Holistically-Attracted Wireframe Parsing
Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, and Liangpei Zhang, Philip H.S. Torr

TL;DR
This paper introduces HAWP, a fast, end-to-end wireframe parsing method that uses a novel geometric representation and attraction field maps to achieve state-of-the-art accuracy and efficiency in detecting wireframes from images.
Contribution
The paper proposes a new holistic wireframe parsing approach using a novel geometric dual representation and attraction field maps, improving accuracy and speed over previous methods.
Findings
Achieves state-of-the-art accuracy on Wireframe and YorkUrban datasets.
Improves msAP by 2.8% over previous methods.
Runs at 29.5 FPS on a single GPU.
Abstract
This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification. For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image. Junctions can be treated as the "basins" in the attraction field. The proposed method is thus called Holistically-Attracted Wireframe Parser (HAWP). In experiments, the proposed method is tested on two benchmarks, the Wireframe dataset, and the YorkUrban dataset. On both…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Holistically-Attracted Wireframe Parsing· youtube
Taxonomy
TopicsImage and Object Detection Techniques · Optical measurement and interference techniques · Advanced Neural Network Applications
