Search Results for author:
Found 6 papers, 2 papers with code
INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields
We propose INFAMOUS-NeRF, an implicit morphable face model that introduces hypernetworks to NeRF to improve the representation power in the presence of many training subjects.
Face Relighting with Geometrically Consistent Shadows
Most face relighting methods are able to handle diffuse shadows, but struggle to handle hard shadows, such as those cast by the nose.
Towards High Fidelity Face Relighting with Realistic Shadows
Furthermore, we introduce a method to use the shadow mask to estimate the ambient light intensity in an image, and are thus able to leverage multiple datasets during training with different global lighting intensities.
Parallel Transport Unfolding: A Connection-based Manifold Learning Approach
Our new geometric procedure exhibits the same strong resilience to noise as one of the staples of manifold learning, the Isomap algorithm, as it also exploits all pairwise geodesic distances to compute a low-dimensional embedding.
Adaptive 3D Face Reconstruction From Unconstrained Photo Collections
Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information.
Unconstrained 3D Face Reconstruction
Second, by leveraging emerging face alignment techniques and our novel normal field-based Laplace editing, a combination of landmark constraints and photometric stereo-based normals drives our surface reconstruction.
