Topology-Aware Skeleton Detection via Lighthouse-Guided Structured Inference

2026-04-21

AI Summary

This work addresses the challenge that skeleton detection in natural images is highly sensitive to minor variations in pose or motion, often resulting in fragmented structures and poor topological continuity. To overcome this limitation, the authors propose Lighthouse-Skel, a dual-branch collaborative network that jointly learns skeleton confidence fields and key structural anchors—specifically endpoints and junctions. Furthermore, they introduce a lighthouse-guided topological completion strategy that reconnects broken segments along low-cost paths to restore structural integrity. Evaluated on four public benchmarks, the method achieves competitive detection accuracy while significantly improving skeleton connectivity and overall structural completeness.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable changes in skeleton structure, increasing the difficulty of detecting the skeleton and often resulting in discontinuous skeletons. Existing methods primarily focus on point-level skeleton point detection and overlook the importance of structural continuity in recovering complete skeletons. To address this issue, we propose Lighthouse-Skel, a topology-aware skeleton detection method via lighthouse-guided structured inference. Specifically, we introduce a dual-branch collaborative detection framework that jointly learns skeleton confidence field and structural anchors, including endpoints and junction points. The spatial distributions learned by the point branch guide the network to focus on topologically vulnerable regions, which improves the accuracy of skeleton detection. Based on the learned skeleton confidence field, we further propose a lighthouse-guided topology completion strategy, which uses detected junction points and breakpoints as lighthouses to reconnect discontinuous skeleton segments along low-cost paths, thereby improving skeleton continuity and structural integrity. Experimental results on four public datasets demonstrate that the proposed method achieves competitive detection accuracy while substantially improving skeleton connectivity and structural integrity.

Problem

• skeleton detection
• structural continuity
• topology awareness
• discontinuous skeletons
• geometric shapes

Innovation

• topology-aware
• skeleton detection
• structured inference
• lighthouse-guided
• skeleton continuity