Staff SWE at Google, working on Digital Humans for AR & VR
Cambridge, UK
Joined January 2011
- Tweets34
- Following209
- Followers372
- Likes909
Erroll Wood retweeted
Intelligent eyewear is coming this fall! โจ
It was a privilege to be onstage at #GoogleIO to show our new audio glasses with #Gemini and share a first look at two designs from the upcoming collections.
Iโm incredibly proud of our team and the partnership with @SamsungMobile and iconic eyewear brands @WarbyParker and @_GentleMonster_ to bring hands-free help to your everyday life.
Read more: goo.gle/intelligenteyewear
Watch I/O Keynote: youtube.com/live/wYSncx9zLIU
Meet D4RT ๐ฏ
A unified model for next-gen scene reconstruction and tracking.
๐ง The Secret Sauce: Incredible results thanks in part to diverse, realistic synthetic data from our team. The results are wild. ๐คฏ
#SyntheticData powers cutting-edge algorithms on #AndroidXR like Hand Tracking, Face Tracking, and more. ๐ฆพ
At #CVPR2025 ? Attend our tutorial (June 12th) to dive deep into Android XR's Perception stack.
Full schedule here: augmentedperception.github.iโฆ
Excited to finally share #AndroidXR #Moohan with the world. We're just getting started ๐ช๐
#AndroidXR is officially here! ๐ Thrilled to see the developer excitement and passion to build immersive experiences. Huge thanks to the @GoogleARVR team and our incredible partners @SamsungMobile and @Qualcomm and more. โก๏ธ blog.google/products/androidโฆ
It turns out that a synthetic-only face prior is great for novel view synthesis ๐ฆพ. If you're heading to SIGGRAPH Asia ๐ฏ๐ต, don't miss Cแด๊ฐแดแด. Great work, @mc_buehler!
A purely synthetic face prior can generalize to casual in-the-wild captures and stylized faces ๐คฏ
I'm happy to share our @SIGGRAPHAsia paper โCafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures.โ
syntec-research.github.io/Caโฆ
Coming to #CVPR23? Come to my talk on Sunday morning at the GAZE workshop gazeworkshop.github.io/2023/ to hear about Synthetic Data for Gaze Estimation & More. Find out what worked ๐๐ป, what didn't ๐ค, and what's next ๐.
At #ECCV2022? Come try our our face tracker, powered by #syntheticdata and some real-time model-fitting magic ๐ช.
๐ผ๏ธ Poster 59 in Thursday's morning session.
๐ microsoft.github.io/DenseLanโฆ
Erroll Wood retweeted
Excited to share our work on #syntheticdata, generating dynamic expression-based wrinkles for digital faces, to appear at #WACV2023!
With @Friggog, @errollw, and Tadas Baltruลกaitis @Microsoft Mixed Reality & AI Cambridge
๐arxiv.org/abs/2210.03529
๐งต1/8
Erroll Wood retweeted
New Video - Microsoft's New AI: Virtual Humans Became Real! ๐คฏ
youtu.be/6-FESfXHF5s
#ai
Very proud to share more about our work on ๐๐ฒ๐ป๐๐ฒ ๐๐ฎ๐ฐ๐ฒ ๐๐ฎ๐ป๐ฑ๐บ๐ฎ๐ฟ๐ธ๐, which will appear at #ECCV2022. Check it out! ๐
๐ microsoft.github.io/DenseLanโฆ
๐ฅ youtube.com/watch?v=M8NNytHyโฆ
๐ arxiv.org/abs/2204.02776
Join me tomorrow at the SyntML workshop at #CVPR2022 to hear about how #syntheticdata helps us solve all sorts of face-related computer vision problems. These aren't toy problems, they are the real deal!
syntml-cvpr2022-workshop.gitโฆ
I'm delighted to share our work on dense landmarks! arxiv.org/abs/2204.02776
๐ Dense landmarks are all you need for accurate 3D face reconstruction and performance capture
๐ช No surprise: the secret sauce is synthetic data
๐ It's fast, running at 150FPS on a single CPU thread
Erroll Wood retweeted
Join technical & business luminaries from @Microsoft, @EpicGames, @Disney Research, @Reallusion, and more for a #GTC22 panel discussion exploring the profound impact of digital humans on industries.
Register free today.
Join us on the #nvidia #gtc22 panel ๐๐ก๐ ๐๐ฆ๐ฉ๐จ๐ซ๐ญ๐๐ง๐๐ ๐จ๐ ๐๐ข๐ ๐ข๐ญ๐๐ฅ ๐๐ฎ๐ฆ๐๐ง๐ฌ ๐๐จ๐ซ ๐๐ง๐๐ฎ๐ฌ๐ญ๐ซ๐ข๐๐ฌ to hear how digital humans will impact industries beyond VFX, including continuing to revolutionize #AI with #syntheticdata.
๐reg.rainfocus.com/flow/nvidiโฆ
Want to know more about how we solve real-world computer vision problems with synthetic data? Hear all about it from Gil and Tadas on November 17th.
๐app.livestorm.co/datagen/impโฆ
The ๐
๐๐ค๐ ๐๐ญ ๐๐ข๐ฅ๐ฅ ๐๐จ๐ฎ ๐๐๐ค๐ ๐๐ญ dataset is now available! 100,000 synthetic face images with pixel-perfect segmentation and landmark labels. All you need for SOTA-level results on real data.
Download it now๐ lnkd.in/gCFu9z4k
#iccv2021 #syntheticdata
Erroll Wood retweeted
[new paper video ๐ฅ] @Microsoft's "Fake It Till You Make It: Face analysis in the wild using synthetic data alone" paper explained!
YT: youtu.be/k0Q-U9U0EQs
@errollw @Friggog @sebadzia @matajoh @TomCashman @JamieDJS Tadas Virginia โค
I'm delighted to announce our work on synthetic data: ๐
๐๐ค๐ ๐๐ญ ๐๐ข๐ฅ๐ฅ ๐๐จ๐ฎ ๐๐๐ค๐ ๐๐ญ - ๐
๐๐๐ ๐๐ง๐๐ฅ๐ฒ๐ฌ๐ข๐ฌ ๐ข๐ง ๐ญ๐ก๐ ๐ฐ๐ข๐ฅ๐ ๐ฎ๐ฌ๐ข๐ง๐ ๐ฌ๐ฒ๐ง๐ญ๐ก๐๐ญ๐ข๐ ๐๐๐ญ๐ ๐๐ฅ๐จ๐ง๐. #iccv2021
microsoft.github.io/FaceSyntโฆ
arxiv.org/abs/2109.15102
youtu.be/wlOMpQe8luQ