\begin{thebibliography}{10}\itemsep=-1pt \bibitem{Pixel6as49} Pixel 6, a smarter chip for a smarter phone - google store. \newblock \url{https://store.google.com/product/pixel_6?hl=en-US}. \newblock (Accessed on 11/14/2021). \bibitem{ttpla} Rabab Abdelfattah, Xiaofeng Wang, and Song Wang. \newblock Ttpla: An aerial-image dataset for detection and segmentation of transmission towers and power lines. \newblock In {\em Proceedings of the Asian Conference on Computer Vision}, 2020. \bibitem{barnes2009patchmatch} Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan~B Goldman. \newblock Patchmatch: A randomized correspondence algorithm for structural image editing. \newblock {\em ACM Trans. Graph.}, 28(3):24, 2009. \bibitem{deeplab} Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan~L Yuille. \newblock Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. \newblock {\em IEEE transactions on pattern analysis and machine intelligence}, 40(4):834--848, 2017. \bibitem{deeplabv3} Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. \newblock Rethinking atrous convolution for semantic image segmentation. \newblock {\em arXiv preprint arXiv:1706.05587}, 2017. \bibitem{deeplabv3p} Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. \newblock Encoder-decoder with atrous separable convolution for semantic image segmentation. \newblock In {\em Proceedings of the European conference on computer vision (ECCV)}, pages 801--818, 2018. \bibitem{glnet} Wuyang Chen, Ziyu Jiang, Zhangyang Wang, Kexin Cui, and Xiaoning Qian. \newblock Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 8924--8933, 2019. \bibitem{cascadepsp} Ho~Kei Cheng, Jihoon Chung, Yu-Wing Tai, and Chi-Keung Tang. \newblock Cascadepsp: toward class-agnostic and very high-resolution segmentation via global and local refinement. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 8890--8899, 2020. \bibitem{darabi2012image} Soheil Darabi, Eli Shechtman, Connelly Barnes, Dan~B Goldman, and Pradeep Sen. \newblock Image melding: Combining inconsistent images using patch-based synthesis. \newblock {\em ACM Transactions on graphics (TOG)}, 31(4):1--10, 2012. \bibitem{isdnet} Shaohua Guo, Liang Liu, Zhenye Gan, Yabiao Wang, Wuhao Zhang, Chengjie Wang, Guannan Jiang, Wei Zhang, Ran Yi, Lizhuang Ma, et~al. \newblock Isdnet: Integrating shallow and deep networks for efficient ultra-high resolution segmentation. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 4361--4370, 2022. \bibitem{hassani2022dilated} Ali Hassani and Humphrey Shi. \newblock Dilated neighborhood attention transformer. \newblock 2022. \bibitem{hassani2022neighborhood} Ali Hassani, Steven Walton, Jiachen Li, Shen Li, and Humphrey Shi. \newblock Neighborhood attention transformer. \newblock 2022. \bibitem{resnet} Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. \newblock Deep residual learning for image recognition. \newblock In {\em Proceedings of the IEEE conference on computer vision and pattern recognition}, pages 770--778, 2016. \bibitem{ccnet} Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, and Wenyu Liu. \newblock Ccnet: Criss-cross attention for semantic segmentation. \newblock In {\em Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages 603--612, 2019. \bibitem{magnet} Chuong Huynh, Anh~Tuan Tran, Khoa Luu, and Minh Hoai. \newblock Progressive semantic segmentation. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 16755--16764, 2021. \bibitem{globallocal} Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi Ishikawa. \newblock Globally and locally consistent image completion. \newblock {\em ACM Transactions on Graphics (ToG)}, 36(4):1--14, 2017. \bibitem{jain2022oneformer} Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, and Humphrey Shi. \newblock {OneFormer: One Transformer to Rule Universal Image Segmentation}. \newblock 2023. \bibitem{jain2021semask} Jitesh Jain, Anukriti Singh, Nikita Orlov, Zilong Huang, Jiachen Li, Steven Walton, and Humphrey Shi. \newblock Semask: Semantically masking transformer backbones for effective semantic segmentation. \newblock {\em arXiv}, 2021. \bibitem{jain2022keys} Jitesh Jain, Yuqian Zhou, Ning Yu, and Humphrey