Yaroslava Lochman

Computer Vision Research Engineer at The Machine Learning Lab.

Currently focused on robust methods for auto-calibrating cameras with severe lens aberrations. Prior, developed deep learning (DL) models for boundary object detection and studied geometry-aware DL approaches for representation learning, dense feature matching, and symmetry detection.

Google Scholar · GitHub · LinkedIn · Kaggle

Publications

Minimal Solvers for Single-View Auto-calibration.
Y. Lochman, O. Dobosevych, R. Hryniv, J. Pritts
Master thesis ( manuscript | code will be open soon)

Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations.
J. Pritts, Z. Kukelova, V. Larsson, Y. Lochman, O. Chum.
In Pattern Analysis and Machine Intelligence (PAMI), 2020 ( paper | code )

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales.
J. Pritts, Z. Kukelova, V. Larsson, Y. Lochman, O. Chum.
In International Journal of Computer Vision (IJCV), 2020 ( paper | code )