我的時間機器：個性化面部年齡轉換

MyTimeMachine: Personalized Facial Age Transformation

November 21, 2024

作者: Luchao Qi, Jiaye Wu, Bang Gong, Annie N. Wang, David W. Jacobs, Roni Sengupta

cs.AI

摘要

面部老化是一個複雜的過程，高度依賴於諸如性別、種族、生活方式等多個因素，這使得學習全球老化先驗以準確預測任何個人的老化變得極具挑戰性。現有技術通常能夠產生逼真且合理的老化效果，但重新老化的圖像通常不像該人在目標年齡時的外貌，因此需要個性化。在許多實際應用中，例如電影和電視節目中的視覺特效，用戶的個人照片收藏通常展示了一個較短的時間間隔（20至40年）的老化過程。然而，對個人照片收藏進行全球老化技術的單純個性化嘗試通常會失敗。因此，我們提出了MyTimeMachine（MyTM），將全球老化先驗與個人照片收藏（僅需50張圖像）結合起來，以學習個性化的年齡轉換。我們引入了一種新型的Adapter Network，將個性化的老化特徵與全球老化特徵結合起來，並使用StyleGAN2生成重新老化的圖像。我們還引入了三種損失函數，通過個性化老化損失、外推正則化和自適應w-norm正則化來個性化Adapter Network。我們的方法也可以擴展到視頻，實現高質量、保持身份並具有時間一致性的老化效果，使其與最先進的方法相比展現出優越性。

English

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 (20sim40 years) is often available. However, naive attempts to personalize global aging techniques on personal photo collections often fail. Thus, we propose MyTimeMachine (MyTM), which combines a global aging prior with a personal photo collection (using as few as 50 images) to learn a personalized age transformation. 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 approach can also be extended to videos, achieving high-quality, identity-preserving, and temporally consistent aging effects that resemble actual appearances at target ages, demonstrating its superiority over state-of-the-art approaches.