WikiSysop: Created page with "== Citation == Cesa, G., Pratik, K. and Behboodi, A. 2023. Equivariant self-supervised deep pose estimation for Cryo EM. Topological, Algebraic and Geometric Learning Workshops 2023 (2023), 21–36. == Abstract == Reconstructing the 3D volume of a molecule from its differently oriented 2D projections is the central problem of Cryogenic Electron Microscopy (cryo-EM), one of the main techniques for macro-molecule imaging. Because the orientations are unknown, the estima..."

2025-09-25T05:56:29Z

Created page with "== Citation == Cesa, G., Pratik, K. and Behboodi, A. 2023. Equivariant self-supervised deep pose estimation for Cryo EM. Topological, Algebraic and Geometric Learning Workshops 2023 (2023), 21–36. == Abstract == Reconstructing the 3D volume of a molecule from its differently oriented 2D projections is the central problem of Cryogenic Electron Microscopy (cryo-EM), one of the main techniques for macro-molecule imaging. Because the orientations are unknown, the estima..."

New page

== Citation ==

Cesa, G., Pratik, K. and Behboodi, A. 2023. Equivariant self-supervised deep pose estimation for Cryo EM. Topological, Algebraic and Geometric Learning Workshops 2023 (2023), 21–36.

== Abstract ==

Reconstructing the 3D volume of a molecule
from its differently oriented 2D projections is
the central problem of Cryogenic Electron Microscopy
(cryo-EM), one of the main techniques
for macro-molecule imaging. Because the orientations
are unknown, the estimation of the images’
poses is essential to solve this inverse problem.
Typical methods either rely on synchronization,
which leverages the estimated relative poses of
the images to constrain their absolute ones, or
jointly estimate the poses and the 3D density of
the molecule in an iterative fashion. Unfortunately,
synchronization methods don’t account
for the complete images’ generative process and,
therefore, achieve lower noise robustness. In the
second case, the iterative joint optimization suffers
from convergence issues and a higher computational
cost, due to the 3D reconstruction steps.
In this work, we directly estimate individual poses
with an equivariant deep graph network trained
using a self-supervised loss, which enforces agreement
in Fourier domain of image pairs along the
common lines defined by their poses. In particular,
the equivariant design turns out essential for
the proper convergence. As a result, our method
can leverage the synchronization constraints - encoded
by the synchronization graph structure - to
improve convergence as well as the images generative
process - via the common lines loss -, with
no need to perform intermediate reconstructions.

== Keywords ==

== Links ==

https://proceedings.mlr.press/v221/cesa23a.html

== Related software ==

== Related methods ==

== Comments ==

2023Cesa Alignment - Revision history