Profile Picture

Kevis-Kokitsi Maninis

Academic Webpage

Hello! I am a Research Scientist at Google Research, working on 3D computer vision. Previously, I obtained my PhD at the Computer Vision Lab of ETH Zürich, where I worked with Prof. Luc Van Gool and Dr. Jordi Pont-Tuset on 2D scene understanding. I received my M.Eng degree from National Technical University of Athens, School of Electrical and Computer Engineering. I was a member of the CVSP lab working on human action recognition in videos with Prof. Petros Maragos. I have interned in Facebook AI Research (FAIR), where I worked on multi-task learning with Prof. Iasonas Kokkinos. This personal web-page will be updated with my research work.

Publications



Conference/Journal Publications


Probe3D icon

A. Krishnan, A. Kundu, K.-K. Maninis, J. Hays, and M. Brown
OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects
European Conference on Computer Vision (ECCV), 2024 - Oral
[BibTex]    [arXiv]    [pdf]    [Data + Code]   

@InProceedings{krishnan2024omninocs,
Author = {Krishnan, Akshay and Kundu, Abhijit and Maninis, Kevis-Kokitsi and Hays, James and Brown, Matthew},
Title = {{OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects}},
BookTitle = {ECCV},
Year = {2024}
}
Probe3D icon

M. El Banani, A. Raj, K.-K. Maninis, A. Kar, Y. Li, M. Rubinstein, D. Sun, L. Guibas, J. Johnson, and V. Jampani
Probing the 3D Awareness of Visual Foundation Models
Computer Vision and Pattern Recognition (CVPR), 2024
[BibTex]    [arXiv]    [pdf]    [Code]   

@InProceedings{elbanani2024probe3d,
Author = {El Banani, Mohamed and Raj, Amit and Maninis, Kevis-Kokitsi and Kar, Abhishek and Li, Yuanzhen and Rubinstein, Michael and Sun, Deqing and Guibas, Leonidas and Johnson, Justin and Jampani, Varun},
Title = {{Probing the 3D Awareness of Visual Foundation Models}},
BookTitle = {CVPR},
Year = {2024}
}
NAVI icon

V. Jampani*, K.-K. Maninis*, A. Engelhardt, A. Karpur, K. Truong, K. Sargent, S. Popov, A. Araujo, R. Martin-Brualla, K. Patel, D. Vlasic, V. Ferrari, A. Makadia, C. Liu, Y. Li, and H. Zhou
NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
Conference on Neural Information Processing Systems (NeurIPS), 2023
Dataset and Benchmarks Track
[BibTex]    [arXiv]    [pdf]    [Project Page]   

@InProceedings{jampani2023navi,
Author = {Jampani, Varun and Maninis, Kevis-Kokitsi and Engelhardt, Andreas and Karpur, Arjun and Truong, Karen and Sargent, Kyle and Popov, Stefan and Araujo, Andre and Martin-Brualla, Ricardo and Patel, Kaushal and Vlasic, Daniel and Ferrari, Vittorio and Makadia, Ameesh and Liu, Ce and Li, Yuanzhen and Zhou, Howard},
Title = {NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations},
BookTitle = {Conference on Neural Information Processing Systems (NeurIPS)},
Year = {2023}
}
CAD-Estate (layouts) icon

D. Rozumnyi, S. Popov, K.K. Maninis, M. Niessner, and V. Ferrari
Estimating Generic 3D Room Structures from 2D Annotations
Conference on Neural Information Processing Systems (NeurIPS), 2023
Dataset and Benchmarks Track
[BibTex]    [arXiv]    [pdf]    [Data + Code]   

@InProceedings{rozumnyi2023layouts,
Author = {Denys Rozumnyi and Stefan Popov and Kevis-Kokitsi Maninis and Matthias Niessner and Vittorio Ferrari},
Title = {Estimating Generic 3D Room Structures from 2D Annotations},
BookTitle = {Conference on Neural Information Processing Systems (NeurIPS)},
Year = {2023}
}
CAD-Estate (objects) icon

K.K. Maninis, S. Popov, M. Niessner, and V. Ferrari
CAD-Estate: Large-scale CAD Model Annotation in RGB Videos
International Conference on Computer Vision (ICCV), 2023
[BibTex]    [arXiv]    [pdf]    [Data + Code]   

@InProceedings{maninis2023cadestate,
Author = {Kevis-Kokitsi Maninis and Stefan Popov and Matthias Niessner and Vittorio Ferrari},
Title = {CAD-Estate: Large-scale CAD Model Annotation in RGB Videos},
BookTitle = {International Conference on Computer Vision (ICCV)},
Year = {2023}
}
RayTran icon

Michał J. Tyszkiewicz, K.K. Maninis, S. Popov, and V. Ferrari
RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers
European Conference on Computer Vision (ECCV), 2022
[BibTex]    [arXiv]    [pdf]   

