{"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/depth-super-resolution-meets-uncalibrated","title":"Depth Super-Resolution Meets Uncalibrated Photometric Stereo","arxiv_id":"1708.00411","date":"2017-08-01","proceeding":null,"authors":["Songyou Peng","Bjoern Haefner","Yvain Quéau","Daniel Cremers"],"abstract":"A novel depth super-resolution approach for RGB-D sensors is presented. It\ndisambiguates depth super-resolution through high-resolution photometric clues\nand, symmetrically, it disambiguates uncalibrated photometric stereo through\nlow-resolution depth cues. To this end, an RGB-D sequence is acquired from the\nsame viewing angle, while illuminating the scene from various uncalibrated\ndirections. This sequence is handled by a variational framework which fits\nhigh-resolution shape and reflectance, as well as lighting, to both the\nlow-resolution depth measurements and the high-resolution RGB ones. The key\nnovelty consists in a new PDE-based photometric stereo regularizer which\nimplicitly ensures surface regularity. This allows to carry out depth\nsuper-resolution in a purely data-driven manner, without the need for any\nad-hoc prior or material calibration. Real-world experiments are carried out\nusing an out-of-the-box RGB-D sensor and a hand-held LED light source.","url_abs":"http://arxiv.org/abs/1708.00411v2","url_pdf":"http://arxiv.org/pdf/1708.00411v2.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":"depth-super-resolution-meets-uncalibrated","repo_url":"https://github.com/pengsongyou/SRmeetsPS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.00411","atlas_url":"https://app.syntology.ai/?focus=1708.00411","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}