Gabriela Csurka
Scholar

Gabriela Csurka

Google Scholar ID: PXm1lPAAAAAJ
Principal Scientist at Naver Labs Europe
Computer VisionArtificial Intelligence
Citations & Impact
All-time
Citations
6,992
 
H-index
37
 
i10-index
77
 
Publications
20
 
Co-authors
38
list available
Resume (English only)
Academic Achievements
  • Publications:
  • - RANa: Retrieval-Augmented Navigation, Transactions on Machine Learning Research (TMLR), November 2025
  • - PanSt3R: Multi-view consistent panoptic segmentation, International Conference on Computer Vision (ICCV), Honolulu, Hawaii, 19-23 October, 2025
  • - Test-time vocabulary adaptation for language-driven object detection, The IEEE International Conference on Image Processing (IEEE ICIP), Anchorage Alaska, USA, 14-17 September, 2025
  • - MUSt3R: Multi-view Network for Stereo 3D Reconstruction, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, Tennessee, USA, 11-15 June, 2025
  • - Gaussian splatting feature fields for (privacy-preserving) visual localization, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, Tennessee, USA, 11-15 June, 2025
  • - What could go wrong? Discovering and describing failure modes in computer vision, Explainable Computer Vision: Where are We and Where are We Going? Workshop at the European Conference on Computer Vision (ECCV), Milan, Italy, 29 September, 2024
  • - SHiNe: Semantic Hierarchy Nexus for open-vocabulary object detection, The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), Seattle, USA, 17-21 June, 2024
  • - Weatherproofing retrieval for localization with generative AI and geometric consistency, The International Conference on Learning Representations (ICLR), Vienna, Austria, 7-11 May, 2024
  • - Self-supervised learning of neural implicit feature fields for camera pose refinement, International Conference on 3D Vision (3DV), Davos, Switzerland, 18-21 March, 2024
  • - CroCo v2: Improved cross-view completion pre-training for stereo matching and optical flow, International Conference on Computer Vision (ICCV), Paris, France, 2-6 October, 2023
  • - RaSP: Relation-aware Semantic Prior for weakly supervised incremental segmentation, Second Conference on Lifelong Learning Agents (CoLLAs) 2023, Montreal, Canada, August 22-25, 2023
  • - SegLoc: Learning segmentation-based representations for privacy-preserving visual localization, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 15380-15391, CVPR 2023, Vancouver, Canada, 18-22 June, 2023
  • - Aligning language models with preferences through 𝑓-divergence minimization, International Conference on Machine Learning (ICML), 23-29 July 2023, Hawaii, USA. PMLR 202:11546-11583, 2023.
  • - CroCo: Self-Supervised Pretraining for 3D Vision Tasks by Cross-View Completion, Neural Information Processing Systems (NeurIPS), hybrid event, New Orleans, Louisiana, USA, 28 November – 9 December, 2022
  • - Semantic image segmentation: two decades of research, Foundations and Trends® in Computer Graphics and Vision: Vol. 14, No. 1-2, pp 1–162. DOI: 10.1561/0600000095.
  • - Deep visual geo-localization benchmark, Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Louisiana, USA, 21-24 June, 2022
  • - On the road to online adaptation for semantic image segmentation, Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Louisiana, USA, 21-24 June, 2022
  • - Investigating the role of image retrieval for visual localization – an exhaustive benchmark, International Journal of Computer Vision (2022) https://doi.org/10.1007/s11263-022-01615-7, 25 May, 2022
  • - Introducing the Expohedron for efficient pareto-optimal fairness-utility amortizations in repeated rankings, Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (WSDM), virtual event, 21-25 February, 2022
  • - Unsupervised domain adaptation for semantic image segmentation: a comprehensive survey, Published on arXiv.org
  • - NAVI: large-scale localiz