view article
Figure 14
InstaMap models heterogeneity by bending space. Cryo-EM images yi (left) with annotated pose and imaging parameters (Ri, Ti, PSFi) are used for gradient-based learning. A vector field in a fixed frame is queried at the rotated, shifted and jittered grid to provide a per-image SE(3) equivariant output Fi. Space is bent via an additive perturbation on the corresponding rotated, shifted and jittered grid. The remaining pipeline is per Fig. 1[link].

Journal logoSTRUCTURAL
BIOLOGY
ISSN: 2059-7983
Volume 81| Part 4| April 2025| Pages 147-169
https://doi.org/10.1107/S2059798325002025
Follow Acta Cryst. D
Sign up for e-alerts
E-alerts
Follow Acta Cryst. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS