{"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/image-restoration-using-convolutional-auto","title":"Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections","arxiv_id":"1606.08921","date":"2016-06-29","proceeding":null,"authors":["Xiao-Jiao Mao","Chunhua Shen","Yu-Bin Yang"],"abstract":"Image restoration, including image denoising, super resolution, inpainting,\nand so on, is a well-studied problem in computer vision and image processing,\nas well as a test bed for low-level image modeling algorithms. In this work, we\npropose a very deep fully convolutional auto-encoder network for image\nrestoration, which is a encoding-decoding framework with symmetric\nconvolutional-deconvolutional layers. In other words, the network is composed\nof multiple layers of convolution and de-convolution operators, learning\nend-to-end mappings from corrupted images to the original ones. The\nconvolutional layers capture the abstraction of image contents while\neliminating corruptions. Deconvolutional layers have the capability to upsample\nthe feature maps and recover the image details. To deal with the problem that\ndeeper networks tend to be more difficult to train, we propose to symmetrically\nlink convolutional and deconvolutional layers with skip-layer connections, with\nwhich the training converges much faster and attains better results.","url_abs":"http://arxiv.org/abs/1606.08921v3","url_pdf":"http://arxiv.org/pdf/1606.08921v3.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":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/AdneneBoumessouer/Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/AdneneBoumessouer/LEGO-Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/AdneneBoumessouer/MVTec-Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/Georg030/MRI-Image-Denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/MNaseerSubhani/MVTec-Anomaly-Detection-For-Industry","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/OlafChrist-github/Image-Denoising-using-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/Shakib-IO/Diminishing_Image_Noise_Using_Deep_Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/chintan1995/Image-Denoising-using-Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/jupiterman/Super-Resolution-Images","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/lee-aaron/Image-Super-Resolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/meitalB/NN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/miriskalt/AnomalyDetectionAutoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/nekitmm/starnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/nunof98/AiVision_Anomaly_Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/teakkkz/imageSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/titu1994/Image-Super-Resolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-restoration-using-convolutional-auto","repo_url":"https://github.com/ved27/RED-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"jpeg-artifact-correction","task_name":"JPEG Artifact Correction"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma10","task":"Grayscale Image Denoising","dataset":"BSD200 sigma10","model":"RED30","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"33.63","SSIM":"0.9319"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma30","task":"Grayscale Image Denoising","dataset":"BSD200 sigma30","model":"RED30","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"27.95","SSIM":"0.8019"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma50","task":"Grayscale Image Denoising","dataset":"BSD200 sigma50","model":"RED30","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"25.75","SSIM":"0.7167"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma70","task":"Grayscale Image Denoising","dataset":"BSD200 sigma70","model":"RED30","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"24.37","SSIM":"0.6551"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"RED30","rank_in_archive_order":25,"of":30,"metrics":{"PSNR":"31.99","SSIM":"0.8974"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-3x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 3x upscaling","model":"RED30","rank_in_archive_order":17,"of":21,"metrics":{"PSNR":"28.93","SSIM":"0.7994"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"RED30","rank_in_archive_order":44,"of":71,"metrics":{"PSNR":"27.4","SSIM":"0.729"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"RED30","rank_in_archive_order":33,"of":35,"metrics":{"PSNR":"32.94","SSIM":"0.9144"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 3x upscaling","model":"RED30","rank_in_archive_order":22,"of":24,"metrics":{"PSNR":"29.61","SSIM":"0.8341"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"RED30","rank_in_archive_order":84,"of":104,"metrics":{"PSNR":"27.86","SSIM":"0.7718"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"RED30","rank_in_archive_order":31,"of":41,"metrics":{"PSNR":"37.66","SSIM":"0.9599"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"RED30","rank_in_archive_order":28,"of":32,"metrics":{"PSNR":"33.82","SSIM":"0.923"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Grayscale)","model":"RED30","rank_in_archive_order":9,"of":12,"metrics":{"PSNR":"31.73"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10-1","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 10 Grayscale)","model":"RED30","rank_in_archive_order":10,"of":13,"metrics":{"PSNR":"29.35"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.08921","atlas_url":"https://app.syntology.ai/?focus=1606.08921","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}