For all the other recordings, they all worked fine, so I thought it might be other issues? All other recordings have a detection rate of aorund 94%

Hi all! I hope you are well I am writing to you regarding an issue we are facing

My team is using the Neon Glasses with PsychoPy on Windows 11

We are using the following versions PsychoPy 2025.1.1 Plugin 0.8.1 Python 13.3.2

*But the experiment does not work for us, it works with MouseGaze but not with Neon Glasses. We also tried removing PsychoPy, Pupil Lab files, etc from the laptop, didn't fix the issue. We also tried resetting the laptop, still didn't fix the issue. We have tried the gaze contingent demo provided by the Pupil Labs team and also some of our own experiments, but none of them work.

It was working in the past with PsychoPy 2024.2.4 and Plugin version 0.7.7, but then stopped working and now when we install the older version of PsychoPy we don't even see the eye tracking components like April Tags and Record on PsychoPy.

Also, when selecting the eye tracker in the "Experiment settings" we get multiple options like "Pupil Labs", "Pupil Labs (Neon)", "Pupil Labs (iohub)", etc. Sometimes double for each, like two options with the same title.

I wonder which versions work together the best. And has anyone encountered this issue before?

Hi @user-f4f9e1 , thanks. Since we already started communication in your Support Ticket in 🛟 troubleshooting , is it alright if we continue there for now?

Hi! I created the events posthoc in Pupil Cloud. The events are visible in the timeline of the Cloud. I have not checked in Neon Player.

Hi everyone, I’m trying to use Pupil Labs Neon with LSL streaming in a university environment, and I’m running into network issues. The Neon app shows “Stream over LSL” as active, but my Windows PC cannot detect any LSL streams (LabRecorder). Both devices are connected to the university WiFi, and they get IPs in the same range , but the PC never sees the Neon streams. Our IT says the firewall isn’t blocking anything, but I suspect the WiFi network is blocking local peer-to-peer traffic, multicast, or UDP port 16570, which LSL requires.

Has anyone dealt with LSL not working on enterprise/university WiFi networks? Any advice or experience would be super helpful — I’m trying to run experiments and need to solve this. Thanks!

Hi I am trying to use a wired connection. I have both the phone and the headset connected via usb adapter which seems to be connected ok. I have this adapter then connected via network cable to PC (both set to be on the same network) but when i run the discovery functions the pc cant find the eye tracker. Does anyone know how to troubleshoot this? thanks

Thanks! I made a local network, but I'm still using the computer from the University. I have the phone connected to the same local network as in the PC, and I don't see the Neon streams in Lab Recorder at all. Do you think the university computer is blocking something with firewall or something like this? what would you reccomend doing?

Hi I want to know what is the recommended observation range for Neon and Core eye trackers, and is there a range? Thanks

I want to know the effective tracking distance of Pupil Core head mounted eye tracker. Assuming the subject maintains a fixed position without moving, within what range of target objects (in meters) can the best quality eye movement data be obtained? I also hope to understand whether it is affected by the resolution of the scene camera, lighting conditions, or target size, as well as the changes in tracking accuracy at different distances.

Thank you

Hi! The chargers for our Motorola Companion Phones got lost in our lab- have you tested any chargers that I could buy to use with the phones+ devices? I'm located in Germany.

Yes. I tried this in another network at home and it’s working but not in the lab computer, which is controlled by the university IT. They seam to be blocking something that doesn’t allow me to see the streams… any idea what that can be?

Thanks- I did try with multiple chargers USB-C that worked for other phones, but both Motorolas didn't charge at all over a few hours- they kept switching on and off. Is this a known issue? This is the first time charging them

I'm not using the university WiFi, but created a local one (isolated from internet too). The institutional computer is still not seing the Neon streams even when only connected to that local wifi network. What could be still blocking the lsl streams on the PC?

it's a Netgear wifi router that I bought and created a wifi network with it. When I try neon.local:8080 in the computer I do see the video coming in... yet no streams in lab recorder.

One of the chargers I tried was this one: https://www.ikea.com/de/de/p/sjoess-ladegeraet-mit-1-usb-ausgang-65-w-00609743/ and the cable that came with our Neon set. The phone kept vibrating and the power signal would show up every few seconds on the screen for hours. We ordered the devices about a year ago and haven't used them, so yes I assume they were completely discharged for a while.

