Lukas Uzolas

Computer Graphics. Computer Vision. Machine Learning.

Hey, I am a PhD Candidate at CGV, TU Delft (Netherlands). My research interests lie at the intersection of Computer Vision and Computer Graphics. I am generally working on image synthesis and animation with a focus on 3D controllability, allowing for easy interaction with 3D representations and images.

I received a M.Sc. degree with honours in Computer Vision and Image Processing, jointly coordinated by the Autonomous University of Madrid (Spain), University of Bordeaux (France), and Pázmány Péter Catholic University (Hungary) under the Erasmus Mundus initiative. I wrote my Master’s thesis at the Visual Computing Group at Harvard University (USA). Before this, I obtained a B.Sc. with distinction at the University of Hamburg (Germany) in Human-Computer Interaction. Next to my studies, I worked as a student software developer at various companies. For more details check my CV.

Prospective master thesis students please check here.

News

Mar 25, 2025 New project page on Surface-Aware Distilled 3D Semantic Features is online.
Nov 5, 2024 Our paper on zero-shot mesh animation (MotionDreamer) was accepted at 3DV 2025.
Oct 10, 2024 Getting back into creative programming by combining my Mandarin learning and SMPL.
May 31, 2024 MotionDreamer project page is up.
Sep 22, 2023 Paper on articulated point clouds accepted to NeurIPS 2023 🥳.
May 30, 2023 Project page released for our preprint on articulated point clouds.
May 30, 2022 Deep Anomaly Generation paper accepted at IEEE Access.
May 1, 2022 Joined the CGV group at TU Delft as a PhD Candidate.
Oct 17, 2021 Extended my previous work to generate animations with StyleGAN2 in this post without training.
Oct 11, 2021 Little blog post on projecting facial landmarks into the StyleGAN2 latent space.