DeepFashion

Dataset Information
Modalities
Images
Introduced
2016
Homepage

Overview

DeepFashion is a dataset containing around 800K diverse fashion images with their rich annotations (46 categories, 1,000 descriptive attributes, bounding boxes and landmark information) ranging from well-posed product images to real-world-like consumer photos.

Source: A Benchmark for Inpainting of Clothing Images with Irregular Holes

Variants: Deep-Fashion, DeepFashion

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Text-to-3D-Human Generation CCH Text-guided 3D Human Generation from … 2023-05-23
Image Retrieval RCCapsNet Fashion Image Retrieval with Capsule … 2019-08-26

Research Papers

Recent papers with results on this dataset: