Sinisa Stekovic

Sinisa Stekovic is a postdoctoral researcher who earned his PhD with distinction under the expert guidance of Professors Friedrich Fraundorfer and Vincent Lepetit. His primary research interests revolve around the advancement of Deep Learning and Computer Vision techniques within the realm of 3D Scene Understanding. Sinisa's work delves into the exciting possibilities of creating digital twins for indoor environments, with a specific emphasis on the intricate task of reconstructing 3D objects and structural elements in demanding and complex scenarios.

Publications

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit
In Proc. International Conference on Computer Vision (ICCV), 2021
[arXiv][project]

Monte Carlo Scene Search for 3D Scene Understanding
Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar, Chetan Srinivasa Kumar, Friedrich Fraundorfer, Vincent Lepetit
In Proc. Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[arXiv][project]

General 3D Room Layout from a Single View by Render-and-Compare
Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit
In Proc. European Conference on Computer Vision (ECCV), 2020
[arXiv][supplementary][project]

Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning
Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
[arXiv]

S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation
Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
arXiv:1812.10717
[arXiv]

To top

Contact

Record not found: Person