Semantics-Aware Image to Image Translation and Domain Transfer
This addresses the problem of domain adaptation and object manipulation in computer vision, but it appears incremental as it builds on existing GAN-based translation methods.
The paper tackles unsupervised image-to-image translation by leveraging semantic information for object transfiguration and domain transfer, demonstrating effectiveness compared to state-of-the-art methods.
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.