Hello, I am Christos. I am a postdoctoral researcher at Computer Vision Lab, ETH Zurich. My broad research fields are Computer Vision and Machine Learning. The focus of my research is on high-level visual perception in adverse conditions, domain adaptation, segmentation, depth estimation, and synthetic data generation, with emphasis on their application to autonomous cars. I am a member of the TRACE-Zurich project on automated driving, hosted at Computer Vision Lab. I obtained my PhD in Electrical Engineering and Information Technology from ETH Zurich in June 2021, working at Computer Vision Lab and supervised by Prof. Luc Van Gool. Prior to joining Computer Vision Lab, I received my MSc in Computer Science from ETH Zurich in 2016 and my Diploma in Electrical and Computer Engineering from National Technical University of Athens in 2014, conducting my Diploma thesis at CVSP Group under the supervision of Prof. Petros Maragos.



News

2021-07-23: We got two papers accepted to ICCV 2021.
One paper is on our new ACDC dataset and the other is on fog simulation for LiDAR-based 3D object detection.

2021-04-29: ACDC dataset released! ACDC is a new large-scale driving dataset for training and testing semantic segmentation algorithms on adverse visual conditions, such as fog, nighttime, rain, and snow. The dataset and associated benchmarks are now available at https://acdc.vision.ee.ethz.ch.

2020-12-18: Our article on semantic segmentation at nighttime has been accepted to IEEE T-PAMI.
Check out the code for the MGCDA method we have developed.

Publications

ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding
Christos Sakaridis, Dengxin Dai, and Luc Van Gool
International Conference on Computer Vision (ICCV), 2021
[PDF]   [Dataset]   [BibTeX]   [arXiv]   [Supplement]

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
Martin Hahner, Christos Sakaridis, Dengxin Dai, and Luc Van Gool
International Conference on Computer Vision (ICCV), 2021
[PDF]   [Code]   [BibTeX]   [arXiv]   [Supplement]

Scale-Aware Domain Adaptive Faster R-CNN
Yuhua Chen, Haoran Wang, Wen Li, Christos Sakaridis, Dengxin Dai, and Luc Van Gool
International Journal of Computer Vision (IJCV), 2021
[Article]   [Code]   [BibTeX]

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
Christos Sakaridis, Dengxin Dai, and Luc Van Gool
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2020
[PDF]   [Code]   [UIoU Challenge]   [Project]   [arXiv]   [BibTeX]

Semantic Understanding of Foggy Scenes with Purely Synthetic Data
Martin Hahner, Dengxin Dai, Christos Sakaridis, Jan-Nico Zaech, and Luc Van Gool
Intelligent Transportation Systems Conference (ITSC), 2019
[PDF]   [BibTeX]   [arXiv]   [Project]

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
Christos Sakaridis, Dengxin Dai, and Luc Van Gool
International Conference on Computer Vision (ICCV), 2019
[PDF]   [BibTeX]   [arXiv]   [Project]   [UIoU Challenge]   [Supplement]

Active Contour Methods on Arbitrary Graphs Based on Partial Differential Equations
Christos Sakaridis, Nikos Kolotouros, Kimon Drakopoulos, and Petros Maragos
in Handbook of Numerical Analysis, Volume 20: Processing, Analyzing and Learning of Images, Shapes, and Forms: Part 2, Ron Kimmel and Xue-Cheng Tai (Eds.), Ch. 4, pp. 149-190, Elsevier, 2019
[PDF]   [BibTeX]
The PDF above is a post-peer-review, pre-copyedit version of the article published in HNA. The final authenticated version is available online here.

Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding
Dengxin Dai, Christos Sakaridis, Simon Hecker, and Luc Van Gool
International Journal of Computer Vision (IJCV), 2020
[PDF]   [BibTeX]   [arXiv]   [Project]
The PDF above is a post-peer-review, pre-copyedit version of the article published in IJCV. The final authenticated version is available online here.

Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding
Christos Sakaridis, Dengxin Dai, Simon Hecker, and Luc Van Gool
European Conference on Computer Vision (ECCV), 2018
[PDF]   [BibTeX]   [arXiv]   [Project]  
The final authenticated version is available online here.

Domain Adaptive Faster R-CNN for Object Detection in the Wild
Yuhua Chen, Wen Li, Christos Sakaridis, Dengxin Dai, and Luc Van Gool
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[arXiv]   [BibTeX]   [Code]

Semantic Foggy Scene Understanding with Synthetic Data
Christos Sakaridis, Dengxin Dai, and Luc Van Gool
International Journal of Computer Vision (IJCV), 2018
[PDF]   [Final PDF: view-only]   [BibTeX]   [arXiv]   [Project]  
The first PDF above is a post-peer-review, pre-copyedit version of the article published in International Journal of Computer Vision. The final authenticated version is available online here.

Theoretical Analysis of Active Contours on Graphs
Christos Sakaridis, Kimon Drakopoulos, and Petros Maragos
SIAM Journal on Imaging Sciences (SIIMS), 2017
[PDF]   [BibTeX]   [arXiv]   [Code]   [Project]