Zuzana Kukelova (original) (raw)

About Me

Who Am I?

I am an assistant professor at Czech Technical University in Prague, working in the fields of Computer Vision and Algebraic Geometry. My research is focused on algebraic methods for solving systems of polynomial equations with applications in camera geometry estimation and robotics. Recently I received a GAČR JUNIOR STAR 5-year grant to support my own research team of 3 PhD students and 2 Postdocs working on the topic of combining learning-based and algebraic approaches for camera geometry estimation.

Minimal Problems

Algebraic geometry

Camera Geometry

3D Reconstruction

Open PhD and Postdoc positions. Send CV and transcripts by email to apply.

CVPR 2023 Papers

K. Chelani, T. Sattler, F. Kahl, Z. Kukelova, Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses [Paper]

V. Panek, Z. Kukelova, T. Sattler, Visual Localization using Imperfect 3D Models from the Internet [webpage] [github] [Paper]

Recipient of a GAČR JUNIOR STAR grant December 2021

Project Title: New generation of camera geometry solvers ,
Open PhD and PostDoc Positions (Topic: Combining Learning-based and Algebraic Approaches for Camera Geometry Estimation).

JUNIOR STAR grants are intended for excellent scientists in their early careers. The 5-year project allows them to receive up to CZK 25 million and gives them an opportunity to attain scientific independence or even start their own research team, which can bring new areas of research into Czech science.

Recent Projects

Recent Projects

Visual Localization using 3D Models from the Internet

Benchmark for visual localization on imperfect 3D mesh models

[webpage] [github] [Paper]

Semi-generalized homography

Registering a perspective camera w.r.t. a generalized camera.

[github] [Paper]

Automatic generator of sparse resultant-based solvers

Automatic generator of sparse resultant-based solver for minimal problems

[github] [Paper1] [Paper2]

Rolling shutter absolute pose solvers

Code for different rolling shutter absolute pose solvers

[github] [Paper1] [Paper2]

Rectification from Coplanar Repeats

Image rectification pipeline and minimal solvers based on coplanar repeats

[github] [Paper1] [Paper2]

From two rolling shutters to one global shutter

RS distortion correction using 2 cameras with different rolling shutter directions.

[github] [Video] [Paper]

Globally Optimal Relative Pose Estimation with Gravity Prior

Globally optimal solver for relative pose estimation with know gravity firection

[github] [paper]

Multi-camera calibration

Infrastructure-based Multi-Camera Calibration using Radial Projections

[github] [paper]

Panoramic stitching with gravity prior

Minimal Solutions for Panoramic Stitching Given Gravity Prior

[github] [paper]

Journal Publications

• 
  J. Pritts, Z. Kukelova, V. Larsson, Y. Lochman, O. Chum
  Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations.
  IEEE Trans. Pattern Analysis and Machine Intelligence, 2020, DOI: 10.1109/TPAMI.2020.2992261 [pdf|code] IF 6.071

• 
  J. Pritts, Z. Kukelova, V. Larsson, Y. Lochman, O. Chum
  Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales.
  International Journal of Computer Vision, 128, 950–968, 2020 [pdf|code] IF 6.071

• 
  C. Albl, Z. Kukelova, V. Larsson, T. Pajdla
  Rolling Shutter Camera Absolute Pose.
  IEEE Trans. Pattern Analysis and Machine Intelligence, Volume: 42, Issue: 6, 2020 [html|code] IF 17.73

• 
  F. Šrajer, Z. Kukelova, A Fitzgibbon
  A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning.
  Optimization Methods and Software, February 2018 [pdf] IF 1.183

• 
  J. Kileel, Z. Kukelova, T. Pajdla, B. Sturmfels
  Distortion varieties.
  Foundations of Computational Mathematics, 18, pages1043–1071 (2018) [html|pdf] IF 2.829

• 
  Z. Kukelova, M. Bujnak, T. Pajdla
  Polynomial Eigenvalue Solutions to Minimal Problems in Computer Vision.
  IEEE Trans. Pattern Analysis and Machine Intelligence, 2012, DOI: 10.1109/TPAMI.2011.230 [html|pdf] Spotlight Paper, IF 4.795

• 
  Z. Kukelova, T. Pajdla
  A Minimal Solution to Radial Distortion Autocalibration.
  IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2410-2422, Dec. 2011 [html|pdf] IF 4.908

