Dynamic Texture Transfer using PatchMatch and Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913219195437056 |
|---|---|
| author | Pu, Guo Xu, Shiyao Cao, Xixin Lian, Zhouhui |
| author_facet | Pu, Guo Xu, Shiyao Cao, Xixin Lian, Zhouhui |
| contents | How to automatically transfer the dynamic texture of a given video to the target still image is a challenging and ongoing problem. In this paper, we propose to handle this task via a simple yet effective model that utilizes both PatchMatch and Transformers. The key idea is to decompose the task of dynamic texture transfer into two stages, where the start frame of the target video with the desired dynamic texture is synthesized in the first stage via a distance map guided texture transfer module based on the PatchMatch algorithm. Then, in the second stage, the synthesized image is decomposed into structure-agnostic patches, according to which their corresponding subsequent patches can be predicted by exploiting the powerful capability of Transformers equipped with VQ-VAE for processing long discrete sequences. After getting all those patches, we apply a Gaussian weighted average merging strategy to smoothly assemble them into each frame of the target stylized video. Experimental results demonstrate the effectiveness and superiority of the proposed method in dynamic texture transfer compared to the state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00606 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Texture Transfer using PatchMatch and Transformers Pu, Guo Xu, Shiyao Cao, Xixin Lian, Zhouhui Computer Vision and Pattern Recognition How to automatically transfer the dynamic texture of a given video to the target still image is a challenging and ongoing problem. In this paper, we propose to handle this task via a simple yet effective model that utilizes both PatchMatch and Transformers. The key idea is to decompose the task of dynamic texture transfer into two stages, where the start frame of the target video with the desired dynamic texture is synthesized in the first stage via a distance map guided texture transfer module based on the PatchMatch algorithm. Then, in the second stage, the synthesized image is decomposed into structure-agnostic patches, according to which their corresponding subsequent patches can be predicted by exploiting the powerful capability of Transformers equipped with VQ-VAE for processing long discrete sequences. After getting all those patches, we apply a Gaussian weighted average merging strategy to smoothly assemble them into each frame of the target stylized video. Experimental results demonstrate the effectiveness and superiority of the proposed method in dynamic texture transfer compared to the state of the art. |
| title | Dynamic Texture Transfer using PatchMatch and Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.00606 |