Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting

TL;DR

Trans-Adapter is a versatile plug-and-play framework that enables diffusion-based models to directly inpaint transparent RGBA images, improving transparency consistency and edge quality, with broad applicability and controllable editing.

Contribution

We introduce Trans-Adapter, a novel plug-and-play adapter that allows diffusion models to directly process transparent images, addressing transparency preservation issues in existing methods.

Findings

Trans-Adapter effectively preserves transparency consistency.

It improves transparency edge quality compared to traditional methods.

The framework is compatible with various diffusion models and supports controllable editing.

Abstract

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.