Papers › Holistically-Attracted Wireframe Parsing
Holistically-Attracted Wireframe Parsing
Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr
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 benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. For example, on the Wireframe dataset, compared to the previous state-of-the-art method L-CNN, it improves the challenging mean structural average precision (msAP) by a large margin (2.8% absolute improvements) and achieves 29.5 FPS on single GPU (89% relative improvement). A systematic ablation study is performed to further justify the proposed method.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Line Segment Detection | York Urban Dataset | HAWP | FH | 66.3 | #9 of 16 | Archive leaderboard | report |
| Line Segment Detection | York Urban Dataset | HAWP | sAP10 | 28.5 | #9 of 16 | Archive leaderboard | report |
| Line Segment Detection | York Urban Dataset | HAWP | sAP15 | 29.7 | #9 of 16 | Archive leaderboard | report |
| Line Segment Detection | York Urban Dataset | HAWP | sAP5 | 26.1 | #9 of 16 | Archive leaderboard | report |
| Line Segment Detection | wireframe dataset | HAWP | FH | 83.1 | #4 of 10 | Archive leaderboard | report |
| Line Segment Detection | wireframe dataset | HAWP | sAP10 | 66.5 | #4 of 10 | Archive leaderboard | report |
| Line Segment Detection | wireframe dataset | HAWP | sAP15 | 68.2 | #4 of 10 | Archive leaderboard | report |
| Line Segment Detection | wireframe dataset | HAWP | sAP5 | 62.5 | #4 of 10 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections