# Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer

arXiv: https://arxiv.org/abs/2007.05146 · HTML: https://mlsanity.com/paper/2007.05146/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

## Built on by (most cited first, 30 of 34)

- [NeRF-Art: Text-Driven Neural Radiance Fields Stylization](https://mlsanity.com/paper/2212.08070/) (2022)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Learning to Stylize Novel Views](https://mlsanity.com/paper/2105.13509/) (2021)
- [Unified Implicit Neural Stylization](https://mlsanity.com/paper/2204.01943/) (2022)
- [StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions](https://mlsanity.com/paper/2112.01530/) (2021)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [Defending against Model Stealing via Verifying Embedded External Features](https://mlsanity.com/paper/2112.03476/) (2021)
- [Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes](https://mlsanity.com/paper/2103.17185/) (2021)
- [Learning Frequency Domain Approximation for Binary Neural Networks](https://mlsanity.com/paper/2103.00841/) (2021)
- [AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets](https://mlsanity.com/paper/2208.08084/) (2022)
- [Undistillable: Making A Nasty Teacher That CANNOT teach students](https://mlsanity.com/paper/2105.07381/) (2021)
- [AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks](https://mlsanity.com/paper/2307.09724/) (2023)
- [TinySAM: Pushing the Envelope for Efficient Segment Anything Model](https://mlsanity.com/paper/2312.13789/) (2023)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [SNeRF: Stylized Neural Implicit Representations for 3D Scenes](https://mlsanity.com/paper/2207.02363/) (2022)
- [MOVE: Effective and Harmless Ownership Verification via Embedded External Features](https://mlsanity.com/paper/2208.02820/) (2022)
- [Gaussian Splatting in Style](https://mlsanity.com/paper/2403.08498/) (2024)
- [Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis](https://mlsanity.com/paper/2507.20454/) (2025)
- [GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing](https://mlsanity.com/paper/2103.13998/) (2021)
- [Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer](https://mlsanity.com/paper/2305.05464/) (2023)
- [PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models](https://mlsanity.com/paper/2203.13452/) (2022)
- [I2V-GAN: Unpaired Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2108.00913/) (2021)
- [Learning Long-Term Style-Preserving Blind Video Temporal Consistency](https://mlsanity.com/paper/2103.07278/) (2021)
- [Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow](https://mlsanity.com/paper/2201.05723/) (2022)
- [MuVieCAST: Multi-View Consistent Artistic Style Transfer](https://mlsanity.com/paper/2312.05046/) (2023)
- [MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field](https://mlsanity.com/paper/2309.13607/) (2023)
- [G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles](https://mlsanity.com/paper/2408.13508/) (2024)
- [ColoristaNet for Photorealistic Video Style Transfer](https://mlsanity.com/paper/2212.09247/) (2022)
- [WAIT: Feature Warping for Animation to Illustration video Translation using GANs](https://mlsanity.com/paper/2310.04901/) (2023)

## Abstract (arXiv)

Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted, despite its high computational complexity, e.g. occupying over 97% inference time. This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlights the improvements made by optical flow, which is then adopted to distill the target student network. Furthermore, a low-rank distillation loss is employed to stabilize the output of student network by mimicking the rank of input videos. Extensive experiments demonstrate that our student network without an optical flow module is still able to generate stable video and runs much faster than the teacher network.