shu

I’m a computer vision/graphics researcher focused on bringing assistive AI tooling to artists, particularly creators working on anime-style content.

In 2024, I founded Dondon Technologies, a startup providing AI assistance to traditional 2D animators using the Japanese anime pipeline.

( ➤ publications page )
I did my PhD at the Univ. of Maryland - College Park with Prof. Matthias Zwicker; my thesis was on ML for animation, illustration, and 3D characters.

( ➤ experiences page )
I’ve also collaborated outside academia, with both the tech and anime industries (TikTok, Meta, OLM Digital, Arch Inc., etc.).

( ➤ anime page )
I just so happen to like anime; my favorite is Nichijou (2011). To trash on my taste, please see my mal or my top anime page.

( ➤ artwork page )
I can draw a bit (not very well). Despite being a researcher in AI+art, I don’t use ML models for my own artwork; they still don’t do what I want…

research areas

[sauce] [model]

AI-assisted animation. By studying animation industry practices, scaling data pipelines, bridging domain gaps, leveraging 3d priors, etc., I hope to uncover what AI can do for animation.

[yubi] [yubi]

3d character modeling. My work tries to democratize 3d character creation, bringing customizable experiences to the next generation of social interaction.

[source]

Deep rendering. I firmly believe graphics is the future of computer vision. As such, I’m also interested in new 3d representations and rendering techniques.