Scholar
Siniša Šteković
Google Scholar ID: T0qGNQYAAAAJ
Postdoctoral Researcher, Ecole des Ponts ParisTech
Citations & Impact
Citations
199
H-index
9
i10-index
7
Publications
17
Co-authors
8
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - [October 2025] Our GuideFlow3D will be presented at NeurIPS 2025.
- - [May 2025] Honored to be listed among the outstanding reviewers for CVPR 2025.
- - [May 2025] SCANnotate++ to be presented at CVPR 2025 Workshop – Synthetic Data for Computer Vision.
- - [March 2025] PyTorchGeoNodes (PGN) will be presented at CVPR2025.
- - [August 2024] Public release of the implementation of the PyTorchGeoNodes module.
- - [March 2024] Released PyTorchGeoNodes, a differentiable module for reconstructing 3D objects from images using interpretable shape programs.
- - [October 2023] Released SCANnotateDataset that contains CAD model and pose annotations for objects in the ScanNet dataset.
- - [October 2023] HOC-Search accepted at 3DV.
- - [September 2023] Successfully defended PhD thesis titled 'Playing Proposal Selection Games in 3D Scene Understanding'.
Research Experience
- Currently at Snap Inc.; Previously, a postdoctoral researcher at École des Ponts ParisTech and TU Graz.
Education
- PhD from TU Graz, under the guidance of Professors Vincent Lepetit and Friedrich Fraundorfer.
Background
- Research Interests: Advancement of Machine Learning and Computer Vision methods within the field of 3D Scene Understanding; Professional Field: Creating digital twins for indoor environments, with a specific emphasis on reconstructing 3D objects and structural elements in complex scenarios.
Miscellany
- Living in Paris, France; Looking forward to the bakeries.
