Holistically-Attracted Wireframe Parsing

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 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.