Maria Parelli

I am a Ph.D. student in the Autonomous Vision Group at the University of Tübingen, led by Prof. Andreas Geiger, as part of the International Max Planck Research School for Intelligent Systems (IMPRS-IS). I am also co-supervised by Federico Tombari, Michael Niemeyer and Michael Oechsle from Google Zurich. My focus area is 3D generative modeling.

Prior to this, I completed my Master's in Data Science at ETH Zurich under the supervision of Prof. Otmar Hilliges. Earlier, I earned a Diploma in Electrical and Computer Engineering from the National Technical University of Athens, where I worked with Prof. Petros Maragos. Before joining ETH, I worked as an ML Engineer/Researcher at Deeplab on interpretable vision-language understanding.

Email  /  Scholar  /  Twitter  /  Github

profile photo

Research

I'm interested in computer vision, deep learning and generative AI.

fast-texture HOLD: Category-agnostic 3d reconstruction of interacting hands and objects from video
Zicong Fan, Maria Parelli, Maria Eleni Kadoglou, Muhammed Kocabas, Xu Chen, Michael J. Black, Otmar Hilliges
CVPR, 2024   (Highlight)
project page / paper
fast-texture Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes
Alexandros Delitzas*, Maria Parelli*, Nikolas Hars, Georgios Vlassis, Sotirios Anagnostidis, Gregor Bachmann, Thomas Hofmann
BMVC, 2023   (Oral Presentation)
project page / paper
fast-texture CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes
Maria Parelli*, Alexandros Delitzas*, Nikolas Hars, Georgios Vlassis, Sotirios Anagnostidis, Gregor Bachmann, Thomas Hofmann
CVPR Workshops, 2023
paper
fast-texture Interpretable visual question answering via reasoning supervision
Maria Parelli, Dimitrios Mallis, Markos Diomataris, Vassilis Pitsikalis
ICIP, 2023
paper
fast-texture Spatio-temporal graph convolutional networks for continuous sign language recognition
Maria Parelli, Katerina Papadimitriou, Gerasimos Potamianos, Georgios Pavlakos, Petros Maragos
ICASSP, 2022
paper
fast-texture Exploiting 3d hand pose estimation in deep learning-based sign language recognition from rgb videos
Maria Parelli, Katerina Papadimitriou, Gerasimos Potamianos, Georgios Pavlakos, Petros Maragos
ECCV Workshops, 2020
paper

Design and source code from Jon Barron's wesite