Abstract
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 this http URL 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.
Abstract (translated)
基于神经表示的视频方法（NeRV）因其在各种视频任务中的出色表现而获得了广泛的关注。然而，现有的NeRV方法常常难以捕捉精细的空间细节，导致重建效果模糊不清。为此，在本文中我们提出了一种新的方法——基于频率分离和增强的神经视频表示（FANeRV），它通过核心的小波频谱升级模块解决了这些问题。 FANeRV的核心在于其采用了离散小波变换来将输入帧显式地分离为高频与低频成分，随后利用专门设计的模块对特定成分进行针对性提升。最终，一个特别设计的门控网络有效融合了这些频率组件以实现最优重建效果。此外，在网络后期阶段还集成了卷积残差增强块，这有助于平衡参数分布并进一步改善高频细节的恢复。 实验结果表明，FANeRV在视频压缩、修复和插值等多任务上显著提升了重建性能，并超越了现有的NeRV方法的表现。
URL
https://arxiv.org/abs/2504.06755
