A
Anat Levin
Researcher at Technion – Israel Institute of Technology
Publications - 107
Citations - 14409
Anat Levin is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Speckle pattern & Scattering. The author has an hindex of 42, co-authored 91 publications receiving 12993 citations. Previous affiliations of Anat Levin include Stanford University & Hebrew University of Jerusalem.
Papers
More filters
Understanding camera trade-offs through a Bayesian analysis of light field projections - A revision
TL;DR: In this paper, a unified framework for analyzing computational imaging approaches is introduced, where each sensor element is modeled as an inner product over the 4D light field, and the imaging task is posed as Bayesian inference: given the observed noisy light field projections and a new prior on light field signals, estimate the original light field.
Proceedings ArticleDOI
Visual odometry and map correlation
Anat Levin,Richard Szeliski +1 more
TL;DR: This paper studies how estimates of ego-motion based on feature tracking (visual odometry) can be improved using a rough map of where the observer has been using a graphical model whose MAP estimate is inferred using loopy belief propagation.
Book ChapterDOI
An Evaluation of Computational Imaging Techniques for Heterogeneous Inverse Scattering
TL;DR: This work takes first steps in tackling the problem of heterogeneous inverse scattering from simulated measurements of different computational imaging configurations, by deriving theoretical results, developing an algorithmic framework, and performing quantitative evaluations.
Taxonomy of Large Margin Principle Algorithms for Ordinal Regression Problems
Amnon Shashua,Anat Levin +1 more
TL;DR: Experiments performed on visual classification and “collaborative filtering” show that both approaches outperform existing ordinal regression algorithms applied for ranking and multi-class SVM applied to general multi- class classification.
Proceedings ArticleDOI
Manifold pursuit: a new approach to appearance based recognition
TL;DR: A simple and effective technique for obtaining invariance to image-plane transformations within a linear dimensionality reduction approach is demonstrated.