Spyridon (Spiros) Thermos

I am a computer scientist on a startup quest as a co-founder of Moverse.

Previously I was postdoctoral researcher at the University of Edinburgh and adjunct professor (for a year) at the University of Thessaly (UTH). I received my Diploma in computer engineering (2013), my M.Sc. cum laude in computer science (2015), and my Ph.D. from UTH (2020).

My research interests lie in the intersection of representation learning and computer vision. Now I'm focusing on generative AI for human motion.

/ /


News


Highlighted publications

game

Towards Practical Single-Shot Motion Synthesis
K. Roditakis, S. Thermos, N. Zioulis
CVPRW, 2024

project page / bibtex
@inproceedings{roditakis2024synthesis,
  author    = {Roditakis, Konstantinos, and Thermos, Spyridon, and Zioulis, Nikolaos.},
  title     = {Towards Practical Single-Shot Motion Synthesis},
  booktitle = {IEEE/CVF Computer Vision and Pattern Recognition (CVPR) AI for 3D Generation Workshop},
  year      = {2024}  
}
                

game

Noise-in, Bias-out: Balanced and Real-time MoCap Solving
G. Albanis, N. Zioulis, S. Thermos, A. Chatzitofis, K. Kolomvatsos
ICCVW, 2023

project page / bibtex
@inproceedings{albanis2023noise,
  author    = {Albanis, Georgios, and Zioulis, Nikolaos, and Thermos, Spyridon, and Chatzitofis, Anargyros and Kolomvatsos, Kostas.},
  title     = {Noise-in, Bias-out: Balanced and Real-time MoCap Solving},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
  year      = {2023}  
}
                

game

Suit Up: AI MoCap
A. Chatzitofis, G. Albanis, N. Zioulis, S. Thermos
SIGGRAPH, 2023

video / project page / bibtex
@inproceedings{chatzitofis2023siggraph,
  author    = {Anargyros Chatzitofis and Georgios Albanis and Nikolaos Zioulis and Spyridon Thermos.},
  title     = {Suit Up: AI MoCap},
  booktitle = {ACM SIGGRAPH 2023 Real-Time Live!},
  year      = {2023}  
}
                

game

Learning disentangled representations in the imaging domain
X. Liu, P. Sanchez, S. Thermos, A. O'Neil, S. A. Tsaftaris
Medical Image Analysis, 2022

repo / bibtex
@article{liu2022tutorial,
  author       = "Xiao Liu and Pedro Sanchez and Spyridon Thermos and Alison O'Neil and Sotirios A. Tsaftaris",
  title        = "Learning Disentangled Representations in the Imaging Domain",
  journal      = "Medical Image Analysis",
  volume       = "80"
  pages        = "102516",
  year         = "2022"}
                

game

Measuring the Biases and Effectiveness of Content-Style Disentanglement
X. Liu, S. Thermos, G. Valvano, A. Chartsias, A. O'Neil, S. A. Tsaftaris
BMVC, 2021

repo / bibtex
@inproceedings{liu2021metrics,
  author       = "Xiao Liu and Spyridon Thermos and Gabriele Valvano and Agisilaos Chartsias and Alison O'Neil and Sotirios A. Tsaftaris",
  title        = "Measuring the Biases and Effectiveness of Content-Style Disentanglement",
  booktitle    = "BMVC",
  year         = "2021"}
                

game

Controllable cardiac synthesis via disentangled anatomy arithmetic
S. Thermos, X. Liu, A. O'Neil, S. A. Tsaftaris
MICCAI, 2021 (oral)

repo / bibtex
@inproceedings{thermos2021miccai,
author       = "Spyridon Thermos and Xiao Liu and Alison O'Neil and Sotirios A. Tsaftaris",
title        = "Controllable cardiac synthesis via disentangled anatomy arithmetic",
booktitle    = "International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)",
pages        = "",
year         = "2021"}
                

game

Deep Soft Procrustes for Markerless Volumetric Sensor Alignment
V. Sterzentsenko, A. Doumanoglou, S. Thermos, N. Zioulis, D. Zarpalas, P. Daras
IEEE VR, 2020

project page / video / bibtex
@inproceedings{sterzentsenko2020alignment,
  author       = "Vladimiros Sterzentsenko and Alexandros Doumanoglou and Spyridon Thermos and Nikolaos Zioulis and Dimitrios Zarpalas and Petros Daras",
  title        = "Deep Soft Procrustes for Markerless Volumetric Sensor Alignment",
  booktitle    = "Proc. IEEE VR",
  year         = "2020"}
                

game

A Deep Learning Approach To Object Affordance Segmentation
S. Thermos, P. Daras, G. Potamianos
ICASSP, 2020

repo / video / bibtex
@inproceedings{thermos2020icassp,
  author       = "Spyridon Thermos and Petros Daras and Gerasimos Potamianos",
  title        = "A Deep Learning Approach To Object Affordance Segmentation",
  booktitle    = "Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP)",
  pages        = "2358-2362",
  year         = "2020"}
                

game

Self-Supervised Deep Depth Denoising
V. Sterzentsenko, L. Saroglou, A. Chatzitofis, S. Thermos, N. Zioulis, A. Doumanoglou, D. Zarpalas, P. Daras
ICCV, 2019

arxiv / project page / bibtex
@inproceedings{sterzentsenko2019denoising,
  author       = "Vladimiros Sterzentsenko and Leonidas Saroglou and Anargyros Chatzitofis and Spyridon Thermos and Nikolaos Zioulis and Alexandros Doumanoglou and Dimitrios Zarpalas and Petros Daras",
  title        = "Self-Supervised Deep Depth Denoising",
  booktitle    = "ICCV",
  pages        = "1242-1251",
  year         = "2019"}
                

game

Deep Affordance-grounded Sensorimotor Object Recognition
S. Thermos, G.T. Papadopoulos, P. Daras, G. Potamianos
CVPR, 2017 (spotlight)

arxiv / bibtex
@inproceedings{thermos2017cvpr,
  author       = "S. Thermos and G.T. Papadopoulos and P. Daras and G. Potamianos",
  title        = "Deep Affordance-grounded Sensorimotor Object Recognition",
  booktitle    = "CVPR",
  pages        = "6167-6175"
  year         = "2017"}
                


Theme "borrowed" from Georgia Gkioxari and John Barron