2026

Enrico Arapi

I’m Enrico Arapi, a designer focused on interfaces and experiences for virtual and mixed reality.

My work often centres on themes of gesture-based interaction, computer vision in AR/MR, and real-time spatial experiences, developed for platforms like the Meta Quest 3.

I enjoy exploring how users can navigate and interpret digital layers within space, building both speculative proof-of-concepts and working prototypes to translate ideas into usable embodied experiences.

Alongside this, I maintain a strong foundation with roots in traditional graphic design, which informs the clarity and structure of my work; I position myself in the intersection between visual design and technical implementation, using XR as a medium for coherent, future-facing interface/product design.

Patterns in Place

Patterns in Place is a project which aimed to observe and reveal a location’s attributes through a visual outcome. In my case, I chose Aylesford Priory, Kent, for its rich history and architecture, and sense of stillness one can achieve there with its spiritually calming ambience.

To visualise this, I continued on from previous experience with point cloud photogrammetry to test scanning various elements of the site, eventually deciding on the focal point of the main shrine-piazza complex.

From here, I merged multiple scans using Supersplat and imported it into Unity using aras-p’s package from GitHub. After adding in some solid boundaries and adjusting the renderer with OpenAI’s Codex to ensure compatibility with the Quest 3’s cameras, I transformed it into an immersive VR experience.

Cinematic preview of the gaussian splat environment

Demo of the VR experience running on the Meta Quest 3

The central shrine altar

Cloister archways

An aerial view of the full combined scan of the shrine-piazza complex

Paper Plane Folder

Building on Unity Sentis to run a local ML vision model on the Quest 3, I decided to take it a step further as a self-directed project to develop a Perceptually-enabled Task Guidance (PTG) system, inspired by DARPA’s R&D and inspirations of Anduril’s EagleEye and Cyberpunk 2077’s Kiroshi Optics.

To do this, I decided upon a specialised task to train my own computer vision model on; the stages of folding a paper plane.

Using Roboflow and what amounted to ~3000 frames of images taken from POV videos of me folding paper planes shot on the Quest’s cameras, I annotated each one with labels of where the paper was located and what stage it was currently on, and then trained a YOLOv11 model using Ultralytics on my MacBook.

From there, I integrated it within the base Meta-Unity Sentis sample, and then designed and built a UI on top of it to guide a user through each step, one fold at a time.

Whilst this particular task may not be all that useful for XR, it is proof that local, specialised ML vision models can be used with XR for solving problems; as a hypothetical, I can almost imagine a marketplace where people train models on their own activities using their smart glasses’ cameras, and then can share them so other people can download their ‘skills’?

What an idea that would be!

Enrico Arapi

Email address

Instagram

Web Portfolio

Biography