Hi @user-d407c1 , could you please explain the difference between Wearer Reach and the new Recording reach? I see the explanation line, but cannot understand the algorithm. It works with neon, but not with invisible, right?

Hi @user-3c26e4 ! This applies regardless of whether the data comes from Neon or Invisible, it’s simply a new metric calculated on the AOIs.

You can have multiple recordings from the same wearer, so both metrics are valid depending on what you want to measure:

If you are interested on how many wearers looked at that area of interest, that would be Wearer reach. If you are interested on how many recordings they looked at that AOI, independently if the same person was recorded multiple times or not, that would be Recording Reach.

What's the added value? E.g. You can see 100% of your participants looked at that area of interest, but looking at the recordings reach, it may drop if they did not look at that AOI on every recording.

Hello

We are currently evaluating your eye tracking solutions for a potential purchase. Before proceeding, we would like to clarify a few important points:

1-) Does the device require any specific software license to operate? If yes, is the license included in the purchase price or sold separately?

2-) Are software updates included, or do they require an additional subscription or maintenance fee?

3-) Do you provide any form of training or onboarding for first time users? If yes, is this service included or billed separately?

4-) Is there any ongoing support or service fee after the purchase?

5-) Are there any regional restrictions or differences for usage in Germany or the EU?

Thank you 🙏

Hi Rob, I realized that the number of fixations in the recording is empty. May I know why that is? Thanks!

Hi, I need some clarification if the data can still be stored on the companion app without using the cloud.

Also, we recently got error messages sometimes during recordings. It happened after about 30 min of recordings (not always). What can we do to prevent this? Is this a problem if heat if the phone?

Is 2.9.23-prod the newest update of the companion app?

@user-6c24c0 thanks for reaching out here as well. Yes, the 2.9.23-prod is the latest version of the App. We saw you opened a ticket and sent an email regarding the issues you're encountering. I'd recommend keeping the communication in the Discord Ticket for now so we don't lose track of information across channels.

Hi, I have a quick question. I used Neon by Pupil about years ago, and I recently noticed that my cloud plan has expired. I have a couple of questions:

1. If I purchase the Unlimited Analysis Plan, will I be able to access my originally recorded data?

2. My department will place the order on my behalf to receive an academic discount. In this case, should the contact information on the quote be mine, or do I just need the activation key to register the cloud plan after they purchased an order for me?

Thank you for your help!

Hello, We are interested in the Neon All Clear Eye Tracking System. We need some information regarding the device and its features.

Questions:

Does the device have a CE certificate?

Can results, data, and documents be exported in CSV or EDF format?  a) If not, in which formats can they be exported?

Can AOI, Dwell Time, Revisits, Heatmap, Fixation, and Saccade data be exported?  a) In which format can these data be exported?  b) Are there any additional features available in the software besides these data?

Is there any time limitation for unlimited data export starting from the date of product purchase?  a) If there is a time limit (for example, 3 years), will we still be able to manually export the data afterward?  b) Will any fees be charged after this period?

Is there any fee for collecting data via the cloud or for operating multiple devices under the same cloud account?  a) If yes, how much is it?  b) Is there any duration or usage limitation?

What are the warranty conditions?

Do you provide training and technical support services?  a) What is the duration?  b) Is it paid?

Hi @user-0b1519 - I saw you also reached out via email - I reply here as well, but you'll find more details in the email.

• Yes, Neon has a CE Certificate. I shared it via email.

• All data collected with Neon can be exported as CSV files (see here).

• All AOI-based metrics can be exported when using our analysis platform, Pupil Cloud in CSV files. Pupil Cloud offers powerful gaze mapping tools that allow you to map gaze data from the eye tracking recordings onto screens or areas of interest in the real world environment. You can then extract detailed fixation metrics (e.g., dwell time, number of fixations), and create scanpaths. You can read more about the analysis and visualization tools here.

• Neon always allows manual raw data export via USB. If you plan to use Pupil Cloud, note that with every Neon purchase, you get access to all the features of Pupil Cloud and up to 2 hours of recording storage, such that you can try it out. To unlock unlimited features on Pupil Cloud, we recommend the Unlimited Analysis Plan (see here). As said before, Cloud-based analysis is optional. The raw data are always accessible locally by transferring recordings from the phone to your computer and run your own analysis pipeline with no dependency on Pupil Cloud.

• Neon comes with a 1-year hardware warranty covering manufacturing defects.

