Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
This addresses the limitation of existing conditional image synthesis methods that generate only a single or fixed number of images, offering a solution for applications requiring varied visual outputs from structured inputs.
The paper tackles the problem of generating diverse images from a single semantic layout, introducing a method based on Implicit Maximum Likelihood Estimation (IMLE) that produces more diverse images with fewer artifacts compared to leading approaches.
Most existing methods for conditional image synthesis are only able to generate a single plausible image for any given input, or at best a fixed number of plausible images. In this paper, we focus on the problem of generating images from semantic segmentation maps and present a simple new method that can generate an arbitrary number of images with diverse appearance for the same semantic layout. Unlike most existing approaches which adopt the GAN framework, our method is based on the recently introduced Implicit Maximum Likelihood Estimation (IMLE) framework. Compared to the leading approach, our method is able to generate more diverse images while producing fewer artifacts despite using the same architecture. The learned latent space also has sensible structure despite the lack of supervision that encourages such behaviour. Videos and code are available at https://people.eecs.berkeley.edu/~ke.li/projects/imle/scene_layouts/.