Collected Sign Language Motion Capture

Hello this is Studio Galt. Since 2020 we have been recording Motion Capture, primarily of American Sign Language. I'm going to run the rest of the ReadMe as an FAQ.

1. General FAQ
2. Tech FAQ
3. Avatar FAQ

1. What's the License?

CC0, we don't reserve any rights, use this as you feel. We want to make these assets free for everyone.

2. CC0 forever?

Yes, unless we are forced by law to change. So please no crimes.

3. Why Sign Language?

It hadn't been done, or not publicly available. Also, we mainly do ASL (American Sign Language).

4. Why ASL?

I'm in English speaking North America.

5. Speaking, you are not Deaf?

Nope, I am hearing person, my knowledge of ASL is not complete.

6. Why would I come to you for translation then?

You shouldn't. I do not offer translation services. I offer the ability to turn translation into animation.

7. I speak English, why don't I just do it myself?

That would be SEE (Signed Exact English) not ASL. That may be appropriate for your project or not, depending on what project is. Like a dictionary it can teach certain things about a language, but not others.

8. Do you intend to do other languages?

We try to do the base alphabets for as many languages as we can but to another full language, I would require sponsorship and assistance with the language.

9. Sponsorship?

This is not my fulltime job, but I would like it to be. We will fight to keep the resources free and CC0 in any case.

10. What do you mean language assistance?

Most Sign Language resources are written in the local spoken. I can do ASL and BANZL (British, Australian and New Zealand Sign Language) because the resources are in English, but doing it without knowing the spoken language will increase errors exponentially.

11. Errors?

While 100% accuracy is the goal, mistake can and will happen. Yet another reason we recommend using professional translation. We do have system for correcting errors.

12. How do you correct errors?

Every file has date on it, when an error is found, we receate the motion under a new date. We try to avoid deleting old motions, even if incorrect, because we believe it is important be able to reproduce any results (even the errors). General rule of thumb, newer is more accurate.

13. Can I use the motions for non-sign language purposes?

Yes, but these motions are part of a language as such it has meaning or context can confuse and annoy people (see Neon Genesis Evangelion). A good way around this is modify it to be less likely to mistaken for something they shouldn't be.

14. We can modify these files?

Absolutely. That is point of this project. Retarget to your characters.

15. Can I use this for other languages other than ASL?

If you know a sign in another language matches an ASL one, or how to modify an existing motion to do so go for it. Please advise us as well, if this project ever does tackle other languages being able to reuse existing motions would be a great aid.

16. Can use this for machine learning?

Going to split this in two. For translation, yes but I have requests for that, one test it, and don't test on the unwilling. We're quite skeptical of how well machine learning will translate to various sign languages but would love to be wrong. For Art AI, yes, but we please respect other artists decision to not want to be used for AIs Art.

17. Can we use them for NFT?

Yes, but we will not endorse any NFT projects. We are for maximum access to everyone, where NFT are about controlled access. This is not a bad goal, but it is not our goal.

1. What do you record at?

All recordings are done at 240 frames per second. However, we post at 60 frame per second.

2. Why change fps (frames per second)?

Limiting the size of the files, and reducing clean up time.

3. What is your equipment?

I use Xsens Link suit, and StretchSense Gloves.

4. Are you sponsored by them?

No, but I would like to be.

5. What Software do you use?

Blender is the primary, it's free and open source, so it is natural. We do occasional quality checks to make sure files load into Autodesk Maya, Nvidia Omniverse, Unity and Unreal Engine. But not every motion will be checked. If something does not work please let us know!

6. What about X software?

We don't have access to every software, but Blender is very good at interoperability.

7. What are your export formats?

FBX and USD. The FBX is broken up into with Mesh and No Mesh. No Mesh is less data but will not have any facial information. USD is open format create by Pixar, and is being adopted many parts of the 3d industry. We intend to make tutorials and workflows for both.

8. Facial data?

ASL and other sign languages use facial movements convey tone and information. Some signs require facial movement to be complete, other it adds extra information (similar to punctuation of vocal tone). Because there are a wide range of tones, the facial data is usually left blanket unless required to complete the motion (such as anger).

9. How do I change her face?

Shapekeys, sometimes called Blendshapes. This will explained in the Tutorials.

10. Where are your tutorials?

All tutorials will be posted at https://www.studiogalt.com/.

1. Who is the Avatar?

Her name is Galtis. Very creative. But we stan.

2. Why is she a girl?

Hatsune Miku demands it. The real reason is part of the clean up process is making sure the mesh doesn't intersect itself. This is a more likely to happen on a female avatar than a male avatar. If the avatar intersections are fixed for female, it should be fixed for a male avatar.

3. Can I use her in X?

She is opensource and free to use. Please no crimes.