cs.CVNov 10, 2026

TMAL: Topology-preserving Multi-offset Affinity Learning for Curvilinear Structure Segmentation

Authors: Suho Han, Soungsill Park, Kanghyun Ryu, Yoseob Han

Organizations: Soongsil University, Republic of Korea · Korea Institute of Science and Technology, Republic of Korea

Abstract

Curvilinear structures such as retinal vessels and surface cracks need both pixel-level accuracy and structural continuity. Pixel-wise supervision does not model the connections between pixels, and topology-based losses still produce ordinary masks. Connectivity-based methods predict these connections directly, but they use binary connectivity targets over a fixed local range. Such labels give the same value to thin segments and to thick regions, and they cannot describe connections at larger offsets. To address these limitations, we propose Topology-preserving Multi-offset Affinity Learning (TMAL). TMAL uses soft affinities that emphasize thin regions near the boundary, and it predicts directional affinities at several offsets to reach further. It then combines these affinities with weights that come from the decoder features, so local continuity and wider context are used together. An auxiliary segmentation branch adds region-level supervision and keeps the overlap accuracy high. On the retinal vessel dataset DRIVE and the crack inspection dataset DeepCrack, TMAL reaches the highest Dice, IoU, and clDice scores, and it greatly reduces the connected-component error Δβ0Δβ_0. Code is available at https://github.com/suho-han/TMAL.

Figures & tables

Explore similar work

CardsList
  1. Widest-Path Reachability Fields for Connectivity-Preserving Slender Structure Segmentation

    Jul 8, 2026Youcheng Zong, Runda Jia, Minxuan Hu +2Image SegmentationTopology-Preserving Image Segmentation

  2. Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentation

    Mar 7, 2025Juan Miguel Valverde, Maja Østergaard, Adrian Rodriguez-Palomo +4Topology-Preserving Image SegmentationThin-Structure Segmentation

  3. Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentation

    Aug 10, 2026Yongsong Huang, Tomo Miyazaki, Kai Xu +3Retinal Vessel SegmentationDomain Adaptation