Ameesh Makadia

Staff Research Scientist
Google NYC
lastname@gmail.com

I am currently a Computer Vision Research Scientist at Google NYC. My research interests lie at the intersection of Geometric 3D Vision, Harmonic Analysis, and Learning. Prior to joining Google Research I completed my PhD at the GRASP Lab at UPENN where I was advised by Kostas Daniilidis.

See Scholar for a full publication record. Selected publications are listed below.



Geometry of 3D Environments and Sum of Squares Polynomials
Amir Ali Ahmadi, Georgina Hall, Ameesh Makadia, and Vikas Sindhwani
arXiv preprint
November, 2016
Download: PDF

Learning 3D Part Detection from Sparsely Labeled Data
Ameesh Makadia and Mehmet Yumer.
3DV, Tokyo, December 2014.
Oral Presentation
Download: PDF

Co-Segmentation of Textured 3D Shapes with Sparse Annotations
Mehmet Yumer, Won Chun, and Ameesh Makadia.
IEEE Conference on Computer Vision and Pattern Recognition, Columbus, June 2014.
Download: PDF (Supplemental material)

Label Partitioning For Sublinear Ranking
Jason Weston, Ameesh Makadia, and Hector Yee.
International Conference on Machine Learning, Atlanta, June 2013.
Download: PDF

Feature Tracking for Wide-Baseline Image Retrieval
Ameesh Makadia.
European Conference on Computer Vision, Crete, September 2010.
Download: PDF

Baselines for Image Annotation
Ameesh Makadia, Vladimir Pavlovic, and Sanjiv Kumar.
International Journal of Computer Vision, Volume 90, Issue 1, October 2010.
Download: PDF
Website and Data

Spherical Correlation of Visual Representations for 3D Model Retrieval
Ameesh Makadia and Kostas Daniilidis.
International Journal of Computer Vision, Vol. 89, Issue 2, September 2010.
Download: PDF

Shape-based Object Recognition in Videos Using 3D Synthetic Object Models
Alexander Toshev, Ameesh Makadia, and Kostas Daniilidis.
IEEE Conference on Computer Vision and Pattern Recognition, Miami, May 2009.
Download: PDF

A New Baseline for Image Annotation
Ameesh Makadia, Vladimir Pavlovic, and Sanjiv Kumar.
European Conference on Computer Vision, Marseille, October 2008.
Download: PDF
Website and Data

Harmonic Silhouette Matching for 3D Models
Ameesh Makadia, Mirko Visontai, and Kostas Daniilidis.
3DTV, Kos, May 2007.
Download: PDF

Correspondence-free Structure from Motion
Ameesh Makadia and Christopher Geyer and Kostas Daniilidis.
International Journal of Computer Vision, Vol. 75, No. 3, December, 2007.
Download: PDF

Fully Automatic Registration of 3D Point Clouds
Ameesh Makadia, Alexander Patterson, and Kostas Daniilidis.
IEEE Conference on Computer Vision and Pattern Recognition, New York, June 2006.
Oral Presentation (Acceptance Ratio 6%)
Download: PDF

Correspondenceless Visual Navigation under Constrained Motion
Ameesh Makadia.
Imaging Beyond the Pinhole Camera
Editors: Kostas Daniilidis, Reinhard Klette, and Ales Leonardis
To appear in Kluwer Press, 2006.

Rotation Recovery from Spherical Images without Correspondences
Ameesh Makadia and Kostas Daniilidis.
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 7, July 2006.
Download: PDF

Radon-based Structure from Motion Without Correspondences
Ameesh Makadia, Christopher Geyer, Shankar Sastry, and Kostas Daniilidis.
IEEE Conference on Computer Vision and Pattern Recognition, San Diego, June 2005.
Oral Presentation (Acceptance Ratio 6%)
Download: PDF

Correspondenceless Ego-Motion Estimation using an IMU
Ameesh Makadia and Kostas Daniilidis.
IEEE International Conference on Robotics and Automation, Barcelona, April 2005.
Download: PDF

Planar Ego-Motion Without Correspondences
Ameesh Makadia, Dinkar Gupta, and Kostas Daniilidis.
IEEE Workshop on Motion and Video Computing, Breckenridge, January 2005.
Download: PDF

Rotation Estimation from Spherical Images
Ameesh Makadia, Lorenzo Sorgi, and Kostas Daniilidis.
International Conference on Pattern Recognition, Cambridge, August 2004.
Download: PDF

Direct 3D-Rotation Estimation from Spherical Images via a Generalized Shift Theorem
Ameesh Makadia and Kostas Daniilidis.
IEEE Conference on Computer Vision and Pattern Recognition, Madison, June 2003.
Oral Presentation (Acceptance Ratio 6%)
Download: PDF

Omnidirectional Sensing for Robot Control
Kostas Daniilidis, Christopher Geyer, Volkan Isler, and Ameesh Makadia.
Workshop on Control Problems in Robotics and Automation, STAR series: Springer Tracts in Advanced Robotics, Springer-Verlag, 2002.

Image Processing in Catadioptric Planes: Spatiotemporal Derivatives and Optical Flow Computation
Kostas Daniilidis, Ameesh Makadia, and Thomas Bülow.
Workshop on Omnidirectional Vision (in conjunction with ECCV 2002), Copenhagen, June 22, pages 3-12, 2002.
Download: PDF