The paper introduces a fast Bayesian method for estimating homographies from noisy point correspondences, providing a posterior distribution over the homography parameters. A closed‑form solution for the posterior mean in homogeneous coordinates is derived, complemented by an iterative Bayesian approach to address non‑linearities. Experiments on synthetic data and real image stitching show improved accuracy over DLT and supply uncertainty estimates for the homography.
By Hanne Beuter, Sebastian Dorn
arXiv:2609.15524v1 Announce Type: new
Abstract: BraTS-GoAT evaluates tumor segmentation across heterogeneous populations. We trained a conventional 3D nnU-Net on 1,351 labeled cases using five-fold c...
By Tristan Kirscher (ICube, Institut Strauss), Vivian Metzger (Institut Strauss), Philippe Meyer (Institut Strauss, ICube), Xavier Coubez (Institut Strauss, ICube)
arXiv:2609.15228v1 Announce Type: new
Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrad...
By Kezheng Xiong, Shiyun Xu, Sheng Ao, Siqi Shen, Cheng Wang, Chenglu Wen
MedSAM-3 is a text‑promptable medical segmentation model that builds on the Segment Anything Model (SAM) by fine‑tuning it with medical images and semantic concept labels. It enables precise anatomical segmentation through open‑vocabulary text descriptions, moving beyond purely geometric prompts. The accompanying MedSAM-3 Agent incorporates multimodal large language models to perform complex reasoning and iterative refinement, and experiments across X‑ray, MRI, ultrasound, CT, and video modalities show it outperforms existing specialist and foundation models.
By Anglin Liu, Xu R. Cao, Yifan Shen, Yi Lu, Xiang Li, Qianqian Chen, Jintai Chen
arXiv:2609.14377v1 Announce Type: new
Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background...
By Haodong Yang, Zhongling Huang, Gong Cheng
arXiv:2609.14560v1 Announce Type: new
Abstract: General-purpose object detectors lose accuracy on UAV footage, where targets span only a handful of pixels and onboard compute is limited. Prior work c...
By Quratulain Nayeem, Fahmina Taranum, Mohammed Mudassir Uddin
arXiv:2609.14943v1 Announce Type: new
Abstract: Pseudo-labeling is a strong paradigm for semi-supervised medical image segmentation, yet its effectiveness is highly sensitive to confidence thresholdi...
By Hongyu Liu, Yinlong Wang, Lusha Li, Hui Meng
arXiv:2501.08815v2 Announce Type: replace
Abstract: UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model verti...
By Matej Suchanek, Miroslav Purkrabek, Jiri Matas
MedVA is an end‑to‑end neuro‑symbolic agentic system designed to streamline medical volume visualization. It combines a neuro‑symbolic intent formulation agent that refines natural‑language requests with symbolic reasoning, a multi‑model ROI identification agent that uses pretrained medical segmentation models to locate specified regions, and an objective‑driven visualization optimization agent that evaluates ROI visibility using a volume‑based objective. Extensive evaluations and a formative user study demonstrate the system’s effectiveness and high usability across users with varying expertise.
By Haill An, Suhyeon Kim, Minjun Kang, Eunwoo Lee, Bin Sheng, Lei Bi, Younhyun Jung
Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe perf...
Progress in inclusive household surveys has strengthened socioeconomic evidence for forcibly displaced populations, providing indispensable benchmarks on living conditions and welfare. However, these...
The paper presents an automated pipeline that uses unmanned aircraft systems (UAS) multispectral imagery and a Vision Transformer to detect wheat streak mosaic virus (WSMV) at the plant level. While the model achieved 89% accuracy on over 6,500 test patches using treatment-based labels, ELISA-based ground truth revealed significant label noise, indicating that the high accuracy was largely due to label bias rather than true disease detection. When evaluated against more reliable row‑level symptom severity and plant‑level ELISA labels, both deep learning and classical machine learning models showed limited generalization and weak separability between infected and mock‑inoculated plants, underscoring the importance of biologically grounded labels and realistic data conditions for UAS‑based disease detection.
By Dewi Endah Kharismawati, Sandeep Dhakal, Courtney E. McCusker, Jennifer R. Wilson, Erik W. Ohlson, Sami Khanal
The paper introduces SV-Cine, a cardiac MRI segmentation framework tailored for single ventricle physiology (SVP). It combines a generative data augmentation pipeline that creates synthetic 3D cardiac meshes and MRI, with a diagnosis-conditioned adaptation of the CineMA foundation model that uses patient-level diagnostic information to improve segmentation. Evaluations on an internal cohort show high Dice scores for left and right ventricles, outperforming nnU-Net, and demonstrate that incorporating diagnosis priors can adapt a pretrained model to specialized SVP tasks.
By Lila Cunge, Yuehong Liu, Hang Xu, Thomas Coudert, Pierangelo Renella, J Paul Finn, William Hsu, Kim-Lien Nguyen
arXiv:2609.12920v1 Announce Type: new
Abstract: We model total latency as the convolution of preprocessing, inference, and postprocessing distributions under a simplifying independence approximation,...
By Qingyang Zhang, Fumio Machida, Laura Carnevali
arXiv:2609.12825v1 Announce Type: new
Abstract: State Space Models (SSMs), particularly VMamba, have emerged as efficient alternatives for modeling long-range dependencies in medical image analysis....
By Mustafa Bora \c{C}elik, Hayriye Akta\c{s} Din\c{c}er, Ayse Keles
The paper introduces CELM, a data‑free framework for federated learning that estimates class‑wise contribution by maximizing logits. It constructs a cross‑client evidence matrix to quantify each client’s competence and coverage for each class, then uses this matrix to compute weighted aggregation that upweights clients offering strong evidence for underrepresented classes. The method maintains stability through simplex constraints and momentum smoothing, and it is compatible with standard FL pipelines, showing improved robustness to class imbalance and heterogeneity on vision benchmarks.
By Asim Ukaye, Nurbek Tastan, Mubarak Abdu-Aguye, Karthik Nandakumar
The paper introduces a physics-guided synthetic high‑frequency ultrasound (HFUS) generation framework for skin layer segmentation. It builds multilayer acoustic skin phantoms, assigns layer‑dependent acoustic properties, and uses k‑Wave simulation to produce paired synthetic HFUS images, dense layer masks, and metadata. When used to pretrain segmentation models and fine‑tuned on real HFUS data, the synthetic pretraining yields performance comparable to real‑only training and improves mean Dice/IoU in most architectures, indicating that the synthetic images carry transferable anatomical and textural cues.
By Junkyung ju, Kyungho Yoon, Minwoo Shin
arXiv:2609.13043v1 Announce Type: new
Abstract: Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Mode...
By Ziliang Hong, Hongyi Pan, Halil Ertugrul Aktas, Andrea Bejar, Elif Keles, Frank H. Miller, Michael B. Wallace, Rajesh N. Keswani, Gorkem Durak, Ulas Bagci
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
By Bo Ma, Jinsong Wu, Weiqi Yan
arXiv:2609.12898v1 Announce Type: new
Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized b...
By Xinqiang Yu, Zekun qi, Jiawei He, Wenyao Zhang, Xuchuan Chen, Guaocai Yao, Li Yi, Zhaoxiang Zhang, He Wang