Holistically-Attracted Wireframe Parsing

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. read more

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Line Segment Detection wireframe dataset HAWP F1 score 0.831 # 2
sAP5 62.5 # 4
sAP10 66.5 # 4
sAP15 68.2 # 2
Line Segment Detection York Urban Dataset HAWP F1 score 0.663 # 2
sAP5 26.1 # 4
sAP10 28.5 # 4
sAP15 29.7 # 3