TUM AI Guest Lecture Series

Welcome to the TUM AI Guest Lecture Series. This is a virtual talk series on various topics in computer vision and artificial intelligence. Our invited speakers are experts in their field and have already received international recognition for their work.

Upcoming Talks


photo Ben Poole
Google DeepMind

Previous Talks


2022


photo Andrea Tagliasacchi
Simon Fraser University, Google Research, University of Toronto
photo Björn Ommer
LMU Munich
Complete Codec Telepresence
photo Michael Zollhöfer
Meta
Efficient Neural Scene Representation, Rendering, and Generation
photo Gordon Wetzstein
Stanford University
Shape Editing, Generation and Stylization
photo Rana Hanocka
University of Chicago
Deep Surface Meshes
photo Pascal Fua
EPFL
Learning to Walk with Vision and Proprioception
photo Jitendra Malik
UC Berkeley, Facebook AI Research

2021


Self-supervising 3D Scene Representations for Perception, Control and Language Grounding
photo Katerina Fragkiadaki
Carnegie Mellon University
Joint Learning Over Visual and Geometric Data
photo Leonidas J. Guibas
Stanford University
Learning Geometric Structures
photo Ron Kimmel
Technion
Broad Data for Broad Robot Generalization
photo Chelsea Finn
Stanford University
Towards Virtual Humans: Putting Realistic People in Realistic Scenes doing Realistic Things
photo Michael Black
MPI Tübingen
AI-Generated Digital Humans
photo Hao Li
Pinscreen, UC Berkeley
Sensible Algorithms for Learning from Geometric Data
photo Justin Solomon
MIT CSAIL
Learning with energy-based models
photo Thomas Pock
TU Graz
Symmetries in Inference and Learning
photo Max Welling
University of Amsterdam, Qualcomm
Understanding and Mitigating Bias in Visual Recognition
photo Judy Hoffman
Georgia Tech
Towards novel architectures for shape matching and comparison
photo Maks Ovsjanikov
Ecole Polytechnique
Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News
photo Kate Saenko
Boston University, MIT-IBM Watson AI Lab
HoloLens, Mixed Reality and Spatial Computing
photo Marc Pollefeys
ETH, Microsoft
New Generative Models for Images, Landscape Videos and 3D Avatars
photo Victor Lempitsky
Samsung AI Center, Skoltech
A Future With Self-Driving Vehicles
photo Raquel Urtasun
University of Toronto, Uber
On Removing Supervision from Contrastive Self-Supervised Learning
photo Alexei Efros
UC Berkeley
Reflections on Image-Based Rendering
photo Richard Szeliski
University of Washington
Explainability and Compositionality for Visual Recognition with Minimal Supervision
photo Zeynep Akata
University of Tübingen, MPI
Learning Representations and Geometry from Unlabelled Videos
photo Andrea Vedaldi
University of Oxford, Facebook AI Research

2020


Photorealistic Telepresence
photo Yaser Sheikh
Facebook Reality Labs
Pushing Factor Graphs beyond SLAM
photo Frank Dellaert
Georgia Tech, Google
Sights, sounds, and space: Audio-visual learning in 3D environments
photo Kristen Grauman
University of Texas, Facebook AI Research
Controllable Content Generation without Direct Supervision
photo Niloy Mitra
University College London, Adobe Research
New methods for Reconstruction and Neural Rendering of Real World Scenes
photo Christian Theobalt
MPI for Informatics, Saarland University
Learning to Retime People in Videos
photo Tali Dekel
Google, Weizmann Institute of Science
The Moon Camera
photo Bill Freeman
MIT, Google
Understanding and Extending Neural Radiance Fields
photo Jonathan T. Barron
Google
Towards Graph-Based Spatial AI
photo Andrew Davison
Imperial College London
Reconstructing the Plenoptic Function
photo Noah Snavely
Cornell Tech, Google
Neural Implicit Representations for 3D Vision
photo Andreas Geiger
University of Tübingen, MPI
AI for 3D Content Creation
photo Sanja Fidler
University of Toronto, Nvidia, Vector Institute
A Question of Representation in 3D Computer Vision
photo Bharath Hariharan
Cornell University
Shape Representations: Parametric Meshes vs Implicit Functions
photo Gerard Pons-Moll
Max Planck Institute for Informatics
Making 3D Predictions with 2D Supervision
photo Justin Johnson
University of Michigan, Facebook AI Research
Computer Vision Startup Trends & Commercializing Research
photo Evan Nisselson
LDV Capital
Perceiving Humans in the 3D World
photo Angjoo Kanazawa
UC Berkeley, Google Research
Implicit Neural Scene Representations
photo Vincent Sitzmann
Stanford University, MIT

Contact us


If you have any questions regarding the TUM AI Guest Lecture Series, do not hesitate to contact us at: shivangi.aneja@tum.de


People

Shivangi Aneja
Shivangi Aneja
Matthias Nießner
Matthias Nießner