SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.05334 · NeurIPS · 2020

Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains

Justin Pinkney

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

GANs can generate photo-realistic images from the domain of their training data. However, those wanting to use them for creative purposes often want to generate imagery from a truly novel domain, a task which GANs are inherently unable to do. It is also desirable to have a level of control so that there is a degree of artistic direction rather than purely curation of random results. Here we present a method for interpolating between generative models of the StyleGAN architecture in a resolution dependent manner. This allows us to generate images from an entirely novel domain and do this with a degree of control over the nature of the output. Figure 1: Interpolation between a base model trained on FFHQ (a) and a transferred model trained on ukiyo-e faces (b). Resolution dependent model interpolation creates new models (c-e) which generate images from a novel domain (we use the simple layer swapping formulation described in Section 2). Depending on which model the high and low resolution layers are taken from, we can select either structural characteristics of ukiyo-e faces with photo-realistic rendering (c) or vice-versa (d). Furthermore, by selecting which layers are swapped we can tune the effect (e).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.05334")
get_code_for_paper("2010.05334")
have("2010.05334")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.05334.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.05334.svg)](https://syntology.ai/paper/2010.05334)

Connect an agent — have() is free.