arXiv Analytics

Sign in

arXiv:1908.02671 [cs.CV]AbstractReferencesReviewsResources

Dual-reference Age Synthesis

Yuan Zhou, Bingzhang Hu, Ling Shao

Published 2019-08-07Version 1

Age synthesis has received much attention in recent years. State-of-the-art methods typically take an input image and utilize a numeral to control the age of the generated image. In this paper, we revisit the age synthesis and ask: is a numeral capable enough to describe the human age? We propose a new framework Dual-reference Age Synthesis (DRAS) that takes two images as inputs to generate an image which shares the same personality of the first image and has the similar age with the second image. In the proposed framework, we employ a joint manifold feature which consists of disentangled age and identity information. The final images are generated by training a generative adversarial network which competes against an age agent and an identity agent. Experimental results demonstrate the appealing performance and flexibility of the proposed framework by comparing with the state-of-the-art and ground truth.

Related articles: Most relevant | Search more
arXiv:2105.00490 [cs.CV] (Published 2021-05-02)
Residual Enhanced Multi-Hypergraph Neural Network
arXiv:1905.12261 [cs.CV] (Published 2019-05-29)
KG-GAN: Knowledge-Guided Generative Adversarial Networks
arXiv:2006.07084 [cs.CV] (Published 2020-06-12)
A Face Preprocessing Approach for Improved DeepFake Detection