We work on finding and understanding elements of algebra, geometry, statistics and optimization to apply them in computer vision, robotics and machine learning.We are part of Robotics and Machine Perception at the Czech Institute of Informatics, Robotics and Cybernetics and of the Center for Machine Perception  at the Czech Technical University in Prague.
Recent Results

I Rocco, M Cimpoi, R Arandjelović, A Torii, T Pajdla, J Sivic. Neighbourhood Consensus Networks. NIPS 2018 pdf | arXiv

V Larsson, M Oskarsson, K Åström, A Wallis, Z Kukelova, T Pajdla. Beyond Gröbner Bases: Basis Selection for Minimal Solvers. CVPR 2018 pdf | arXiv

H Taira, M Okutomi, T Sattler, M Cimpoi, M Pollefeys, J Sivic, T Pajdla, A Torii. InLoc: Indoor Visual Localization with Dense Matching and View Synthesis. CVPR 2018 pdf | arXiv

T Sattler, W Maddern, C Toft, A Torii, L Hammarstrand, E Stenborg, D Safari, M Okutomi, M Pollefeys, J Sivic, F Kahl, T Pajdla. Benchmarking 6DOF Urban Visual Localization in Changing Conditions. CVPR 2018 pdf | arXiv

A Torii, R Arandjelovic, J Sivic, M Okutomi, T Pajdla. 24/7 Place Recognition by View Synthesis.IEEE TPAMI 2018 pdf | CVPR 2015 pdf | Project page+data+code

R Arandjelovic, P Gronat, A Torii, T Pajdla and J Sivic. NetVLAD: CNN architecture for weakly supervised place recognition. IEEE PAMI 2018 pdf|CVPR 2016(oral)pdf Project page video

See more results