K
Kiran Varanasi
Researcher at German Research Centre for Artificial Intelligence
Publications - 46
Citations - 2126
Kiran Varanasi is an academic researcher from German Research Centre for Artificial Intelligence. The author has contributed to research in topics: Inpainting & Convolutional neural network. The author has an hindex of 18, co-authored 46 publications receiving 1815 citations. Previous affiliations of Kiran Varanasi include Max Planck Society & French Institute for Research in Computer Science and Automation.
Papers
More filters
Proceedings ArticleDOI
Surface feature detection and description with applications to mesh matching
TL;DR: A 3D feature detector and feature descriptor for uniformly triangulated meshes, invariant to changes in rotation, translation, and scale are proposed and defined generically for any scalar function, e.g., local curvature.
Journal ArticleDOI
Reconstruction of Personalized 3D Face Rigs from Monocular Video
Pablo Garrido,Michael Zollhöfer,Dan Casas,Levi Valgaerts,Kiran Varanasi,Patrick Pérez,Christian Theobalt +6 more
TL;DR: A novel approach for the automatic creation of a personalized high-quality 3D face rig of an actor from just monocular video data, based on three distinct layers that allow the actor's facial shape as well as capture his person-specific expression characteristics at high fidelity, ranging from coarse-scale geometry to fine-scale static and transient detail on the scale of folds and wrinkles.
Journal ArticleDOI
Sparse localized deformation components
TL;DR: A new way to extend the theory of sparse matrix decompositions to 3D mesh sequence processing, and further contribute with an automatic way to ensure spatial locality of the decomposition in a new optimization framework.
Journal ArticleDOI
VDub: Modifying Face Video of Actors for Plausible Visual Alignment to a Dubbed Audio Track
Pablo Garrido,Levi Valgaerts,Hamid Sarmadi,Ingmar Steiner,Kiran Varanasi,Patrick Pérez,Christian Theobalt +6 more
TL;DR: This paper builds on high‐quality monocular capture of 3D facial performance, lighting and albedo of the dubbing and target actors, and uses audio analysis in combination with a space‐time retrieval method to synthesize a new photo‐realistically rendered and highly detailed 3D shape model of the mouth region to replace the target performance.
Proceedings ArticleDOI
Shading-based dynamic shape refinement from multi-view video under general illumination
TL;DR: This work presents an approach to add true fine-scale spatio-temporal shape detail to dynamic scene geometry captured from multi-view video footage and uses weak temporal priors on lighting, albedo and geometry which improve reconstruction quality yet allow for temporal variations in the data.