SIGGRAPH 2026

Abstract

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this potential. Decomposition-based methods often struggle with clean separation, while generation-based methods suffer from difficulty in training data acquisition, reducing quality and scene diversity. In this paper, we propose BFS, a novel generation-based framework for layered image synthesis. Specifically, given a background image and user guidance, BFS synthesizes a foreground layer that incorporates not only a foreground object but also its associated visual effects, such as shadows and reflections, while seamlessly harmonizing with the background to produce a coherent composite. To enable diverse and high-quality foreground layer synthesis while overcoming data scarcity, we leverage the comparatively easy-to-learn knowledge of unlayered image synthesis for the foreground synthesis. To this end, we adopt a dual-branch diffusion framework in which two interconnected branches generate a composite image and a foreground layer, respectively, enabling bidirectional knowledge transfer. Based on this framework, we propose a two-stage training scheme that utilizes a high-quality unlayered composite image dataset to effectively enhance foreground quality. Extensive experiments, including a user study, show that BFS produces high-quality layered images, consistently outperforming prior methods.

Overview

Overall framework of BFS. Given a background image B, a bounding box M, and a foreground prompt T, BFS generates a foreground RGBA layer F through a bidirectionally interconnected dual-branch diffusion transformer. The composite branch produces a composite latent for knowledge transfer, but its output is not decoded. Only the foreground latent is decoded to obtain the final result.

Results

Editing Examples

BibTeX

@inproceedings{kang2026bfs,
  author    = {Kang, Kyoungkook and Sim, Gyujin and Cho, Sunghyun},
  title     = {BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer},
  booktitle = {Proceedings of the SIGGRAPH 2026 Conference Papers},
  year      = {2026}
}