DynHair at ECCV 2026: Dynamic 3D Hair Strand Reconstruction for Photorealistic Head Avatars
Michael_J_Black · x · 2026-09-09
Researchers from ETH Zurich, MPI and others present DynHair (ECCV 2026): reconstructing dynamic explicit hair strands from multi-view video using structured 3D Gaussian Splatting. A temporal network conditioned on head angular velocity, acceleration and gravity models strand deformation, jointly optimized with the face-region 3DGS via differentiable splatting. Paper and code are available.
More from Multimodal
- Images 2.5 vs 2.0: Stop-Motion Animation Test Shows a Clear Leap — nickbaumann_ · 2026-09-09
- LTX-2.5 Pro Trick: A→B Keyframes Drive Explosive Brutalist Object Transformations — egeberkina · 2026-09-09
- Learning 3D editing without paired supervision via generative prior distillation — Hao Wen · 2026-09-09
- Full Prompt Shared: Turning Everyday Objects into Brutalist Concrete Industrial Designs — egeberkina · 2026-09-09
- Blowing up everyday objects into brutalist structures with LTX-2.5 Pro (prompts included) — egeberkina · 2026-09-09
- Linus Ekenstam Builds an Interactive 3D Studio Tour With ChatGPT — LinusEkenstam · 2026-09-09