Saved in:
Bibliographic Details
Main Authors: Wang, Chao, Li, Xuanying, Dai, Cheng, Feng, Jinglei, Luo, Yuxiang, Ouyang, Yuqi, Qin, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18252
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918305350025216
author Wang, Chao
Li, Xuanying
Dai, Cheng
Feng, Jinglei
Luo, Yuxiang
Ouyang, Yuqi
Qin, Hao
author_facet Wang, Chao
Li, Xuanying
Dai, Cheng
Feng, Jinglei
Luo, Yuxiang
Ouyang, Yuqi
Qin, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18252
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing
Wang, Chao
Li, Xuanying
Dai, Cheng
Feng, Jinglei
Luo, Yuxiang
Ouyang, Yuqi
Qin, Hao
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.18252