• In terms of support, every Neon bundle includes a 30-minute onboarding workshop to help you set up and guide you through our software, but you can always reach us via email or on our Discord server. For more tailored support (e.g., training seminars, custom analysis pipelines), we offer consultancy packages.

Is there a way to manually edit an event timestamp in Pupil Cloud? I want to add an event that is precisely 5 seconds after another event.

Hi, question about exporting Neon data without using Pupil Cloud: we recorded a short session using the Companion App + Neon, and we’re trying to extract the gaze metrics and timeseries data (CSV) locally. Our current approach was to connect the phone via USB, copy the recorded folder from the Neon Export directory to our PC, and then drag it into the latest Neon Player. However, Neon Player briefly loads the folder and then immediately closes. Is there a recommended workflow for obtaining gaze/timeseries CSV data locally without relying on Pupil Cloud downloads? Thank you!

Neon Player will do what you need, and it's meant to work just how you're doing it, but it sounds like there is a problem. Are you able to collect and share the Neon Player log file and/or the recording you're attempting to load?

Unfortunately, I won't be able to troubleshoot from just this. There should be a log file in the neon_player within your home directory. That will be much more useful.

Otherwise, if you can create a zip file of your recording and upload to a sharing site (like Google Drive), that'd be great. You can share the link here or send it to info@pupil-labs.com

Hi Neil, we're using marker mappers on pupil cloud. After that we've been trying to use the Automated AOI Masking tool described here https://docs.pupil-labs.com/alpha-lab/gaze-metrics-in-aois/. The eye tracker is the Neon.

Yup, we were planning on only looking at the boxes. If we need we may decide to divide it into quadrants.

Hi, Following your guidance, I purchased a new Unlimited Data Analysis Plan. I activated the key, but I still cannot access my previously recorded data. It shows the message: “Storage is full. Manage recordings or upgrade your storage with a Cloud Plan.”

I’ve never seen this message before when I worked with the same data earlier. Could you help me with this? (how to get access to my originally recorded data?)

Thank you

Hi, what mDNS parameters are needed for this service (airprint) to function? My institution is trying to connect the neon android phone to the university network.

This is an example of an airprint service which uses mDNS similarly to the neon software (according to IT).

This is another reference (chromecast).

Are there any reference to other mdns services their software works off of? For example does it match up to chromecast, airplay, miracast, ect?

Hi @user-7c5b51 ! Adding to my colleague's response, the Python Realtime API utilizes zeroconf, which is built on top of Bonjour and Avahi. You can find more info here.

@user-4c21e5 , @user-f43a29 and others from the amazing pupil labs team, we (at the Intelligent Biomedical Sensing Lab here in Berlin) are working with the PupilLabs Neon (we love it!), and are also customizing the frame for various experiments. Since the default frame and also the "is this on?" frame are not always suitable for our setups where we need to combine with various head gear, we build solutions like the one attached.

The ideal solution would be one where we can also modify the frame itself (e.g. by removing the lower part). The problem is that the files that are openly available for the frame do not include a heat sink, and we also did not find a file for the heatsink geometry itself. We tried to 3D scan it, but its too finicky for a proper scan.

The question: Would you be willing to share a CAD/STL file of the frames with heatsink OR the heatsink file, so we can build custom frames that work with our Neon's heat sink? We are happy to openly share the results back with you and the community! My PhD Student Bilal ( @user-39ee45 ) is a real pro when it comes to 3D design and printing, so the quality will be decent 😉

Hi @user-fcdbb6 👋 ! Really cool frame there! Have you already seen the Ready Set Go! frame? Seems similar to what you are trying to achieve.

That said, yes we can share those! We will update the repository next week to include new files 😉

thank you @user-d407c1 ! thats great news! We saw it, its a great solution. For what we need to integrate with (whole head neuroimaging sensors) we will need to further customize, so really a huge thank you for sharing next week!

Thank you so much @user-d407c1 ! Really appreciate you taking the time to share those files. Excited to check them out!

Hi everyone, I am comparing the fixations I got from pupil Cloud and pupil Player. It seems, that pupil Player may concatenate fixations if i understand the docs correctly https://docs.pupil-labs.com/core/terminology/#offline-fixation-detection (and also according to my data). Is there a paper that explains the algorithm for pupil Player in more detail? I found the whitepaper for the one Pupil Labs fixation detector (Algorithm description - 3.6.24), which I assume to be the one for Pupil Cloud?

