Jan Kautz

Jan Kautz, Ph.D.
Senior Director of Visual Computing and Machine Learning Research
Jan Kautz's picture

Jan leads the Visual Computing Research team at NVIDIA, working predominantly on computer vision problems — from low-level vision (denoising, super-resolution, computational photography) and geometric vision (structure from motion, SLAM, optical flow) to high-level vision (detection, recognition, classification) as well as machine learning problems (deep learning, reinforcement learning, generative models). Before joining NVIDIA in 2013, Jan was a tenured faculty member at University College London. He holds a BSc in Computer Science from University of Erlangen-Nürnberg (1999), an MMath from the University of Waterloo (1999), received his PhD from the Max-Planck-Institut für Informatik (2003), and worked as a post-doc at the Massachusetts Institute of Technology (2003-2006). Jan is particularly interested in computational photography and imaging, computer vision, and computational displays, on which he has published many articles at various conferences including ACM SIGGRAPH, Eurographics, CVPR, ECCV, CHI, and many more. A full publication list is available on his web-page.

Jan was program co-chair of the Eurographics Symposium on Rendering 2007, program chair of the IEEE Symposium on Interactive Ray-Tracing 2008, program co-chair for Pacific Graphics 2011, and program chair of CVMP 2012. He co-chaired Eurographics 2014 and is on the editorial board of IEEE Transactions on Visualization & Computer Graphics and The Visual Computer.

My team is hiring world-class research scientists and/or post-docs in computational photography, computer vision, and machine learning! See here, here, and here for details, or feel free to contact me via email.

Research Interests:

computational photography and imaging, computer vision, and machine learning.

Reconstructing Intensity Images from Binary Spatial Gradient Cameras
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
Computational Zoom: A Framework for Post-Capture Image Composition
Loss Functions for Image Restoration with Neural Networks
Polarimetric Multi-view Stereo
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Networks
Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
Towards Selecting Robust Hand Gestures for Automotive Interfaces
Accelerated Generative Models
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks
MLMD: Maximum Likelihood Mixture Decoupling for Fast and Accurate Point Cloud Registration
Robust Model-based 3D Head Pose Estimation
Locally Non-rigid Registration for Mobile HDR Photography
An Adaptive Acceleration Structure for Screen-space Ray Tracing
Filtering Environment Illumination for Interactive Physically-Based Rendering in Mixed Reality
Hand Gesture Recognition with 3D Convolutional Neural Networks
Slim near eye display using pinhole aperture arrays
FlexISP: A Flexible Camera Image Processing Framework
Cascaded Displays: Spatiotemporal Superresolution using Offset Pixel Layers
Hemispherical Rasterization for Self-Shadowing of Dynamic Objects
Matrix Radiance Transfer