BachGAN: High-Resolution Image Synthesis from Salient Object Layout
This work addresses a practical image generation task for applications like design and content creation, but it is incremental as it builds on existing GAN-based methods with a novel retrieval and fusion approach.
The paper tackles the problem of generating high-resolution images from only salient object layouts, without segmentation maps, by proposing BachGAN, which retrieves and fuses background candidates to create realistic images. Experiments on Cityscapes and ADE20K datasets show improved visual fidelity and alignment compared to existing methods.
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.