MPI-INF Logo
Homepage

Contact

Firstname Lastname

Kartik Teotia

Max-Planck-Institut für Informatik
D6: Visual Computing and Artificial Intelligence
 office: Campus E1 4, Room 115D
Saarland Informatics Campus
66123 Saarbrücken
Germany
 email: kteotia@mpi-inf.mpg.de
 phone: +49 681 9325 4535

Research Interests

  • Dynamic Facial Representations
  • 3D Computer Graphics
  • Virtual/Augmented Reality

Publications

GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations

K. Teotia, H. Kim, P. Garrido, M. Habermann, M. Elgharib, C. Theobalt,

ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2024)   —   SIGGRAPH Asia 2024

We propose a new method for generating dynamic, deformable human head avatars from multi-view imagery in real-time. Our coarse-to-fine facial representation enables high-fidelity expression synthesis from novel viewpoints.

[pdf] [project page]


HQ3DAvatar: High Quality Implicit 3D Head Avatar

K. Teotia, M. B R, X. Pan, H. Kim, P. Garrido, M. Elgharib, C. Theobalt,

ACM Transactions on Graphics (TOG)   —   ACM TOG 2024 (presented at SIGGRAPH 2024)

We present a novel method for rendering photorealistic human head avatars. Our method utilizes an implicitly learned canonical space constrained using optical flow in a multiresolution hash encoding framework. Our approach outperforms related methods and excels in reconstructing regions exhibiting complex geometric details e.g. mouth interior and hair.

[pdf] [project page]


AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars

M. Mendiratta, X. Pan, M. Elgharib, K. Teotia, M. B R, A. Tewari, V. Golyanik, A. Kortylewski, C. Theobalt,

ACM Transactions on Graphics (SIGGRAPH Asia 2023)   —   SIGGRAPH Asia 2023

AvatarStudio uses text-based editing on dynamic head avatars, employing NeRF and a text-to-image diffusion model with multiple keyframes, achieving superior personalized, 3D- and time-consistent edits in visual and numerical assessments.

[pdf] [project page]


Automatic segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs

J. R. Harish Kumar, K. Teotia, P.K. Raj, J. Andrade, K. V. Rajagopal, C. S. Seelamantula,

International Conference on Acoustics, Speech, and Signal Processing   —   ICASSP 2019

We propose a fully automated algorithm for the segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs.

[pdf]


Education