• 
  Z. Kukelova, M. Byrod, K. Josephson, T. Pajdla, K. Astrom
  Fast and robust numerical solutions to minimal problems for cameras with radial distortion
  Computer Vision and Image Understanding, vol. 114, no. 2, pp. 234-244, Feb. 2010. [html|pdf] IF 2.404

Conference papers

2023

• 
  K. Chelani, T. Sattler, F. Kahl, Z. Kukelova
  Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'23), 2023 [pdf]

• 
  V. Panek, Z. Kukelova, T. Sattler
  Visual Localization using Imperfect 3D Models from the Internet
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'23), 2023 [pdf | webpage]

• 
  S. Bhayani, T. Sattler, V. Larsson, J. Heikkilä, Z. Kukelova
  Partially calibrated semi-generalized pose from hybrid point correspondences
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV'23), 2023 [pdf | supp]

2022

• 
  D. Barath, Z. Kukelova
  Relative Pose from SIFT Features
  In European Conference on Computer Vision (ECCV’22), 2022 [pdf | supp]

• 
  V. Panek, Z. Kukelova, T. Sattler
  MeshLoc: Mesh-Based Visual Localization
  In European Conference on Computer Vision (ECCV’22), 2022 [pdf | code | supp]

• 
  Y. Ding, D. Barath, J. Yang, Z. Kukelova
  Relative Pose From a Calibrated and an Uncalibrated Smartphone Image
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'22), 2022 [pdf | code | supp]

2021

• 
  D. Barath, Y. Ding, Z. Kukelova, V. Larsson
  Image Stitching with Locally Shared Rotation Axis
  In International Conference on 3D Vision (3DV'21), 2021

• 
  S. Bhayani, Z. Kukelova, J. Heikkilä
  Computing stable resultant-based minimal solvers by hiding a variable
  International Conference on Pattern Recognition (ICPR'21), 2021 [pdf]

• 
  S. Bhayani, T. Sattler, D. Barath, P. Beliansky, J. Heikkilä, Z Kukelova
  Calibrated and Partially Calibrated Semi-Generalized Homographies
  IEEE/CVF International Conference on Computer Vision (ICCV’21), 2021 [pdf | code | video]
  [Oral presentation, Acceptance rate 3%]

• 
  Y. Ding, D. Baráth, Z. Kukelova
  Minimal Solutions for Panoramic Stitching Given Gravity Prior
  IEEE/CVF International Conference on Computer Vision (ICCV’21), 2021 [pdf | code | video | dataset]
  [Oral presentation, Acceptance rate 3%]

• 
  Y. Ding, D. Baráth, Z. Kukelova
  Globally Optimal Relative Pose Estimation with Gravity Prior
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021 [pdf | code | video | dataset]

2020

• 
  Z. Kukelova, C. Albl, A. Sugimoto, K. Schindler, T. Pajdla
  Minimal rolling shutter absolute pose with unknown focal length and radial distortion
  In European Conference on Computer Vision (ECCV’20), 2020 [pdf | code]

• 
  Y. Lin, V. Larsson, M. Geppert, Z. Kukelova, M. Pollefeys, T. Sattler
  Infrastructure-based multi-camera calibration using radial projections
  In European Conference on Computer Vision (ECCV’20), 2020 [pdf | code]

• 
  D. Barath, M. Polic, W. Förstner, T. Sattler, T. Pajdla, Z. Kukelova
  Making affine correspondences work in camera geometry computation
  In European Conference on Computer Vision (ECCV’20), 2020 [pdf | code]

• 
  C. Albl, Z. Kukelova, V. Larsson, M. Polic, T. Pajdla, K. Schindler
  From two rolling shutters to one global shutter
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20), 2020 [pdf | code | video | webpage]
  [Oral presentation, Acceptance rate 5.7%]

• 
  S. Bhayani, Z. Kukelova, J. Heikkilä
  A sparse resultant based method for efficient minimal solvers
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20), 2020 [pdf | code | video]

• 
  M. Polic, S. Steidl, Z. Kukelova, C. Albl, T. Pajdla
  Uncertainty Based Camera Model Selection
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20), 2020 [pdf | code | video]

2019

• 
  D. Barath, Z. Kukelova
  Homography from two orientation- and scale-covariant features
  In IEEE International Conference on Computer Vision (ICCV'19), Soul, Korea, 2019 [pdf | code]

