year:
2019/2020
with:
CIRG
tools:
AR Core
TensorFlow.js
Processing
Runway
for:
Space10

Private Collection

Together with Space10 we investigated the treatment of sensitive personal information in AR applications, designing and building a feature which allows users to mask this information by choosing different levels of abstraction.

Within this context our goal was to design and built a feature which allows users to anonymize this information, visually and technically. This feature was only one part of a broader research and design project, aiming at creating a trustful relationship between users and companies, across digital products.

Picture showing side by side comparison of girl in a living room, being clearly visible on the left and blurred on the right.

Using common computer vision techniques allows users to select and adjust the abstraction of books, documents, faces, people, windows and doors, before any data leaves their phones. This process is deliberately integrated into the main interface, elevating privacy controls from sub-menus to being an accessible main interaction. The aesthetical integration alongside a short feedback loops are key to making these controls as frictionless as possible.

Picture showing a bedroom window with a blurred view, through an app interface with adjustment slider.

Besides working on the technical implementation, my main focus was on designing the visual language which:

Picture showing a sitting woman looking at a blurred representation of herself on an iPad, filmed fromt the other side of the room.

Especially in AR people rarely think of themselves in the picture, yet they always are. To get a better understanding of how people would ultimately accept such a feature, I prototyped a system that allowed people to see their abstracted selves and react to it. This process ultimately shaped the final visual treatment.

Picture showing a sitting woman looking at a blurred representation of herself on an iPad, filmed fromt the other side of the room.
Testing abstracion filters in self-perception prototype environment

Private Collection shows that treating people's data with respect does not exclude the use of intelligent AR applications in the home. By outlining the appropriate technical infrastructure we demonstrated an approach to foster more trustful relationships between people and service providers through digital interfaces.

Picture showing blurred books and documents on an otherwise clearly visible table, through an app interface with adjustment slider.
Picture showing the blurred view through a door from an otherwise clearly visible room, through an app interface with adjustment slider.