用递归共享结构减少视频神经表示的参数冗余，提升压缩效率。
SRNeRV: A Scale-wise Recursive Framework for Neural Video Representation
- 采用尺度自相似性设计递归共享架构，分离空间与通道混合模块。
- 在多个尺度上复用主要参数的通道混合模块，模型尺寸显著缩小。
- 在INR友好场景下实现更优率失真性能，适合高效视频表示任务。
隐式神经表示（INRs）已成为视频表征与压缩的有前景范式。然而，现有多尺度INR生成器通常通过堆叠独立处理模块实现各尺度处理，导致显著的参数冗余。受生成过程尺度自相似性的启发，我们提出SRNeRV，一种新型分尺度递归框架，用参数高效的共享架构替代堆叠设计。其核心是将处理模块解耦为尺度相关空间混合模块与尺度无关通道混合模块，递归复用包含大部分参数的通道混合模块于所有尺度，显著降低模型规模，同时保留学习尺度特定空间模式的关键能力。大量实验表明，SRNeRV在INR友好场景下实现了显著的率失真性能提升，验证了该共享方案成功放大了INR范式的本质优势。
原文摘要 · Abstract (English)
Implicit Neural Representations (INRs) have emerged as a promising paradigm for video representation and compression. However, existing multi-scale INR generators often suffer from significant parameter redundancy by stacking independent processing blocks for each scale. Inspired by the principle of scale self-similarity in the generation process, we propose SRNeRV, a novel scale-wise recursive framework that replaces this stacked design with a parameter-efficient shared architecture. The core of our approach is a hybrid sharing scheme derived from decoupling the processing block into a scale-specific spatial mixing module and a scale-invariant channel mixing module. We recursively apply the same shared channel mixing module, which contains the majority of the parameters, across all scales, significantly reducing the model size while preserving the crucial capacity to learn scale-specific spatial patterns. Extensive experiments demonstrate that SRNeRV achieves a significant rate-distortion performance boost, especially in INR-friendly scenarios, validating that our sharing scheme successfully amplifies the core strengths of the INR paradigm.
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。