Despoina Paschalidou

I am Postdoctoral Researcher at Stanford University working with Prof. Leonidas Guibas at the Geometric Computation Group. I did my PhD at the Max Planck ETH Center for Learning Systems , where I worked with Prof. Andreas Geiger and Prof. Luc van Gool. Prior to this, I was an undergraduate in the School of Electrical and Computer Engineering in the Aristotle University of Thessaloniki in Greece, where I worked with Prof. Anastasios Delopoulos and Christos Diou. I am very interested in computer vision, particularly in the areas of interpretable shape representations, scene understanding and generative models and unsupervised deep learning.

Selected Publications
ATISS: Autoregressive Transformers for Indoor Scene Synthesis
Advances in Neural Information Processing Systems (NeurIPS), 2021
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
Computer Vision and Pattern Recognition (CVPR), 2021
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image
Computer Vision and Pattern Recognition (CVPR), 2020
Despoina Paschalidou, Luc van Gool, Andreas Geiger
Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
Computer Vision and Pattern Recognition (CVPR), 2019
Despoina Paschalidou, Ali Osman Ulusoy, Andreas Geiger
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds
Computer Vision and Pattern Recognition (CVPR), 2019
Aseem Behl, Despoina Paschalidou, Simon Donné, Andreas Geiger
RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
Computer Vision and Pattern Recognition (CVPR), 2018
(Spotlight Presentation)
Learning local feature aggregation functions with backpropagation
European Signal Processing Conference (EUSIPCO), 2017
Fast Supervised LDA for Discovering Micro-Events in Large-Scale Video Datasets
ACM Multimedia Conference (ACMM), 2016