Dragos Costea

According to our database, Dragos Costea authored at least 13 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Maia: A Real-time Non-Verbal Chat for Human-AI Interaction.

Dragos Costea, Alina Marcu, Cristina Lazar, Marius Leordeanu

CoRR, 2024

2023

Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving.

Alexandra Budisteanu, Dragos Costea, Alina Marcu, Marius Leordeanu

CoRR, 2023

Self-supervised Hypergraphs for Learning Multiple World Interpretations.

Alina Marcu, Mihai Cristian Pîrvu, Dragos Costea, Emanuela Haller, Emil Slusanschi, Nabil Belbachir, Rahul Sukthankar, Marius Leordeanu

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

UFO Depth: Unsupervised learning with flow-based odometry optimization for metric depth estimation.

Vlad Licaret, Victor Robu, Alina Marcu, Dragos Costea, Emil Slusanschi, Rahul Sukthankar, Marius Leordeanu

Proceedings of the 2022 International Conference on Robotics and Automation, 2022

2021

Depth Distillation: Unsupervised Metric Depth Estimation for UAVs by Finding Consensus Between Kinematics, Optical Flow and Deep Learning.

Mihai Cristian Pîrvu, Victor Robu, Vlad Licaret, Dragos Costea, Alina Marcu, Emil Slusanschi, Rahul Sukthankar, Marius Leordeanu

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus.

Marius Leordeanu, Mihai Cristian Pîrvu, Dragos Costea, Alina Elena Marcu, Emil Slusanschi, Rahul Sukthankar

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Semantics Through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation.

Alina Marcu, Vlad Licaret, Dragos Costea, Marius Leordeanu

Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

2019

Towards Automatic Annotation for Semantic Segmentation in Drone Videos.

Alina Marcu, Dragos Costea, Vlad Licaret, Marius Leordeanu

CoRR, 2019

2018

A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization.

Alina Marcu, Dragos Costea, Emil Slusanschi, Marius Leordeanu

CoRR, 2018

SafeUAV: Learning to Estimate Depth and Safe Landing Areas for UAVs from Synthetic Data.

Alina Marcu, Dragos Costea, Vlad Licaret, Mihai Cristian Pîrvu, Emil Slusanschi, Marius Leordeanu

Proceedings of the Computer Vision - ECCV 2018 Workshops, 2018

Roadmap Generation Using a Multi-Stage Ensemble of Deep Neural Networks With Smoothing-Based Optimization.

Dragos Costea, Alina Marcu, Emil Slusanschi, Marius Leordeanu

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

2017

Creating Roadmaps in Aerial Images with Generative Adversarial Networks and Smoothing-Based Optimization.

Dragos Costea, Alina Marcu, Marius Leordeanu, Emil Slusanschi

Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, 2017

2016

Aerial image geolocalization from recognition and matching of roads and intersections.

Dragos Costea, Marius Leordeanu

Proceedings of the British Machine Vision Conference 2016, 2016