Inverse rendering of faces with a 3D morphable model
O Aldrian, WAP Smith - IEEE transactions on pattern analysis …, 2012 - ieeexplore.ieee.org
In this paper, we present a complete framework to inverse render faces with a 3D Morphable
Model (3DMM). By decomposing the image formation process into geometric and …
Model (3DMM). By decomposing the image formation process into geometric and …
Artificial intelligence and stochastic optimization algorithms for the chaotic datasets
Almost every natural process is stochastic due to the basic consequences of nature's
existence and the dynamical behavior of each process that is not stationary but evolves with …
existence and the dynamical behavior of each process that is not stationary but evolves with …
Simultaneous registration of multiple images: similarity metrics and efficient optimization
C Wachinger, N Navab - IEEE transactions on pattern analysis …, 2012 - ieeexplore.ieee.org
We address the alignment of a group of images with simultaneous registration. Therefore,
we provide further insights into a recently introduced framework for multivariate similarity …
we provide further insights into a recently introduced framework for multivariate similarity …
3D stent recovery from one x-ray projection
In the current clinical workflow of endovascular abdominal aortic repairs (EVAR) a stent graft
is inserted into the aneurysmatic aorta under 2D angiographic imaging. Due to the missing …
is inserted into the aneurysmatic aorta under 2D angiographic imaging. Due to the missing …
Efficient groupwise non-rigid registration of textured surfaces
Advances in 3D imaging have recently made 3D surface scanners, capable of capturing
textured surfaces at video rate, affordable and common in computer vision. This is a …
textured surfaces at video rate, affordable and common in computer vision. This is a …
Automatic construction of parts+ geometry models for initializing groupwise registration
Groupwise nonrigid image registration is a powerful tool to automatically establish
correspondences across sets of images. Such correspondences are widely used for …
correspondences across sets of images. Such correspondences are widely used for …
Semi-supervised facial landmark annotation
Landmark annotation for training images is essential for many learning tasks in computer
vision, such as object detection, tracking, and alignment. Image annotation is typically …
vision, such as object detection, tracking, and alignment. Image annotation is typically …
Facial contour labeling via congealing
It is a challenging vision problem to discover non-rigid shape deformation for an image
ensemble belonging to a single object class, in an automatic or semi-supervised fashion …
ensemble belonging to a single object class, in an automatic or semi-supervised fashion …
Using bounded diameter minimum spanning trees to build dense active appearance models
We present a method for producing dense active appearance models (AAMs), suitable for
video-realistic synthesis. To this end we estimate a joint alignment of all training images …
video-realistic synthesis. To this end we estimate a joint alignment of all training images …
Automatic 3D modelling of craniofacial form
Three-dimensional models of craniofacial variation over the general population are useful
for assessing pre-and post-operative head shape when treating various craniofacial …
for assessing pre-and post-operative head shape when treating various craniofacial …