Hubert Kompanowski
PhD Researcher in 3D Generative AI
About Me
I am a PhD researcher at Trinity College Dublin, specializing in 3D Generative AI, diffusion models, and computer vision. My work focuses on enabling fine-grained control over style, shape, texture, and material properties and improving generative model quality.
Previously, I worked as a Machine Learning Engineer at MIM Solutions and ecVision, where I applied ML to medical imaging and surveillance.
Selected Research
FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention Adaptation
FROMAT is a lightweight appearance transfer technique for multiview diffusion models. We use self-attention adaptation for high-fidelity material transfer from single reference image.
Dream-in-Style: Text-to-3D Generation using Stylized Score Distillation
Dream-in-Style is a method for stylizing text-to-3D generation. We introduce stylized score distillation to guide a text-to-3D optimization process to output visually plausible geometry and appearance.