Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.04052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929681399283712 |
|---|---|
| author | Tabatabaei, Aref Dehghanian, Zahra Amirmazlaghani, Maryam |
| author_facet | Tabatabaei, Aref Dehghanian, Zahra Amirmazlaghani, Maryam |
| contents | Artifacts often degrade the visual quality of virtual try-on (VTON) and pose transfer applications, impacting user experience. This study introduces a novel conditional inpainting technique designed to detect and remove such distortions, improving image aesthetics. Our work is the first to present an end-to-end framework addressing this specific issue, and we developed a specialized dataset of artifacts in VTON and pose transfer tasks, complete with masks highlighting the affected areas. Experimental results show that our method not only effectively removes artifacts but also significantly enhances the visual quality of the final images, setting a new benchmark in computer vision and image processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04052 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfer Tabatabaei, Aref Dehghanian, Zahra Amirmazlaghani, Maryam Computer Vision and Pattern Recognition Artifacts often degrade the visual quality of virtual try-on (VTON) and pose transfer applications, impacting user experience. This study introduces a novel conditional inpainting technique designed to detect and remove such distortions, improving image aesthetics. Our work is the first to present an end-to-end framework addressing this specific issue, and we developed a specialized dataset of artifacts in VTON and pose transfer tasks, complete with masks highlighting the affected areas. Experimental results show that our method not only effectively removes artifacts but also significantly enhances the visual quality of the final images, setting a new benchmark in computer vision and image processing. |
| title | Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.04052 |