Skip to content

DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationPattern Recognition
Subtitle of host publication40th German Conference, GCPR 2018, Stuttgart, Germany, October 9-12, 2018, Proceedings
EditorsThomas Brox, Andrés Bruhn, Mario Fritz
Publisher or commissioning bodySpringer, Cham
Number of pages16
ISBN (Electronic)978-3-030-12939-2
ISBN (Print)978-3-030-12938-5
DateAccepted/In press - 27 Aug 2018
DateE-pub ahead of print (current) - 14 Feb 2019

Publication series

ISSN (Print)0302-9743


This paper describes DeepKey, an end-to-end deep neural architecture capable of taking a digital RGB image of an ‘everyday’ scene containing a pin tumbler key (e.g. lying on a table or carpet) and fully automatically inferring a printable 3D key model. We report on the key detection performance and describe how candidates can be transformed into physical prints. We show an example opening a real-world lock. Our system is described in detail, providing a breakdown of all components including key detection, pose normalisation, bitting segmentation and 3D model inference. We provide an in-depth evaluation and conclude by reflecting on limitations, applications, potential security risks and societal impact. We contribute the DeepKey Datasets of 5,300+ images covering a few test keys with bounding boxes, pose and unaligned mask data.



  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Springer Nature at Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 5 MB, PDF-document

    Embargo ends: 14/08/21

    Request copy


View research connections

Related faculties, schools or groups