Abstract: Kinematic rigs make 3D meshes editable, but they do not specify which poses are plausible for a given asset. As a result, naively manipulating rig parameters can easily produce unrealistic deformations. Artists often address this by manually authoring pose spaces, but doing so requires substantial effort and expertise.

In this talk, I will first give a brief overview of my research on neural and numerical methods for physical simulation. I will then present Video-informed Pose Spaces (ViPS) for Auto-Rigged Meshes, a feed-forward generative model that automatically discovers plausible pose spaces for auto-rigged 3D meshes by distilling motion priors from pretrained video diffusion models. Without relying on scarce, artist-authored 4D datasets, ViPS supports diverse pose generation, constrained editing, smooth interpolation, and pose-guided video generation. Our work shows that video priors can be turned into practical and controllable tools for articulated 3D content, with strong generalization to unseen species and skeletal structures.

Speaker Bio: Honglin Chen is a fifth-year PhD student in Computer Science at Columbia University, advised by Prof. Changxi Zheng. Her research lies at the intersection of computer graphics/vision, physical simulation, and machine learning. She develops methods for simulating the 3D physical world, with the goal of making animation and creative tools more realistic, reliable, and accessible. She is a recipient of the Roblox Graduate Fellowship and a 2024 WiGRAPH Rising Star in Computer Graphics.

Sponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox.