Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.14720 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916406347431936 |
|---|---|
| author | Cheng, Di Shi, YingJie Sun, ShiXin Zhang, JiaFu Wang, WeiJing Liu, Yu |
| author_facet | Cheng, Di Shi, YingJie Sun, ShiXin Zhang, JiaFu Wang, WeiJing Liu, Yu |
| contents | Multimodal clothing image editing refers to the precise adjustment and modification of clothing images using data such as textual descriptions and visual images as control conditions, which effectively improves the work efficiency of designers and reduces the threshold for user design. In this paper, we propose a new image editing method ControlEdit, which transfers clothing image editing to multimodal-guided local inpainting of clothing images. We address the difficulty of collecting real image datasets by leveraging the self-supervised learning approach. Based on this learning approach, we extend the channels of the feature extraction network to ensure consistent clothing image style before and after editing, and we design an inverse latent loss function to achieve soft control over the content of non-edited areas. In addition, we adopt Blended Latent Diffusion as the sampling method to make the editing boundaries transition naturally and enforce consistency of non-edited area content. Extensive experiments demonstrate that ControlEdit surpasses baseline algorithms in both qualitative and quantitative evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ControlEdit: A MultiModal Local Clothing Image Editing Method Cheng, Di Shi, YingJie Sun, ShiXin Zhang, JiaFu Wang, WeiJing Liu, Yu Computer Vision and Pattern Recognition Multimodal clothing image editing refers to the precise adjustment and modification of clothing images using data such as textual descriptions and visual images as control conditions, which effectively improves the work efficiency of designers and reduces the threshold for user design. In this paper, we propose a new image editing method ControlEdit, which transfers clothing image editing to multimodal-guided local inpainting of clothing images. We address the difficulty of collecting real image datasets by leveraging the self-supervised learning approach. Based on this learning approach, we extend the channels of the feature extraction network to ensure consistent clothing image style before and after editing, and we design an inverse latent loss function to achieve soft control over the content of non-edited areas. In addition, we adopt Blended Latent Diffusion as the sampling method to make the editing boundaries transition naturally and enforce consistency of non-edited area content. Extensive experiments demonstrate that ControlEdit surpasses baseline algorithms in both qualitative and quantitative evaluations. |
| title | ControlEdit: A MultiModal Local Clothing Image Editing Method |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.14720 |