# SRNeRV: A Scale-wise Recursive Framework for Neural Video Representation

arXiv: https://arxiv.org/abs/2603.08227 · HTML: https://mlsanity.com/paper/2603.08227/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [HNeRV: A Hybrid Neural Representation for Videos](https://mlsanity.com/paper/2304.02633/) (2023)
- [Semi-Amortized Variational Autoencoders](https://mlsanity.com/paper/1802.02550/) (2018)
- [HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation](https://mlsanity.com/paper/2306.09818/) (2023)
- [Boosting Neural Representations for Videos with a Conditional Decoder](https://mlsanity.com/paper/2402.18152/) (2024)
- [A Convolutional Neural Network Approach for Half-Pel Interpolation in Video Coding](https://mlsanity.com/paper/1703.03502/) (2017)
- [UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compression](https://mlsanity.com/paper/2503.02733/) (2025)
- [CANeRV: Content Adaptive Neural Representation for Video Compression](https://mlsanity.com/paper/2502.06181/) (2025)

## Abstract (arXiv)

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.