• 
  V. Larsson, T. Sattler, Z. Kukelova, M. Pollefeys
  Revisiting Radial Distoriton Absolute Pose
  In IEEE International Conference on Computer Vision (ICCV'19), Soul, Korea, 2019 [pdf | code]

• 
  Z. Kukelova, V. Larsson
  Radial Distoriton Triangulation
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'19), Long Beach, USA, 2019 [pdf]

2018

• 
  ​J. ​Pritts, Z. Kukelova, V. Larsson, O. Chum
  Rectification from Radially-Distorted Scales
  In 14th Asian Conference on Computer Vision (ACCV'18), Perth, Australia, 2018 [pdf | code]
  [Oral presentation, Saburo Tsuji Best Paper Award]

• 
  Z. Kukelova, C. Albl, A. Sugimoto, T. Pajdla
  Linear solution to the minimal absolute pose rolling shutter problem
  In 14th Asian Conference on Computer Vision (ACCV'18), Perth, Australia, 2018 [pdf]

• 
  ​V. Larsson, M. Oskarsson, K. Astroem, A. Wallis, Z. Kukelova, T. Pajdla
  Beyond Gröbner Bases: Basis Selection for Minimal Solvers
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'18), SLC, USA, 2018 [pdf | video]

• 
  ​V. Larsson, Z. Kukelova, Y. Zheng
  Camera Pose Estimation with Unknown Principal Point
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'18), SLC, USA, 2018 [pdf | supp]

• 
  ​​J. Pritts, Z. Kukelova, V. Larsson, O. Chum
  Radially-Distorted Conjugate Translations
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'18), SLC, USA, 2018 [pdf | code]

2017

• 
  ​V. Larsson, Z. Kukelova, Y. Zheng
  Making Minimal Solvers for Absolute Pose Estimation Compact and Robust
  In IEEE International Conference on Computer Vision (ICCV'17), Venice, Italy, 2017 [pdf | supp]

• 
  ​C. Albl, Z. Kukelova, A. Fitzgibbon, J. Heller, M. Smid, T. Pajdla
  On the Two-View Geometry of Unsynchronized Cameras
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17), Honolulu, USA, 2017 [pdf | supp | poster]

• 
  ​Z. Kukelova, J. Kileel, T. Pajdla, B. Sturmfels
  A Clever Elimination Strategy for Efficient Minimal Solvers
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17), Honolulu, USA, 2017 [pdf | supp | poster]

Older publications

Older publications are available on my Google Scholar page.

Awards

• 2018
  Saburo Tsuji Best Paper Award - The 14th Asian Conference on Computer Vision

• 2015
  The winner of the 2015 Cor Baayen Award - an annual award given to a promising young researcher in computer science and applied mathematics by ERCIM – The European Research Consortium for Informatics and Mathematics

• 2014
  Best Paper Honourable Mention - The 12th Asian Conference on Computer Vision

• 2013
  The best PhD dissertation in cybernetics and informatics in the Czech Republic - The winner of CSKI (Czech Society for Cybernetics and Informatics) prize in 2013

• 2013
  Dean prize for prestigious PhD thesis

• 2012
  Spotlight Paper for the July 2012 issue of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Supervision

• Charalampos Tzamos
  Topic: Combining Algebraic and Learning-based Approaches for Camera Geometry Estimation (2022-now)

• Michal Polic
  (co-supervision 50%), Topic: Uncertainty in Structure from Motion Algorithms (submitted 2023)

• James Pritts
  (co-supervision 50%), Topic: Rectification from coplanar repeats (defended in 2020)

• Čeněk Albl
  (co-supervision 50%), Topic: 3D reconstruction with time-variant geometry (defended in 2019)

Community Service

• General Chair
  International Conference on 3D Vision (3DV) 2022

• Program Chair
  European Conference on Computer Vision (ECCV) 2026, 3DV 2020, 23rd Computer Vision Winter Workshop (CVWW 2018), 19th Computer Vision Winter Workshop (CVWW 2014)

• Area Chair
  CVF/IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Asian Conference on Computer Vision (ACCV) 2022, CVPR 2022, ACCV 2020, 3DV 2019, 3DV 2018

• Guest editor
  International Journal of Computer Vision (IJCV) Special Issue on 3D Computer Vision

Karlovo namesti 13, Prague 2. (G-10a)