SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.14754 · CVPR · 2021

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing

Youngjung Uh, Yunjey Choi, Hyunsu Kim, Junho Kim, Sungjoo Yoo

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

Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) timeconsuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder. We propose StyleMapGAN: the intermediate latent space has spatial dimensions, and a spatially variant modulation replaces AdaIN. It makes the embedding through an encoder more accurate than existing optimization-based methods while maintaining the properties of GANs. Experimental results demonstrate that our method significantly outperforms state-of-the-art models in various image manipulation tasks such as local editing and image interpolation. Last but not least, conventional editing methods on GANs are still valid on our StyleMapGAN. Source code is available at https://github.com/naver-ai/ StyleMapGAN .

For agents

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

get_harvested_code_for_paper("2104.14754")
get_code_for_paper("2104.14754")
have("2104.14754")

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

curl https://syntology.ai/api/ran/2104.14754.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.14754.svg)](https://syntology.ai/paper/2104.14754)

Connect an agent — have() is free.