English

Semantics-Aware Image to Image Translation and Domain Transfer

Computer Vision and Pattern Recognition 2021-03-02 v2

Abstract

Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image to image translation technique that leverages the underlying semantic information for object transfiguration and domain transfer tasks. Specifically, we present a generative adversarial learning approach that jointly translates images and labels from a source domain to a target domain. Our main technical contribution is an encoder-decoder based network architecture that jointly encodes the image and its underlying semantics and translates both individually to the target domain. Additionally, we propose object transfiguration and cross-domain semantic consistency losses that preserve semantic labels. Through extensive experimental evaluation, we demonstrate the effectiveness of our approach as compared to the state-of-the-art methods on unsupervised image-to-image translation, domain adaptation, and object transfiguration.

Keywords

Cite

@article{arxiv.1904.02203,
  title  = {Semantics-Aware Image to Image Translation and Domain Transfer},
  author = {Pravakar Roy and Nicolai Häni and Jun-Jee Chao and Volkan Isler},
  journal= {arXiv preprint arXiv:1904.02203},
  year   = {2021}
}
R2 v1 2026-06-23T08:28:35.467Z