A picture of Ameesh Ameesh Makadia
Research Scientist
Google Research
New York, NY
makadia@gmail.com



     

New

  • 3 papers accepted to CVPR 2021! Details coming soon.
  • 2 papers accepted to NeurIPS 2020! See the project details below.

About

Since the Fall of 2007 I have been a Research Scientist with Google in New York City. Prior to joining Google Research (aka Google AI), I completed my PhD in the GRASP Lab at UPENN.

My research interests lie at the intersection of Computer Vision and Machine Learning. For specifics please see my CV or research statement below.
CV (abridged) Research Statement


Publications

Select publications are listed below. See Scholar for the full list.


CVPR'21 De-rendering the World’s Revolutionary Artefacts
Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021


CVPR'21 Oral KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control
Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021


CVPR'21 Wide-Baseline Relative Camera Pose Estimation with Directional Learning
Kefan Chen, Noah Snavely, Ameesh Makadia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021


NeurIPS'20 An Analysis of SVD for Deep Rotation Estimation
Jake Levinson, Carlos Esteves, Kefan Chen, Noah Snavely, Angjoo Kanazawa, Afshin Rostamizadeh, Ameesh Makadia
Neural Information Processing Systems (NeurIPS), December 2020
Video Code PDF Bibtex


NeurIPS'20 Spin-Weighted Spherical CNNs
Carlos Esteves, Ameesh Makadia, Kostas Daniilidis
Neural Information Processing Systems (NeurIPS), December 2020
Video PDF Bibtex


arXiv Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
Andrew Liu*, Richard Tucker*, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa
arXiv, December 2020
Website Code PDF Bibtex


CVPR'20 Local Implicit Grid Representations for 3D Scenes
Chiyu "Max" Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang, Matthias Nießner, Tom Funkhouser
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2020
Website Code PDF Bibtex


arXiv Time Dependence in Non-Autonomous Neural ODEs
Jared Quincy Davis, Krzysztof Choromanski, Jake Varley, Honglak Lee, Jean-Jacques Slotine, Valerii Likhosterov, Adrian Weller, Ameesh Makadia, Vikas Sindhwani
arXiv, May 2020
PDF Bibtex


ICML'19 Cross-Domain 3D Equivariant Image Embeddings
Carlos Esteves, Avneesh Sud, Zhengyi Luo, Kostas Daniilidis, and Ameesh Makadia
International Conference on Machine Learning (ICML), June 2019
Code Poster PDF Bibtex


Google I/O Tensorflow Graphics: Computer Graphics Meets Deep Learning
Julien Valentin, Cem Keskin, Pavel Pidlypenskyi, Ameesh Makadia, Avneesh Sud, and Sofien Bouaziz
2019
Project (a core TF Library) Bibtex


ICML'19 Labeling Panoramas with Spherical Hourglass Networks
Carlos Esteves, Kostas Daniilidis, and Ameesh Makadia
360-degree Perception and Interaction Workshop at ECCV, September 2018
PDF Bibtex


ECCV'18 Oral and 12 best Learning SO(3) Equivariant Representations with Spherical CNNs
Carlos Esteves, Christine Allen-Blanchette, Ameesh Makadia, and Kostas Daniilidis
European Conference on Computer Vision (ECCV), September 2018
Selected as one of the best 12 papers by the Program Committee (0.4% - 776 accepted papers, 2.5K submissions)
Talk Code PDF "Best of ECCV" IJCV Special Issue Bibtex


CVPR'18 Deformable Shape Completion with Graph Convolutional Autoencoders
Or Litany, Alex Bronstein, Michael Bronstein, and Ameesh Makadia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
PDF Bibtex


RSS'17 Geometry of 3D Environments and Sum of Squares Polynomials
Amir Ali Ahmadi, Georgina Hall, Ameesh Makadia, and Vikas Sindhwani
Robotics: Science and Systems (RSS), July 2017
PDF Bibtex


