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

• URL: http://arxiv.org/abs/2608.24025v1
• Date: Tue, 25 Aug 2026 03:30:03 GMT
• Title: Low-Rank Velocity Fields as a Structural Prior for Unsupervised 4D Medical Image Interpolation
• Abstract summary: unsupervised 4D medical image synthesizes intermediate volumes from sparsely sampled sequences with only the start and end volumes available for training.<n>This weakly constrained setting often yields intermediates with unstable boundaries and non-physiological motion, limiting interpretability and downstream analysis.<n>We propose low-rank velocity fields as a structural prior, constraining motion to a structured Tucker low-rank velocity field space.
• Score: 18.528994588096076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 encouraging spatially correlated, anatomy-consistent deformation while suppressing voxel-wise high-frequency artifacts. To capture global coordination and local non-rigid details, we model motion in a coarse-to-fine multi-scale scheme and compose scale-wise deformations at inference to synthesize volumes at arbitrary times. We further provide a theoretical analysis showing that, under Tucker parameterization, low-rank parameters control the smoothness energy of the velocity field, explaining why low-rank modeling promotes smoother motion. Experiments on ACDC and 4D-Lung demonstrate state-of-the-art performance, remaining competitive with methods trained with intermediate-frame supervision, and producing intermediates with improved structural coherence and more stable anatomical contours.

Related papers

• Phase-Aligned Finite-Fourier Periodic Deformation for 4D Medical Image Interpolation [16.72607735100725]
  4D medical image aims to recover missing volumes from sparsely observed time points.<n>A key challenge is that this structure is not always encoded directly in state-of-the-art representations for ACDC.
  arXiv  Detail & Related papers  (2026-08-25T03:34:54Z)
• DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer [86.4618122245946]
  DyG$2$T is a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations.<n>Experiments on both synthetic and real-world datasets demonstrate that DyG$2$T achieves accurate dynamics modeling and reasoning.
  arXiv  Detail & Related papers  (2026-08-19T03:44:28Z)
• GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis [94.20462261657525]
  GrainGS is a dynamic framework that combines a hierarchical anchor scaffold with per-Gaussian deformation.<n>It achieves high reconstruction quality, real-time novel view synthesis, and compact storage.
  arXiv  Detail & Related papers  (2026-07-23T15:52:35Z)
• Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos [65.51845732149306]
  We introduce HTD-Refine, a post-processing framework that augments Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics.<n>At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video.
  arXiv  Detail & Related papers  (2026-05-26T11:38:36Z)
• AtomicMotion: Learning Human Motion From Different Human Parts [9.72019653340761]
  We present AtomicMotion, a framework designed to decouple and re-integrate body dynamics through three core innovations.<n>First, we introduce a logical body partitioning scheme that decomposes the skeleton into five distinct clusters based on functional intent.<n>Second, to robustly map sparse inputs to high-dimensional poses, we employ a masked full-body pre-conditioning strategy.<n>Third, addressing the limitations of vanilla spatial attention, we propose Kinematic Attention.
  arXiv  Detail & Related papers  (2026-05-21T15:39:38Z)
• HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation [0.0]
  HYPERPOSE is a novel 3D human pose estimation framework.<n>It performs Loren-temporal reasoning entirely within the hierarchical tree of the human skeleton.
  arXiv  Detail & Related papers  (2026-05-11T07:17:32Z)
• Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency [74.90075313101933]
  This paper revisits the same optical-flow primitive through a more local supervision design.<n>We use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop.<n>To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:53:31Z)
• Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics [51.85385061275941]
  Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics.<n>Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation.<n>We present STAR-MD, a scalable diffusion model that generates physically plausible protein trajectories over micro-scale timescales.
  arXiv  Detail & Related papers  (2026-02-02T14:13:28Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.