PhD Proposal: ML for Anime: Illustration, Animation, and 3D Characters
Shuhong Chen
Thursday, February 23, 2023, 11:00 am-1:00 pm 
Abstract
As anime-style content becomes more popular on the global stage, we ask whether new vision/graphics techniques could contribute to the artform. However, the highly-expressive and non-photorealistic nature of anime poses additional challenges not addressed by standard ML models, and much of the existing work in the domain does not align with real artist workflows. In this preliminary exam, we will present several works building foundational 2D/3D infrastructure for ML in anime, including pose estimation, video frame interpolation, and 3D character reconstruction. In addition, we will outline ongoing/future projects designing targeted interactive tools for 2D animators.
Examining Committee
Bio
Shuhong (Shu) Chen is a 4th year CS PhD student at UMD, advised by Prof. Matthias Zwicker. Prior to joining UMD in 2019, he received his BS in CS and Math from Rutgers University, where he worked with Prof. Ivan Marsic on ML for healthcare informatics in trauma resuscitation. Outside of academia, his industry experiences include vision internships at MIT Lincoln Labs and ByteDance/TikTok. Currently, his research interests are in non-photorealistic traditional 2D animation and 3D character modeling. He somewhat unfortunately spends his spare time on anime, vtubers, and gacha games.
This talk is organized by Tom Hurst