SOURCE-LINKED INTELLIGENCE

Low-Rank Velocity Fields as a Structural Prior for Unsupervised 4D Medical Image Interpolation

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Endpoint-only unsupervised 4D medical image interpolation synthesizes intermediate volumes from sparsely sampled sequences with only the start and end volumes available for training; however, this weakly constrained setting often yields intermediates with unstable boundaries and non-physiological motion, limiting interpretability and downstream analysis. We propose low-rank velocity fields as a structural prior, constraining motion to a structured Tucker low-rank velocity field space that decomposes motion into globally shared spatial bases and a compact sample-specific core, thereby encouragi

Read original source ↗ Open in workspace

recordType

paper

region

Global