thumbnail

Photo Repair and 3D Structure from Flatbed Scanners Using 4- and 2-Source Photometric Stereo

Ruggero Pintus, Thomas Malzbender, Oliver Wang, Ruth Bergman, Hila Nachlieli, and Gitit Ruckenstein

2010

Abstract

We recently introduced a technique that allows 3D information to be captured from a conventional flatbed scanner. The technique requires no hardware modification and allows untrained users to easily capture 3D datasets. Once captured, these datasets can be used for interactive relighting and enhancement of surface detail on physical objects. We have also found that the method can be used to scan and repair damaged photographs. Since only the 3D structure on these photographs will typically be surface tears and creases, our method provides an accurate procedure for automatically detecting these flaws without any user intervention. Once detected, automatic techniques, such as infilling and texture synthesis, can be leveraged to seamlessly repair such damaged areas. We here provide a more thorough exposition and significant new material. We first present a method that is able to repair damaged photographs with minimal user interaction and then show how we can achieve similar results using a fully automatic process.

Reference and download information

Ruggero Pintus, Thomas Malzbender, Oliver Wang, Ruth Bergman, Hila Nachlieli, and Gitit Ruckenstein. Photo Repair and 3D Structure from Flatbed Scanners Using 4- and 2-Source Photometric Stereo. In AlpeshKumar Ranchordas, Joao Madeiras Pereira, Helder J. Araujo, and Joao Manuel R. S. Tavares, editors, Computer Vision, Imaging and Computer Graphics. Theory and Applications. Volume 68 of Communications in Computer and Information Science. Pages 326-342, Springer Berlin Heidelberg, 2010. https://doi.org/10.1007/978-3-642-11840-1_24.

Related multimedia productions

Bibtex citation record

@InCollection{Pintus:2010:PR3,
    author = {Ruggero Pintus and Thomas Malzbender and Oliver Wang and Ruth Bergman and Hila Nachlieli and Gitit Ruckenstein},
    affiliation = {CRS4 (Center for Advanced Studies, Research and Development in Sardinia), Parco Scientifico e Tecnologico, POLARIS, Edificio 1, 09010 Pula, CA Italy},
    editor = {AlpeshKumar Ranchordas and {Joao Madeiras} Pereira and {Helder J.} Araujo and {Joao Manuel R. S.} Tavares},
    title = {Photo Repair and 3D Structure from Flatbed Scanners Using 4- and 2-Source Photometric Stereo},
    booktitle = {Computer Vision, Imaging and Computer Graphics. Theory and Applications},
    series = {Communications in Computer and Information Science},
    volume = {68},
    pages = {326-342},
    publisher = {Springer Berlin Heidelberg},
    year = {2010},
    isbn = {978-3-642-11840-1},
    abstract = { We recently introduced a technique that allows 3D information to be captured from a conventional flatbed scanner. The technique requires no hardware modification and allows untrained users to easily capture 3D datasets. Once captured, these datasets can be used for interactive relighting and enhancement of surface detail on physical objects. We have also found that the method can be used to scan and repair damaged photographs. Since only the 3D structure on these photographs will typically be surface tears and creases, our method provides an accurate procedure for automatically detecting these flaws without any user intervention. Once detected, automatic techniques, such as infilling and texture synthesis, can be leveraged to seamlessly repair such damaged areas. We here provide a more thorough exposition and significant new material. We first present a method that is able to repair damaged photographs with minimal user interaction and then show how we can achieve similar results using a fully automatic process. },
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Pintus:2010:PR3'},
}