KONSTANTINOS REMATAS
Postdoc

I am a postdoctoral researcher in the GRAIL lab of University of Washington, working with Steve Seitz, Brian Curless and Ira Kemelmacher-Shlizerman. My current research interests are in the area of virtual and augmented reality (I guess the air of Seattle has something to do with that). In particular I am looking into ways of capturing and visualizing real-life content in VR/AR headsets.

I finished my PhD in the Visics group of K.U. Leuven where I worked with Tinne Tuytelaars, Mario Fritz and Tobias Ritschel. My thesis focused on generating novel views of 2D objects with the guidance of 3D models. During my PhD, I also spent some time in the Graphics and Vision departments of MPI Informaticsc in Saarbrucken. Before going to Leuven, I attended the Media Informatics master program of RWTH Aachen University and University of Bonn in Germany. Even before, I did my Bachelor in Computer Science at the Aristotle University of Thessaloniki.


Publications*

*Click on image for pdf

Natural Illumination from Multiple Materials Using Deep Learning

S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, T. Tuytelaars and L. Van Gool
in arXiv.

DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination

S. Georgoulis*, K. Rematas*, T. Ritschel, M. Fritz, L. Van Gool and T. Tuytelaars
in arXiv.
*denotes equal contribution

Novel Views of Objects from a Single Image

K. Rematas, N. Chuong, T. Ritschel, M. Fritz, T. Tuytelaars
to appear in Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.

Deep Reflectance Maps

K. Rematas, T. Ritschel, M. Fritz, E. Gavves, T. Tuytelaars
in Computer Vision and Pattern Recognition, 2016 (CVPR'16).

Dataset Fingerprints: Exploring Image Collections Through Data Mining

K. Rematas, B. Fernando, Frank Dellaert, T. Tuytelaars
in Computer Vision and Pattern Recognition, 2015 (CVPR'15).

Learning Like a Toddler: Watching Television Series to Learn Vocabulary from Images and Audio

E. Yilmaz, K. Rematas, T. Tuytelaars, H. Van hamme
in ACM International Conference on Multimedia, 2014 (ACM MM'14).

Project    Bibtex
Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models

K. Rematas, T. Ritschel, M Fritz, T. Tuytelaars
in Computer Vision and Pattern Recognition, 2014 (CVPR'14, oral).

Does Evolution cause a Domain Shift?

K. Rematas, B. Fernando, T. Tommasi, T. Tuytelaars
in ICCV '13 Workshop on Visual Domain Adaptation and Dataset Bias.

Kernel Density Topic Models: Visual Topics Without Visual Words

K. Rematas, M. Fritz, T. Tuytelaars
in NIPS '12 Workshop Modern Non-Parametric Methods in Machine Learning.

Project    Bibtex
The Pooled NBNN Kernel: Beyond Image-to-Class and Image-to-Image

K. Rematas, M. Fritz, T. Tuytelaars
in Asian Conference in Computer Vision, 2012 (ACCV'12).

Efficient Object Detection and Segmentation with a Cascaded Hough Forest ISM

K. Rematas, B. Leibe
in ICCV'11 Workshop on Challenges and Opportunities in Robot Perception (CORP'11).

Level-Set Person Segmentation and Tracking with Multi-Region Appearance Models and Top-Down Shape Information

E. Horbert, K. Rematas, B. Leibe
in International Conference on Computer Vision, 2011 (ICCV'11).

Multi-Class Image Labeling with Top-Down Segmentation and Generalized Robust P^N Potentials

G. Floros, K. Rematas, B. Leibe
in British Machine Vision Conference, 2011 (BMVC'11).