The authors apply test-time training with rotation prediction or 3D masked autoencoders to 4D medical image interpolation, claiming state-of-the-art results on Cardiac and 4D-Lung datasets, though the reported gains are marginal.
Transmorph: Transformer for unsupervised med- ical image registration,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Test Time Training for 4D Medical Image Interpolation
The authors apply test-time training with rotation prediction or 3D masked autoencoders to 4D medical image interpolation, claiming state-of-the-art results on Cardiac and 4D-Lung datasets, though the reported gains are marginal.