{"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/fast-and-accurate-single-image-super","title":"Fast and Accurate Single Image Super-Resolution via Information Distillation Network","arxiv_id":"1803.09454","date":"2018-03-26","proceeding":"CVPR 2018 6","authors":["Zheng Hui","Xiumei Wang","Xinbo Gao"],"abstract":"Recently, deep convolutional neural networks (CNNs) have been demonstrated\nremarkable progress on single image super-resolution. However, as the depth and\nwidth of the networks increase, CNN-based super-resolution methods have been\nfaced with the challenges of computational complexity and memory consumption in\npractice. In order to solve the above questions, we propose a deep but compact\nconvolutional network to directly reconstruct the high resolution image from\nthe original low resolution image. In general, the proposed model consists of\nthree parts, which are feature extraction block, stacked information\ndistillation blocks and reconstruction block respectively. By combining an\nenhancement unit with a compression unit into a distillation block, the local\nlong and short-path features can be effectively extracted. Specifically, the\nproposed enhancement unit mixes together two different types of features and\nthe compression unit distills more useful information for the sequential\nblocks. In addition, the proposed network has the advantage of fast execution\ndue to the comparatively few numbers of filters per layer and the use of group\nconvolution. Experimental results demonstrate that the proposed method is\nsuperior to the state-of-the-art methods, especially in terms of time\nperformance.","url_abs":"http://arxiv.org/abs/1803.09454v1","url_pdf":"http://arxiv.org/pdf/1803.09454v1.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":"fast-and-accurate-single-image-super","repo_url":"https://github.com/Zheng222/IDN-Caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"fast-and-accurate-single-image-super","repo_url":"https://github.com/jangsoopark/IDN-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"IDN","rank_in_archive_order":42,"of":71,"metrics":{"PSNR":"27.41","SSIM":"0.7297"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-ixi","task":"Image Super-Resolution","dataset":"IXI","model":"IDN","rank_in_archive_order":4,"of":9,"metrics":{"PSNR 2x T2w":"39.09","PSNR 4x T2w":"31.37","SSIM 4x T2w":"0.9312","SSIM for 2x T2w":"0.9846"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"IDN","rank_in_archive_order":76,"of":104,"metrics":{"PSNR":"28.25","SSIM":"0.773"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"IDN","rank_in_archive_order":54,"of":65,"metrics":{"PSNR":"25.41","SSIM":"0.7632"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.09454","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}