A
Amir Akbarzadeh
Researcher at Microsoft
Publications - 20
Citations - 1979
Amir Akbarzadeh is an academic researcher from Microsoft. The author has contributed to research in topics: Facial recognition system & Global Positioning System. The author has an hindex of 15, co-authored 20 publications receiving 1898 citations. Previous affiliations of Amir Akbarzadeh include University of Kentucky & Katholieke Universiteit Leuven.
Papers
More filters
Journal ArticleDOI
Detailed Real-Time Urban 3D Reconstruction from Video
Marc Pollefeys,David Nister,Jan-Michael Frahm,Amir Akbarzadeh,Philippos Mordohai,Brian Clipp,Chris Engels,David Gallup,Seon Joo Kim,Paul Merrell,C. Salmi,Sudipta N. Sinha,B. Talton,Wang Liang,Qingxiong Yang,Henrik Stewenius,Ruigang Yang,Gregory F. Welch,Herman Towles +18 more
TL;DR: A system for automatic, geo-registered, real-time 3D reconstruction from video of urban scenes that extends existing algorithms to meet the robustness and variability necessary to operate out of the lab and shows results on real video sequences comprising hundreds of thousands of frames.
Proceedings ArticleDOI
Real-Time Visibility-Based Fusion of Depth Maps
Paul Merrell,Amir Akbarzadeh,Wang Liang,Philippos Mordohai,Jan-Michael Frahm,Ruigang Yang,David Nister,Marc Pollefeys +7 more
TL;DR: A viewpoint-based approach for the quick fusion of multiple stereo depth maps by selecting depth estimates for each pixel that minimize violations of visibility constraints and thus remove errors and inconsistencies from the depth maps to produce a consistent surface.
Proceedings ArticleDOI
Towards Urban 3D Reconstruction from Video
Amir Akbarzadeh,Jan-Michael Frahm,Philippos Mordohai,Brian Clipp,Chris Engels,David Gallup,Paul Merrell,M. Phelps,Sudipta N. Sinha,B. Talton,Wang Liang,Qingxiong Yang,Henrik Stewenius,Ruigang Yang,Gregory F. Welch,Herman Towles,David Nister,Marc Pollefeys +17 more
TL;DR: A data collection system and a processing pipeline for automatic geo-registered 3D reconstruction of urban scenes from video and design processing modules that can achieve fast performance on multiple CPUs and GPUs aiming at real-time performance in the near future are introduced.
Proceedings ArticleDOI
Near Real-time Stereo for Weakly-Textured Scenes
TL;DR: This work segments the image via a novel real-time color segmentation algorithm; it subsequently fit planes to textureless segments and refine them using consistency constraints to improve the quality of the stereo algorithm.
Proceedings ArticleDOI
A robust elastic and partial matching metric for face recognition
Gang Hua,Amir Akbarzadeh +1 more
TL;DR: This work enables both elastic and partial matching by computing a part based face representation and reveals that filtering the face image by a simple difference of Gaussian brings significant robustness to lighting variations and beats the more utilized self-quotient image.