Shi. \newblock Keys to better image inpainting: Structure and texture go hand in hand. \newblock {\em arXiv preprint arXiv:2208.03382}, 2022. \bibitem{swiftlane} Oshada Jayasinghe, Damith Anhettigama, Sahan Hemachandra, Shenali Kariyawasam, Ranga Rodrigo, and Peshala Jayasekara. \newblock Swiftlane: Towards fast and efficient lane detection. \newblock {\em arXiv preprint arXiv:2110.11779}, 2021. \bibitem{karras2020analyzing} Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. \newblock Analyzing and improving the image quality of stylegan. \newblock In {\em Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages 8110--8119, 2020. \bibitem{kaspar2015self} Alexandre Kaspar, Boris Neubert, Dani Lischinski, Mark Pauly, and Johannes Kopf. \newblock Self tuning texture optimization. \newblock In {\em Computer Graphics Forum}, volume~34, pages 349--359. Wiley Online Library, 2015. \bibitem{cable_inst} Bo Li, Cheng Chen, Shiwen Dong, and Junfeng Qiao. \newblock Transmission line detection in aerial images: An instance segmentation approach based on multitask neural networks. \newblock {\em Signal Processing: Image Communication}, 96:116278, 2021. \bibitem{focal} Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Doll{\'a}r. \newblock Focal loss for dense object detection. \newblock In {\em Proceedings of the IEEE international conference on computer vision}, pages 2980--2988, 2017. \bibitem{partialconv} Guilin Liu, Fitsum~A Reda, Kevin~J Shih, Ting-Chun Wang, Andrew Tao, and Bryan Catanzaro. \newblock Image inpainting for irregular holes using partial convolutions. \newblock In {\em Proceedings of the European conference on computer vision (ECCV)}, pages 85--100, 2018. \bibitem{swin} Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. \newblock Swin transformer: Hierarchical vision transformer using shifted windows. \newblock {\em arXiv preprint arXiv:2103.14030}, 2021. \bibitem{adamw} Ilya Loshchilov and Frank Hutter. \newblock Decoupled weight decay regularization. \newblock {\em arXiv preprint arXiv:1711.05101}, 2017. \bibitem{lsnet} Van~Nhan Nguyen, Robert Jenssen, and Davide Roverso. \newblock Ls-net: Fast single-shot line-segment detector. \newblock {\em arXiv preprint arXiv:1912.09532}, 2019. \bibitem{contextencoder} Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, and Alexei~A Efros. \newblock Context encoders: Feature learning by inpainting. \newblock In {\em Proceedings of the IEEE conference on computer vision and pattern recognition}, pages 2536--2544, 2016. \bibitem{dalle} Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. \newblock Hierarchical text-conditional image generation with clip latents. \newblock {\em arXiv preprint arXiv:2204.06125}, 2022. \bibitem{dpt} Ren{\'e} Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. \newblock Vision transformers for dense prediction. \newblock In {\em Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages 12179--12188, 2021. \bibitem{rombach2022high} Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj{\"o}rn Ommer. \newblock High-resolution image synthesis with latent diffusion models. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 10684--10695, 2022. \bibitem{ohem} Abhinav Shrivastava, Abhinav Gupta, and Ross Girshick. \newblock Training region-based object detectors with online hard example mining. \newblock In {\em Proceedings of the IEEE conference on computer vision and pattern recognition}, pages 761--769, 2016. \bibitem{structurelane} Jinming Su, Chao Chen, Ke Zhang, Junfeng Luo, Xiaoming Wei, and Xiaolin Wei. \newblock Structure guided lane detection. \newblock {\em arXiv preprint arXiv:2105.05403}, 2021. \bibitem{suvorov2022resolution} Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, Anastasia Remizova, Arsenii Ashukha, Aleksei Silvestrov, Naejin Kong, Harshith Goka, Kiwoong Park, and Victor Lempitsky. \newblock Resolution-robust large mask inpainting with fourier convolutions. \newblock In {\em Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision}, pages 2149--2159, 2022. \bibitem{lanedet} Lucas Tabelini, Rodrigo Berriel, Thiago~M Paixao, Claudine Badue, Alberto~F De~Souza, and Thiago Oliveira-Santos. \newblock Keep your eyes on the lane: Real-time attention-guided lane detection. