Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Aligning Latent and Image Spaces to Connect the Unconnectable

About

In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spaces. Latent codes, when sampled, are positioned on the coordinate grid, and each pixel is computed from an interpolation of the nearby style codes. We modify the AdaIN mechanism to work in such a setup and train the generator in an adversarial setting to produce images positioned between any two latent vectors. At test time, this allows for generating complex and diverse infinite images and connecting any two unrelated scenes into a single arbitrarily large panorama. Apart from that, we introduce LHQ: a new dataset of \lhqsize high-resolution nature landscapes. We test the approach on LHQ, LSUN Tower and LSUN Bridge and outperform the baselines by at least 4 times in terms of quality and diversity of the produced infinite images. The project page is located at https://universome.github.io/alis.

Ivan Skorokhodov, Grigorii Sotnikov, Mohamed Elhoseiny• 2021

Related benchmarks

TaskDatasetResultRank
Infinite Image GenerationBridge 256x256
FID10.24
5
Infinite Image GenerationTower 256x256
FID8.83
5
Infinite Image GenerationLandscapes 256x256
FID10.48
5
Showing 3 of 3 rows

Other info

Code

Follow for update