Research:
Interests: Computer Vision (Semantics x Geometry), Machine Learning, Robotics
Current Projects: I am currently working on perception for Microsoft HoloLens. In the recent past I built computer vision systems for self-driving cars. This included basic research on exploiting deep neural networks for 3D reconstruction problems, as well as systems work for an embedded ADAS pipeline that combines monocular visual odometry, GPS fusion, object detection and tracking, detailed 3D object localization, among other capabilities. A bit earlier, I worked on analysis and implementation of dense SLAM algorithms for embedded and many-core platforms, and on marrying object recognition with 3D reasoning.
Publications: Google Scholar profile, Semantic Scholar page
 | Learning Keypoint Descriptors and Matching Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences Mohammed Fathy, Quoc-Huy Tran, M Zeeshan Zia, Paul Vernaza, Manmohan Chandraker arXiv March/2018 (PDF) |
 | Data-Driven Inductive Biases into Neural Networks Deep Supervision with Intermediate Concepts Chi Li, M Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory Hager, Manmohan Chandraker Submission to TPAMI 2018 PDF, KITTI-3D (159 MB), Labeled CAD models (1 GB), Rendered Images (Chair+Sofa, 14 GB), Rendered Images (Cars) |
 | 3D Object Geometry with deep CNNs Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Chi Li, M Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory Hager, Manmohan Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 PDF, Supplementary Material, KITTI-3D (159 MB), Labeled CAD models (1 GB), Rendered Images (Chair+Sofa, 14 GB), Rendered Images (Cars) |
 | Simultaneous Localization and Mapping (SLAM) x 3D Object Localization Monocular Reconstruction of Vehicles: Combining SLAM with Shape Priors Falak Chhaya, Dinesh Reddy, Sarthak Upadhyay, Visesh Chari, M Zeeshan Zia, KM Krishna IEEE Conference on Robotics and Automation (ICRA), 2016 (PDF, Project Page and Supplementary Material, Spotlight talk by Falak) |
  | Simultaneous Localization and Mapping (SLAM) Architectures Comparative Design Space Exploration of Dense and Semi-Dense SLAM M Zeeshan Zia, Luigi Nardi, Andrew Jack, Emanuele Vespa, Bruno Bodin et al. IEEE Conference on Robotics and Automation (ICRA), 2016 (PDF, Slides (interactive), Slides (spotlight)) Integrating Algorithmic Parameters into Benchmarking and Design Space Exploration in 3D Scene Understanding Brudo Bodin, Luigi Nardi, M Zeeshan Zia, Harry Wagstaff, Govind S Shenoy et al. International Conf. on Parallel Architecture and Compilation Techniques (PACT), 2016 (PDF, Code) SLAMBench: A performance and accuracy benchmarking methodology for SLAM Luigi Nardi, Bruno Bodin, M Zeeshan Zia, John Mawer, Andrew Nisbet et al. IEEE Conference on Robotics and Automation (ICRA), 2015 (PDF, Slides, Project Page / Code) In Media: Jetson Hacks HiPEAC Newsletter |
     | 3D Object Localization and Scene Understanding Towards Scene Understanding with Detailed 3D Object Representations M Zeeshan Zia, Michael Stark, Konrad Schindler International Journal of Computer Vision (IJCV): vol. 112(2), p.188-203, 2015 (PDF, Code, Evaluation Script and Test set) 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 Our IJCV'15 paper contains expanded explanations and results for this work. (PDF, Poster, Code, Evaluation Script and Test set) 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 (PDF, Supplemental, Poster, Code, Training set~1.5 GB, Test set~260 MB) Detailed 3D Representations for Object Modeling and Recognition M Zeeshan Zia, Michael Stark, Bernt Schiele, Konrad Schindler IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI): vol. 35(11), p.2608-2623, 2013 (PDF, Code, Annotations) Revisiting 3D geometric models for accurate object shape and pose M Zeeshan Zia, Michael Stark, Bernt Schiele, Konrad Schindler IEEE Workshop on 3D Representation and Recognition (3dRR/ICCV WS), 2011 Best Paper Award from Microsoft Research (PDF, Slides, Annotations) High-Resolution 3D Layout from a Single View M Zeeshan Zia PhD thesis, Swiss Federal Institute of Technology (ETH-Zurich), 2014 (PDF, Slides) |
 | Color and Pattern Matching on Mobile Exemplar-Based Color Classification Zeeshan Zia, Emilio Maggio, Qi Pan, Michael Gervautz, Zsolt Szalavari US Patent Application 20,150,279,047 (Link) |
 | 3D Object Detection 3D Model Selection from an Internet Database for Robotic Vision Ulrich Klank, M Zeeshan Zia, Michael Beetz IEEE Conference on Robotics and Automation (ICRA), 2009 (PDF) Acquisition of Dense 3D Model Database for Robotic Vision M Zeeshan Zia, Ulrich Klank, Michael Beetz The 14th International Conference on Advanced Robotics (ICAR), 2009 (PDF, Slides) |
 | Dynamic 3D Scene Understanding and Action Recognition Inside-Out Activity Analysis using 3D Hand, Object, and Scene Tracking M Zeeshan Zia MS thesis, Electrical Engineering, Technical University of Munich, 2009 (PDF) |