COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles

Abstract

How to recommend outfits has gained considerable attention in both academia and industry in recent years. Many studies have been carried out regarding fashion compatibility learning, to determine whether the fashion items in an outfit are compatible or not. These methods mainly focus on evaluating the compatibility of existing outfits and rarely consider applying such knowledge to 'design' new fashion items. We propose the new task of generating complementary and compatible fashion items based on an arbitrary number of given fashion items. In particular, given some fashion items that can make up an outfit, the aim of this paper is to synthesize photo-realistic images of other, complementary, fashion items that are compatible with the given ones. To achieve this, we propose an outfit generation framework, referred to as COutfitGAN, which includes a pyramid style extractor, an outfit generator, a UNet-based real/fake discriminator, and a collocation discriminator. To train and evaluate this framework, we collected a large-scale fashion outfit dataset with over 200K outfits and 800K fashion items from the Internet. Extensive experiments show that COutfitGAN outperforms other baselines in terms of similarity, authenticity, and compatibility measurements.

This paper was accepted by IEEE TMM

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distributed Representations of Sentences and Documents
• Which Training Methods for GANs do actually Converge?
• Learning Fashion Compatibility with Bidirectional LSTMs
• Semantic Photo Manipulation with a Generative Image Prior
• Mining Fashion Outfit Composition Using An End-to-End Deep Learning Approach on Set Data
• Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks
• Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network

Cited by in corpus (8)

• SGDiff: A Style Guided Diffusion Model for Fashion Synthesis
• Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environments
• BC-GAN: A Generative Adversarial Network for Synthesizing a Batch of Collocated Clothing
• FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting
• PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation
• Towards Intelligent Design: A Self-driven Framework for Collocated Clothing Synthesis Leveraging Fashion Styles and Textures
• AVE Speech: A Comprehensive Multi-Modal Dataset for Speech Recognition Integrating Audio, Visual, and Electromyographic Signals
• Fashion Image-to-Image Translation for Complementary Item Retrieval