# Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion

arXiv: https://arxiv.org/abs/2609.03520 · HTML: https://mlsanity.com/paper/2609.03520/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [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)
- [HNeRV: A Hybrid Neural Representation for Videos](https://mlsanity.com/paper/2304.02633/) (2023)
- [Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression](https://mlsanity.com/paper/2401.15864/) (2024)
- [Offline and Online Optical Flow Enhancement for Deep Video Compression](https://mlsanity.com/paper/2307.05092/) (2023)
- [Neural Video Compression with Context Modulation](https://mlsanity.com/paper/2505.14541/) (2025)

## Abstract (arXiv)

In conditional coding-based neural video compression, the quality of temporal context directly affects compression per- formance. Existing methods mostly construct context from prop- agated reference features, but they are vulnerable to motion esti- mation and local alignment errors in regions with complex mo- tion, occlusion, and high-frequency textures, resulting in inaccu- rate temporal information. To address this issue, this paper pro- poses a method combining deformable temporal alignment and difference-aware spatial selective fusion. A Context-aware Tem- poral Alignment Module is used to generate complementary tem- poral context, while a Difference-aware Spatial Selective Fusion module adaptively selects reliable temporal information and sup- presses misalignment. Experiments show that the proposed method achieves certain rate-distortion performance improve- ment over DCVC-DC.