Content-aware frame interpolation (CAFI): Deep Learning-based temporal super-resolution for fast bioimaging

Gaboriau, David C. A.; Priessner, Martin; Sheridan, Arlo; Lenn, Tchern; Garzon-Coral, Carlos; Dunn, Alexander R.; M. Tousley, Aiden; Majzner, Robbie; R. Chubb, Jonathan; Manor, Uri; Vilar, Ramon; Laine, Romain
F.

doi:10.25418/crick.24631974.v1

- No file added yet -

Content-aware frame interpolation (CAFI): Deep Learning-based temporal super-resolution for fast bioimaging

poster

posted on 2023-11-29, 13:07 authored by David C. A. Gaboriau, Martin Priessner, Arlo SheridanArlo Sheridan, Tchern Lenn, Carlos Garzon-Coral, Alexander R. Dunn, Aiden M. Tousley, Robbie Majzner, Jonathan R. Chubb, Uri Manor, Ramon Vilar, Romain F. Laine

Poster presented as part of the Crick BioImage Analysis Symposium 2023.

Observing fast cellular dynamics is challenging because of phototoxicity and photobleaching. We implement two content-aware frame interpolation networks (CAFI): Zooming SlowMo (ZS) and Depth-Aware Video Frame Interpolation (DAIN). ZS and DAIN predict images between image pairs, in Time and Z dimensions, better than standard interpolation. We benchmark CAFI on 12 datasets from 4 microscopy modalities (point-scanning confocal, spinning-disk confocal, lattice light sheet and confocal brightfield microscopy. CAFI improves tracking of simulated and real objects, and segmentation of labelled nuclei. CAFI allows for reduced exposure: go faster and reduce phototoxicity or get more images for same exposure.

Permission has been given by authors to upload to Crick Figshare. Copyright remains with the original authors.