Our paper "End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes" has been accepted as a conference paper at the IEEE International Conference on Signal Processing, Sensors, and Intelligent Systems (SPSIS), 2022. The paper is co-authored by Qiao Chen, and Charalambos Poullis. Abstract: Image-based 3D reconstruction is one of the most important tasks

Our paper "Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Prediction" has been accepted as a conference paper at the IEEE Computational Intelligence In Vehicles And Transportation Systems (CIVTS), 2022. The paper is co-authored by Naghmeh Shafiee Roudbari, Zachary Patterson, Ursula Eicker, and Charalambos

Our work on "Unsupervised Structure-Consistent Image-to-Image Translation " has been accepted as a conference paper at the 17th International Symposium on Visual Computing (ISVC), 2022. The paper is co-authored by Shima Shahfar and Charalambos Poullis. Abstract: The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve

ICT lab researcher Mohsen Parisay’s journal paper “EyeTAP: A Novel Technique using Voice Inputs to Address the Midas Touch Problem for Gaze-based Interactions” is published in the International Journal of Human-Computer Studies, Elsevier, 2021. The paper is co-authored with Parisay M., Poullis C., Kersten M. Abstract: One of the

ICT lab researcher Mohsen Parisay will be presenting our work “IDEA: Index of Difficulty for Eye Tracking Applications. An Analysis Model for Target Selection Tasks”. The work was co-authored by Mohsen Parisay, Charalambos Poullis, and Marta Kersten. Abstract: Fitts’ law is a prediction model to measure the difficulty level of

ICT lab researcher Yashas Joshi will be presenting our work ” Dynamic Foveated Rendering for Redirected Walking in Virtual Reality” as a poster at SIGGRAPH 2020. The work was co-authored by Yashas Joshi and Charalambos Poullis. Abstract: We present a novel redirected walking technique for virtual reality leveraging dynamic foveated rendering

ICT lab researcher Mohsen Parisay will be presenting our work “FELiX: Fixation-based Eye Fatigue Load Index A Multi-factor Measure for Gaze-based Interactions” at the International Conference on Human System Interaction, 2020. The work is co-authored by M. Parisay, C. Poullis, M. Kersten. 🥇 The paper is the recipient of the Best

The work on “Inattentional Blindness for Redirected Walking Using Dynamic Foveated Rendering” has been accepted for publication in IEEE Access 2020. The work is co-authored by Yashas Joshi and Charalambos Poullis. Abstract: Redirected walking is a Virtual Reality (VR) locomotion technique which enables users to navigate virtual environments (VEs) that

ICT lab researcher will be presenting our work “Portal to knowledge: A Virtual Library Using Markerless Augmented Reality System for Mobile Device” at SPIE AR|VR|MR 2020. The work is co-authored by Yashas Joshi and Charalambos Poullis. Abstract: Since exceedingly efficient hand-held devices became readily available to the world,

ICT lab researcher Majid Pourmemar will be presenting our work “Visualizing and Interacting with Hierarchical Menus in Immersive Augmented Reality”. The work is co-authored with Majid Pourmemar and Charalambos Poullis. 🥇 Majid, who will be presenting the work at the conference, received the “VRCAI 2019 Diversity and Inclusion Scholarship” sponsored by

ICT lab researcher Pinjing Xu will be presenting our work “Delineation of Road Networks Using Deep Residual Neural Networks and Iterative Hough Transform”. The work is co-authored with Pinjing Xu and Charalambos Poullis. In this paper we present a complete pipeline for extracting road network vector data from satellite RGB

Join us at the 16th Conference on Computer and Robot Vision, 2019 [https://www.eecs.yorku.ca/~mbrown/CRV19/] ICT lab researcher Bodhiswatta Chatterjee will be presenting our work “On Building Classification from Remote Sensor Imagery Using Deep Neural Networks and the Relation Between Classification and Reconstruction Accuracy Using Border

Our work on “Large-scale Urban Reconstruction with Tensor Clustering and Global Boundary Refinement” has been published as a regular journal paper in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019. The work is authored by C. Poullis. Abstract: Accurate and efficient methods for large-scale urban reconstruction are of significant

DAEDALUS(Massive-scale Urban Reconstruction, Classification, and Rendering from Remote Sensor Imagery) has received $599,317.50 CAD in funding from Presagis Inc, Canada’s Department of National Defense, and the Natural Sciences and Engineering Research Council of Canada under grant agreement DNDPJ515556- 17. On August 1st, 2018, the kick-off meeting

Join us at the 3DTV Conference 2018 [https://3dtv-con.org] ICT lab researcher Chen Qiao will be presenting our work on “Single-shot Dense Reconstruction with Epic-flow”. This work is co-authored with Chen Qiao, Charalambos Poullis. Abstract: In this paper we present a novel method for generating dense reconstructions by applying

The Photogrammetric Vision lab of the Cyprus University of Technology [https://photogrammetric-vision.weebly.com]will be presenting the joint work “Underwater Photogrammetry in Very Shallow Waters: Caustics Effect Removal and Main Challenges” at the ISPRS Technical Commission II Symposium, 2018 [https://www.isprs.org/tc2-symposium2018/]. This work was done in