… poses by leveraging learned shape deformation via … deformation prior, we propose neural
deformation fields as described in Section 3.2 which can be learned from large deformation …

… Next, we test our deformation prior on the task of learning a shape space from “real-life”
raw scans. We considered the D-Faust raw scans dataset [8], consisting of 41k scans from 10 …

… Neural Network (CNN), we propose an intermediate step to estimate the deformation of a
pre-learned shape prior to improve the learning of intra-class shape variation. Our …

… shape Ss and a target shape St, we design a deep neural network that predicts a cage
deformation that … For man-made shapes, we use two additional losses that leverage priors of this …

… Our structure-aware neural deformation leverages learned shape priors to complete missing
… , similar to prior work [41] we can Input Retrieved Deformed Input Retrieved Deformed …

… deformations as well as to help learning disentangled shape and pose spaces. We demonstrate
our Neural … , as well as their capability in shape and pose transfer and interpolation. In …

… a shape prior term for the deformable framework through a non-linear energy term designed
to attract a shape … In this paper, we depart from the small deformation assumption and …

… which incorporate shape priors into neural networks. Though … the prior and the loss is
calculated on the deformed prior and … a deformation model, conditioned on a shape prior to deform …

… used by these methods tend to be purely geometric (eg, promoting near isometry or
divergencefree deformation fields), and, as we demonstrate below, are not always applicable, …

… framework for deforming and animating the neural radiance … -based representation as
deformation prior, which is category… perform deformation based on the target novel pose/shape …