DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph
This addresses a security vulnerability for lock systems by enabling key replication from casual photos, though it is incremental as it builds on existing computer vision and 3D modeling techniques.
The paper tackles the problem of replicating physical keys from a single photograph by introducing DeepKey, an end-to-end deep neural architecture that automatically infers a printable 3D key model from an RGB image of a scene containing a pin tumbler key, with an example shown to open a real-world lock.
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.