Segmentation mask and feature similarity loss guided GAN for object-oriented image-to-image translation

作者：

Highlights：

• Proposed object-level image-to-image translation model to learn cross-domain mappings

• Proposed model to learn complex segmentation-guided attributes of shapes and positions

• Proposed feature similarity loss to constrain generated patches and maintain its appearance

摘要

•Proposed object-level image-to-image translation model to learn cross-domain mappings•Proposed model to learn complex segmentation-guided attributes of shapes and positions•Proposed feature similarity loss to constrain generated patches and maintain its appearance

论文关键词：Image-to-image translation,Object transfiguration,GAN

论文评审过程：Received 23 September 2021, Revised 26 February 2022, Accepted 3 March 2022, Available online 4 April 2022, Version of Record 4 April 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.102926