Pixel3DMM predicts per-pixel face normals and UV correspondences from a DINOv2 backbone and fits FLAME geometry from these priors, improving posed-expression single-image 3D face reconstruction by over 15% over baselines on a new benchmark.
How far are we from solving the 2d & 3d face alignment problem?(and a dataset of 230,000 3d facial landmarks)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
Pixel3DMM predicts per-pixel face normals and UV correspondences from a DINOv2 backbone and fits FLAME geometry from these priors, improving posed-expression single-image 3D face reconstruction by over 15% over baselines on a new benchmark.