{"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/s-net-a-scalable-convolutional-neural-network","title":"S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction","arxiv_id":"1810.07960","date":"2018-10-18","proceeding":null,"authors":["Bolun Zheng","Rui Sun","Xiang Tian","Yaowu Chen"],"abstract":"Recent studies have used deep residual convolutional neural networks (CNNs)\nfor JPEG compression artifact reduction. This study proposes a scalable CNN\ncalled S-Net. Our approach effectively adjusts the network scale dynamically in\na multitask system for real-time operation with little performance loss. It\noffers a simple and direct technique to evaluate the performance gains obtained\nwith increasing network depth, and it is helpful for removing redundant network\nlayers to maximize the network efficiency. We implement our architecture using\nthe Keras framework with the TensorFlow backend on an NVIDIA K80 GPU server. We\ntrain our models on the DIV2K dataset and evaluate their performance on public\nbenchmark datasets. To validate the generality and universality of the proposed\nmethod, we created and utilized a new dataset, called WIN143, for\nover-processed images evaluation. Experimental results indicate that our\nproposed approach outperforms other CNN-based methods and achieves\nstate-of-the-art performance.","url_abs":"http://arxiv.org/abs/1810.07960v1","url_pdf":"http://arxiv.org/pdf/1810.07960v1.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":[],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"jpeg-artifact-correction","task_name":"JPEG Artifact Correction"},{"task_slug":"jpeg-compression-artifact-reduction","task_name":"Jpeg Compression Artifact Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 10 Color)","model":"S-Net","rank_in_archive_order":6,"of":9,"metrics":{"PSNR":"27.35","PSNR-B":"27.36","SSIM":"0.809"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Color)","model":"S-Net","rank_in_archive_order":5,"of":9,"metrics":{"PSNR":"29.81","PSNR-B":"29.79","SSIM":"0.878"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Grayscale)","model":"S-Net","rank_in_archive_order":7,"of":12,"metrics":{"PSNR":"31.83","PSNR-B":"31.76","SSIM":"0.8975"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10-1","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 10 Grayscale)","model":"S-Net","rank_in_archive_order":8,"of":13,"metrics":{"PSNR":"29.44","PSNR-B":"29.39","SSIM":"0.8325"},"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}