| %auto-ignore | |
| \section{Conclusion} | |
| In this paper, we propose a fully automated wire segmentation and removal system for high-resolution imagery. We demonstrate a segmentation method that maximally preserves sparse wire features and annotations, with a two-stage model that effectively uses global context and local details. The predicted segmentation mask is used in our tile-based wire inpainting model that has been demonstrated to produce seamless inpainting results. | |
| We also introduce \benchmark, the first benchmark wire dataset with high-quality annotations. We hope our proposed method will provide insights into tackling semantic segmentation with high resolution image and annotation properties, and that our benchmark dataset encourage further research in wire segmentation and removal. | |
| %\todo{ending} | |
| % Our wire segmentation and removal system method is a key component in automatic wire removal, and encourages research in recognizing associated wire entities such as its shadows and reflections. Our work will also motivate research in efficient inpainting algorithms with a focus on challenging appearances of wires. | |