ReliMorph is a novel 3D deformable registration framework that integrates correspondence reliability with spatial expert routing and residual velocity gating. By using local correlation distributions to assess match ambiguity, the method guides expert fusion and velocity updates during coarse‑to‑fine refinement, with inverse‑inconsistency feedback refining decisions at finer levels. Experiments show that ReliMorph consistently improves anatomical overlap over competing methods in both unimodal and multimodal registration tasks.
arXiv:2609.15669v1 Announce Type: cross Abstract: Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures o...
Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures often exhibit substantially different image intensit...
The paper introduces Recursive Uncertainty-Gated Image Registration (RUGI), an iterative refinement method that updates deformation fields predicted by learning-based registration models using a gating map. Two gating strategies are explored: an uncertainty-based approach and an image residual error approach, both concentrating updates on difficult regions. Experiments on cardiac MRI and echocardiography datasets show that RUGI consistently improves registration accuracy, with the error-gated variant reducing MSE by 27‑37% on pretrained models and lowering ejection fraction estimation errors.
Objective. Deformable image registration remains challenging because corresponding anatomy may exhibit different intensity relationships. Hand-crafted modality-robust descriptors such as Modality-Inde...
BINDER is a new probabilistic model for medical image registration that builds on mutual information and uses latent voxel‑wise correspondences to enable closed‑form iterative updates. The approach yields a demons‑like optimization algorithm that performs robustly on both monomodal and multimodal tasks, and a sampler that quantifies uncertainty in high‑dimensional 3D deformations. The authors provide the code on GitHub for public use.
arXiv:2610.34600v1 Announce Type: new Abstract: Objective. Deformable image registration remains challenging because corresponding anatomy may exhibit different intensity relationships. Hand-crafted...
arXiv:2609.24560v1 Announce Type: new Abstract: Confocal Laser Endomicroscopy (CLE) provides real-time, cellular-resolution optical biopsy but has a narrow field of view, which image mosaicing can ex...
arXiv:2410.14083v2 Announce Type: replace Abstract: This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The di...
arXiv:2608. 09182v1 Announce Type: cross Abstract: Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis.
The paper introduces M2CG, a one-pass deformable image registration network that replaces recursive refinement with multi-level, multi-space contextual guidance. M2CG performs progressive pyramid registration within a single iteration, leveraging cues from previous, current, and subsequent steps across image, image feature, segmentation, and segmentation feature spaces. It achieves state‑of‑the‑art results on eight public medical datasets in both unsupervised and semi‑supervised settings, challenging the prevailing reliance on recursive architectures.
DMM-Align introduces a closed‑loop framework for 2D‑3D registration that jointly refines correspondences, estimates pose, and learns representations using a shared differentiable geometric state. The method employs two diffusion processes: a geometry‑aware diffusion that improves the soft matching matrix for robust correspondence estimation, and a geometry‑conditioned diffusion teacher that feeds pose‑induced supervision back into feature learning. Experiments on 7‑Scenes and RGB‑D Scenes V2 show that DMM‑Align outperforms strong baselines, particularly in low‑overlap and heavily occluded scenarios, demonstrating the value of closed‑loop geometric feedback.
XCalib is an unsupervised dense registration framework that aligns thermal and visible video streams by optimizing virtual pinhole camera parameters and predicted monocular depth, thereby restricting spatial displacements to physically valid projection geometries. It introduces a novel registration paradigm using camera parameterization as an implicit regularizer, a robust Normalized Edges Correlation (NEC) metric for cross‑spectral alignment, and demonstrates superior temporal stability and alignment accuracy on public ADAS datasets compared to unconstrained dense flow baselines.