A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces

by   Claudio Ferrari, et al.

The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face shapes. To build a 3DMM, a training set of scans in full point-to-point correspondence is required, and its modeling capabilities directly depend on the variability of the training data. Hence, to increase the descriptive power of a 3DMM, accurately establishing dense correspondence across heterogeneous scans with sufficient diversity in terms of identities, ethnicities, or expressions becomes essential. In this manuscript, we present a fully automatic approach that leverages a 3DMM to establish a dense correspondence across raw 3D faces. We propose a novel formulation to learn a set of sparse deformation components with local support on the face that, together with an original non-rigid deformation algorithm, allow the 3DMM to precisely fit unseen faces and transfer its semantic annotation to arbitrary 3D faces. We experimented our approach on three large and diverse datasets, showing it can effectively generalize to very different samples and accurately establish a dense correspondence even in presence of complex facial expressions. The accuracy of the dense registration is demonstrated by building a heterogeneous, large-scale 3DMM from more than 9,000 fully registered scans obtained by joining the three datasets.


page 4

page 5

page 9

page 10

page 11

page 13

page 15

page 17


3D Face Modeling from Diverse Raw Scan Data

Traditional 3D models learn a latent representation of faces using linea...

BLiSS: Bootstrapped Linear Shape Space

Morphable models are fundamental to numerous human-centered processes as...

Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method

Dense vertex-to-vertex correspondence between 3D faces is a fundamental ...

Dense 3D Face Correspondence

We present an algorithm that automatically establishes dense corresponde...

Densely tracking sequences of 3D face scans

3D face dense tracking aims to find dense inter-frame correspondences in...

Automatic landmark annotation and dense correspondence registration for 3D human facial images

Dense surface registration of three-dimensional (3D) human facial images...

Instant Multi-View Head Capture through Learnable Registration

Existing methods for capturing datasets of 3D heads in dense semantic co...

Please sign up or login with your details

Forgot password? Click here to reset