@InProceedings{tyszkiewicz2022raytran,
Author = {Michał J. Tyszkiewicz and Kevis-Kokitsi Maninis and Stefan Popov and Vittorio Ferrari},
Title = {RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers},
BookTitle = {European Conference on Computer Vision (ECCV)},
Year = {2022}
}
Vid2CAD icon

K.K. Maninis*, S. Popov*, M. Niessner, and V. Ferrari
Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
[BibTex]    [arXiv]    [pdf]    [Project Page]

@Article{maninis2022vid2cad,
Author = {Kevis-Kokitsi Maninis and Stefan Popov and Matthias Nießner and Vittorio Ferrari},
Title = {Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos},
Journal = {IEEE Transactions on Pattern Analysis and Machine Inttelligence},
Year = {2022}
}
ASTMT icon

K.K. Maninis, I. Radosavovic, I. Kokkinos
Attentive Single-Tasking of Multiple Tasks
Computer Vision and Pattern Recognition (CVPR), 2019
[BibTex]    [arXiv]    [Code]

@InProceedings{maninis2019multitask,
Author = {Kevis-Kokitsi Maninis and Ilija Radosavovic and Iasonas Kokkinos},
Title = {Attentive Single-Tasking of Multiple Tasks},
Booktitle = {Computer Vision and Pattern Recognition (CVPR)},
Year = {2019}
}
OSVOS-S icon

K.K. Maninis*, S. Caelles*, Y. Chen, J. Pont-Tuset, L. Leal-Taixé, D. Cremers, and L. Van Gool
Video Object Segmentation Without Temporal Information
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
[BibTex]    [arXiv]    [pdf]    [Project, Code]

@Article{Man+18b,
Author = {Kevis-Kokitsi Maninis and Sergi Caelles and Yuhua Chen and Jordi Pont-Tuset and Laura Leal-Taixé and Daniel Cremers and Luc Van Gool},
Title = {Video Object Segmentation Without Temporal Information},
Journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Year = {2018}
}
Keypoints to Stereo icon

T. Probst*, K.K. Maninis*, A. Chhatkuli, M. Ourak, E. Vander Poorten, and L. Van Gool
Automatic Tool Landmark Detection for Stereo Vision in Robot-Assisted Retinal Surgery
Robotics and Automation Letters (RA-L), 2018
[BibTex]    [arXiv]    [pdf]    [Project Page]

@Article{Pro+18,
Author = {Thomas Probst and Kevis-Kokitsi Maninis and Ajad Chhatkuli and Mouloud Ourak and Emmanuel Vander Poorten and Luc Van Gool},
Title = {Automatic Tool Landmark Detection for Stereo Vision in Robot-Assisted Retinal Surgery},
Journal = {Robotics and Automation Letters (RA-L)},
Year = {2018}
}
Keypoints to Stereo icon

K.K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 4, pp. 819 - 833, 2018.
[BibTex]    [pdf]    [Code]    [Project Page]

@Article{Man+18a,
Author = {Kevis-Kokitsi Maninis and Jordi Pont-Tuset and Pablo Arbel\'{a}ez and Luc Van Gool},
Title = {Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks},
Journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Year = {2018},
Volume = {40},
Number = {4},
Pages = {819 - 833}
}
DEXTR icon

K.K. Maninis*, S. Caelles*, J. Pont-Tuset, and L. Van Gool
Deep Extreme Cut: From Extreme Points to Object Segmentation
Computer Vision and Pattern Recognition (CVPR), 2018
[BibTex]    [arXiv]    [pdf]    [Project, Code]

@InProceedings{Man+18,
Author = {Kevis-Kokitsi Maninis and Sergi Caelles and Jordi Pont-Tuset and Luc Van Gool},
Title = {Deep Extreme Cut: From Extreme Points to Object Segmentation},
Booktitle = {Computer Vision and Pattern Recognition (CVPR)},
Year = {2018}
}
Iterative icon

C. Ventura, J. Pont-Tuset, S. Caelles, K.K. Maninis, and L. Van Gool
Iterative Deep Learning for Road Topology Extraction
British Machine Vision Conference (BMVC), 2018
[BibTex]    [pdf]    [Project, Code]

@InProceedings{Ven+18,
Author = {Carles Ventura and Jordi Pont-Tuset and Sergi Caelles and Kevis-Kokitsi Maninis and Luc Van Gool},
Title = {Iterative Deep Learning for Road Topology Extraction},
Booktitle = {British Machine Vision Conference (BMVC)},
Year = {2018}
}
OSVOS icon

S. Caelles*, K.K. Maninis*, J. Pont-Tuset, L. Leal-Taixé, D. Cremers, and L. Van Gool
One-Shot Video Object Segmentation
Computer Vision and Pattern Recognition (CVPR), 2017
[BibTex]    [arXiv]    [pdf]    [Project, Code]

