Improving Detail in Pluralistic Image Inpainting with Feature Dequantization
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_ | 1866910724039639040 |
|---|---|
| author | Park, Kyungri Jung, Woohwan |
| author_facet | Park, Kyungri Jung, Woohwan |
| contents | Pluralistic Image Inpainting (PII) offers multiple plausible solutions for restoring missing parts of images and has been successfully applied to various applications including image editing and object removal. Recently, VQGAN-based methods have been proposed and have shown that they significantly improve the structural integrity in the generated images. Nevertheless, the state-of-the-art VQGAN-based model PUT faces a critical challenge: degradation of detail quality in output images due to feature quantization. Feature quantization restricts the latent space and causes information loss, which negatively affects the detail quality essential for image inpainting. To tackle the problem, we propose the FDM (Feature Dequantization Module) specifically designed to restore the detail quality of images by compensating for the information loss. Furthermore, we develop an efficient training method for FDM which drastically reduces training costs. We empirically demonstrate that our method significantly enhances the detail quality of the generated images with negligible training and inference overheads. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01046 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Detail in Pluralistic Image Inpainting with Feature Dequantization Park, Kyungri Jung, Woohwan Computer Vision and Pattern Recognition Pluralistic Image Inpainting (PII) offers multiple plausible solutions for restoring missing parts of images and has been successfully applied to various applications including image editing and object removal. Recently, VQGAN-based methods have been proposed and have shown that they significantly improve the structural integrity in the generated images. Nevertheless, the state-of-the-art VQGAN-based model PUT faces a critical challenge: degradation of detail quality in output images due to feature quantization. Feature quantization restricts the latent space and causes information loss, which negatively affects the detail quality essential for image inpainting. To tackle the problem, we propose the FDM (Feature Dequantization Module) specifically designed to restore the detail quality of images by compensating for the information loss. Furthermore, we develop an efficient training method for FDM which drastically reduces training costs. We empirically demonstrate that our method significantly enhances the detail quality of the generated images with negligible training and inference overheads. |
| title | Improving Detail in Pluralistic Image Inpainting with Feature Dequantization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.01046 |