https://3demmethods.i2pc.es/index.php?action=history&feed=atom&title=2020Miolane_VAEGAN2020Miolane VAEGAN - Revision history2026-06-13T13:46:24ZRevision history for this page on the wikiMediaWiki 1.44.2https://3demmethods.i2pc.es/index.php?title=2020Miolane_VAEGAN&diff=3734&oldid=prevWikiSysop: Created page with "== Citation == Miolane, N.; Poitevin, F.; Li, Y.-T., Holmes, S. Estimation of orientation and camera parameters from cryo-electron microscopy images with variational autoenco..."2020-07-09T07:23:38Z<p>Created page with "== Citation == Miolane, N.; Poitevin, F.; Li, Y.-T., Holmes, S. Estimation of orientation and camera parameters from cryo-electron microscopy images with variational autoenco..."</p>
<p><b>New page</b></p><div>== Citation ==<br />
<br />
Miolane, N.; Poitevin, F.; Li, Y.-T., Holmes, S. Estimation of orientation and camera parameters from cryo-electron microscopy images with variational autoencoders and generative adversarial networks, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, 970-971 <br />
<br />
== Abstract ==<br />
<br />
Cryo-electron microscopy (cryo-EM) is capable of producing reconstructed 3D images of biomolecules at nearatomic resolution. However, raw cryo-EM images are only<br />
highly corrupted - noisy and band-pass filtered - 2D projections of the target 3D biomolecules. Reconstructing the 3D<br />
molecular shape requires the estimation of the orientation<br />
of the biomolecule that has produced the given 2D image,<br />
and the estimation of camera parameters to correct for intensity defects. Current techniques performing these tasks<br />
are often computationally expensive, while the dataset sizes<br />
keep growing. There is a need for next-generation algorithms that preserve accuracy while improving speed and<br />
scalability. In this paper, we combine variational autoencoders (VAEs) and generative adversarial networks (GANs)<br />
to learn a low-dimensional latent representation of cryoEM images. This analysis leads us to design an estimation<br />
method for orientation and camera parameters of singleparticle cryo-EM images, which opens the door to faster<br />
cryo-EM biomolecule reconstruction.<br />
<br />
== Keywords ==<br />
<br />
== Links ==<br />
<br />
https://openaccess.thecvf.com/content_CVPRW_2020/papers/w57/Miolane_Estimation_of_Orientation_and_Camera_Parameters_From_Cryo-Electron_Microscopy_Images_CVPRW_2020_paper.pdf<br />
<br />
== Related software ==<br />
<br />
== Related methods ==<br />
<br />
== Comments ==</div>WikiSysop