Z-UPSCALING: Optical Flow Guided Frame Interpolation for Isotropic Reconstruction of 3D EM Volumes

We propose a novel optical flow based approach to enhance the axial resolution of anisotropic 3D EM volumes to achieve isotropic 3D reconstruction. Assuming spatial continuity of 3D biological structures in well aligned EM volumes, we reasoned that optical flow estimation techniques, often applied for temporal resolution enhancement in videos, can be utilized. Pixel-level motion is estimated between neighboring 2D slices along z, using spatial gradient flow estimates to interpolate and generate new 2D slices resulting in isotropic voxels. We leverage recent state-of-the-art learning methods for video frame interpolation and transfer learning techniques, and demonstrate the success of our approach on publicly available ultrastructure EM volumes.

Authors

Institutions

Publication Details

Published
2025-04-14
DOI
https://doi.org/10.1109/isbi60581.2025.10980767
Citations
2
Primary Topic
Characterization and Applications of Magnetic Nanoparticles
Type
article
Field-Weighted Citation Impact
1.35
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Z-UPSCALING: Optical Flow Guided Frame Interpolation for Isotropic Reconstruction of 3D EM Volumes

Krishnan Venkataraman, Khaled Khairy, Jaison John, Ali Khalighifar et al.
2 citations
Characterization and Applications of Magnetic Nanoparticles
1.35
article

Z-UPSCALING: Optical Flow Guided Frame Interpolation for Isotropic Reconstruction of 3D EM Volumes

Krishnan Venkataraman, Khaled Khairy, Jaison John, Ali Khalighifar, Fisseha Admasu Ferede
article en
2 citations

Abstract

We propose a novel optical flow based approach to enhance the axial resolution of anisotropic 3D EM volumes to achieve isotropic 3D reconstruction. Assuming spatial continuity of 3D biological structures in well aligned EM volumes, we reasoned that optical flow estimation techniques, often applied for temporal resolution enhancement in videos, can be utilized. Pixel-level motion is estimated between neighboring 2D slices along z, using spatial gradient flow estimates to interpolate and generate new 2D slices resulting in isotropic voxels. We leverage recent state-of-the-art learning methods for video frame interpolation and transfer learning techniques, and demonstrate the success of our approach on publicly available ultrastructure EM volumes.

St. Jude Children's Research Hospital (US)
Openalex Percentile: Top 20%
Characterization and Applications of Magnetic Nanoparticles
1.35
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.