Mahdi Rad

More information can be found on my web page.

I am a postdoctoral researcher in the Institute of Computer Graphics and Vision (ICG) of Graz University of Technology (TUG), collaborating with Prof. Vincent Lepetit. I received the Ph.D. degree in 2018 from ICG under the supervision of Prof. Vincent Lepetit. Before that, I received a master’s and bachelor's degree in Computer Science in 2014 and 2012 respectively, both from Ecole Polytechnique Fédérale de Lausanne (EPFL). My research interests are Machine Learning methods for Computer Vision, specifically Deep Learning, and methods for 3D object pose estimation, 3D hand pose estimation, and hand-object interaction.

I served as a reviewer for many international conferences and journals, such as CAVW, CVPR, CVWW, ECCV, ICCV, Image Matching, IPSJ, ISMAR, PR, R6D, TMCCA, TOMM, TPAMI, WACV.

Google Scholar

Publications

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit
In Proc. International Conference on Computer Vision (ICCV), 2021
[arXiv][project]

General 3D Room Layout from a Single View by Render-and-Compare
Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit
In Proc. European Conference on Computer Vision (ECCV), 2020
[arXiv][supplementary][project]

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
Anil Armagan, ..., Mahdi Rad, ..., Vincent Lepetit
In Proc. European Conference on Computer Vision (ECCV), 2020
[arXiv]

ALCN: Adaptive Local Contrast Normalization
Mahdi Rad, Peter M. Roth and Vincent Lepetit
Computer Vision and Image Understanding (CVIU), 2020
[arXiv][project][video-1] [video-2]

HOnnotate: A method for 3D Annotation of Hand and Objects Poses
Shreyas Hampali, Mahdi Rad, Markus Oberweger and Vincent Lepetit
In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020
[arXiv][project][video][supplementary]

3D Pose Estimation from Color Images without Manual Annotations
Mahdi Rad, Markus Oberweger, and Vincent Lepetit
In Proc. Austrian Association of Pattern Recognition Workshop(OAGM), 2019
[paper][project]

Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations
Mahdi Rad, Markus Oberweger, and Vincent Lepetit
In Proc. Asian Conf. on Computer Vision (ACCV), 2018
[arXiv] [project] [video]

Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation
Markus Oberweger, Mahdi Rad, and Vincent Lepetit
In Proc. European Conf. on Computer Vision (ECCV), 2018
[paper] [project]

Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
Mahdi Rad, Markus Oberweger, and Vincent Lepetit
In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018
[paper] [project] [video-1] [video-2] [arXiv]

BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
Mahdi Rad and Vincent Lepetit
In Proc. IEEE Int'l Conf. on Computer Vision (ICCV), 2017
[paper] [project] [video-1] [video-2] [video-3] [arXiv]

Adaptive Local Contrast Normalization for Robust Object Detection and 3D Pose Estimation
Mahdi Rad, Peter M. Roth and Vincent Lepetit
In Proc. British Machine Vision Conf. (BMVC), 2017
[paper] [project] [video-1] [video-2] [arXiv]

Robust 3D Object Tracking from Monocular Images using Stable Parts
Alberto Crivellaro, Mahdi Rad, Yannick Verdie, Kwang Moo Yi, Pascal Fua, and Vincent Lepetit
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017
[paper] [video] [project]

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Imagess
Alberto Crivellaro, Mahdi Rad, Yannick Verdie, Kwang Moo Yi, Pascal Fua, and Vincent Lepetit
In Proc. IEEE Int'l Conf. on Computer Vision (ICCV), 2015
[paper] [video] [project]