Samer Abualhanud

PhD Student/Research Staff · Leibniz University Hannover

Hannover, Germany

I am a PhD student and research staff member at the Institute of Photogrammetry and GeoInformation (IPI) at LUH, Germany. I am supervised by Dr.-Ing. Max Mehltretter and Prof. Christian Heipke. My research focuses on multi-view consistency in 3D reconstruction. I completed my M.Sc. in Mechatronics and Robotics at LUH. Previously, I was an intern at Bosch Research, working on NeRF, where I also wrote my master’s thesis on 3D occupancy prediction.

Publications

CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation

Samer Abualhanud, Christian Grannemann, Max Mehltretter

CVPRW 2026

Project Page arXiv PDF Supp. Code

Novel geometry-guided cylindrical attention for self-supervised surround-view depth estimation, improving cross-view consistency by extending the receptive field across views and restricting cross-view attention to a small neighborhood. State-of-the-art results on nuScenes and DDAD.

Self-Supervised 3D Semantic Occupancy Prediction from Multi-View 2D Surround Images

Samer Abualhanud, Eashwara Erahan, Max Mehltretter

PFG-Journal Karl Kraus Young Talent Award Lower Saxony Robotics Talent Award

PDF

A CNN-based approach for 3D semantic occupancy prediction from surround-view images, investigating 2D/3D supervised training and proposing novel self-supervised training scheme, showing promising results on the Occ3D dataset.