Diverse Image Synthesis from Semantic Layouts via Conditional IMLE
arXiv:1811.12373
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/.
arXiv comment18 pages, 16 figures; IEEE International Conference on Computer Vision (ICCV), 2019
References in corpus (13)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Learning of Video Representations using LSTMs
- Toward Multimodal Image-to-Image Translation
- Adversarial Feature Learning
- Adversarially Learned Inference
- Autoencoding beyond pixels using a learned similarity metric
- Learning What and Where to Draw
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Super-Resolution with Deep Convolutional Sufficient Statistics
- Implicit Maximum Likelihood Estimation
- Likelihood-free inference via classification
- Super-Resolution via Conditional Implicit Maximum Likelihood Estimation