@InProceedings{Cae+17,
Author = {Sergi Caelles and Kevis-Kokitsi Maninis and Jordi Pont-Tuset and Laura Leal-Taix\'{e} and Daniel Cremers and Luc Van Gool},
Title = {One-Shot Video Object Segmentation},
Booktitle = {Computer Vision and Pattern Recognition (CVPR)},
Year = {2017}
}
COB ECCV icon

K.K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool
Convolutional Oriented Boundaries
European Conference on Computer Vision (ECCV), 2016
[BibTex]    [pdf]    [Code]    [Project Page]    [Computer Vision News]

@InProceedings{Man+16a,
Author = {Kevis-Kokitsi Maninis and Jordi Pont-Tuset and Pablo Arbel\'{a}ez and Luc Van Gool},
Title = {Convolutional Oriented Boundaries},
Booktitle = {European Conference on Computer Vision (ECCV)},
Year = {2016}
}
DRIU icon

K.K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool
Deep Retinal Image Understanding
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016
[BibTex]    [pdf]    [Supplemental]    [Code]    [Project Page]

@InProceedings{Man+16,
Author = {Kevis-Kokitsi Maninis and Jordi Pont-Tuset and Pablo Arbel\'{a}ez and Luc Van Gool},
Title = {Deep Retinal Image Understanding},
Booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
Year = {2016}
}


PhD Dissertation


PhD thesis icon

K.K. Maninis, Exploiting Low-Level Features for Higher-Level Scene Understanding
ETH Zürich, 2019
[BibTex]    [pdf]   

@phdthesis{Man2019,
Author = {Kevis-Kokitsi Maninis},
Title = {Exploiting Low-Level Features for Higher-Level Scene Understanding},
School = {ETH Zürich},
Year = {2019}
}


Other Publications


DAVIS 2018 icon

S. Caelles, A. Montes, K.K. Maninis, Y. Chen, L. sPan Gool, Federico Perazzi, and J. Pont-Tuset
The 2018 DAVIS Challenge on Video Object Segmentation
arXiv, 2018
[BibTex]    [arXiv]    [Webpage]    [Baseline]

@Article{Cae+18,
Author = {Sergi Caelles and Alberto Montes and Kevis-Kokitsi Maninis and Yuhua Chen and Luc Van Gool and Federico Perazzi and Jordi Pont-Tuset},
Title = {The 2018 DAVIS Challenge on Video Object Segmentation},
Journal = {arXiv:1803.00557},
Year = {2018}
}
Miriam icon

M. Bellver, K.K. Maninis, J. Pont-Tuset, X. Giró-i-Nieto, J. Torres, and L. Van Gool
Detection-aided liver lesion segmentation using deep learning
NeurIPS Machine Learning for Health Workshop, 2017
[BibTex]    [pdf]

@InProceedings{Bel+17,
Author = {Miriam Bellver and Kevis-Kokitsi Maninis and Jordi Pont-Tuset and Xavier Giró-i-Nieto and ordi Torres and Luc Van Gool},
Title = {Detection-aided liver lesion segmentation using deep learning},
Booktitle = {NIPS Machine Learning for Health Workshops},
Year = {2017}
}
Mobihealth icon

G. Chalvatzaki, G. Pavlakos, K.K. Maninis, X. Papageorgiou, V. Pitsikalis, C. Tzafestas, and P. Maragos
Towards an Intelligent Robotic Walker for Assisted Living using Multimodal Sensorial Data
International Conference on Mobile Communication and Healthcare (Mobihealth), 2014
[BibTex]    [pdf]

@InProceedings{Cha+14,
Author = {Georgia Chalvatzaki and Georgios Pavlakos and Kevis-Kokitsi Maninis and Xanthi Papageorgiou and Vassilis Pitsikalis and Costas Tzafestas, and Petros Maragos},
Title = {Towards an Intelligent Robotic Walker for Assisted Living using Multimodal Sensorial Data},
Booktitle = {4th International Conference on Wireless Mobile Communication and Healthcare (Mobihealth)},
Year = {2014}
}
ICIP icon

K.K. Maninis, P. Koutras, and P. Maragos
Advances on Action Recognition in Videos Using an Interest Point Detector Based on Multiband Spatio-Temporal Enegies
International Conference on Image Processing (ICIP), 2014
[BibTex]    [pdf]

@InProceedings{MKM14,
Author = {Kevis-Kokitsi Maninis and Petros Koutras and Petros Maragos},
Title = {Advances on Action Recognition in Videos Using an Interest Point Detector Based on Multiband Spatio-Temporal Enegies},
Booktitle = {IEEE International Conference on Image Processing (ICIP)},
Year = {2014}
}

Contact

E-mail: kevismaninis@gmail.com