Bar-Ilan University
PhD Candidate, Electrical Engineering, advised by Prof. Yosi Keller. Field of research - Deep-visual end-to-end camera pose localization.

Tel-Aviv University
MSc, Electrical Engineering, advised by Prof. Leonid Yaroslavsky. Project - 3D content rendering

Ben-Gurion University of the Negev
BSc, Electrical Engineering, advised by Prof. Stanley Rotman. Project - Point target detection in Hyper-spectral Images

Blink Technologies
Director of Architecture and AI.

Huawei
Research Team Lead.

Intel
Senior Research Engineer.

Intel
Research Team Lead.

Intel
Algorithm and Software Engineer.

Zoran
Software Engineer.

HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset We advocate for incorporating hypernetworks into single-scene and multiscene camera pose regression models.

Coarse-to-Fine Multi-Scene Pose Regression with Transformers We extend our previous MSTransformer approach by introducing a mixed classification-regression architecture that improves the localization accuracy.

Learning Multi-Scene Absolute Pose Regression with Transformers We propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into candidate pose predictions.

Learning single and multi-scene camera pose regression with transformer encoders We propose an attention-based approach for pose regression, where the convolutional activation maps are used as sequential inputs.

Do We Really Need Scene-specific Pose Encoders? We propose that scene-specific pose encoders are not required for pose regression and that encodings trained for visual similarity can be used instead.

Introduction to Camera Pose Estimation with Deep Learning We review deep learning approaches for camera pose estimation. We describe key methods in the field and identify trends aiming at improving the original deep pose regression solution. We further provide an extensive cross-comparison of existing learning-based pose estimators, together with practical notes on their execution for reproducibility purposes. Finally, we discuss emerging solutions and potential future research directions.