Multilinear Wavelets: A Statistical Shape Space for Human Faces
This work addresses the need for accurate face shape reconstruction in applications like tele-presence and gaming, though it is incremental as it builds on prior multilinear and PCA models.
The authors tackled the problem of reconstructing 3D human faces from noisy and occluded scans by developing a statistical model that uses wavelet transforms and localized multilinear models, resulting in better preservation of fine detail and faster computation compared to existing methods.
We present a statistical model for $3$D human faces in varying expression, which decomposes the surface of the face using a wavelet transform, and learns many localized, decorrelated multilinear models on the resulting coefficients. Using this model we are able to reconstruct faces from noisy and occluded $3$D face scans, and facial motion sequences. Accurate reconstruction of face shape is important for applications such as tele-presence and gaming. The localized and multi-scale nature of our model allows for recovery of fine-scale detail while retaining robustness to severe noise and occlusion, and is computationally efficient and scalable. We validate these properties experimentally on challenging data in the form of static scans and motion sequences. We show that in comparison to a global multilinear model, our model better preserves fine detail and is computationally faster, while in comparison to a localized PCA model, our model better handles variation in expression, is faster, and allows us to fix identity parameters for a given subject.