Furthermore, we show how existing algorithms in the GiNGR framework can perform probabilistic registration to obtain a distribution of different registrations instead of a single best registration.
This leads to a synergistic effect, in which the segmentation network prevents the face encoder from fitting to the occlusion, enhancing the reconstruction quality.
Ranked #2 on 3D Face Reconstruction on NoW Benchmark
Furthermore, in a reconstruction task, we show how to estimate the posterior distribution of missing data without assuming a fixed point-to-point correspondence.
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.
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
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.
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.
Non-rigid registration of faces is significant for many applications in computer vision, such as the construction of 3D Morphable face models (3DMMs).
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.