computer-vision-5

Wireframe Parsing

3260 papers • 126 benchmarks • 313 datasets

Detect Line Segments and their connecting Junctions in a single perspective image.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in wireframe-parsing-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find wireframe-parsing-5 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

End-to-End Wireframe Parsing

Yichao Zhou, Haozhi Qi, Y. Ma•Tue May 07 2019

This work presents a conceptually simple yet effective algorithm that significantly outperforms the previous state-of-the-art wireframe and line extraction algorithms and proposes a new metric for wireframe evaluation that penalizes overlapped line segments and incorrect line connectivities.

185

Content

0

Paper Graph

Holistically-Attracted Wireframe Parsing

Liangpei Zhang, Guisong Xia, Philip H. S. Torr, Tianfu Wu, Nan Xue, S. Bai, Fudong Wang•Mon Mar 02 2020

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, and is thus called Holistically-Attracted Wireframe Parser (HAWP).

111 0

Paper Graph

SOLD2: Self-supervised Occlusion-aware Line Description and Detection

M. Pollefeys, Martin R. Oswald, Viktor Larsson, Rémi Pautrat, Juan-Ting Lin•Tue Apr 06 2021

This work proposes the first joint detection and description of line segments in a single deep network, which is highly discriminative, while remaining robust to viewpoint changes and occlusions.

111 0

Paper Graph

Semantic Room Wireframe Detection from a Single View

David Gillsjö, Gabrielle Flood, Kalle Åström•Tue May 31 2022

It is shown qualitatively that the SRW-Net handles complex room geometries better than previous Room Layout Estimation algorithms while quantitatively out-performing the baseline in non-semantic Wireframe Detection.

6 0

Paper Graph

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

Philip H. S. Torr, Nan Xue, L. Zhang, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia•Sun Oct 23 2022

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.

39 0

Paper Graph

Detecting Line Segments in Motion-Blurred Images With Events

Guisong Xia, Hao Li, Wen Yang, Lei Yu, Huai Yu•Sun Nov 13 2022

This work designs a general frame-event feature fusion network to extract and fuse the detailed image textures and low-latency event edges and utilizes the state-of-the-art wireframe parsing networks to detect line segments on the fused feature map.

13 0

Paper Graph

Adding a benchmark result helps the community track progress.