# Real-time Localized Photorealistic Video Style Transfer

arXiv: https://arxiv.org/abs/2010.10056 · HTML: https://mlsanity.com/paper/2010.10056/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [ARF: Artistic Radiance Fields](https://mlsanity.com/paper/2206.06360/) (2022)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions](https://mlsanity.com/paper/2112.01530/) (2021)
- [Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation](https://mlsanity.com/paper/2211.12824/) (2022)
- [SNeRF: Stylized Neural Implicit Representations for 3D Scenes](https://mlsanity.com/paper/2207.02363/) (2022)
- [QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity](https://mlsanity.com/paper/2212.10431/) (2022)
- [Geometry Transfer for Stylizing Radiance Fields](https://mlsanity.com/paper/2402.00863/) (2024)
- [UniVST: A Unified Framework for Training-free Localized Video Style Transfer](https://mlsanity.com/paper/2410.20084/) (2024)
- [Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylization](https://mlsanity.com/paper/2303.13232/) (2023)
- [When Creators Meet the Metaverse: A Survey on Computational Arts](https://mlsanity.com/paper/2111.13486/) (2021)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers](https://mlsanity.com/paper/2304.11335/) (2023)
- [Video Color Grading via Look-Up Table Generation](https://mlsanity.com/paper/2508.00548/) (2025)
- [M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers](https://mlsanity.com/paper/2104.01122/) (2021)
- [Evaluation in Neural Style Transfer: A Review](https://mlsanity.com/paper/2401.17109/) (2024)
- [Guided Linear Upsampling](https://mlsanity.com/paper/2307.09582/) (2023)
- [WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians](https://mlsanity.com/paper/2409.17917/) (2024)
- [LISA: Localized Image Stylization with Audio via Implicit Neural Representation](https://mlsanity.com/paper/2211.11381/) (2022)
- [Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging](https://mlsanity.com/paper/2503.07363/) (2025)
- [Optimal Image Transport on Sparse Dictionaries](https://mlsanity.com/paper/2311.01984/) (2023)
- [G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles](https://mlsanity.com/paper/2408.13508/) (2024)
- [MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning](https://mlsanity.com/paper/2201.04851/) (2022)
- [Image Style Transfer: from Artistic to Photorealistic](https://mlsanity.com/paper/2203.06328/) (2022)
- [ColoristaNet for Photorealistic Video Style Transfer](https://mlsanity.com/paper/2212.09247/) (2022)

## Abstract (arXiv)

We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism. Local regions may be selected either fully automatically from an image, through using video segmentation algorithms, or from casual user guidance such as scribbles. Our method, based on a deep neural network architecture inspired by recent work in photorealistic style transfer, is real-time and works on arbitrary inputs without runtime optimization once trained on a diverse dataset of artistic styles. By augmenting our video dataset with noisy semantic labels and jointly optimizing over style, content, mask, and temporal losses, our method can cope with a variety of imperfections in the input and produce temporally coherent videos without visual artifacts. We demonstrate our method on a variety of style images and target videos, including the ability to transfer different styles onto multiple objects simultaneously, and smoothly transition between styles in time.