Page Content
to Navigation
Processing Digital Camera Images (WS09/10)
| Instructor: | Prof. Dr. Marc Alexa |
|---|---|
| Contact | Mathias Eitz |
| Course structure: | Seminar - 2 SWS |
| Room: | E-N 719 |
| Date: | Tuesday 4pm - 6pm Start: 13 Oct 2009 End: 10 Feb 2010 |
| Description: | Images taken with a digital camera can be processed and manipulated to create novel imagery unachievable with a single shot. In this course we will computationally create novel imagery by combining a large number of existing images, coming either from multiple shots of the same scene taken with varying camera parameters or from existing large image databases (e.g. Flickr). Additionally, we will explore state of the art methods for visualizing the results using natural user interfaces, e.g. multi-touch surfaces. |
| Requirements: | Interest in visual arts/photography, programming skills, ideally access to a digital camera (although this could be arranged for a limited number of participants). |
| Details: | The course gives a brief overview of the basic ideas and several recent developments in this field. Students will work in small teams on a chosen topic and present the basics of their topic in an intermediate talk. Finally, each team will implement a recent research paper and present their topic, application and results in a concluding talk. Both efficiency of the underlying algorithms as well as visual quality of the resulting imagery are important aspects in this course. Grading will be based on all aspects of performance. |
| Registration: | Please register for the course until October 13th by sending an eMail mentioning the course title, your name and student id to Helga Kallan. |
Final project reports
- Automatic colorization of a greyscale image (left) using statistics learned from a large image database. The colorized result is shown on the right.
- © Patrick Busse
This semester, we had several great projects with amazing result -- see the final project report websites:
- Artificial Infinite Panoramas (Florian Thiemer, Christopher Koenig)
- Coloring Grayscale Images from Large Image Databases (Patrick Busse)
- High Dynamic Range Imaging and Tonemapping (Sebastian Negraszus, Daniel Pirch)
- Gradient Domain Imaging (Oleg Fischer, Felix Fehlhaber)
- Dark Flash Photography (Lukas N.P. Egger, Martin Zuber)
Slides
Das Dateilinks-Plugin steht nicht mehr zur Verfügung. Bitte verwenden Sie statt dessen das Plugin TUB Downloadliste. Für die Löschung des alten Inhaltselements wenden Sie sich bitte an webmaster unter Nennung des Direktzugangs.
Sample projects from previous courses
- Generating an image with optimal depth of field from a series of images.
- © CG TUB
Some samples of what students in previous classes implemented:
WS 08/09:
- Scene Completion from Millions of Photographs (Carlo Fürst, Ruben Gerlach, Moritz Schneeweiss)
- Image Flight (Matthias Hausburg, Ronald Richter, Ingo Breßler)
- Tone Mapping (Roman Zimmer, Philipp Herholz, Volker Parsiegla)
- Image Mosaics (Mario Bodemann, Sebastian Koch, Dmitry Nedospasov, Helen Perkunder)
- HDR image creation (Marcel Poppe, Christian Corona)
WS 07/08:
Contact
- Questions regarding course topics: Mathias Eitz
- Administration: Helga Kallan