Thomas Wimmer
Scholar

Thomas Wimmer

Google Scholar ID: LjdBF_IAAAAJ
Max Planck Institute for Informatics & ETH Zurich
Computer VisionDeep Learning3D Computer VisionNatural Language Processing
Citations & Impact
All-time
Citations
77
 
H-index
4
 
i10-index
2
 
Publications
8
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Published several papers, including:
  • - 'AnyUp: Universal Feature Upsampling', arXiv preprint, 2025
  • - 'Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels', accepted to ICCV 2025
  • - 'MEt3R: Measuring Multi-View Consistency in Generated Images', accepted to CVPR 2025
  • - 'Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes', accepted to 3DV 2025
Research Experience
  • During his studies, he has had the chance to work with various great people, including Daniel Cremers, Maks Ovsjanikov, Peter Wonka, and Federico Tombari.
Education
  • Graduated with a double master’s degree from the Technical University of Munich and the Institut Polytechnique de Paris. PhD advisors are Jan Eric Lenssen, Bernt Schiele, Christian Theobalt (MPI), and Siyu Tang (ETH).
Background
  • Currently pursuing a PhD through the Max Planck ETH Center for Learning Systems (CLS) and ELLIS programs. Main research interests lie at the intersection of computer vision, computer graphics, and geometry processing, focusing on (dynamic) 3D scene understanding, reconstruction, and generation, as well as visual semantics.