Local Facial Attribute Transfer through Inpainting

Durall, Ricard; Pfreundt, Franz-Josef; Keuper, Janis

doi:10.48550/arxiv.2002.03040

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CGAN (Mirza and Osindero, 2014) was the first work to introduce conditions on GANs, shortly followed by a flurry of works ever since. There have been many different forms of conditional image generation, including class-based (Mirza and Osindero, 2014;Odena et al, 2017;Brock et al, 2018) , imagebased (Isola et al, 2017;Huang et al, 2018;Mao et al, 2019) , mask-and bounding box-based (Hinz et al, 2019;Park et al, 2019;Durall et al, 2020), as well as text-based (Reed et al, 2016;Xu et al, 2018;Hong et al, 2018). This intensive research has led to impressive development of a huge variety of techniques, paving the road towards the challenging task of generating more complex scenes.…”

Section: Conditional Generative Adversarial Networkmentioning

confidence: 99%

Latent Space Conditioning on Generative Adversarial Networks

Durall¹,

Ho²,

Pfreundt³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data. These supervised methods allow a much finer-grained control of the output image, offering more flexibility and stability. Nevertheless, the main drawback of such models is the necessity of annotated data. In this work, we introduce an novel framework that benefits from two popular learning techniques, adversarial training and representation learning, and takes a step towards unsupervised conditional GANs. In particular, our approach exploits the structure of a latent space (learned by the representation learning) and employs it to condition the generative model. In this way, we break the traditional dependency between condition and label, substituting the latter by unsupervised features coming from the latent space. Finally, we show that this new technique is able to produce samples on demand keeping the quality of its supervised counterpart.

show abstract