Garvita Tiwari | Visual Intelligence & Perception | Max-Planck-Institute for Informatics

University of Tübingen
Maria-von-Linden Strasse 6
72076
gtiwari@mpi-inf.mpg.de

About Me

I am a Ph.D. student at the Real Virtual Humans group, Max Planck Institute for Informatics (MPI-INF), Saarbrücken and University of Tuebingen, under the supervision of Prof. Dr. Gerard Pons-Moll. Currently, I am also collaborating with Dr. Tony Tung (Research Scientist Manager, Facebook Reality Labs).

Education

Ph.D: Max Planck Institute for Informatics and University of Tuebingen, December 2019 - Present
M.Sc. in Visual Computing, Saarland University, Saarbrücken, Germany, October 2017 - November 2019
B.Tech in Electronics and Communication Engineering, IIIT-Allahabad, India, July 2012 - May 2016

Work

Research Scientist Intern, FAIR, Meta, London, July 2022 - November 2022
Computer Vision Software Engineer at Infurnia Technologies, Bengaluru, India, July 2016 - May 2017

Research Interests

Computer vision for graphics
Geometric deep learning
3D Human modelling
Clothing models and dynamics

Academic Services

Reviewing(Conferences): CVPR(2022- Outstanding Reviewer), ICCV (2021), ECCV(2022), 3DV (2020, 2021), Eurographics (2021), SIGGRAPH (2021), UIST (2020), MVA (2021)
Reviewing(Journals): IEEE Transactions on Visualization and Computer Graphics(2021), Computers & Graphics(2020, 2022), Journal of Systems & Applications in Computer Graphics(2021), PeerJ Computer Science(2021)

Awards

Adobe Research Fellowship Program(2021)- Finalist
Best Paper Honorable Mention(ECCV 2022)

Talks

Learning Size Sensitive Clothing Model from Real Data @ MPI-IS -February 2021
Modeling Human Pose Manifolds with Neural Distance Fields @ Google Research -July 2022

Teaching

Deep Learning for Vision and Graphics Seminar, University of Tuebingen, SS 2022
Virtual Humans, University of Tuebingen, WS 2022-23

Media

Pose-NDF was featured in the BEST OF ECCV 2022 of Computer Vision News magazine

Publications

MoLingo: Motion-Language Alignment for Text-to-Motion Generation

Yannan He, Garvita Tiwari, Xiaohan Zhang, Pankaj Bora, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll
MoLingo: Motion-Language Alignment for Text-to-Motion Generation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

arXiv Website

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

Yannan He, Garvita Tiwari, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll
NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight