Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing

TL;DR

Co-PLNet introduces a collaborative framework for wireframe parsing that exchanges spatial cues between point and line detection tasks, improving accuracy, robustness, and efficiency in structured geometric perception.

Contribution

It proposes a novel point-line collaborative approach with a prompt encoder and cross-guidance decoder, enhancing point-line consistency and robustness over existing methods.

Findings

Improves accuracy and robustness on Wireframe and YorkUrban datasets.

Achieves real-time efficiency in structured geometry perception.

Demonstrates consistent performance gains over prior methods.

Abstract

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness. We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks, where early detections are converted into spatial prompts via a Point-Line Prompt Encoder (PLP-Encoder), which encodes geometric attributes into compact and spatially aligned maps. A Cross-Guidance Line Decoder (CGL-Decoder) then refines predictions with sparse attention conditioned on complementary prompts, enforcing point-line consistency and efficiency. Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency, demonstrating our effectiveness for structured geometry perception.