{"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/dslr-quality-photos-on-mobile-devices-with","title":"DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks","arxiv_id":"1704.02470","date":"2017-04-08","proceeding":"ICCV 2017 10","authors":["Andrey Ignatov","Nikolay Kobyshev","Radu Timofte","Kenneth Vanhoey","Luc van Gool"],"abstract":"Despite a rapid rise in the quality of built-in smartphone cameras, their\nphysical limitations - small sensor size, compact lenses and the lack of\nspecific hardware, - impede them to achieve the quality results of DSLR\ncameras. In this work we present an end-to-end deep learning approach that\nbridges this gap by translating ordinary photos into DSLR-quality images. We\npropose learning the translation function using a residual convolutional neural\nnetwork that improves both color rendition and image sharpness. Since the\nstandard mean squared loss is not well suited for measuring perceptual image\nquality, we introduce a composite perceptual error function that combines\ncontent, color and texture losses. The first two losses are defined\nanalytically, while the texture loss is learned in an adversarial fashion. We\nalso present DPED, a large-scale dataset that consists of real photos captured\nfrom three different phones and one high-end reflex camera. Our quantitative\nand qualitative assessments reveal that the enhanced image quality is\ncomparable to that of DSLR-taken photos, while the methodology is generalized\nto any type of digital camera.","url_abs":"http://arxiv.org/abs/1704.02470v2","url_pdf":"http://arxiv.org/pdf/1704.02470v2.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":"dslr-quality-photos-on-mobile-devices-with","repo_url":"https://github.com/aiff22/DPED","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dslr-quality-photos-on-mobile-devices-with","repo_url":"https://github.com/antegrbesa/cnn-image-color-enhancer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dslr-quality-photos-on-mobile-devices-with","repo_url":"https://github.com/antegrbesa/cnn-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"dped","name":"DPED","full_name":"DSLR Photo Enhancement Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.02470","atlas_url":"https://app.syntology.ai/?focus=1704.02470","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}