Publications (14)
Representing 3D Faces with Learnable B-Spline Volumes
Prashanth Chandran, Daoye Wang, Timo Bolkart
We present CUBE (Control-based Unified B-spline Encoding), a new geometric representation for human faces that combines B-spline volumes with learned features, and demonstrate its…
Artist-Friendly Relightable and Animatable Neural Heads
Yingyan Xu, Prashanth Chandran, Sebastian Weiss +3
An increasingly common approach for creating photo-realistic digital avatars is through the use of volumetric neural fields. The original neural radiance field (NeRF) allowed for i…
Anatomically Constrained Implicit Face Models
Prashanth Chandran, Gaspard Zoss
Coordinate based implicit neural representations have gained rapid popularity in recent years as they have been successfully used in image, geometry and scene modeling tasks. In th…
A Perceptual Shape Loss for Monocular 3D Face Reconstruction
Christopher Otto, Prashanth Chandran, Gaspard Zoss +3
Monocular 3D face reconstruction is a wide-spread topic, and existing approaches tackle the problem either through fast neural network inference or offline iterative reconstruction…
Spline-based Transformers
Prashanth Chandran, Agon Serifi, Markus Gross +1
We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animati…
An Implicit Physical Face Model Driven by Expression and Style
Lingchen Yang, Gaspard Zoss, Prashanth Chandran +5
3D facial animation is often produced by manipulating facial deformation models (or rigs), that are traditionally parameterized by expression controls. A key component that is usua…