Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912516000448512 |
|---|---|
| author | Dai, Yuekun Li, Haitian Zhou, Shangchen Loy, Chen Change |
| author_facet | Dai, Yuekun Li, Haitian Zhou, Shangchen Loy, Chen Change |
| contents | RGBA images, with the additional alpha channel, are crucial for any application that needs blending, masking, or transparency effects, making them more versatile than standard RGB images. Nevertheless, existing image inpainting methods are designed exclusively for RGB images. Conventional approaches to transparent image inpainting typically involve placing a background underneath RGBA images and employing a two-stage process: image inpainting followed by image matting. This pipeline, however, struggles to preserve transparency consistency in edited regions, and matting can introduce jagged edges along transparency boundaries. To address these challenges, we propose Trans-Adapter, a plug-and-play adapter that enables diffusion-based inpainting models to process transparent images directly. Trans-Adapter also supports controllable editing via ControlNet and can be seamlessly integrated into various community models. To evaluate our method, we introduce LayerBench, along with a novel non-reference alpha edge quality evaluation metric for assessing transparency edge quality. We conduct extensive experiments on LayerBench to demonstrate the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01098 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting Dai, Yuekun Li, Haitian Zhou, Shangchen Loy, Chen Change Computer Vision and Pattern Recognition RGBA images, with the additional alpha channel, are crucial for any application that needs blending, masking, or transparency effects, making them more versatile than standard RGB images. Nevertheless, existing image inpainting methods are designed exclusively for RGB images. Conventional approaches to transparent image inpainting typically involve placing a background underneath RGBA images and employing a two-stage process: image inpainting followed by image matting. This pipeline, however, struggles to preserve transparency consistency in edited regions, and matting can introduce jagged edges along transparency boundaries. To address these challenges, we propose Trans-Adapter, a plug-and-play adapter that enables diffusion-based inpainting models to process transparent images directly. Trans-Adapter also supports controllable editing via ControlNet and can be seamlessly integrated into various community models. To evaluate our method, we introduce LayerBench, along with a novel non-reference alpha edge quality evaluation metric for assessing transparency edge quality. We conduct extensive experiments on LayerBench to demonstrate the effectiveness of our approach. |
| title | Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01098 |