# Boosting Neural Video Codec via Scale-Driven Online Flow Refinement

arXiv: https://arxiv.org/abs/2606.23023 · HTML: https://mlsanity.com/paper/2606.23023/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Neural Video Compression with Feature Modulation](https://mlsanity.com/paper/2402.17414/) (2024)
- [Temporal Context Mining for Learned Video Compression](https://mlsanity.com/paper/2111.13850/) (2021)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction](https://mlsanity.com/paper/2206.07460/) (2022)
- [USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s](https://mlsanity.com/paper/2409.08481/) (2024)
- [Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression](https://mlsanity.com/paper/2401.15864/) (2024)
- [Bi-Directional Deep Contextual Video Compression](https://mlsanity.com/paper/2408.08604/) (2024)
- [Offline and Online Optical Flow Enhancement for Deep Video Compression](https://mlsanity.com/paper/2307.05092/) (2023)
- [Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression](https://mlsanity.com/paper/2405.04274/) (2024)
- [EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding](https://mlsanity.com/paper/2509.04118/) (2025)
- [Emerging Advances in Learned Video Compression: Models, Systems and Beyond](https://mlsanity.com/paper/2504.21445/) (2025)
- [Motion-Adaptive Inference for Flexible Learned B-Frame Compression](https://mlsanity.com/paper/2402.08550/) (2024)
- [Content-Adaptive Inference for State-of-the-art Learned Video Compression](https://mlsanity.com/paper/2510.07283/) (2025)
- [Parameter-Efficient Instance-Adaptive Neural Video Compression](https://mlsanity.com/paper/2405.08530/) (2024)
- [L-LBVC: Long-Term Motion Estimation and Prediction for Learned Bi-Directional Video Compression](https://mlsanity.com/paper/2504.02560/) (2025)
- [L-STEC: Learned Video Compression with Long-term Spatio-Temporal Enhanced Context](https://mlsanity.com/paper/2512.12790/) (2025)
- [Content Adaptive based Motion Alignment Framework for Learned Video Compression](https://mlsanity.com/paper/2512.12936/) (2025)
- [Neural Video Compression with Domain Transfer](https://mlsanity.com/paper/2605.13476/) (2026)

## Abstract (arXiv)

Although state-of-the-art neural video codecs (NVCs) have achieved remarkable performance, they suffer from limited generalization when encountering complex motion patterns unseen during training. To bridge this domain gap without the expensive cost of online fine-tuning, we propose a Training-Free Scale-Driven Online Flow Refinement (SOFR) method. Serving as a plug-and-play module, SOFR integrates motion information from coarse and fine scales and dynamically fuses them according to warping accuracy, effectively rectifying motion estimation errors with negligible computational overhead. Furthermore, we design a rate-aware strategy that selects different dynamic fusion strategies according to bitrate modes, and employs a reliability check based on warping error to ensure robustness. Extensive experiments on the USTC-TD dataset verify the effectiveness and generalization of SOFR across various NVC frameworks, including DCVC-SDD, DCVC-FM, and EHVC. Notably, it brings an average of 2.84% and 4.05% bitrate savings in terms of PSNR and MS-SSIM, respectively, to DCVC-FM with negligible coding time increase. Our code is available at https://github.com/SunnyMass/SOFR.