• Mathematics, Computer Science
  • Published in ArXiv 2018

Fashion-Gen: The Generative Fashion Dataset and Challenge

@article{Rostamzadeh2018FashionGenTG,
  title={Fashion-Gen: The Generative Fashion Dataset and Challenge},
  author={Negar Rostamzadeh and Seyedarian Hosseini and Thomas Boquet and Wojciech Stokowiec and Ying Zhang and Christian Jauvin and Christopher Joseph Pal},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.08317}
}
We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists. Each item is photographed from a variety of angles. We provide baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions. We invite the community to improve upon these baselines. In this paper, we also outline the details of a challenge that we are launching based upon this… CONTINUE READING
105
Twitter Mentions

Citations

Publications citing this paper.
SHOWING 1-10 OF 15 CITATIONS

Context-Aware Visual Compatibility Prediction

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

TailorGAN: Making User-Defined Fashion Designs

VIEW 1 EXCERPT

A Brief Review of Recent Progress in Fashion Landmark Detection

  • Yungang Zhang, Cai Jun Zhang, Fei Fei Du
  • 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2019
VIEW 1 EXCERPT
CITES METHODS

Dressing for Diverse Body Shapes

VIEW 3 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Stacked Generative Adversarial Networks

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Bidirectional recurrent neural networks

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Text to Image Synthesis

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Learning Deep Representations of Fine-Grained Visual Descriptions

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

A Note on the Inception Score

VIEW 2 EXCERPTS

Hierarchical Adversarially Learned Inference

VIEW 2 EXCERPTS

Photographic Text-to-Image Synthesis with a Hierarchically-Nested Adversarial Network

VIEW 1 EXCERPT