# BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer

arXiv: https://arxiv.org/abs/2605.24894 · HTML: https://mlsanity.com/paper/2605.24894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 24 May 2026.

## Builds on (most cited first, 26 of 26)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion](https://mlsanity.com/paper/2403.18818/) (2024)
- [IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation](https://mlsanity.com/paper/2403.10701/) (2024)
- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)
- [Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models](https://mlsanity.com/paper/2411.07232/) (2024)
- [ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation](https://mlsanity.com/paper/2502.18364/) (2025)
- [LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model](https://mlsanity.com/paper/2403.11929/) (2024)
- [Thinking Outside the BBox: Unconstrained Generative Object Compositing](https://mlsanity.com/paper/2409.04559/) (2024)
- [LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors](https://mlsanity.com/paper/2412.04460/) (2024)
- [SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control](https://mlsanity.com/paper/2312.05039/) (2023)
- [DreamCom: Finetuning Text-guided Inpainting Model for Image Composition](https://mlsanity.com/paper/2309.15508/) (2023)
- [ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation](https://mlsanity.com/paper/2412.08645/) (2024)
- [LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge](https://mlsanity.com/paper/2501.01197/) (2025)
- [DreamFuse: Adaptive Image Fusion with Diffusion Transformer](https://mlsanity.com/paper/2504.08291/) (2025)
- [ORIDa: Object-centric Real-world Image Composition Dataset](https://mlsanity.com/paper/2506.08964/) (2025)
- [Multitwine: Multi-Object Compositing with Text and Layout Control](https://mlsanity.com/paper/2502.05165/) (2025)
- [FurryGAN: High Quality Foreground-aware Image Synthesis](https://mlsanity.com/paper/2208.10422/) (2022)
- [Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion](https://mlsanity.com/paper/2412.14462/) (2024)

## Abstract (arXiv)

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.