Bio I am a Perception Software Engineer @ Lyft, Level 5, Self-Driving Division.
Previously, I completed my postdoc in the Geometric Computation Group headed by Prof. Leonidas Guibas, at the Computer Science Department at Stanford University. Before that, I obtained my PhD at the Computer Science Department at the Technion, Israel, where I was advised by Prof. Ron Kimmel, and my MSc and BSc from the Electrical Engineering Department, also at the Technion.
My research interests are in geometry processing and computer vision, in particular: machine learning for 3D shape analysis, synthesis and completion; spectral methods for non-rigid 3D shape analysis; variational methods for image and shape analysis; medical image analysis. See the list of my publications below.
[Email] [Google scholar] [Github][LinkedIn]
News
Composite Shape Modeling via Latent Space Factorization
Anastasia Dubrovina, Fei Xia, Panos Achlioptas, Mira Shalah, Raphael Groscot
and Leonidas Guibas
ICCV, 2019
[ arxiv ] [ pdf ] [ suppl ] [ bibtex ]
Conference
Supervised fitting of geometric primitives to 3D point clouds
Lingxiao Li*, Minhyuk Sung*, Anastasia Dubrovina, Li Yi, and Leonidas Guibas (* equal contribution)
CVPR, 2019 (Oral)
[ arxiv | code ]
Conference
Learning fuzzy set representations of partial shapes on dual embedding spaces
Minhyuk Sung, Anastasia Dubrovina, Vladimir G. Kim, and Leonidas Guibas
Eurographics Symposium on Geometry Processing (SGP), 2018
[ project | pdf | presentation | code | bibtex ]
Conference
Spectral generalized multidimensional scaling
Yonathan Aflalo, Anastasia Dubrovina and Ron Kimmel
International Journal of Computer Vision (IJCV), 2016
[ pdf | bibtex | springer sharedit ]
Journal
Computational mammography using deep neural networks
Anastasia Dubrovina, Pavel Kisilev, Boris Ginsburg, Sharbel Hashoul and Ron Kimmel
Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2016
[ pdf | poster | bibtex ]
Journal
Non-rigid shape correspondence using surface descriptors and metric structures in the spectral domain
Anastasia Dubrovina, Yonathan Aflalo and Ron Kimmel
Dagstuhl seminar no. 14072: New Perspectives in Shape Analysis, 2016
[ pdf ]
Book chapter
Multi-region active contours with a single level set function
Anastasia Dubrovina, Guy Rosman and Ron Kimmel
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2015
[ pdf | bibtex ]
Journal
Multi-region active contours with a single level set function
Anastasia Dubrovina, Guy Rosman and Ron Kimmel
Women in Computer Vision (WiCV), CVPR workshop, 2015
[ Abstract | presentation | poster ]
Workshop
Computational mammography using deep neural networks
Anastasia Dubrovina, Pavel Kisilev, Boris Ginsburg, Sharbel Hashoul and Ron Kimmel
Deep Learning in Medical Image analisys (DLMIA), MICCAI workshop, 2015
[ pdf | poster ]
Workshop
Geometric algorithms for image and surface analysis
Anastasia Dubrovina
PhD dissertation, Technion, 2015
[ pdf | bibtex ]
PhD thesis
Image editing using level set trees
Anastasia Dubrovina, Rom Hershkovitz and Ron Kimmel
IEEE Int. Conf. on Image Processing (ICIP), 2014
[ pdf | presentation | poster | bibtex ]
Conference
Hierarchical framework for shape correspondence
Dan Raviv, Anastasia Dubrovina and Ron Kimmel
Numerical Mathematics: Theory, Methods and Applications (NM-TMA), 2013
[ pdf | bibtex ]
Journal
Patch collaborative spectral point cloud denoising
Guy Rosman, Anastasia Dubrovina and Ron Kimmel
Computer Graphics Forum (CGF), 2013
[ pdf | bibtex ]
Journal
Active contours for multi-region image segmentation with a single level set function
Anastasia Dubrovina, Guy Rosman and Ron Kimmel
Scale Space and Variational Methods in Computer Vision (SSVM), 2013
[ pdf | poster | bibtex ]
Conference
The Laplace-Beltrami operator: a ubiquitous tool for image and shape processing
Aaron Wetzler, Yonathan Aflalo, Anastasia Dubrovina and Ron Kimmel
Mathematical Morphology and Its Applications to Signal and Image Processing, 2013
[ pdf | bibtex ]
Conference
Non-rigid shape correspondence using pointwise surface descriptors and metric structures
Anastasia Dubrovina, Dan Raviv and Ron Kimmel
Dagstuhl seminar no. 11142, Innovations for Shape Analysis: Models and Algorithms, 2013
[ pdf | bibtex ]
Book chapter
Sparse modeling of shape from structured light
Guy Rosman, Anastasia Dubrovina and Ron Kimmel
Int. Conf. on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DPVT), 2012
[ pdf | bibtex ]
Conference
Efficient and robust image descriptor for GUI object classification
Anastasia Dubrovina, Pavel Kisilev, Daniel Freedman, Sagi Schein, and Ruth Bergman
Int. Conf. on Pattern Recognition (ICPR), 2012
[ pdf | poster | HP Labs technical report | bibtex ]
Conference
Approximately isometric shape correspondence by matching pointwise spectral features and global geodesic structures
Anastasia Dubrovina and Ron Kimmel
Advances in Adaptive Data Analysis (AADA), 2011
[ pdf | bibtex ]
Journal
Hierarchical matching of non-rigid shapes
Dan Raviv (equal contributor), Anastasia Dubrovina (equal contributor) and Ron Kimmel
Int. Conf. on Scale Space and Variational Methods in Computer Vision (SSVM), 2011
[ pdf> | presentation | bibtex ]
Conference
Matching shapes by eigendecomposition of the Laplace-Beltrami operator
Anastasia Dubrovina and Ron Kimmel
International Symposium on 3D Data Processing Visualization and Transmission (3DPVT), 2010
[ pdf | presentation | bibtex ]
Conference
SHREC 2010: robust correspondence benchmark
A. M. Bronstein, M. M. Bronstein, U. Castellani, A. Dubrovina, L. J. Guibas, R. P. Horaud, R. Kimmel, D. Knossow, E. von Lavante, D. Mateus, M. Ovsjanikov, and A. Sharma
Proc. EUROGRAPHICS Workshop on 3D Object Retrieval (3DOR), 2010
[ pdf | bibtex ]
Workshop
Non-rigid shape correspodence by matching spectral features and global geodesic structures
Anastasia Dubrovina
MSc dissertation, Technion, 2010
[ pdf | bibtex ]
MSc thesis
Computer Science Department, Stanford University
Computer Science Department, Technion
Electrical Engineering Department, Technion