Liam Schoneveld
@liamschoneveld.bsky.social
Computer vision research engineer @ Woven by Toyota.
Focused on reconstructing humans and their environments in 3D.
Focused on reconstructing humans and their environments in 3D.
🐑🐑 SHeaP inference code is out ! 🐑🐑For all your real-time head pose and expression tracking desires! Check it out at: 🤗 HuggingFace spaces: huggingface.co/spaces/nlml/... 📟 Github: github.com/nlml/sheap
SHeaP - Self-Supervised Head Geometry Predictor - a Hugging Face Space by nlml
Upload an image or video to get a 3D mesh overlay showing head geometry. The output includes three views: the original, the rendered mesh, and the mesh overlaid on the original.
huggingface.co
December 9, 2025 at 8:54 AM
🐑🐑 SHeaP inference code is out ! 🐑🐑For all your real-time head pose and expression tracking desires! Check it out at: 🤗 HuggingFace spaces: huggingface.co/spaces/nlml/... 📟 Github: github.com/nlml/sheap
📢 Our new paper - SHeaP - is out! 📢
TLDR: self-supervised head tracking and geometry (FLAME) prediction, learned via photometric loss with a 2D gaussian splatting renderer.
See more:
🌍 nlml.github.io/sheap/
🎥 youtu.be/vhXsZJWCBMA/
TLDR: self-supervised head tracking and geometry (FLAME) prediction, learned via photometric loss with a 2D gaussian splatting renderer.
See more:
🌍 nlml.github.io/sheap/
🎥 youtu.be/vhXsZJWCBMA/
April 18, 2025 at 12:56 AM
📢 Our new paper - SHeaP - is out! 📢
TLDR: self-supervised head tracking and geometry (FLAME) prediction, learned via photometric loss with a 2D gaussian splatting renderer.
See more:
🌍 nlml.github.io/sheap/
🎥 youtu.be/vhXsZJWCBMA/
TLDR: self-supervised head tracking and geometry (FLAME) prediction, learned via photometric loss with a 2D gaussian splatting renderer.
See more:
🌍 nlml.github.io/sheap/
🎥 youtu.be/vhXsZJWCBMA/
Interested in working (in Tokyo!) on reconstructing humans and their environments in 3D? We've just opened a position for a summer research intern!
jobs.lever.co/woven-by-toy...
jobs.lever.co/woven-by-toy...
Woven by Toyota - Computer Vision Researcher, XR Interface AI (Internship)
TEAM Toyota is redefining what it means to move. We're challenging the current state of mobility by enhancing the movement of people, goods, information and energy. Centered around three core concepts...
jobs.lever.co
January 26, 2025 at 6:01 AM
Interested in working (in Tokyo!) on reconstructing humans and their environments in 3D? We've just opened a position for a summer research intern!
jobs.lever.co/woven-by-toy...
jobs.lever.co/woven-by-toy...
Our latest work (shout out Jiapeng Tang) in the head avatars space!
(1/2)
📢📢𝐆𝐀𝐅: 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐀𝐯𝐚𝐭𝐚𝐫 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐟𝐫𝐨𝐦 𝐌𝐨𝐧𝐨𝐜𝐮𝐥𝐚𝐫 𝐕𝐢𝐝𝐞𝐨𝐬 𝐯𝐢𝐚 𝐌𝐮𝐥𝐭𝐢-𝐯𝐢𝐞𝐰 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧📢📢
We reconstruct animatable Gaussian head avatars from monocular videos captured by commodity devices such as smartphones.
📢📢𝐆𝐀𝐅: 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐀𝐯𝐚𝐭𝐚𝐫 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐟𝐫𝐨𝐦 𝐌𝐨𝐧𝐨𝐜𝐮𝐥𝐚𝐫 𝐕𝐢𝐝𝐞𝐨𝐬 𝐯𝐢𝐚 𝐌𝐮𝐥𝐭𝐢-𝐯𝐢𝐞𝐰 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧📢📢
We reconstruct animatable Gaussian head avatars from monocular videos captured by commodity devices such as smartphones.
January 9, 2025 at 6:36 AM
Our latest work (shout out Jiapeng Tang) in the head avatars space!