High-level 3D object and scene modeling from single views

We explore detailed 3D representations of rigid, deformable 3D object classes, amenable to both estimating the 3D shape and pose of individual objects, and to scene understanding tasks such as reasoning jointly about multiple object instances or about scene-level interactions such as occlusions.

Representative Publications:

Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects
M.Zeeshan Zia, Michael Stark, Konrad Schindler
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

Explicit Occlusion Modeling for 3D Object Class Representations
M.Zeeshan Zia, Michael Stark, Konrad Schindler
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

Detailed 3D Representations for Object Modeling and Recognition
M.Zeeshan Zia, Michael Stark, Bernt Schiele, Konrad Schindler
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2013

Contact person: Zeeshan Zia