On the Issues of TrueDepth Sensor Data for Computer Vision Tasks Across Different iPad Generations

01/26/2022
by   Steffen Urban, et al.
0

In 2017 Apple introduced the TrueDepth sensor with the iPhone X release. Although its primary use case is biometric face recognition, the exploitation of accurate depth data for other computer vision tasks like segmentation, portrait image generation and metric 3D reconstruction seems natural and lead to the development of various applications. In this report, we investigate the reliability of TrueDepth data - accessed through two different APIs - on various devices including different iPhone and iPad generations and reveal two different and significant issues on all tested iPads.

READ FULL TEXT

page 7

page 8

page 11

research
01/09/2022

A Survey on Face Recognition Systems

Face Recognition has proven to be one of the most successful technology ...
research
02/16/2023

Tuning computer vision models with task rewards

Misalignment between model predictions and intended usage can be detrime...
research
06/08/2023

Does Image Anonymization Impact Computer Vision Training?

Image anonymization is widely adapted in practice to comply with privacy...
research
01/04/2017

Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection

Convolutional Neural Networks (CNNs) have become the state-of-the-art in...
research
08/25/2020

HoloLens 2 Research Mode as a Tool for Computer Vision Research

Mixed reality headsets, such as the Microsoft HoloLens 2, are powerful s...
research
03/26/2023

On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks

Learning-based methods to solve dense 3D vision problems typically train...
research
10/18/2022

Computational pathology in renal disease: a comprehensive perspective

Computational pathology is a field that has complemented various subspec...

Please sign up or login with your details

Forgot password? Click here to reset