{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gated-fusion-network-for-joint-image","title":"Gated Fusion Network for Joint Image Deblurring and Super-Resolution","arxiv_id":"1807.10806","date":"2018-07-27","proceeding":null,"authors":["Xinyi Zhang","Hang Dong","Zhe Hu","Wei-Sheng Lai","Fei Wang","Ming-Hsuan Yang"],"abstract":"Single-image super-resolution is a fundamental task for vision applications\nto enhance the image quality with respect to spatial resolution. If the input\nimage contains degraded pixels, the artifacts caused by the degradation could\nbe amplified by super-resolution methods. Image blur is a common degradation\nsource. Images captured by moving or still cameras are inevitably affected by\nmotion blur due to relative movements between sensors and objects. In this\nwork, we focus on the super-resolution task with the presence of motion blur.\nWe propose a deep gated fusion convolution neural network to generate a clear\nhigh-resolution frame from a single natural image with severe blur. By\ndecomposing the feature extraction step into two task-independent streams, the\ndual-branch design can facilitate the training process by avoiding learning the\nmixed degradation all-in-one and thus enhance the final high-resolution\nprediction results. Extensive experiments demonstrate that our method generates\nsharper super-resolved images from low-resolution inputs with high\ncomputational efficiency.","url_abs":"http://arxiv.org/abs/1807.10806v1","url_pdf":"http://arxiv.org/pdf/1807.10806v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gated-fusion-network-for-joint-image","repo_url":"https://github.com/jacquelinelala/GFN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"gated-fusion-network-for-joint-image","repo_url":"https://github.com/xiangyu-liu/DBSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.10806","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}