3D Understanding Group Leader
Avram Golbert leads Rafael’s 3D Understanding group, which specializes in 3D scene reconstruction and applying geometric understanding to numerous algorithms such as mapping, real time urban navigation and object detection. Avram holds a BSc in Mathematics and MSc in Computer Science from the Hebrew University where he researched object detection using geometric and semantic context.
Piecewise Planar and Non-Planar Segmentation of City Scale 3D Urban Models
Despite advances in multiview algorithms, flat surfaces in urban areas with little texture are still a challenge. We present a method for planar area recognition and model correction while avoiding deformation of non-planar areas such as domes, pillars and plant matter. We describe a segmentation of the model into bounded planar and non-planar areas driven by a global error function incorporating model shape and original image textures. The error is minimized iteratively using locally restricted graph cuts and the model is corrected accordingly. The algorithm was tested on various challenging real-world urban scenes and synthetic photo-realistic images are created from novel viewpoints without noticeable deformities that are common to typical reconstructions.