Is there a way with which I can extract the same fixations offline as in the cloud?

Best, Tim

Hi, I aim to use gaze_mapper.py on real-time-screen-gaze and surface_tracker via Git to capture gaze on the monitor in real time. However, the coordinates obtained are being interpreted as the monitor's boundaries, as shown by the red line in the attached image. Is there an API we need that we're missing? Or is there another cause?

Hi! I have a question related to real-time streaming:

Can you stream the data of the eye tracker directly from the companion device to your computer, without saving anything on the companion device? I know there are streaming and recording features in the real-time API here (https://pupil-labs.github.io/pl-realtime-api/dev/methods/async/remote-control/) but wondered if we can control storage location.

Hi

I hope you are well

I just received my product

How I can adjust the strap

Fixed 💙

Yes, we want the data saved directly to the computer instead of the companion device (as is the default behavior)

This is very useful thank you!

Also another quick question regarding real-time, has anyone tried using a hotspot on the companion device and connect the monitor PC to the companion device's hotspot? previously we were using a local network, but we'd like to know if it's feasible to get cell service on the companion device and then make a hotspot so we can still use the monitor

Hi @user-ffef53 , it is not necessary to have cell service to create a hotspot. Many phones create hotspots by re-purposing the WiFi chip in the phone. This approach of running the hotspot on the Companion device has been tried and is used by some, I believe.

Hi devs! I have a question regarding how to use the time_offset_ms and roundtrip_duration_ms generated by device.estimate_time_offset() in the realtime API.

If I understand it correctly, time offset is the offset between the two clocks. However, it's unclear to me whether this offset has been corrected for the roundtrip time. If so, I think it makes a lot of sense to send events using neon.send_event(event_name, int(time.time_ns() - offset)). If not, however, users should be wary that the time offset also contains the time required for the ping signals to travel between the devices, and thus should do neon.send_event(event_name, int(time.time_ns() - offset + roundtrip_duration)) In our recordings, we observed that the events are often timestamped earlier than they should be, suggesting the latter is more possible. But I want a confirmation from the team on this matter. Thanks a lot in advance!

Thanks Rob for the reply! The post is helpful in explaining how, when the measured clock offset is objectively accurate, mitigates the problem. However, my question is actually about how the clock offset is measured. I imagine you would send a command from PC (and log PC_time), when the command reaches companion, companion sends back its clock time (companion_time) to PC. PC then receives this time, and compare it with PC_time to derive the clock offset. If this is the case, I personally believe the clock offset might have been overestimated, given that the original command from PC to companion also takes transmission time (which could be assumed to be roundtrip_duration / 2). What do you think about this possibility? Or has the realtime api corrected for this delay?

Thanks for point to the documentation! It does exactly the type of correction I was wondering about. Then it is indeed a bit mysterious why our events are over-compensated. Here's my code snippet: offset = device.estimate_time_offset(500).time_offset_ms.median * 1_000_000 # Estimate 500 times and take the median, convert from ms to ns device.recording_start() ... device.send_event("xxx", int(time.time_ns() - offset))

We used a simple psychopy experiment, where we presented stimuli (e.g. fixation cross). And then I how well the timing of events aligns with stimulus onset in the video. For example in this recording, when "fixation cross" event is logged, the actual fixation hasn't been shown yet. It is only after another ~250ms the fixation actually appears.

the PsychoPy code is: fix_cross.draw() device.send_event("fixation onset", int(time.time_ns() - offset)) win.flip()

I considered if send_event would take some time so that win.flip() was delayed during its execution, but in your source code send event is async, so I guess it's not likely?

The image upload failed in dc, trying again. The diamond event is the logged "fixation onset"

Thanks for the hint! I will try it out tomorrow

https://discordapp.com/channels/285728493612957698/1047111711230009405/1438110550860103742 The goals I'm trying to achieve are outlined in this chat history. I used the surface trucker because it seemed referenced in the real-time-screen-gaze package, but was it unnecessary?

In your original messages, it sounded like you wanted to know the coordinates on the monitor, but in your newest message, it sounds like you do not want coordinates on the monitor? Am I correct?

Can you also explain how you generated that red boundary in the image here? https://discord.com/channels/285728493612957698/1047111711230009405/1449701237774880922

Hi, we are using Neon!