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 294--302, 2021. \bibitem{attention} Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan~N Gomez, {\L}ukasz Kaiser, and Illia Polosukhin. \newblock Attention is all you need. \newblock In {\em Advances in neural information processing systems}, pages 5998--6008, 2017. \bibitem{wexler2007space} Yonatan Wexler, Eli Shechtman, and Michal Irani. \newblock Space-time completion of video. \newblock {\em IEEE Transactions on pattern analysis and machine intelligence}, 29(3):463--476, 2007. \bibitem{segformer} Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose~M Alvarez, and Ping Luo. \newblock Segformer: Simple and efficient design for semantic segmentation with transformers. \newblock {\em arXiv preprint arXiv:2105.15203}, 2021. \bibitem{xu2022image} Xingqian Xu, Shant Navasardyan, Vahram Tadevosyan, Andranik Sargsyan, Yadong Mu, and Humphrey Shi. \newblock Image completion with heterogeneously filtered spectral hints. \newblock In {\em WACV}, 2023. \bibitem{powerlinedataset} {\"O}mer~Emre Yetgin, {\"O}mer~Nezih Gerek, and {\"O}mer Nezih. \newblock Power image dataset (infrared-ir and visible light-vl). \newblock {\em Mendeley Data}, 8, 2017. \bibitem{hifill} Zili Yi, Qiang Tang, Shekoofeh Azizi, Daesik Jang, and Zhan Xu. \newblock Contextual residual aggregation for ultra high-resolution image inpainting. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 7508--7517, 2020. \bibitem{contextual} Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas~S Huang. \newblock Generative image inpainting with contextual attention. \newblock In {\em Proceedings of the IEEE conference on computer vision and pattern recognition}, pages 5505--5514, 2018. \bibitem{yu2019free} Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas~S Huang. \newblock Free-form image inpainting with gated convolution. \newblock In {\em Proceedings of the IEEE/CVF international conference on computer vision}, pages 4471--4480, 2019. \bibitem{zeng2020high} Yu Zeng, Zhe Lin, Jimei Yang, Jianming Zhang, Eli Shechtman, and Huchuan Lu. \newblock High-resolution image inpainting with iterative confidence feedback and guided upsampling. \newblock In {\em European conference on computer vision}, pages 1--17. Springer, 2020. \bibitem{pldu} Heng Zhang, Wen Yang, Huai Yu, Haijian Zhang, and Gui-Song Xia. \newblock Detecting power lines in uav images with convolutional features and structured constraints. \newblock {\em Remote Sensing}, 11(11):1342, 2019. \bibitem{supercaf} Lingzhi Zhang, Connelly Barnes, Kevin Wampler, Sohrab Amirghodsi, Eli Shechtman, Zhe Lin, and Jianbo Shi. \newblock Inpainting at modern camera resolution by guided patchmatch with auto-curation. \newblock In {\em European Conference on Computer Vision}, pages 51--67. Springer, 2022. \bibitem{pspnet} Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. \newblock Pyramid scene parsing network. \newblock In {\em Proceedings of the IEEE conference on computer vision and pattern recognition}, pages 2881--2890, 2017. \bibitem{comodgan} Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric~I Chang, and Yan Xu. \newblock Large scale image completion via co-modulated generative adversarial networks. \newblock {\em arXiv preprint arXiv:2103.10428}, 2021. \bibitem{zheng2022cm} Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Eli Shechtman, Connelly Barnes, Jianming Zhang, Ning Xu, Sohrab Amirghodsi, and Jiebo Luo. \newblock Cm-gan: Image inpainting with cascaded modulation gan and object-aware training. \newblock {\em arXiv preprint arXiv:2203.11947}, 2022. \bibitem{setr} Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip~HS Torr, et~al. \newblock Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. \newblock In {\em Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages 6881--6890, 2021. \bibitem{zhou2017places} Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. \newblock Places: A 10 million image database for scene recognition. \newblock {\em IEEE Transactions on Pattern Analysis and Machine Intelligence}, 2017. \end{thebibliography}