English

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

Computer Vision and Pattern Recognition 2019-08-30 v2 Graphics Machine Learning

Abstract

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/.

Keywords

Cite

@article{arxiv.1811.12373,
  title  = {Diverse Image Synthesis from Semantic Layouts via Conditional IMLE},
  author = {Ke Li and Tianhao Zhang and Jitendra Malik},
  journal= {arXiv preprint arXiv:1811.12373},
  year   = {2019}
}

Comments

18 pages, 16 figures; IEEE International Conference on Computer Vision (ICCV), 2019

R2 v1 2026-06-23T06:25:45.256Z