· 2017
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
- 22,010citations
- 2017year
Short summary
This paper introduces a novel method for image-to-image translation that does not require paired training data, a common limitation in existing techniques.
AI-generated from the title and abstract; the full text is not read.
Key points
- Enables image-to-image translation without paired training data.
- Introduces a "cycle consistency loss" to enforce reversibility of translations.
- Achieves state-of-the-art results on unpaired translation tasks.
- Applicable to style transfer, object transfiguration, and season transfer.
AI-generated from the title and abstract; the full text is not read.
Abstract
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F : Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.
The authors' abstract, as published at the source., 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science