# Visualize and Paint GAN Activations

Source: [Visualize and Paint GAN Activations](<https://www.sota2.com/research/paper/68fa74601e209131cea61478>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:08:39.928Z

Authors: Rudolf Herdt, Peter Maass

Published: 2024-05-24T15:22:58.000Z

## Abstract

We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. This gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.15636>)

[PDF](<https://arxiv.org/pdf/2405.15636.pdf>)