Jon Starck

Creating video through code, CTO @synthesiaIO.
Using algorithms to create pixels and making synthetic humans look real.
#ai #digitalhumans #syntheticmedia

[Jon Starck @jnstrck]

🤩 Really excited to finally share our brand video - check out what you can do with synthetic humans at @synthesiaIO
Enjoy & let me know what you think!
https://t.co/zPhV7Yxn7S

[Matthias Niessner @MattNiessner]

Super excited - our company @synthesiaIO is now a unicorn🦄🦄🦄 !!!

We are making important steps in advancing cutting-edge research in generative AI. Check out our first publications this year at #CVPR and #SIGGRAPH -- a lot of cool stuff is in the pipeline and yet to come!

[Jon Starck @jnstrck]

This has been a great first project working with @SGiebenhain our sponsored PhD student @synthesiaIO together with an awesome team - @MattNiessner @TobiasKirschst1 Markos @martin_ruenz @LourdesAgapito 😎 - looking forward to #CVPR2023!

[Matthias Niessner @MattNiessner]

(1/2)
We released our Neural Parametric Head Models (NPHM) dataset from our #CVPR2023 paper!

It includes over 5600 high-fidelity 3D scans of human heads from 272 subjects - all publicly available!

Check it out!
https://t.co/ynlcqd8ynr
https://t.co/npsZulVUHO

[AK @_akhaliq]

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion

a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints

project page: https://t.co/R4JadHUpjE
paper page: https://t.co/jEgXS2vKrL

[Jon Starck @jnstrck]

This is great news: our first academic paper @synthesiaIO collaborating with an awesome team at TUM and UCL. Accepted at #CVPR2023 - one of the world's most prestigious AI conferences.

[Matthias Niessner @MattNiessner]

(1/2)
Excited to share "Learning Neural Parametric Head Models" #CVPR2023!

We capture over 5200 high-quality 3D human head scans from which we build a neural parametric head model that disentangles & expressions and deformations.

https://t.co/ynlcqd8ynr
https://t.co/npsZulVUHO

[Matthias Niessner @MattNiessner]

(1/2)
Excited to share "Learning Neural Parametric Head Models" #CVPR2023!

We capture over 5200 high-quality 3D human head scans from which we build a neural parametric head model that disentangles & expressions and deformations.

https://t.co/ynlcqd8ynr
https://t.co/npsZulVUHO

[Jon Starck @jnstrck]

🗣 I’m excited to talk about @Synthesia and Synthetic Humans at the @LondonAI meet-up this week. Looking forwarding to seeing some folks in person! If you’re in London and into AI, come and join us.
Details & registration: https://t.co/6XKFm8X11K

[Synthesia 🎥 @synthesiaIO]

Let’s talk about synthetic humans: who they are, where they come from and where they’re going. 🚀🚀🚀

If this sounds interesting, come join us (well, our CTO @jnstrck) at the @londonai meet-up next week. More info here:

[Jon Starck @jnstrck]

More NERFs going fast… https://t.co/tEo8yImeWa

[Jon Starck @jnstrck]

I had to give some fatherly advice today. It seems pretty relevant - "don't sweat it!". Don't worry about failing. What matters is wanting to achieve your goals and never giving up. Turns out there is a "father of tech" that said it a lot better 👇
https://t.co/mE0IrazFlP

[Jon Starck @jnstrck]

#NeuralNetworks can help unlock artist creativity in VFX. Take a compute heavy task, train a network to replicate it - then an artist can iterate fast to create the effect the want. Check out this demo for real-time cloth from @DigitalDomainDD 👇

https://t.co/qdT6rc7HbW

[Jon Starck @jnstrck]

I love a DAG. Here's a snapshot from the early days of node-based compositing in film VFX. Hugely complex effects are now built using Directed Acyclic Graphs (DAGs) in VFX tools like Nuke / Maya / Houdini / Katana.
https://t.co/1C88o5OM16

[Jon Starck @jnstrck]

If you're from the world of VFX wondering about neural networks. They're just DAGs too - this time with millions of parameters to tweak to get the right effect.

[Jon Starck @jnstrck]

Fun with AI!

https://t.co/xP58Ly7Aag

[Jon Starck @jnstrck]

More info on internships @synthesiaIO here

https://t.co/og2XO9Uacq

[Jon Starck @jnstrck]

What questions could you get in an #internship interview in #ComputerVision #ComputerGraphics #MachineLearning?

Here's some tips for what we focus on at @synthesiaIO with our Co-Founders @LourdesAgapito @MattNiessner👇

[Jon Starck @jnstrck]

3. 🚀Your research, your internship
Meet our academic leaders to talk through your research. We look for passion and the opportunity to really push the state-of-the-art.

[Jon Starck @jnstrck]

A powerful message, one that hopefully can still reach out. This video will stand the test of time and resonate in the future.

https://t.co/vycqP68TDc