Google releases GNM, a parametric 3D head model with identity and expression control
rsasaki0109 · x · 2026-07-29
Google’s GNM is a state-of-the-art parametric 3D statistical model of the human head trained on a large set of 3D scans.
It offers fine-grained control over identity, expression, and head pose, and the released package includes NumPy, JAX, PyTorch, and TensorFlow implementations plus visualization and semantic parameter sampling tools. The README also highlights dense face geometry covering skin, eyes, teeth, and tongue.
Related event: Google Open-Sources GNM 3D Head Model(2 posts)→
More from Multimodal
- Dynamic multimodal fact-checking benchmarks still hide 17%–29% contamination risk — Haorui He · 2026-07-29
- ComfyUI demo builds an anime 2D motion sequence in one hour, end to end — petewoodbridge · 2026-07-29
- Kimi K3 via MCP models a 190-room hotel in 9 days, cutting costs to $10.5K — anselm · 2026-07-29
- Dreamina teases Seedance 2.5 with 50 multimodal refs and 30-second video output — eyishazyer · 2026-07-29
- Netflix Under Fire for Using Deepfake Instead of Blurring Faces in Documentary — burkov · 2026-07-29
- KRAFTON AI and SK Telecom release a 21B SpeechLM with tool use and emotion recognition — Kangwook_Lee · 2026-07-29