Dual-reference Age Synthesis
This addresses age synthesis for computer vision applications, offering a more flexible approach than single-image methods, but it is incremental as it builds on existing age synthesis techniques.
The paper tackles age synthesis by proposing a dual-reference framework that uses two input images—one for identity and one for age—to generate a new image with soft age control, achieving appealing performance on UTKFace and CACD datasets.
Age synthesis methods typically take a single image as input and use a specific number to control the age of the generated image. In this paper, we propose a novel framework taking two images as inputs, named dual-reference age synthesis (DRAS), which approaches the task differently; instead of using "hard" age information, i.e. a fixed number, our model determines the target age in a "soft" way, by employing a second reference image. Specifically, the proposed framework consists of an identity agent, an age agent and a generative adversarial network. It takes two images as input - an identity reference and an age reference - and outputs a new image that shares corresponding features with each. Experimental results on two benchmark datasets (UTKFace and CACD) demonstrate the appealing performance and flexibility of the proposed framework.