Clothing generation by multi-modal embedding: A compatibility matrix-regularized GAN model

作者：

Highlights：

• We introduce a multi-modal embedding module under a clothing image generation framework.

• We propose to learn a compatibility space to regularize source latent features during the generation process.

• We develop a compatibility matrix-regularized generative adversarial network for clothing generation.

摘要

•We introduce a multi-modal embedding module under a clothing image generation framework.•We propose to learn a compatibility space to regularize source latent features during the generation process.•We develop a compatibility matrix-regularized generative adversarial network for clothing generation.

论文关键词：Multi-modal embedding,Compatibility learning,Generative adversarial network,Image translation,Fashion data

论文评审过程：Received 10 September 2020, Revised 30 November 2020, Accepted 3 January 2021, Available online 6 January 2021, Version of Record 13 January 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104097