Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing
This addresses the workload of professional retouchers by automating image editing tasks, though it is incremental as it builds on existing background generation methods.
The paper tackles the problem of automated background replacement and foreground adjustment in image editing, which typically requires tedious manual work, by proposing the ART framework that improves semantic and spatial consistency, achieving good performance on human body foregrounds.
Replacing the background and simultaneously adjusting foreground objects is a challenging task in image editing. Current techniques for generating such images relies heavily on user interactions with image editing softwares, which is a tedious job for professional retouchers. To reduce their workload, some exciting progress has been made on generating images with a given background. However, these models can neither adjust the position and scale of the foreground objects, nor guarantee the semantic consistency between foreground and background. To overcome these limitations, we propose a framework -- ART(Auto-Retoucher), to generate images with sufficient semantic and spatial consistency. Images are first processed by semantic matting and scene parsing modules, then a multi-task verifier model will give two confidence scores for the current background and position setting. We demonstrate that our jointly optimized verifier model successfully improves the visual consistency, and our ART framework performs well on images with the human body as foregrounds.