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

Under Review

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.

3DV 2025

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.

Get in Touch

I am currently seeking research internship opportunities for 2026. If you are looking for a dedicated researcher to join your team, or if you simply want to discuss emerging trends in 3D Generative AI, please reach out!