# Interactive Video Stylization Using Few-Shot Patch-Based Training

arXiv: https://arxiv.org/abs/2004.14489 · HTML: https://mlsanity.com/paper/2004.14489/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 30 of 43)

- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [StableVideo: Text-driven Consistency-aware Diffusion Video Editing](https://mlsanity.com/paper/2308.09592/) (2023)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [CoDeF: Content Deformation Fields for Temporally Consistent Video Processing](https://mlsanity.com/paper/2308.07926/) (2023)
- [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023)
- [AI-Generated Content (AIGC): A Survey](https://mlsanity.com/paper/2304.06632/) (2023)
- [Real-World Image Variation by Aligning Diffusion Inversion Chain](https://mlsanity.com/paper/2305.18729/) (2023)
- [Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization](https://mlsanity.com/paper/2212.02766/) (2022)
- [A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information](https://mlsanity.com/paper/2206.02846/) (2022)
- [SNeRF: Stylized Neural Implicit Representations for 3D Scenes](https://mlsanity.com/paper/2207.02363/) (2022)
- [Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion](https://mlsanity.com/paper/2406.09402/) (2024)
- [Neural Neighbor Style Transfer](https://mlsanity.com/paper/2203.13215/) (2022)
- [Locally Stylized Neural Radiance Fields](https://mlsanity.com/paper/2309.10684/) (2023)
- [Text-Driven Stylization of Video Objects](https://mlsanity.com/paper/2206.12396/) (2022)
- [Reference-based Controllable Scene Stylization with Gaussian Splatting](https://mlsanity.com/paper/2407.07220/) (2024)
- [UMat: Uncertainty-Aware Single Image High Resolution Material Capture](https://mlsanity.com/paper/2305.16312/) (2023)
- [V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents](https://mlsanity.com/paper/2503.12077/) (2025)
- [Automatic Non-Linear Video Editing Transfer](https://mlsanity.com/paper/2105.06988/) (2021)
- [Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks](https://mlsanity.com/paper/2211.01783/) (2022)
- [NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing](https://mlsanity.com/paper/2406.06523/) (2024)
- [Neural Photometry-guided Visual Attribute Transfer](https://mlsanity.com/paper/2112.02520/) (2021)
- [NeuBTF: Neural fields for BTF encoding and transfer](https://mlsanity.com/paper/2307.01199/) (2023)
- [Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields](https://mlsanity.com/paper/2307.12909/) (2023)
- [Segment Anything for Videos: A Systematic Survey](https://mlsanity.com/paper/2408.08315/) (2024)
- [Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization](https://mlsanity.com/paper/2105.14739/) (2021)
- [GRIG: Few-Shot Generative Residual Image Inpainting](https://mlsanity.com/paper/2304.12035/) (2023)

## Abstract (arXiv)

In this paper, we present a learning-based method to the keyframe-based video stylization that allows an artist to propagate the style from a few selected keyframes to the rest of the sequence. Its key advantage is that the resulting stylization is semantically meaningful, i.e., specific parts of moving objects are stylized according to the artist's intention. In contrast to previous style transfer techniques, our approach does not require any lengthy pre-training process nor a large training dataset. We demonstrate how to train an appearance translation network from scratch using only a few stylized exemplars while implicitly preserving temporal consistency. This leads to a video stylization framework that supports real-time inference, parallel processing, and random access to an arbitrary output frame. It can also merge the content from multiple keyframes without the need to perform an explicit blending operation. We demonstrate its practical utility in various interactive scenarios, where the user paints over a selected keyframe and sees her style transferred to an existing recorded sequence or a live video stream.