
Cecilia Curreli
PhD StudentTechnical University of MunichSchool of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany
Tel: +49-89-289-17771
Fax: +49-89-289-17757
Office: 02.09.033
Mail: cecilia.curreli@tum.de
Research
My research focus is Deep learning for Generative Models, Diffusion for 4D Computer Vision, 3D Human Motion Prediction and Generation.
About me
I am pursuing my PhD with Prof. Cremers at the Computer Vision Group since September 2023. In 2022 I joined Satoh's Lab at the University of Tokyo (UTokyo) and National Intitute of Informatics in Tokyo (NII) as a research intern investigating probabilistic aspects and uncertainty in conditioned human motion generation under the guidance of Prof. Shin'ichi Satoh and Dr. Andreu Girbau. I completed my Master's thesis with Prof. Nießner at Nießner Lab on "Probabilistic Human Motion Prediction with Scene Understanding and Occlusion Handling" completing my degree in computer science (Robotics, Cognition, Intelligence) at TU Munich. I obtained my Bachelor's degree in engineering science at TU Munich after completing a thesis on "Image Retrieval Under Challenging Weather and Lighting Conditions for Place Localization in Autonomous Driving" with Prof. Leal Taixè and Qunjie Zhou.
Publications
Export as PDF, XML, TEX or BIB
Journal Articles
2019
[] Spin-Scenario: A flexible scripting environment for realistic MR simulations , In Journal of magnetic resonance, Elsevier, volume 301, 2019.
Preprints
2025
[] Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction , In arXiv preprint arXiv:2501.06035, 2025.
[] ZDySS – Zero-Shot Dynamic Scene Stylization using Gaussian Splatting , In arXiv preprint arXiv:2501.03875, 2025.
Conference and Workshop Papers
2024
[] Gaussian Splatting in Style , In German Conference on Pattern Recognition (GCPR), 2024.
Student Projects (TUM and collaborators only)
I am always looking for talented and motivated students, for thesis and research projects if the research directions align.
Here a list of completed projects:
- Jialin Yang, Motion Prediction with Text Labels using Motion-to-Text Deep Learning Models. Guided research under joint supervision with Ph.D. candidate Chuqiao Li from the Univeristy of Tubingen.
Courses
- WS24: Master Seminar Recent Advances in 4D Computer Vision together with Mariia Gladkova.
- SS24: Master Seminar HuMANS: 3D Human Motion Analysis together with Mariia Gladkova.