# Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation

arXiv: https://arxiv.org/abs/2511.18724 · HTML: https://mlsanity.com/paper/2511.18724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [BVI-DVC: A Training Database for Deep Video Compression](https://mlsanity.com/paper/2003.13552/) (2020)
- [Extending Neural P-frame Codecs for B-frame Coding](https://mlsanity.com/paper/2104.00531/) (2021)
- [Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression](https://mlsanity.com/paper/2401.15864/) (2024)
- [B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows](https://mlsanity.com/paper/2209.01769/) (2022)
- [Hierarchical B-frame Video Coding Using Two-Layer CANF without Motion Coding](https://mlsanity.com/paper/2304.02690/) (2023)
- [MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression](https://mlsanity.com/paper/2312.15829/) (2023)
- [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)
- [OMRA: Online Motion Resolution Adaptation to Remedy Domain Shift in Learned Hierarchical B-frame Coding](https://mlsanity.com/paper/2402.12816/) (2024)
- [Hierarchical B-frame Video Coding for Long Group of Pictures](https://mlsanity.com/paper/2406.16544/) (2024)
- [Fast-OMRA: Fast Online Motion Resolution Adaptation for Neural B-Frame Coding](https://mlsanity.com/paper/2410.21763/) (2024)

## Abstract (arXiv)

Learned B-frame codecs with hierarchical temporal prediction often encounter the domain-shift issue due to mismatches between the Group-of-Pictures (GOP) sizes for training and testing, leading to inaccurate motion estimates, particularly for large motion. A common solution is to turn large motion into small motion by downsampling video frames during motion estimation. However, determining the optimal downsampling factor typically requires costly rate-distortion optimization. This work introduces lightweight classifiers to predict downsampling factors. These classifiers leverage simple state signals from current and reference frames to balance rate-distortion performance with computational cost. Three variants are proposed: (1) a binary classifier (Bi-Class) trained with Focal Loss to choose between high and low resolutions, (2) a multi-class classifier (Mu-Class) trained with novel soft labels based on rate-distortion costs, and (3) a co-class approach (Co-Class) that combines the predictive capability of the multi-class classifier with the selective search of the binary classifier. All classifier methods can work seamlessly with existing B-frame codecs without requiring codec retraining. Experimental results show that they achieve coding performance comparable to exhaustive search methods while significantly reducing computational complexity. The code is available at: https://github.com/NYCU-MAPL/Fast-OMRA.git.