End-to-End Wireframe Parsing

ICCV 2019  ·  Yichao Zhou, Haozhi Qi, Yi Ma ·

We present a conceptually simple yet effective algorithm to detect wireframes in a given image. Compared to the previous methods which first predict an intermediate heat map and then extract straight lines with heuristic algorithms, our method is end-to-end trainable and can directly output a vectorized wireframe that contains semantically meaningful and geometrically salient junctions and lines. To better understand the quality of the outputs, we propose a new metric for wireframe evaluation that penalizes overlapped line segments and incorrect line connectivities. We conduct extensive experiments and show that our method significantly outperforms the previous state-of-the-art wireframe and line extraction algorithms. We hope our simple approach can be served as a baseline for future wireframe parsing studies. Code has been made publicly available at https://github.com/zhou13/lcnn.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Line Segment Detection wireframe dataset L-CNN sAP5 58.9 # 5
sAP10 62.9 # 7
sAP15 64.7 # 5
Line Segment Detection York Urban Dataset L-CNN sAP5 24.3 # 7
sAP10 26.4 # 9


No methods listed for this paper. Add relevant methods here