Aligning Latent and Image Spaces to Connect the Unconnectable
This work addresses the challenge of creating seamless, arbitrarily large panoramas from unrelated scenes for applications in computer vision and graphics.
The paper tackles the problem of generating infinite high-resolution images with diverse content by aligning latent and image spaces, achieving at least 4 times better quality and diversity than baselines on datasets like LHQ, LSUN Tower, and LSUN Bridge.
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.