Project Details
Program
Computer Science
Field of Study
Computer Science, Applied Mathematics.
Division
Computer, Electrical and Mathematical Sciences and Engineering
Faculty Lab Link
Center Affiliation
Visual Computing Center
Project Description
Inverse problems are abundant in the field of imaging, and range from simple image processing tasks such as denoising and deblurring to full-scale reconstruction problems like computed tomography (reconstructing 3D volumes from 2D projections). The purpose of this internship is to learn about inverse problems, and critical techniques for solving them, including convex and non-convex optimization, sparse coding, and compressive sensing.
About the Researcher
Wolfgang Heidrich
Professor, Computer Science
Affiliations
Education Profile
- Ph.D., University of Erlangen, 1999
- M.Math, University of Waterloo, 1996Diploma in Computer Science, University of Erlangen, 1995
Research Interests
Professor Heidrich's core research interests are in computational photography and display, an emerging research area within visual computing, which combines methods from computer graphics, machine vision, imaging, inverse methods, optics and perception to develop new sensing and display technologies. Computational photography aims to develop new cameras and imaging modalities that optically encode information about the real world in such a way that it can be captured by image sensors. The resulting images represent detailed information such as scene geometry, motion of solids and liquids, multi-spectral information, or high contrast (high dynamic range), which can then be computationally decoded using inverse methods, machine learning, and numerical optimization. Computational displays use a similar approach, but in reverse. Here, the goal is to computationally encode a target image that is then optically decoded by the display hardware for presentation to a human observer. Computational displays are capable of generating glasses-free 3D displays, high dynamic range imagery, or images and videos with spatial and/or temporal super-resolution.Selected Publications
- Low-budget Transient Imaging using Photonic Mixer Devices F. Heide, M. Hullin, J. Gregson, W. Heidrich ACM Transactions on Graphics (Proc. Siggaraph), 32(3):9 pages, July 2013
- Adaptive Image Synthesis for Compressive Displays F. Heide, G. Wetzstein, R. Raskar, W. Heidrich ACM Transactions on Graphics (Proc. Siggaraph), 2013
- High-Quality Computational Imaging Through Simple Lenses F. Heide, M. Rouf, M. Hullin, B. Labitzke, W. Heidrich, A. Kolb ACM Transactions on Graphics, 32:10 pages, 2013
- Stochastic Tomography and its Applications in 3D Imaging of Mixing Fluids J. Gregson, M. Krimerman, M. Hullin, W. Heidrich ACM Transactions on Graphics (Proc. SIGGRAPH), 31(3):52:1a-52:10, August 2012
- Layered 3D: Tomographic Image Synthesis for Attenuation-based Light Field and High Dynamic Range Displays G.Wetzstein, D. Lanman,W. Heidrich, R. Raskar ACM Transactions on Graphics (Proc. SIGGRAPH), 30(3):95:1a-95:12, August 2011
- HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions R. Mantiuk, K. Kim, A. Rempel,W. Heidrich ACM Transactions on Graphics (Proc. SIGGRAPH), 30(3):40:1a-40:14, August 2011
Desired Project Deliverables
This project requires some familiarity with basic numerical methods as well as programming skills. Close collaboration with other team members is expected. Possibility for co-authoring a scientific article in a conference or journal.