Technical University of Munich, Synthesia, University College London · 3D Reconstruction

Pixel3DMM

A fine-tuned DINO ViT that predicts per-pixel surface normals and UV coordinates to constrain 3D morphable face model optimization for single-image 3D face reconstruction. Achieves 15% improvement over baselines on a new benchmark evaluating both posed and neutral facial geometry across diverse expressions, angles, and ethnicities.