{"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/llnet-a-deep-autoencoder-approach-to-natural","title":"LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement","arxiv_id":"1511.03995","date":"2015-11-12","proceeding":null,"authors":["Kin Gwn Lore","Adedotun Akintayo","Soumik Sarkar"],"abstract":"In surveillance, monitoring and tactical reconnaissance, gathering the right\nvisual information from a dynamic environment and accurately processing such\ndata are essential ingredients to making informed decisions which determines\nthe success of an operation. Camera sensors are often cost-limited in ability\nto clearly capture objects without defects from images or videos taken in a\npoorly-lit environment. The goal in many applications is to enhance the\nbrightness, contrast and reduce noise content of such images in an on-board\nreal-time manner. We propose a deep autoencoder-based approach to identify\nsignal features from low-light images handcrafting and adaptively brighten\nimages without over-amplifying the lighter parts in images (i.e., without\nsaturation of image pixels) in high dynamic range. We show that a variant of\nthe recently proposed stacked-sparse denoising autoencoder can learn to\nadaptively enhance and denoise from synthetically darkened and noisy training\nexamples. The network can then be successfully applied to naturally low-light\nenvironment and/or hardware degraded images. Results show significant\ncredibility of deep learning based approaches both visually and by quantitative\ncomparison with various popular enhancing, state-of-the-art denoising and\nhybrid enhancing-denoising techniques.","url_abs":"http://arxiv.org/abs/1511.03995v3","url_pdf":"http://arxiv.org/pdf/1511.03995v3.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":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/2023-MindSpore-1/ms-code-18/tree/main/llnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/llnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/Mind23-2/MindCode-101/tree/main/llnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/llnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/code-implementation1/Code5/tree/main/llnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"llnet-a-deep-autoencoder-approach-to-natural","repo_url":"https://github.com/kglore/llnet_color","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.03995","atlas_url":"https://app.syntology.ai/?focus=1511.03995","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}