Theodora Kontogianni

Theodora Kontogianni

I am an Assistant Professor in 3D Computer Vision at the Department of Applied Mathematics and Computer Science at the Technical University of Denmark . I am also affiliated with the Pioneer Centre for AI , where I collaborate on advancing 3D perception and spatial AI for autonomous systems. Prior to that, I was a postdoctoral fellow at the ETH AI Center with Prof. Dr. Konrad Schindler and Prof. Dr. Siyu Tang .

Before this, I received my PhD from the Computer Vision Group under the supervision of Prof. Dr. Bastian Leibe at RWTH Aachen University . I have also done two internships at Google Research, one in the US and one in Zurich.

My research interests are in computer vision, with a focus on 3D scene understanding, interactive learning, and continual learning.

Publications

Interactive 4D Segmentation

Interactive4D: Interactive 4D LiDAR Segmentation

Ilya Fradlin, Idil Esen Zulfikar, Kadir Yilmaz, Theodora Kontogianni, Bastian Leibe

Proc. International Conference on Robotics and Automation (ICRA), 2025 (to appear).

Project Paper
AGILE3D

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult, Francis Engelmann, Bastian Leibe, Konrad Schindler, Theodora Kontogianni

International Conference on Learning Representations (ICLR), 2024.

Paper Project
Interactive Object Segmentation

Interactive Object Segmentation in 3D Point Clouds

Theodora Kontogianni, Ekin Celikkan, Siyu Tang, Konrad Schindler

Proc. International Conference on Robotics and Automation (ICRA), 2023.

Best Paper Nominee in Human-Robot Interaction

Paper Project Video
Connecting the Dots: Floorplan Reconstruction

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries

Yuanwen Yue, Theodora Kontogianni, Konrad Schindler, Francis Engelmann

Proc. Computer Vision and Pattern Recognition (CVPR), 2023.

Paper Project Code
Continuous Adaptation for Interactive Object Segmentation

Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections

Theodora Kontogianni*, Michael Gygli*, Jasper Uijlings, Vittorio Ferrari

Proc. European Conference on Computer Vision (ECCV), 2020.

Paper Video
DualConvMesh-Net

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes

Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe

Proc. Computer Vision and Pattern Recognition (CVPR), 2020.

Oral Presentation

Paper Project Code
Dilated Point Convolutions

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

Francis Engelmann, Theodora Kontogianni, Bastian Leibe

Proc. International Conference on Robotics and Automation (ICRA), 2020.

Paper Video
3D-BEVIS: Bird's-Eye-View Instance Segmentation

3D-BEVIS: Bird's-Eye-View Instance Segmentation

Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe

Proc. German Conference on Pattern and Recognition (GCPR), 2019.

YRF DAGM Best Master's Thesis Award 2019

Paper
Know What Your Neighbors Do

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

Francis Engelmann, Theodora Kontogianni, Jonas Schult, Bastian Leibe

Proc. European Conference on Computer Vision Workshops (ECCVW), 2018.

Paper
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

Theodora Kontogianni*, Francis Engelmann*, Alexander Hermans, Bastian Leibe

Proc. International Conference on Computer Vision Workshops (ICCVW), 2017. Oral Presentation

Paper Poster Project Video Code
Incremental Object Discovery in Time-Varying Image Collections

Incremental Object Discovery in Time-Varying Image Collections

Theodora Kontogianni, Markus Mathias, Bastian Leibe

Proc. Computer Vision and Pattern Recognition (CVPR), 2016.

Paper