{"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/single-image-super-resolution-with-dilated","title":"Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module","arxiv_id":"1707.07128","date":"2017-07-22","proceeding":null,"authors":["Wuzhen Shi","Feng Jiang","Debin Zhao"],"abstract":"Traditional works have shown that patches in a natural image tend to\nredundantly recur many times inside the image, both within the same scale, as\nwell as across different scales. Make full use of these multi-scale information\ncan improve the image restoration performance. However, the current proposed\ndeep learning based restoration methods do not take the multi-scale information\ninto account. In this paper, we propose a dilated convolution based inception\nmodule to learn multi-scale information and design a deep network for single\nimage super-resolution. Different dilated convolution learns different scale\nfeature, then the inception module concatenates all these features to fuse\nmulti-scale information. In order to increase the reception field of our\nnetwork to catch more contextual information, we cascade multiple inception\nmodules to constitute a deep network to conduct single image super-resolution.\nWith the novel dilated convolution based inception module, the proposed\nend-to-end single image super-resolution network can take advantage of\nmulti-scale information to improve image super-resolution performance.\nExperimental results show that our proposed method outperforms many\nstate-of-the-art single image super-resolution methods.","url_abs":"http://arxiv.org/abs/1707.07128v1","url_pdf":"http://arxiv.org/pdf/1707.07128v1.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":"single-image-super-resolution-with-dilated","repo_url":"https://github.com/wzhshi/MSSRNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"single-image-super-resolution-with-dilated","repo_url":"https://github.com/danielenricocahall/Keras-UNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"MSSRNet","rank_in_archive_order":85,"of":104,"metrics":{"PSNR":"27.83","SSIM":"0.7631"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}