S
Stefano Soatto
Researcher at University of California, Los Angeles
Publications - 499
Citations - 27815
Stefano Soatto is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Motion estimation & Image segmentation. The author has an hindex of 78, co-authored 499 publications receiving 23597 citations. Previous affiliations of Stefano Soatto include University of California & University of California, Davis.
Papers
More filters
Proceedings ArticleDOI
Observability, identifiability and sensitivity of vision-aided inertial navigation
TL;DR: In this paper, the observability of 3D pose from the fusion of visual and inertial sensors is analyzed, and it is shown that the resulting model is not observable, and therefore existing analyses cannot be used to conclude that the set of states that are indistinguishable from the measurements is a singleton.
Proceedings ArticleDOI
3D shape from anisotropic diffusion
TL;DR: An algorithm that can estimate the shape of a scene by inferring the diffusion coefficient of a heat equation is proposed and is optimal, as it poses it as the minimization of a certain cost functional based on the input images, and fast.
Proceedings ArticleDOI
Observability/identifiability of rigid motion under perspective projection
TL;DR: In this paper, a rigid set of point-features in the Euclidean 3D space is represented as a point on the essential manifold and it is globally observable from perspective projections under some general position conditions.
Book ChapterDOI
Shape and Radiance Estimation from the Information-Divergence of Blurred Images
Paolo Favaro,Stefano Soatto +1 more
TL;DR: This work forms the problem of reconstructing the shape and radiance of a scene as the minimization of the information divergence between blurred images, and proposes an algorithm that is provably convergent and guarantees that the solution is admissible.
Proceedings ArticleDOI
Monte Carlo filtering on Lie groups
Alessandro Chiuso,Stefano Soatto +1 more
TL;DR: A nonlinear filter for estimating the trajectory of a random walk on a matrix Lie group with constant computational complexity is proposed, based on a finite-dimensional approximation of the conditional distribution of the state-given past measurements-via a set of fair samples which are updated at each step and proven to be consistent with the updated conditional distribution.