整体吸引线框解析：从监督学习到自监督学习
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
AI总结：
本文提出HAWP方法，利用整体吸引场表示和端点解耦模块，实现从监督到自监督的线框解析，HAWPv3在无标签下展现高效训练与分布外图像解析潜力。
摘要：
本文介绍了整体吸引线框解析（HAWP），一种用于对包含由线段和交点形成的线框的二维图像进行几何分析的方法。HAWP利用一种简洁的整体吸引（HAT）场表示，该表示通过一个闭式四维几何向量场对线段进行编码。所提出的HAWP由三个顺序组件组成，这些组件通过端到端和HAT驱动的设计得以实现：（1）从HAT场生成密集线段集，并从热图生成端点提议；（2）将密集线段绑定到稀疏端点提议以生成初始线框；（3）通过一种新颖的端点解耦线感兴趣对齐（EPD LOIAlign）模块过滤假阳性提议，该模块捕获端点提议与HAT场之间的共现关系以实现更好的验证。得益于我们的新颖设计，HAWPv2在全监督学习中表现出强大的性能，而HAWPv3在自监督学习中表现出色，实现了优越的重复性分数和高效的训练（在单个GPU上仅需24 GPU小时）。此外，HAWPv3在无需提供线框真实标签的情况下，展示了在分布外图像中进行线框解析的巨大潜力。
英文摘要：
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions. HAWP utilizes a parsimonious Holistic Attraction (HAT) field representation that encodes line segments using a closed-form 4D geometric vector field. The proposed HAWP consists of three sequential components empowered by end-to-end and HAT-driven designs: (1) generating a dense set of line segments from HAT fields and endpoint proposals from heatmaps, (2) binding the dense line segments to sparse endpoint proposals to produce initial wireframes, and (3) filtering false positive proposals through a novel endpoint-decoupled line-of-interest aligning (EPD LOIAlign) module that captures the co-occurrence between endpoint proposals and HAT fields for better verification. Thanks to our novel designs, HAWPv2 shows strong performance in fully supervised learning, while HAWPv3 excels in self-supervised learning, achieving superior repeatability scores and efficient training (24 GPU hours on a single GPU). Furthermore, HAWPv3 exhibits a promising potential for wireframe parsing in out-of-distribution images without providing ground truth labels of wireframes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
