# KD-NVC: A Search-and-Distill Framework to Accelerate Neural Video Coding

arXiv: https://arxiv.org/abs/2606.04595 · HTML: https://mlsanity.com/paper/2606.04595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 43 of its 57 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [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)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression](https://mlsanity.com/paper/2207.05894/) (2022)
- [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)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [Perceptual Learned Video Compression with Recurrent Conditional GAN](https://mlsanity.com/paper/2109.03082/) (2021)
- [Frequency Attention for Knowledge Distillation](https://mlsanity.com/paper/2403.05894/) (2024)
- [Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression](https://mlsanity.com/paper/2401.15864/) (2024)
- [ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression](https://mlsanity.com/paper/2410.09706/) (2024)
- [MobileCodec: Neural Inter-frame Video Compression on Mobile Devices](https://mlsanity.com/paper/2207.08338/) (2022)
- [Generative Neural Video Compression via Video Diffusion Prior](https://mlsanity.com/paper/2512.05016/) (2025)
- [MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device](https://mlsanity.com/paper/2310.01258/) (2023)
- [Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance](https://mlsanity.com/paper/2512.07480/) (2025)
- [Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation](https://mlsanity.com/paper/2309.02529/) (2023)
- [SMC++: Masked Learning of Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2406.04765/) (2024)
- [I2VC: A Unified Framework for Intra- & Inter-frame Video Compression](https://mlsanity.com/paper/2405.14336/) (2024)
- [Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2409.11718/) (2024)

## Abstract (arXiv)

While neural video coding (NVC) has achieved remarkable rate-distortion performance, real-time decoding on edge devices has become an important demand but remains limited by high complexity. Knowledge distillation (KD) is widely used for model acceleration, yet its application to NVC faces critical challenges. Specifically, the heterogeneity of NVC sub-modules renders uniform architectural reduction suboptimal, necessitating a per-module design for better rate-distortion-speed trade-off. However, searching for diverse architectures via existing neural architecture search (NAS) algorithms is unaffordable due to the expensive training cost of neural video codecs. Moreover, after the lightweight architecture is determined, existing distillation methods overlook the feature-energy sparsity induced by the rate-constraint, which is essential for maintaining compression performance. To address these issues, we propose a two-stage distillation framework KD-NVC. In the first stage, we introduce an acceleration-efficiency-based neural architecture search (AE-NAS) algorithm. It explores the module-wise Pareto frontier to adaptively allocate the acceleration budget across heterogeneous modules. Also, it introduces the acceleration-efficiency metric to determine the final student architecture without practically training all architecture-level candidates. In the second stage, we design an energy-aware feature distillation (EFD) loss that aligns the spatially-aggregated feature-energy signatures between the teacher and student codecs, transferring the rate-induced sparsity patterns for better compression efficiency. Experimental results demonstrate that the proposed framework consistently outperforms existing codec-oriented distillation methods, and achieves 69 FPS decoding at 1080p on RTX 5060 while maintaining comparable RD performance to VTM-LDB.