Fashion-Gen: Th… (2018-06-21T00:00:00.000000Z)

TL;DR

A new dataset of 293,008 high definition fashion images paired with item descriptions provided by professional stylists is introduced, providing baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions.

Abstract

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 dataset.

Authors

C. Pal

17 papers

Negar Rostamzadeh

5 papers

Seyedarian Hosseini

1 papers

TL;DR

Abstract

Authors

References36 items

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

Stochastic Video Generation with a Learned Prior

Hierarchical Adversarially Learned Inference

A Note on the Inception Score

VITON: An Image-Based Virtual Try-on Network

TL;DR

Abstract

Authors

References36 items

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

Stochastic Video Generation with a Learned Prior

Hierarchical Adversarially Learned Inference

A Note on the Inception Score

VITON: An Image-Based Virtual Try-on Network

Progressive Growing of GANs for Improved Quality, Stability, and Variation

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

Be Your Own Prada: Fashion Synthesis with Structural Coherence

Attention is All you Need

Unsupervised Learning of Disentangled Representations from Video

Stacked Generative Adversarial Networks

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

Image-to-Image Translation with Conditional Adversarial Networks

Unsupervised Cross-Domain Image Generation

Amortised MAP Inference for Image Super-resolution

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations

Improved Techniques for Training GANs

Generative Adversarial Text to Image Synthesis

Learning Deep Representations of Fine-Grained Visual Descriptions

Clothes Co-Parsing Via Joint Image Segmentation and Labeling With Application to Clothing Retrieval

Where to Buy It: Matching Street Clothing Photos in Online Shops

Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences

Deep domain adaptation for describing people based on fine-grained clothing attributes

Neuroaesthetics in fashion: Modeling the perception of fashionability

Learning from massive noisy labeled data for image classification

Deep Learning Face Attributes in the Wild

Microsoft COCO: Common Objects in Context

Getting the look: clothing recognition and segmentation for automatic product suggestions in everyday photos

Apparel Classification with Style

Describing Clothing by Semantic Attributes

Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set

Automated Flower Classification over a Large Number of Classes

Bidirectional recurrent neural networks

Dataset and

Visualizing Data using t-SNE

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names