Hi Rob, I'm happy to report that calling send_event after win.flip() actully makes the event timestamp more accurate. Calling it before win.flip() will log the event earlier than it should be. No significant difference was seen between using send_event after win.flip() and using the win.callOnFlip() method. In both cases, the temporal discrepancy is ~50ms which is considerably low enough given the scene camera's 30FPS

Hi! I’m planning to run an experiment on which I use the position of the eye in real time, in order to generate a change/decision on the task. I’m using matlab and psychtoolbox for the task. Is possible to access the livestream of eye position for this type of eye-computer-interface?

Hi, thanks for the info! Sorry for getting the names mixed up. I used neon player to get fixations from a recording from the companion device, however the fixations i got from exporting from pupil cloud are different. The fixations.csv found in neon_player/offline_data after analysing the same video in neon player are different from the fixations.csv from Timeseries_Data after downloading from Pupil Cloud. So my question is rather is the fixation detector also different between neon player and pupil cloud?

In your link it was mentioned that the Pupil Labs fixation detector is used in Neon. Does that mean neon player or pupil cloud?

Hello! I have a question regarding timestamps. I'd like to obtain UTC (i.e., epoch time) timestamps for the video frames from the sensor/eye cameras. However, based on my understanding, the first sample in the gaze.csv timeseries doesn't align with the first eye-camera video frame. Correct me if I'm wrong.

If this is the case, what is the best way to determine the UTC timestamp corresponding to the first eye-camera video frame?

Hi @user-2e5a7e 👋 ! If you do not mind using Python and the Native recording format, you can simply use our library pl-neon-recording .

Simply install it pip install pupil-labs-neon-recording and:

import pupil_labs.neon_recording as nr
recording = nr.open("YOUR_PATH_TO_NATIVE_REC")
print(recording.eye.time[0])

would get you the first eye camera timestamp.

PS: If you have astral's uv , you can open a python shell with the library by using

uv run -p 3.12 --with pupil-labs-neon-recording python and copy the above.

Hi, I have a question. In my study, children will wear the Crawl Walk Run model and sit on the floor, and play with toys.

I noticed from the video that the center of the gaze is at the lower bottom of the screen (like the picture I sent, the child is playing with the toy, and they should be fixating on the toy that is at the bottom of the screen). I think this is due to children looking down while playing, and the scene camera waw recording the front, and the vertical field of view is not wide enough.

Any suggestions on how to set up the eye-tracker so we can record their hands better? Thank you!

Hi @user-5b6ea3 g 👋
Just to make sure I understand correctly, what you report is that their hands are falling outside the scene camera’s vertical field of view (~80°)?

If that’s the case, one option to extend the FoV, would be to use an additional third-party camera with a wider field of view and map the gaze data, as shown here:
https://docs.pupil-labs.com/alpha-lab/egocentric-video-mapper/

On that example, we used an Insta360 which could be more minimal than a traditional GoPro, but there might be even other options in the market

Hi, @user-5b6ea3! Do you find your children gaze downward more, relative to their head position? Usually in adults, similar gazing coincides with head tilt, to make it easier to look at the object. I also get that an additional camera might be cumbersome. Could you consider putting the toy on a small table to bring it higher in the visual field?

Hello, I am working on a project to study gaze vector during gait tasks. I will synchronize motion capture and eye tracking data, and will buy Neon Glasses for this purpose. Which Neon version or frame type is the most indicated for this kind of measurement?

Hi @user-e4d004 👋 ! If you have a Motion Capture system that uses passive reflective markers, you would probably want the frame Every Move You Make or I Can Track Clearly Now depending on whether you want to use prescription lenses or not.

Hello, I am currently trying to get your Web AOIS application up and running. Everything works fine, but when I try to create a heat map from the data, it is completely off. In addition, after some runs, the data tables are entirely empty. I think this might be because the April tags are not being recognized correctly. I have already tried playing around with the exposure, screen size, distance, and everything else I could think of. Is there anything else I can try?

If so, you can invite us [email removed] to your workspace and we can have a look and give you feedback.

Hello, we are experiencing an issue when controlling the Pupil Labs Neon via a PC (Windows or macOS) or when starting a recording. After two to three recordings that were successfully started and stopped, it is no longer possible to start a new recording, as a network error is displayed on the PC.

