@everyone 📣 A New Alpha Lab is live 🔩 🛠️

Using Neon's standard scene video + gaze overlay, you can see what a subject fixates on, but real-world physical distance is out of the equation.

In our latest Alpha Lab, we show how to extract gaze distance directly from standard RGB video, purely in software.

Using our new Depth Estimation plugin for Neon Player, powered by Depth Anything V3, you can:

• Pair 2D gaze coordinates (X, Y) with frame-by-frame depth map values
• Render interactive depth heatmaps with dynamic distance overlays on scene recordings
• Export frame-by-frame metric depth data (in meters and diopters) for downstream analysis

Explore the Alpha Lab: https://docs.pupil-labs.com/alpha-lab/depth-estimation/ Check out the repo: https://github.com/pupil-labs/npp-depth-estimation

@everyone Introducing the ‘Neon Player Plugins Repository’ - a place to collate and share plugins for Neon Player Desktop software.

What are Plugins? Neon Player has an open source plugin architecture. It lets you build your own plugins for analysis, visualization, or whatever your workflow needs, and run them directly in the software. Read more about them here: https://docs.pupil-labs.com/neon/neon-player/plugin-api/

We've recently built four. They load and synchronize external camera recordings, sync events with Pupil Cloud, plot GPS data on an interactive minimap, and run Whisper locally to transcribe audio into events.

A space for sharing! We naturally wanted to share these with the community. At the same time, we're excited to learn what you will build. So we're launching this repository as a place where relevant plugins can be collated and shared amongst users.

Dive in Head to the repo and check out what we've got. Instructions for adding your own are in the README. Take a look, and tell us what you build 🛠️ 🔩 🔥

https://github.com/pupil-labs/neon-player-plugins

@everyone New Guide Series 📣

One question comes up again and again in our conversations about eye tracking: What makes a good eye tracker?

It sounds like it should have a simple answer, but there is a surprising amount wrapped up in it.

Accuracy matters, but it is only one part of the picture. Calibration, robustness, data access, adaptable hardware, gaze mapping, open interfaces, analysis tools, and support can all affect how well an eye tracker works in practice.

We’ve started writing down how we think about all of this in a new series of articles.

We’re starting with accuracy. What does it mean? How is it measured? And how can you work out how much accuracy a particular study or application actually needs?

Start with the series overview: https://pupil-labs.com/blog/what-makes-a-good-eye-tracker

Read the the first article on accuracy: https://pupil-labs.com/blog/eye-tracker-accuracy

We plan to publish one new article each week. Next up: Calibration-free eye tracking. Stay tuned!