{"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/synthetic-depth-of-field-with-a-single-camera","title":"Synthetic Depth-of-Field with a Single-Camera Mobile Phone","arxiv_id":"1806.04171","date":"2018-06-11","proceeding":null,"authors":["Neal Wadhwa","Rahul Garg","David E. Jacobs","Bryan E. Feldman","Nori Kanazawa","Robert Carroll","Yair Movshovitz-Attias","Jonathan T. Barron","Yael Pritch","Marc Levoy"],"abstract":"Shallow depth-of-field is commonly used by photographers to isolate a subject\nfrom a distracting background. However, standard cell phone cameras cannot\nproduce such images optically, as their short focal lengths and small apertures\ncapture nearly all-in-focus images. We present a system to computationally\nsynthesize shallow depth-of-field images with a single mobile camera and a\nsingle button press. If the image is of a person, we use a person segmentation\nnetwork to separate the person and their accessories from the background. If\navailable, we also use dense dual-pixel auto-focus hardware, effectively a\n2-sample light field with an approximately 1 millimeter baseline, to compute a\ndense depth map. These two signals are combined and used to render a defocused\nimage. Our system can process a 5.4 megapixel image in 4 seconds on a mobile\nphone, is fully automatic, and is robust enough to be used by non-experts. The\nmodular nature of our system allows it to degrade naturally in the absence of a\ndual-pixel sensor or a human subject.","url_abs":"http://arxiv.org/abs/1806.04171v1","url_pdf":"http://arxiv.org/pdf/1806.04171v1.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":"synthetic-depth-of-field-with-a-single-camera","repo_url":"https://github.com/google/portrait-shadow-manipulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1806.04171","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}