Alexandros Delitzas - Alex Delitzas

Alexandros Delitzas (Alex Delitzas)

I am a Computer Science MSc student at ETH Zurich specializing in Machine Learning. I am interested in 3D Computer Vision, particularly in the areas of 3D scene understanding and generative modelling.

Currently, I am conducting my master thesis on 3D scene understanding supervised by Francis Engelmann and Prof. Marc Pollefeys. Furthermore, I conducted a research project in collaboration with the Data Analytics Lab, where I worked on the intersection of 2D/3D vision and natural language. In my semester thesis, I worked on diffusion models and 3D pose transfer supervised by Hao Tang, Prof. Radu Timofte and Prof. Luc Van Gool.

Prior to that, I was an undergraduate student in Electrical and Computer Engineering at the Aristotle University of Thessaloniki, where I worked with Prof. Andreas Symeonidis and Prof. Panagiotis Petrantonakis.

For any inquiries, feel free to reach out!

CV Mail Twitter Scholar Github

News

Apr. 2024: Our work SceneFun3D was accepted at CVPR '24 in Seattle as an oral presentation.
Dec. 2023: The second iteration of our Open-Vocabulary 3D Scene Understanding Workshop will be held in conjunction with CVPR '24 in Seattle.
Oct. 2023: Our work Multi-CLIP was accepted at BMVC '23 in Aberdeen as an oral presentation.

Publications

* indicates equal contribution

SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (Oral Presentation)
Alexandros Delitzas, Ayca Takmaz, Federico Tombari, Robert Sumner, Marc Pollefeys, Francis Engelmann
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2024
Project Page / Paper /

@InProceedings{delitzas2023scenefun3d, 
	author = {Alexandros Delitzas and Ayca Takmaz and Federico Tombari and Robert Sumner and Marc Pollefeys and Francis Engelmann}, 
	title = {SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes}, 
	booktitle = {IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2024}, 
}

Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes (Oral Presentation)
Alexandros Delitzas*, Maria Parelli*, Nikolas Hars, Georgios Vlassis, Sotirios Anagnostidis, Gregor Bachmann, Thomas Hofmann
Proc. of the British Machine Vision Conference (BMVC), 2023
Project Page / Paper /

@InProceedings{delitzas2023multi, 
	author = {Alexandros Delitzas and Maria Parelli and Nikolas Hars and Georgios Vlassis and Sotirios Anagnostidis and Gregor Bachmann and Thomas Hofmann}, 
	title = {Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes}, 
	booktitle = {Proc. of the British Machine Vision Conference (BMVC)}, 
	year = {2023}, 
}

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
Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
Project Page / Paper / Supplemental / Poster / Code /

@InProceedings{Parelli_2023_CVPR, 
	author = {Maria Parelli and Alexandros Delitzas and Nikolas Hars and Georgios Vlassis and Sotirios Anagnostidis and Gregor Bachmann and Thomas Hofmann}, 
	title = {CLIP-Guided Vision-Language Pre-Training for Question Answering in 3D Scenes}, 
	booktitle = {Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, 
	year = {2023}, 
}

Calista: A deep learning-based system for understanding and evaluating website aesthetics
Alexandros Delitzas, Kyriakos Chatzidimitriou, Andreas Symeonidis
International Journal of Human-Computer Studies (IJHCS), 2023
Project Page / Paper / Code /

@InProceedings{DELITZAS2023103019, 
	author = {Alexandros Delitzas and Kyriakos Chatzidimitriou and Andreas Symeonidis}, 
	title = {Calista: A deep learning-based system for understanding and evaluating website aesthetics}, 
	booktitle = {International Journal of Human-Computer Studies (IJHCS)}, 
	year = {2023}, 
}

Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders
Christodoulos Kechris*, Alexandros Delitzas*, Vasileios Matsoukas*, Panagiotis Petrantonakis
International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021
Project Page / Paper / Code /

@InProceedings{9630585, 
	author = {Christodoulos Kechris and Alexandros Delitzas and Vasileios Matsoukas and Panagiotis Petrantonakis}, 
	title = {Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders}, 
	booktitle = {International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)}, 
	year = {2021}, 
}

Invited talks

Open Data in the fight against COVID-19 (Keynote)
Electrical and Computer Engineering Student Conference of Greece (ECESCON 12), 2021
Slides

Homepage Template

This webpage is based on the template provided by Michael Niemeyer. I customized it to support a news section, equal contribution indications in the publications section and google analytics. Feel free to use this version or the original one!