The paper introduces CoLeTra, a data augmentation technique designed to enhance topology accuracy in image segmentation of thin, tubular structures such as blood vessels. By artificially breaking these structures in training images while preserving the original labels, CoLeTra teaches models that continuous structures can appear disconnected, improving segmentation quality even when training labels are topologically inaccurate. Experiments across various architectures, loss functions, and datasets show that CoLeTra yields more topologically accurate segmentations and often boosts Dice and clDice scores, and the authors also release a dedicated dataset for topology-focused segmentation.
By Juan Miguel Valverde, Maja {\O}stergaard, Adrian Rodriguez-Palomo, Peter Alling Strange Vibe, Nina K{\o}lln Wittig, Henrik Birkedal, Anders Bjorholm Dahl
The paper presents a new approach to automatic skeleton generation that tackles two key challenges: encoding branch structures into token sequences and leveraging test-time computation. It introduces branch‑centric tokenization, a representation that groups structurally related elements together and directly encodes connectivity, producing more compact sequences than traditional BFS serialization. Additionally, the authors propose view‑augmented generation, a test‑time augmentation technique that rotates the input mesh, aligns predictions, and selects the best skeleton based on mesh coverage and consistency across views, leading to improved accuracy on benchmark datasets.
By Zhengyuan Li, Chuanyu Pan, Yuanming Hu, Raymond A. Yeh
arXiv:2610.09118v1 Announce Type: new
Abstract: Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity. Current methods model...
By Mihai Bogdan Deaconu, Laura Dio\c{s}an
The paper introduces Skeleton‑Guided Progressive Test‑Time Adaptation (SGP‑TTA) for accurately segmenting thin curvilinear structures such as vessels and roads. It combines Progressive Batch Normalization (ProgBN) to gradually shift normalization statistics toward target data, and Consensus Skeleton Recall (CSR) to enforce structural connectivity by updating only BN affine parameters. Experiments demonstrate that SGP‑TTA outperforms existing test‑time adaptation methods, especially under cross‑modality domain shifts.
By Boa Jang, JunGyu Lee, Gwanho Lee, Jinwook Choi, Young-Gon Kim
The paper introduces TopoEnhance, a framework that improves the reliability of scene topology graphs for autonomous driving by treating topology enhancement as a denoising reconstruction task. It learns to recover structural consistency from corrupted ground‑truth graphs, thereby correcting logical inconsistencies and unreliable connections. Experiments show consistent gains in both continuous topology metrics (TOP score) and discrete connectivity (Topology Jaccard Similarity) across multiple baselines without retraining.
By Xiaoqi Wang, Dingyi Zhaung, David Paz, Wenbin He, Yucai Bai, Peng Zhou, Rui Zhang, Jinhua Zhao, Liu Ren
OcTreeMamba introduces a hierarchical framework that integrates Octree structures into a Mamba-based segmentation model for 3D medical images. It uses a Structure Learner to sparsify anatomy-adaptive regions via hierarchical gating and Gumbel-Softmax sampling, then builds a Dynamic Octree to preserve topological connectivity. A bidirectional Tree-SSM propagates contextual features along leaf–parent–root and root–parent–leaf paths, achieving competitive performance on four benchmark datasets, especially for vascular structures.
By Kaixiang Mai, Jiaqi Yu, Yuzhu Ji, Yiqun Zhang, Zhijie Wang, Haijun Zhang, Yiu-ming Cheung
arXiv:2608. 06031v1 Announce Type: new Abstract: Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts.
By Quanxin Wang, Xuanting Xie, Bingheng Li, Xingtong Yu, Shuo Wang, Ruiyi Fang, Zhao Kang
arXiv:2609.37139v1 Announce Type: new
Abstract: 3D content generation technology has significantly advanced the work of designers, as well as the 3D printing and gaming industries. However, it remain...
By Xianze Fang, Qiyuan Feng, Dongfang Sun, Yan Zhang, Xiuchao Wu, Jingnan Gao, Jiangjing Lyu, Chengfei Lyu, Gang Yu
The paper presents a three‑stage pipeline for colon segmentation in 3D abdominal CT scans that preserves anatomical continuity. First, a deep‑learning model generates an initial segmentation; second, centreline bridging reconnects disjoint regions; third, a reconstruction stage refines the continuity. Experiments on the TotalSegmentator and RAOS datasets show that the method improves topological consistency while keeping segmentation accuracy high.
By Deshan Kalupahana, Sonit Singh, Praveen Ravindran, Arcot Sowmya
arXiv:2607. 12811v1 Announce Type: cross Abstract: Although topological mapping and navigation have been studied extensively, the specific role and downstream effect of loop closures in purely topological representations has received relatively little attention.
By Sarthak Chittawar, Vansh Garg, Aditya Vadali, Krish Pandya, Rohit Jayanti, Sourav Garg, Madhava Krishna
arXiv:2609.26189v1 Announce Type: new
Abstract: Retinal vessel segmentation in multi-domain deployment requires a source model to adapt to domains that differ in imaging conditions and annotation con...
By Yongsong Huang, Tomo Miyazaki, Kai Xu, Xiaofeng Liu, Yaohou Fan, Shinichiro Omachi
The paper introduces a real‑world CAD segmentation benchmark focused on fastener‑relevant hole detection, a task that demands human annotation and presents higher geometric complexity than typical synthetic datasets. It presents two rule‑based methods—a graph‑wire‑search and a multi‑view approach—and trains learning‑based models (UV‑Net and AAGNet) on a newly annotated engineering CAD dataset. Extensive experiments evaluate parameter tuning, cross‑domain generalisation, and performance across dataset sizes and IoU thresholds, revealing that rule‑based methods generalise without training data while learning‑based methods excel with sufficient annotations but are less robust to domain shift.
"whyItMatters":"The study provides a realistic benchmark and actionable insights into the trade‑offs between data requirements and robustness for CAD segmentation, informing future research and practical applications in engineering tasks."
By Kai Sch\"utte, Edgar Heinert, Matthias Rottmann