Multi-scale Attention Guided Pose Transfer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916618411442176 |
|---|---|
| author | Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada |
| author_facet | Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada |
| contents | Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. In this paper, we present an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_06777 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Multi-scale Attention Guided Pose Transfer Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada Computer Vision and Pattern Recognition Multimedia Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. In this paper, we present an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset. |
| title | Multi-scale Attention Guided Pose Transfer |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2202.06777 |