3DV'14 Oral Learning 3D Part Detection from Sparsely Labeled Data
Ameesh Makadia and Mehmet Yumer
3DV, December 2014
PDF Bibtex


CVPR'14 Co-Segmentation of Textured 3D Shapes with Sparse Annotations
Mehmet Yumer, Won Chun, and Ameesh Makadia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014
PDF Supplemental Bibtex


ICML'13 Label Partitioning For Sublinear Ranking
Jason Weston, Ameesh Makadia, and Hector Yee
International Conference on Machine Learning (ICML), June 2013
PDF Bibtex


IJCV'10 Baselines for Image Annotation
Ameesh Makadia, Vladimir Pavlovic, and Sanjiv Kumar
International Journal of Computer Vision (IJCV), Volume 90, Issue 1, October 2010
Website and Data PDF Bibtex


ECCV'10 Feature Tracking for Wide-Baseline Image Retrieval
Ameesh Makadia
European Conference on Computer Vision (ECCV), September 2010
PDF Bibtex


IJVC'10 Spherical Correlation of Visual Representations for 3D Model Retrieval
Ameesh Makadia and Kostas Daniilidis
International Journal of Computer Vision (IJCV), Vol. 89, Issue 2, September 2010
PDF Bibtex


CVPR'09 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 (CVPR), May 2009
PDF Bibtex


ECCV'08 A New Baseline for Image Annotation
Ameesh Makadia, Vladimir Pavlovic, and Sanjiv Kumar
European Conference on Computer Vision (ECCV), October 2008
Website and Data PDF Bibtex


IJCV'07 Correspondence-free Structure from Motion
Ameesh Makadia and Christopher Geyer and Kostas Daniilidis
International Journal of Computer Vision (IJCV), Vol. 75, No. 3, December, 2007
PDF Bibtex


3DTV'07 Harmonic Silhouette Matching for 3D Models
Ameesh Makadia, Mirko Visontai, and Kostas Daniilidis
3DTV, May 2007
PDF Bibtex


Ph.D. Dissertation Best thesis award Robust correspondence-free algorithms for 3D motion recovery
Ameesh Makadia
Computer and Information Science, University of Pennsylvania, 2007
Morris and Dorothy Rubinoff Award for the best CIS PhD dissertation
Thesis Bibtex


CVPR'06 Oral Fully Automatic Registration of 3D Point Clouds
Ameesh Makadia, Alexander Patterson, and Kostas Daniilidis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, 2006
Oral presentation (acceptance ratio 6%)
PDF Bibtex


Book chapter Correspondenceless Visual Navigation under Constrained Motion
Ameesh Makadia
Kluwer Press, 2006
Chapter Bibtex


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


CVPR'05 Oral Radon-based Structure from Motion Without Correspondences
Ameesh Makadia, Christopher Geyer, Shankar Sastry, and Kostas Daniilidis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2005
Oral presentation (acceptance ratio 6%)
PDF Bibtex


WACV/MOTION'05 Planar Ego-Motion Without Correspondences
Ameesh Makadia, Dinkar Gupta, and Kostas Daniilidis
IEEE Workshops on Applications of Computer Vision (WACV/MOTION), Volume 1, January 2005
PDF Bibtex


ICPR'04 Rotation Estimation from Spherical Images
Ameesh Makadia, Lorenzo Sorgi, and Kostas Daniilidis
International Conference on Pattern Recognition (ICPR), August 2004
PDF Bibtex


CVPR'03 Oral 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 (CVPR), June 2003
Oral presentation (acceptance ratio 6%)
PDF Bibtex


Book chapter Omnidirectional Sensing for Robot Control
Kostas Daniilidis, Christopher Geyer, Volkan Isler, and Ameesh Makadia
Control Problems in Robotics, Springer-Verlag, 2002
Chapter Bibtex


OMNIVIS'02 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, June 2002
PDF Bibtex