Search for: All records

Facial aging is a complex process, highly dependent on multiple factors like gender, ethnicity, lifestyle, etc., making it extremely challenging to learn a global aging prior to predict aging for any individual accurately. Existing techniques often produce realistic and plausible aging results, but the re-aged images often do not resemble the person's appearance at the target age and thus need personalization. In many practical applications of virtual aging, e.g. VFX in movies and TV shows, access to a personal photo collection of the user depicting aging in a small time interval (20~40 years) is often available. However, naive attempts to personalize global aging techniques on personal photo collections often fail. Thus, we propose MyTimeMachine (MyTM), a method that combines a global aging prior with a personalized photo collection (ranging from as few as 10 images, ideally 50) to learn individualized age transformations. We introduce a novel Adapter Network that combines personalized aging features with global aging features and generates a re-aged image with StyleGAN2. We also introduce three loss functions to personalize the Adapter Network with personalized aging loss, extrapolation regularization, and adaptive w-norm regularization. Our method demonstrates strong performance on fair-use imagery of widely recognizable individuals, producing photorealistic and identity-consistent age transformations that generalize well across diverse appearances. It also extends naturally to video, delivering high-quality, temporally consistent results that closely resemble actual appearances at target ages—outperforming state-of-the-art approaches. 

Abstract Caffeine is a natural compound that inhibits the major cellular signaling regulator target of rapamycin (TOR), leading to widespread effects including growth inhibition. Saccharomyces cerevisiae yeast can adapt to tolerate high concentrations of caffeine in coffee and cacao fermentations and in experimental systems. While many factors affecting caffeine tolerance and TOR signaling have been identified, further characterization of their interactions and regulation remain to be studied. We used experimental evolution of S. cerevisiae to study the genetic contributions to caffeine tolerance in yeast, through a collaboration between high school students evolving yeast populations coupled with further research exploration in university labs. We identified multiple evolved yeast populations with mutations in PDR1 and PDR5, which contribute to multidrug resistance, and showed that gain-of-function mutations in multidrug resistance family transcription factors Pdr1, Pdr3, and Yrr1 differentially contribute to caffeine tolerance. We also identified loss-of-function mutations in TOR effectors Sit4, Sky1, and Tip41 and showed that these mutations contribute to caffeine tolerance. These findings support the importance of both the multidrug resistance family and TOR signaling in caffeine tolerance and can inform future exploration of networks affected by caffeine and other TOR inhibitors in model systems and industrial applications.