arXiv Computer Vision September 11, 2026 By Mohammadjavad Matinkia, Nilanjan Ray

Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration

Read the original on arXiv Computer Vision →

The paper introduces a new framework for learning continuous-time diffeomorphic image registration by modeling a non-autonomous ODE as a two-parameter flow map. By enforcing cocycle consistency, the method learns flow maps without time discretization or velocity integration during training, enabling efficient inference with few compositions. Experiments on nine datasets show consistent alignment improvements, including a 2.1% Dice gain on brain MRI, 12% TRE reduction on lung CT, and 2.6% Dice improvement on cardiac MRI and ultrasound.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jul 2

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

arXiv:2511. 10841v3 Announce Type: replace-cross Abstract: Modeling continuous-time dynamics from sparse and irregularly-sampled time series remains a fundamental challenge.

By YongKyung Oh, Dong-Young Lim, Sungil Kim

benchmarks safety

arXiv Machine Learning

Aug 11

Uncertainty in a Single Pass: A Closed-Form Identity for One-Step Flow Matching

arXiv:2605. 00941v5 Announce Type: replace Abstract: Flow matching provides a highly effective framework for generative modeling, yet estimating the uncertainty of its generated samples remains a fundamental challenge.

By Jiarui Xing, Song Wang, Jian Wang

diffusion benchmarks

arXiv Computer Vision

Aug 26

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

arXiv:2608.24025v1 Announce Type: new Abstract: Endpoint-only unsupervised 4D medical image interpolation synthesizes intermediate volumes from sparsely sampled sequences with only the start and end...

By Haojin Li, Hengzhuo Wang, Chang Liu, Zhiheng Ma, Heng Li, Jiang Liu

benchmarks safety

arXiv AI

Jul 7

Efficient Flow Matching for Sparse-View CT Reconstruction

arXiv:2603. 00205v2 Announce Type: replace-cross Abstract: Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems.

By Jiayang Shi, Lincen Yang, Zhong Li, Tristan van Leeuwen, Daniel M. Pelt, K. Joost Batenburg

diffusion

arXiv AI

Jun 18

Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

arXiv:2512. 09185v4 Announce Type: replace-cross Abstract: Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment.

By Hao Chen, Rui Yin, Yifan Chen, Qi Chen, Chao Li

diffusion benchmarks safety

Hugging Face Trending Papers

Jun 17

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data

We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical images. Existing approaches to spatio-temporal atlas construction rely on black-box generative models that lack flexibility, limit interpretability, and struggle to scale to high-dimensional data.

diffusion benchmarks safety

One email a morning, machine-written

Related stories

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

Uncertainty in a Single Pass: A Closed-Form Identity for One-Step Flow Matching

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

Efficient Flow Matching for Sparse-View CT Reconstruction

Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data