Geometry-based loss functions let single-image 3D face reconstruction networks train without weighting hyperparameters, matching tuned baselines in accuracy while improving reprojection alignment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hyperparameter-Free Losses for Model-Based Monocular Reconstruction
Geometry-based loss functions let single-image 3D face reconstruction networks train without weighting hyperparameters, matching tuned baselines in accuracy while improving reprojection alignment.