We have tested this both within a shared network (PC and device connected to the same network) and via the hotspot of the supplied Motorola smartphone. We have also tried using the Chrome and Firefox browsers.

Could this be a device-specific issue, or are there certain browser settings that could resolve this behavior? Alternatively, we would like to ask whether it is possible to use the Pupil Capture software with the Pupil Labs Neon.

Okay thanks. I have send you an invite.

@user-f43a29 thank you for your quick response. Currently, version 2.9.23-prod of the Neon Companion App is installed on the Motorola device. The individual recordings are approximately 10 seconds long, with a pause of about 10–20 seconds before the next recording is started.

Thank you, I will try this when I get back in the office after christmas and report back to you. Happy holidays 🙂

Dear Sir I apologize for troubling you when you are busy, could you kindly respond to the following questions?

Q1 Could you please explain the differences between the following products? For System ②, is the only difference from ① the appearance (for example, is the bare metal part of ② less noticeable to others)? Regarding ③, since it seems to include multiple lenses with different diopters, does this mean that users with poor eyesight can use it without wearing their own glasses?

System ① Just act natural ② Nothing to see here ③ I can see clearly now

Q2 Do all of these systems come with a smartphone as standard (i.e., is the companion device a smartphone)?

Q3 When purchasing only the frames for each system, is it necessary to purchase the 6,090-euro bare metal unit as well? Alternatively, is it possible to detach the bare metal part from a NEON unit that we already own and attach it freely to different frames?

Hi @user-5c56d0. I’m happy to clarify:

Q1: Regarding the "Just act natural" and "Nothing to see here" frames, yes, the only difference is cosmetic. Specifically, it affects how visible the Neon module is to others. For reference, the "Bare Metal" is not the Neon module itself, but the nest PCB, which can be purchased separately if you want to develop your own custom frame. The cosmetic difference between "Just act natural" and "Nothing to see here" can be useful in applications such as consumer research, where researchers want participants to wear a very inconspicuous eye tracker to ensure natural behavior, as if they were wearing normal glasses.

For "I can see clearly now", you are correct. This frame comes with a magnetically swappable lens kit ranging from -3 to +3 in 0.5 diopter steps. This allows researchers to fit the lenses needed for each participant so they can use the eye tracking glasses without wearing their own prescription glasses.

Q2: Yes, all Neon bundles come with an Android smartphone as the Neon Companion device. We are currently shipping the Samsung S25.

Q3: Every Neon bundle already includes the Neon module attached to the frame, meaning the system is ready to use. When purchasing a bundle, you do not need to buy anything extra, as it already includes the frame of your choice, the Neon module, and the Neon Companion device.

If you would like to swap frames depending on participant needs (for example, a "Just act natural" frame for participants who do not need glasses, and an "I can see clearly now" frame for those who do), you can purchase an additional accessory frame - not a full bundle - and simply transfer the module across frames. This is straightforward, as the module attaches to the frame with just two screws.

Yes, that’s correct! Our documentation includes a dedicated guide with a video to help users swap the Neon module correctly between different frames.

Hi, does the eyelid data available if I import the raw data directly from the Companion app over USB? I am particularly interesting in eyelid angles and eyelid aperture. I am looking at https://pupil-labs.github.io/pl-realtime-api/dev/api/async/#pupil_labs.realtime_api.streaming.gaze.GazeDataType, EyestateEyelidGazeData class, it seems it includes both, but still not quite clear from the docs. Could you also send the link to the available eyestate/eyelid fields doc for raw recordings imported directly from Companion app. Thank you.

Hi @user-912183 👋 ! Eye lid aperture, also referred as eye openness in our documentation is part of the eye state data.

Your are pointing to the realtime api documentation, and yes, it is available in real time if you enable "Compute eye state" from versions +2.9.0 or above of the Companion App.

But it seems you want to access the data post recording instead, and using the native recording rather than the Timeseries, is that correct? If so, you would probably want to access the eye state data using pl-neon-recording as shown here https://github.com/pupil-labs/pl-neon-recording/blob/main/examples/csv_export.py#L186-L217

Hello! I am curious about the difference between the output from Pupil Cloud vs Neon Player. Thank you!

hey I'm working on pupil neon eye tracker for my Mtech thesis in IIT Madras, Chennai, India. In my pupil cloud it is showing cloud plan expired. So do i need to recharge to get my recorded videos and datas from eyetracker and how to do that