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.
By Stefano Cerri, Amirhossein Hassankhani, Ya\"el Balbastre, Koen Van Leemput
The paper presents a fully Bayesian framework for reconstructing closed curves from point‑cloud data, treating observed points as noisy perturbations of latent locations constrained to lie on an underlying curve. A non‑parametric prior regularizes the curve, and posterior inference is performed with Markov chain Monte Carlo samplers designed for point‑cloud characteristics. Experiments on synthetic and real LiDAR datasets demonstrate accurate reconstructions and quantified uncertainty over the recovered curves.
By Asir Intesar Tushar, Ioannis Sgouralis
arXiv:2609.13691v1 Announce Type: new
Abstract: Most existing visual odometry (VO) systems treat feature correspondences as deterministic measurements or assign uniform uncertainty, ignoring the inhe...
By Yuqing Wang, Xiaoji Niu, Yan Wang, Hailiang Tang, Jian Kuang, Tisheng Zhang
arXiv:2608. 07116v1 Announce Type: cross Abstract: Camera localization in bronchoscopy remains a challenging problem due to stringent accuracy requirements, real-time constraints, and limited training data.
By Lumin Chen, Qingyao Tian, Jinpeng Li, Haoyu Jiang, Huai Liao, Xinyan Huang, Hongbin Liu, Dong Yi
arXiv:2609.25375v1 Announce Type: cross
Abstract: Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated...
By Abolfazl Babanazari, Carson Cramer, Tyler Summers, Carlos Nieto, Kaveh Fathian
The paper introduces SAM‑H, a planar object tracker that estimates 8‑degree‑of‑freedom homographies directly from segmentation mask contours using a training‑free pipeline. When applied to masks from SAM 2, SAM‑H achieves a new state‑of‑the‑art performance on the PlanarTrack benchmark, improving the p@5 metric by 18.4 percentage points. The authors also demonstrate that combining segmentation‑based and correspondence‑based homography estimation yields WOFTSAM, which surpasses all previous methods on both PlanarTrack and POT‑210, and provide precise re‑annotations of PlanarTrack initial poses for more accurate benchmarking.
By Jonas Serych, Jiri Matas