# BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compression

arXiv: https://arxiv.org/abs/2505.09193 · HTML: https://mlsanity.com/paper/2505.09193/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 63 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [Efficient Attention: Attention with Linear Complexities](https://mlsanity.com/paper/1812.01243/) (2018)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [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)
- [HGRN2: Gated Linear RNNs with State Expansion](https://mlsanity.com/paper/2404.07904/) (2024)
- [Neural Video Compression with Feature Modulation](https://mlsanity.com/paper/2402.17414/) (2024)
- [Hierarchically Gated Recurrent Neural Network for Sequence Modeling](https://mlsanity.com/paper/2311.04823/) (2023)
- [Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement](https://mlsanity.com/paper/2003.01966/) (2020)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [Gated Slot Attention for Efficient Linear-Time Sequence Modeling](https://mlsanity.com/paper/2409.07146/) (2024)
- [VCT: A Video Compression Transformer](https://mlsanity.com/paper/2206.07307/) (2022)
- [Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model](https://mlsanity.com/paper/2006.13560/) (2020)
- [Improving Deep Video Compression by Resolution-adaptive Flow Coding](https://mlsanity.com/paper/2009.05982/) (2020)
- [Extending Neural P-frame Codecs for B-frame Coding](https://mlsanity.com/paper/2104.00531/) (2021)
- [Learned Video Compression via Joint Spatial-Temporal Correlation Exploration](https://mlsanity.com/paper/1912.06348/) (2019)
- [Bi-Directional Deep Contextual Video Compression](https://mlsanity.com/paper/2408.08604/) (2024)
- [ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression](https://mlsanity.com/paper/2410.09706/) (2024)
- [B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows](https://mlsanity.com/paper/2209.01769/) (2022)
- [Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression](https://mlsanity.com/paper/2112.13309/) (2021)
- [IBVC: Interpolation-driven B-frame Video Compression](https://mlsanity.com/paper/2309.13835/) (2023)
- [Insights from Generative Modeling for Neural Video Compression](https://mlsanity.com/paper/2107.13136/) (2021)
- [UCVC: A Unified Contextual Video Compression Framework with Joint P-frame and B-frame Coding](https://mlsanity.com/paper/2402.01289/) (2024)

## Built on by (most cited first, 8 of 8)

- [Ultra-Fast Neural Video Compression](https://mlsanity.com/paper/2606.04410/) (2026)
- [DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression](https://mlsanity.com/paper/2601.20564/) (2026)
- [Enhanced Neural Video Representation Compression Across Extreme Complexity and Quality Scales](https://mlsanity.com/paper/2606.28163/) (2026)
- [Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compression](https://mlsanity.com/paper/2603.05756/) (2026)
- [Neural Video Compression with Domain Transfer](https://mlsanity.com/paper/2605.13476/) (2026)
- [Generative Video Compression Based on Hierarchical Referencing](https://mlsanity.com/paper/2608.11618/) (2026)
- [DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer](https://mlsanity.com/paper/2608.20515/) (2026)
- [tcnerv:dual-domain temporal context modeling for implicit neural video compression](https://mlsanity.com/paper/2609.16870/) (2026)

## Abstract (arXiv)

Recent forward prediction-based learned video compression (LVC) methods have achieved impressive results, even surpassing VVC reference software VTM under the Low Delay B (LDB) configuration. In contrast, learned bidirectional video compression (BVC) remains underexplored and still lags behind its forward-only counterparts. This performance gap is mainly due to the limited ability to extract diverse and accurate contexts: most existing BVCs primarily exploit temporal motion while neglecting non-local correlations across frames. Moreover, they lack the adaptability to dynamically suppress harmful contexts arising from fast motion or occlusion. To tackle these challenges, we propose BiECVC, a BVC framework that incorporates diversified local and non-local context modeling along with adaptive context gating. For local context enhancement, BiECVC reuses high-quality features from lower layers and aligns them using decoded motion vectors without introducing extra motion overhead. To model non-local dependencies efficiently, we adopt a linear attention mechanism that balances performance and complexity. To further mitigate the impact of inaccurate context prediction, we introduce Bidirectional Context Gating, inspired by data-dependent decay in recent autoregressive language models, to dynamically filter contextual information based on conditional coding results. Extensive experiments demonstrate that BiECVC achieves state-of-the-art performance, reducing the bit-rate by 13.4% and 15.7% compared to VTM 13.2 under the Random Access (RA) configuration with intra periods of 32 and 64, respectively. To our knowledge, BiECVC is the first learned video codec to surpass VTM 13.2 RA across all standard test datasets.