Skip to content
AI News HubLIVE
Original source2 min read

SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation

Summary

SEMIR replaces the pixel lattice with a parameterized graph minor whose contraction map preserves thin-structure connectivity, enabling full-resolution inference without patching up to 21 MP and matching or exceeding domain-specific baselines on power lines, cracks, and aerial markings while reducing fragmentation by at least 4.6x. Accepted to ECCV 2026.

SourcearXiv Computer VisionAuthor: Luke James Miller, Yugyung Lee
SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.24935] SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation

[Submitted on 22 Jun 2026]

Title:SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation

View a PDF of the paper titled SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation, by Luke James Miller and Yugyung Lee

View PDF HTML (experimental)

Abstract:Thin-structure segmentation--power lines, cracks, lane markings at 1-3 pixel width--requires preserving connectivity that standard representations preclude: patching severs continuous structures and conventional superpixels merge thin targets into background before classification. Topology-aware losses penalize connectivity breaks at the objective level but cannot recover what the representation has already destroyed. We propose SEMIR, a framework that replaces the pixel lattice with a parameterized graph minor whose contraction map preserves thin-structure connectivity under the contraction criterion. The minor collapses millions of pixels into tens or hundreds of boundary-aligned supernodes, enabling full-resolution inference without patching at scales demonstrated up to 21 MP in this paper; a lightweight GNN classifies the reduced graph and an exact map lifts predictions to pixel resolution. One pipeline--identical architecture, features, loss, and GNN hyperparameters across all dataset--matches or exceeds domain-specific baselines on TTPLA (power lines), CrackSeg9k (pavement cracks), and SkyScapes Lane (aerial markings) on Dice, IoU, and Boundary F1 while reducing mask fragmentation by at least 4.6x relative to SLIC at matched inference.

Comments: Accepted to the European Conference on Computer Vision (ECCV) 2026

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.24935 [cs.CV]

(or arXiv:2606.24935v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.24935

arXiv-issued DOI via DataCite

Submission history

From: Luke Miller [view email] [v1] Mon, 22 Jun 2026 14:43:31 UTC (1,155 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation, by Luke James Miller and Yugyung Lee

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Uses a parameterized graph minor to preserve connectivity under contraction, avoiding the information loss inherent in patching and conventional superpixels.
  • Collapses millions of pixels into tens to hundreds of boundary-aligned supernodes, enabling full-resolution inference without patching at scales up to 21 MP.
  • A lightweight GNN classifies the reduced graph and an exact map lifts predictions to pixel resolution; one pipeline matches or exceeds domain-specific baselines on TTPLA, CrackSeg9k, and SkyScapes Lane.
  • Reduces mask fragmentation by at least 4.6x relative to SLIC at matched inference; accepted to ECCV 2026.

Highlights and analysis are generated automatically and may contain errors. Check the original source.