# BachGAN: High-Resolution Image Synthesis from Salient Object Layout

arXiv: https://arxiv.org/abs/2003.11690 · HTML: https://mlsanity.com/paper/2003.11690/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2020.

## Built on by (most cited first, 22 of 22)

- [ReCo: Region-Controlled Text-to-Image Generation](https://mlsanity.com/paper/2211.15518/) (2022)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Modeling Image Composition for Complex Scene Generation](https://mlsanity.com/paper/2206.00923/) (2022)
- [SceneComposer: Any-Level Semantic Image Synthesis](https://mlsanity.com/paper/2211.11742/) (2022)
- [Context-Aware Layout to Image Generation with Enhanced Object Appearance](https://mlsanity.com/paper/2103.11897/) (2021)
- [Unbalanced Feature Transport for Exemplar-based Image Translation](https://mlsanity.com/paper/2106.10482/) (2021)
- [Bi-level Feature Alignment for Versatile Image Translation and Manipulation](https://mlsanity.com/paper/2107.03021/) (2021)
- [Securing Deep Generative Models with Universal Adversarial Signature](https://mlsanity.com/paper/2305.16310/) (2023)
- [Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation](https://mlsanity.com/paper/2304.06671/) (2023)
- [Auto-regressive Image Synthesis with Integrated Quantization](https://mlsanity.com/paper/2207.10776/) (2022)
- [Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration](https://mlsanity.com/paper/2307.09621/) (2023)
- [Layout-to-Image Translation with Double Pooling Generative Adversarial Networks](https://mlsanity.com/paper/2108.12900/) (2021)
- [Boosting Image Outpainting with Semantic Layout Prediction](https://mlsanity.com/paper/2110.09267/) (2021)
- [Few-shot Semantic Image Synthesis Using StyleGAN Prior](https://mlsanity.com/paper/2103.14877/) (2021)
- [Completing Visual Objects via Bridging Generation and Segmentation](https://mlsanity.com/paper/2310.00808/) (2023)
- [TraDiffusion: Trajectory-Based Training-Free Image Generation](https://mlsanity.com/paper/2408.09739/) (2024)
- [Grounding Text-to-Image Diffusion Models for Controlled High-Quality Image Generation](https://mlsanity.com/paper/2501.09194/) (2025)
- [BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models](https://mlsanity.com/paper/2602.20672/) (2026)
- [Neural Scene Decoration from a Single Photograph](https://mlsanity.com/paper/2108.01806/) (2021)
- [Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis](https://mlsanity.com/paper/2410.06841/) (2024)
- [StageDesigner: Artistic Stage Generation for Scenography via Theater Scripts](https://mlsanity.com/paper/2503.02595/) (2025)
- [Counterfactual Edits for Generative Evaluation](https://mlsanity.com/paper/2303.01555/) (2023)

## Abstract (arXiv)

We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout. This new setting allows users to provide the layout of salient objects only (i.e., foreground bounding boxes and categories), and lets the model complete the drawing with an invented background and a matching foreground. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create a background and weave it seamlessly into standalone objects. To tackle this, we propose Background Hallucination Generative Adversarial Network (BachGAN), which first selects a set of segmentation maps from a large candidate pool via a background retrieval module, then encodes these candidate layouts via a background fusion module to hallucinate a suitable background for the given objects. By generating the hallucinated background representation dynamically, our model can synthesize high-resolution images with both photo-realistic foreground and integral background. Experiments on Cityscapes and ADE20K datasets demonstrate the advantage of BachGAN over existing methods, measured on both visual fidelity of generated images and visual alignment between output images and input layouts.