Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Jin, Zhang, Huiyao, Wen, Qi, Li, Ningyang, Li, Shengyang, Rahman, Atta ur, Tian, Xiaolin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914431710003200
author Bai, Jin
Zhang, Huiyao
Wen, Qi
Li, Ningyang
Li, Shengyang
Rahman, Atta ur
Tian, Xiaolin
author_facet Bai, Jin
Zhang, Huiyao
Wen, Qi
Li, Ningyang
Li, Shengyang
Rahman, Atta ur
Tian, Xiaolin
contents The segmentation of thin linear structures is inherently topology allowbreak-critical, where minor local errors can sever long-range connectivity. While recent State-Space Models (SSMs) offer efficient long-range modeling, their isotropic serialization (e.g., raster scanning) creates a geometry mismatch for anisotropic targets, causing state propagation across rather than along the structure trajectories. To address this, we propose FGOS-Net, a framework based on frequency allowbreak-geometric disentanglement. We first decompose features into a stable topology carrier and directional high-frequency bands, leveraging the latter to explicitly correct spatial misalignments induced by downsampling. Building on this calibrated topology, we introduce frequency-aligned scanning that elevates serialization to a geometry-conditioned decision, preserving direction-consistent traces. Coupled with an active probing strategy to selectively inject high-frequency details and suppress texture ambiguity, FGOS-Net consistently outperforms strong baselines across four challenging benchmarks. Notably, it achieves 91.3% mIoU and 97.1% clDice on DeepCrack while running at 80 FPS with only 7.87 GFLOPs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28503
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs
Bai, Jin
Zhang, Huiyao
Wen, Qi
Li, Ningyang
Li, Shengyang
Rahman, Atta ur
Tian, Xiaolin
Computer Vision and Pattern Recognition
The segmentation of thin linear structures is inherently topology allowbreak-critical, where minor local errors can sever long-range connectivity. While recent State-Space Models (SSMs) offer efficient long-range modeling, their isotropic serialization (e.g., raster scanning) creates a geometry mismatch for anisotropic targets, causing state propagation across rather than along the structure trajectories. To address this, we propose FGOS-Net, a framework based on frequency allowbreak-geometric disentanglement. We first decompose features into a stable topology carrier and directional high-frequency bands, leveraging the latter to explicitly correct spatial misalignments induced by downsampling. Building on this calibrated topology, we introduce frequency-aligned scanning that elevates serialization to a geometry-conditioned decision, preserving direction-consistent traces. Coupled with an active probing strategy to selectively inject high-frequency details and suppress texture ambiguity, FGOS-Net consistently outperforms strong baselines across four challenging benchmarks. Notably, it achieves 91.3% mIoU and 97.1% clDice on DeepCrack while running at 80 FPS with only 7.87 GFLOPs.
title Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.28503