Welcome. I'm Balazs Kovacs.
I'm a Research Engineer on the Perception Team at Zoox. My main interests include Machine Learning for Computer Vision, Deep Learning and Robotics. Previously, I got my MSc degree in Computer Science at Cornell University where I was advised by Kavita Bala.
CV (2018 June): [Download]
Publications
-
Context-Aware Asset Search for Graphic Design
Balazs Kovacs, Peter O'Donovan, Kavita Bala, Aaron Hertzmann
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2018
[Paper] [Project] -
Shading Annotations in the Wild
Balazs Kovacs, Sean Bell, Noah Snavely, Kavita Bala
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
[Paper] [Project] -
Intrinsic Decompositions for Image Editing
Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, Kavita Bala
Computer Graphics Forum (Eurographics State of the Art Reports), 2017
[Paper] [Project] -
Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
Andreas Veit*, Balazs Kovacs*, Sean Bell, Julian McAuley, Kavita Bala, Serge Belongie
* equal contribution
IEEE International Conference on Computer Vision (ICCV), 2015
[Paper] [Project] -
Volumetric Transparency with Per-Pixel Fragment Lists
László Szécsi, Pál Barta, Balázs Kovács
Wolfgang Engel (editor) GPU PRO 3: Advanced Rendering Techniques. New York: CRC Press, Taylor & Francis Group, 2012. pp. 323-336
[Link] -
List Mode PET Reconstruction
Balázs Kovács
VI. Hungarian Computer Graphics and Geometry Conference. Budapest, Hungary, 2012.
Budapest: John von Neumann Computer Society, (ISBN: 978-963-313-048-3)
[Paper] -
Order Independent Transparency with Per-Pixel Linked Lists
Pál Barta, Balázs Kovács
Central European Seminar on Computer Graphics. Viničné, Slovakia, 2011.
[Paper] -
Total Variation Regularization in PET Reconstruction
Milán Magdics, Balázs Tóth, Balázs Kovács, László Szirmay-Kalos
Zoltán Kató, Kálmán Palágyi (editors) Képfeldolgozók és Alakfelismerők VIII. Konferenciája. Szeged, 2011.
[Paper]
Teaching
- 2015 Spring - CS4670 - Introduction to Computer Vision.
- 2014 Fall - CS4620 - Introduction to Computer Graphics. Office hours: Mondays, 4-6 PM, G21 Gates Hall
Class Projects
-
Efficient Computation of Co-occurrence Statistics for
Natural Language Processing Tasks
Balazs Kovacs*, Jack Hessel*
* equal contribution
Class project for CS6410
[Paper]
Other Experience
I also worked for a startup, Tresorit. We provide end-to-end encrypted file sync and sharing with no compromise. Try it out!