Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
By Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc Van Gool. 2017
67 citations recorded by the source corpus.
Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset - LLD - of 600k+ logos crawled from the world wide web. Training Generative Adversarial Networks (GANs) for logo synthesis on such multi-modal data is not straightforward and results in mode collapse for some state-of-the-art methods. We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training, and validate this approach on CIFAR-10 and ImageNet-small to demonstrate its generality. We are able to generate a high diversity of plausible logos and demonstrate latent space exploration techniques to ease the logo design task in an interactive manner. GANs can cope with multi-modal data by means of synthetic labels achieved through clustering, and our results show the creative potential of such techniques for logo synthesis and manipulation. Our dataset and models are publicly available at https://data.vision.ee.ethz.ch/sagea/lld/.
Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Andrea Vedaldi
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Antonio Torralba
In Control and Systems Engineering
- Antonio Torralba
- David Bau
- Radu Timofte
- Alexandre Carlier
- Chunyuan Li
- Jun-Yan Zhu
- Martin Danelljan
- Alexandre Alahi
Citations in the corpus
- Diverse Image Generation via Self-Conditioned GANs (2020, methodology): “0006 Logo-GAN-AE [36] 1000.0 ± 0 .”
- DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation (2020, background): “Previous works [18, 13] for icon and logo generation mainly address rasterized image, by building on Generative Adversarial Networks [3].”
- Instance-Conditioned GAN (2021, methodology): “In particular, [36, 46] apply k-means on representations from a pre-trained feature extractor to cluster the data, and then use cluster indices to condition the generator network.”
- Partition-Guided GANs (2021, background): “Mode connecting Based on Theorem 1, to avoid mode connecting one has to either use a latent variable z with a disconnected support, or allow Gθ to be a discontinuous function [27, 36, 40, 46, 64].”