“Machine Learning for Anime: Illustration, Animation, and 3D Characters”, 2024 (; similar):
As anime-style content becomes more popular on the global stage, we ask whether new vision/graphics techniques could contribute to the art form. However, the highly-expressive and non-photorealistic nature of anime poses additional challenges not addressed by standard machine learning (ML) models, and much of the existing work in the domain does not align with real artist workflows.
In this dissertation defense, we will present several works building foundational 2D/3D infrastructure for ML in anime, including pose estimation, video frame interpolation, and 3D character reconstruction.
We will also introduce an interactive tool leveraging novel techniques to assist 2D animators.