UniVST: A Unified Framework for Training-free Localized Video Style Transfer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912715663998976 |
|---|---|
| author | Song, Quanjian Lin, Mingbao Zhan, Wengyi Yan, Shuicheng Cao, Liujuan Ji, Rongrong |
| author_facet | Song, Quanjian Lin, Mingbao Zhan, Wengyi Yan, Shuicheng Cao, Liujuan Ji, Rongrong |
| contents | This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style across entire videos. The endeavors of this paper comprise: (1) A point-matching mask propagation strategy that leverages the feature maps from the DDIM inversion. This streamlines the model's architecture by obviating the need for tracking models. (2) A training-free AdaIN-guided localized video stylization mechanism that operates at both the latent and attention levels. This balances content fidelity and style richness, mitigating the loss of localized details commonly associated with direct video stylization. (3) A sliding-window consistent smoothing scheme that harnesses optical flow within the pixel representation and refines predicted noise to update the latent space. This significantly enhances temporal consistency and diminishes artifacts in stylized video. Our proposed UniVST has been validated to be superior to existing methods in quantitative and qualitative metrics. It adeptly addresses the challenges of preserving the primary object's style while ensuring temporal consistency and detail preservation. Our code is available at https://github.com/QuanjianSong/UniVST. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20084 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniVST: A Unified Framework for Training-free Localized Video Style Transfer Song, Quanjian Lin, Mingbao Zhan, Wengyi Yan, Shuicheng Cao, Liujuan Ji, Rongrong Computer Vision and Pattern Recognition This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style across entire videos. The endeavors of this paper comprise: (1) A point-matching mask propagation strategy that leverages the feature maps from the DDIM inversion. This streamlines the model's architecture by obviating the need for tracking models. (2) A training-free AdaIN-guided localized video stylization mechanism that operates at both the latent and attention levels. This balances content fidelity and style richness, mitigating the loss of localized details commonly associated with direct video stylization. (3) A sliding-window consistent smoothing scheme that harnesses optical flow within the pixel representation and refines predicted noise to update the latent space. This significantly enhances temporal consistency and diminishes artifacts in stylized video. Our proposed UniVST has been validated to be superior to existing methods in quantitative and qualitative metrics. It adeptly addresses the challenges of preserving the primary object's style while ensuring temporal consistency and detail preservation. Our code is available at https://github.com/QuanjianSong/UniVST. |
| title | UniVST: A Unified Framework for Training-free Localized Video Style Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.20084 |