Search Results for author:
Found 5 papers, 3 papers with code
Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?
We observe the following positive effects for face recognition and facial landmark detection tasks: 1) Priming with synthetic face images improves the performance consistently across all benchmarks because it reduces the negative effects of biases in the training data.
Probabilistic Joint Face-Skull Modelling for Facial Reconstruction
We create a probabilistic joint face-skull model and show how to obtain a distribution of plausible face shapes given a skull shape.
Training Deep Face Recognition Systems with Synthetic Data
In our experiments with an off-the-shelf face recognition software we observe the following phenomena: 1) The amount of real training data needed to train competitive deep face recognition systems can be reduced significantly.
Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems
4) We uncover a main limitation of current DCNN architectures, which is the difficulty to generalize when different identities to not share the same pose variation.
Efficient Global Illumination for Morphable Models
Therefore, we propose to learn self-shadowing for Morphable Model parameters directly with a linear model.
