual enhancement blocks are integrated into the later stages of the network to balance parameter distribution and improve the restoration of high-frequency details. Experimental results demonstrate that FANeRV significantly improves reconstruction performance and excels in multiple tasks, including video compression, inpainting, and interpolation, outperforming existing NeRV methods.
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。