# Fast-OMRA: Fast Online Motion Resolution Adaptation for Neural B-Frame Coding

arXiv: https://arxiv.org/abs/2410.21763 · HTML: https://mlsanity.com/paper/2410.21763/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 29 Oct 2024.

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

- [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)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [Video Compression through Image Interpolation](https://mlsanity.com/paper/1804.06919/) (2018)
- [Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression](https://mlsanity.com/paper/2207.05894/) (2022)
- [M-LVC: Multiple Frames Prediction for Learned Video Compression](https://mlsanity.com/paper/2004.10290/) (2020)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [BVI-DVC: A Training Database for Deep Video Compression](https://mlsanity.com/paper/2003.13552/) (2020)
- [End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression](https://mlsanity.com/paper/2112.09529/) (2021)
- [B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows](https://mlsanity.com/paper/2209.01769/) (2022)
- [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)
- [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)

## Built on by (most cited first, 2 of 2)

- [Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding](https://mlsanity.com/paper/2506.07709/) (2025)
- [Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation](https://mlsanity.com/paper/2511.18724/) (2025)

## Abstract (arXiv)

Most learned B-frame codecs with hierarchical temporal prediction suffer from the domain shift issue caused by the discrepancy in the Group-of-Pictures (GOP) size used for training and test. As such, the motion estimation network may fail to predict large motion properly. One effective strategy to mitigate this domain shift issue is to downsample video frames for motion estimation. However, finding the optimal downsampling factor involves a time-consuming rate-distortion optimization process. This work introduces lightweight classifiers to determine the downsampling factor. To strike a good rate-distortion-complexity trade-off, our classifiers observe simple state signals, including only the coding and reference frames, to predict the best downsampling factor. We present two variants that adopt binary and multi-class classifiers, respectively. The binary classifier adopts the Focal Loss for training, classifying between motion estimation at high and low resolutions. Our multi-class classifier is trained with novel soft labels incorporating the knowledge of the rate-distortion costs of different downsampling factors. Both variants operate as add-on modules without the need to re-train the B-frame codec. Experimental results confirm that they achieve comparable coding performance to the brute-force search methods while greatly reducing computational complexity.