arXiv cs.AI· Junho Moon, Ikbeom Jang·· 2 天前AI 评分18
TRACE：面向细长结构分割的拓扑感知预测自适应重连方法
TRACE: Topology-Aware Reconnection via Prediction-Adaptive Connectivity Enforcement for Thin-Structure Segmentation
AI 导读
TRACE 是一种拓扑感知、预测自适应的分割目标函数，利用目标骨架定义所需局部连接，并为每个连接在当前预测下寻找最易实现的有效重连，将其瓶颈与对应骨架点联合监督。该方法还引入拓扑感知骨架载体，同时保留前景与类别特定拓扑。在六个 2D 和 3D 基准上，TRACE 在保持较强分割精度的同时改善了连通性与拓扑，训练开销较低。
正文 · 原文
Abstract:Thin, elongated structures are particularly sensitive to connectivity errors, as even a few local segmentation mistakes can disrupt otherwise continuous paths. Existing skeleton-based objectives typically supervise fixed centerline locations and do not account for alternative local routes that may restore connectivity. We propose TRACE, a topology-aware, prediction-adaptive objective that uses a target skeleton to define required local connections. For each connection, TRACE identifies the easiest valid reconnection under the current prediction and jointly supervises its bottleneck with the corresponding skeleton point. The supervision thus adapts to the evolving prediction rather than remaining fixed to the centerline. We further introduce a topology-aware skeleton carrier that preserves both foreground and class-specific topology, enabling reliable definition of these connections. Extensive experiments across six 2D and 3D benchmarks show that TRACE improves connectivity and topology while maintaining strong segmentation accuracy with low training overhead. Code will be released upon acceptance.
| Comments: | Accepted to WACV 2027 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22210 [cs.CV] |
| (or arXiv:2610.22210v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22210 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junho Moon [view email]
[v1]
Thu, 15 Oct 2026 16:58:50 UTC (2,162 KB)
来源：arXiv cs.AI · arxiv.org