{"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/enhancing-underwater-imagery-using-generative","title":"Enhancing Underwater Imagery using Generative Adversarial Networks","arxiv_id":"1801.04011","date":"2018-01-11","proceeding":null,"authors":["Cameron Fabbri","Md Jahidul Islam","Junaed Sattar"],"abstract":"Autonomous underwater vehicles (AUVs) rely on a variety of sensors -\nacoustic, inertial and visual - for intelligent decision making. Due to its\nnon-intrusive, passive nature, and high information content, vision is an\nattractive sensing modality, particularly at shallower depths. However, factors\nsuch as light refraction and absorption, suspended particles in the water, and\ncolor distortion affect the quality of visual data, resulting in noisy and\ndistorted images. AUVs that rely on visual sensing thus face difficult\nchallenges, and consequently exhibit poor performance on vision-driven tasks.\nThis paper proposes a method to improve the quality of visual underwater scenes\nusing Generative Adversarial Networks (GANs), with the goal of improving input\nto vision-driven behaviors further down the autonomy pipeline. Furthermore, we\nshow how recently proposed methods are able to generate a dataset for the\npurpose of such underwater image restoration. For any visually-guided\nunderwater robots, this improvement can result in increased safety and\nreliability through robust visual perception. To that effect, we present\nquantitative and qualitative data which demonstrates that images corrected\nthrough the proposed approach generate more visually appealing images, and also\nprovide increased accuracy for a diver tracking algorithm.","url_abs":"http://arxiv.org/abs/1801.04011v1","url_pdf":"http://arxiv.org/pdf/1801.04011v1.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":"enhancing-underwater-imagery-using-generative","repo_url":"https://github.com/cameronfabbri/Underwater-Color-Correction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"enhancing-underwater-imagery-using-generative","repo_url":"https://github.com/IRVLab/UGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"underwater-image-restoration","task_name":"Underwater Image Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/underwater-image-restoration-on-lsui","task":"Underwater Image Restoration","dataset":"LSUI","model":"UGAN","rank_in_archive_order":4,"of":6,"metrics":{"PSNR":"19.79"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.04011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}